WO2024114018A1 - 风力发电机组的发电性能评估方法和装置 - Google Patents

风力发电机组的发电性能评估方法和装置 Download PDF

Info

Publication number
WO2024114018A1
WO2024114018A1 PCT/CN2023/117205 CN2023117205W WO2024114018A1 WO 2024114018 A1 WO2024114018 A1 WO 2024114018A1 CN 2023117205 W CN2023117205 W CN 2023117205W WO 2024114018 A1 WO2024114018 A1 WO 2024114018A1
Authority
WO
WIPO (PCT)
Prior art keywords
power generation
power
historical
generation performance
wind turbine
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2023/117205
Other languages
English (en)
French (fr)
Inventor
张鹏飞
米玉霞
赵世培
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Goldwind Science and Technology Co Ltd
Original Assignee
Goldwind Science and Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Goldwind Science and Technology Co Ltd filed Critical Goldwind Science and Technology Co Ltd
Priority to CA3261632A priority Critical patent/CA3261632A1/en
Priority to EP23896175.9A priority patent/EP4629125A4/en
Priority to AU2023399270A priority patent/AU2023399270A1/en
Priority to US18/880,986 priority patent/US20260004020A1/en
Publication of WO2024114018A1 publication Critical patent/WO2024114018A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
    • F03D—WIND MOTORS
    • F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
    • F03D17/005—Monitoring or testing of wind motors, e.g. diagnostics using computation methods, e.g. neural networks
    • F03D17/006—Estimation methods
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
    • F03D—WIND MOTORS
    • F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
    • F03D17/005—Monitoring or testing of wind motors, e.g. diagnostics using computation methods, e.g. neural networks
    • F03D17/0065—Monitoring or testing of wind motors, e.g. diagnostics using computation methods, e.g. neural networks for diagnostics
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
    • F03D—WIND MOTORS
    • F03D17/00—Monitoring or testing of wind motors, e.g. diagnostics
    • F03D17/009—Monitoring or testing of wind motors, e.g. diagnostics characterised by the purpose
    • F03D17/026—Monitoring or testing of wind motors, e.g. diagnostics characterised by the purpose for assessing power production capabilities
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
    • F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
    • F05B2260/00—Function
    • F05B2260/82—Forecasts
    • F05B2260/821—Parameter estimation or prediction
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
    • F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
    • F05B2270/00—Control
    • F05B2270/30—Control parameters, e.g. input parameters
    • F05B2270/335—Output power or torque
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/06—Wind turbines or wind farms
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/02—Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
    • G06F2119/06—Power analysis or power optimisation
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Definitions

  • the present disclosure relates to the technical field of wind power generation, and more specifically, to a method and device for evaluating power generation performance of a wind power generator set.
  • the existing wind turbine performance evaluation is mostly conducted from the power curve or power characteristics, failure rate, etc. to determine the changing trend of the unit's power generation performance.
  • the factors that affect the unit's power generation performance include not only the wind turbine itself, but also external environmental influences.
  • the power generation performance changes caused by the wind turbine itself are relatively mild, while the power generation performance changes caused by environmental influences are relatively obvious. Therefore, for the changes in the power generation performance of the wind turbine within a certain period of time, the changes in the power generation performance caused by the unit itself will be covered up, and these environmental influences have certain fluctuations, so it is difficult to determine the power generation performance changes caused by the wind turbine itself over a long period of time.
  • a method for evaluating power generation performance of a wind turbine generator set comprising: obtaining historical operation data of the wind turbine generator set in n historical time periods, wherein n is a positive integer; determining the actual capacity coefficient and the theoretical capacity coefficient of the wind turbine generator set in the n historical time periods according to the historical operation data; determining the historical power generation performance coefficient of the wind turbine generator set in the n historical time periods based on the actual capacity coefficient and the theoretical capacity coefficient in the n historical time periods; obtaining the historical power generation performance coefficient in the n historical time periods according to the historical power generation performance coefficient.
  • Power generation performance change trend based on the power generation performance change trend, determine the estimated power generation performance coefficient of the wind turbine generator set in the target future time period, and the estimated power generation performance coefficient is used to estimate the power generation performance of the target future time period.
  • determining the actual capacity coefficient and the theoretical capacity coefficient of the wind turbine generator set in the n historical time periods respectively according to the historical operation data includes: determining the ratio of the actual value to the rated value of the power generation index of the wind turbine generator set in the n historical time periods respectively according to the historical operation data to obtain the actual capacity coefficient, wherein the power generation index includes at least one of the power generation time, the online power and the power; determining the ratio of the theoretical average power to the rated power of the wind turbine generator set in the n historical time periods respectively according to the historical operation data to obtain the theoretical capacity coefficient.
  • the historical operating data includes an actual power curve, multiple wind speed intervals, the frequency of each wind speed interval, and the rated power
  • the ratio of the actual value to the rated value of the power generation index of the wind turbine generator set in the n historical time periods is determined according to the historical operating data to obtain the actual capacity factor, including: for each historical time period, based on the actual power curve, determining the actual power average value of each wind speed interval; determining the expected actual power average value according to the actual power average value and frequency of each wind speed interval as the actual average power of the wind turbine generator set in the historical time period; determining the ratio of the actual average power of the wind turbine generator set in the historical time period to the rated power to obtain the actual capacity factor.
  • the historical operation data also includes a theoretical power curve, and the ratio of the theoretical average power to the rated power of the wind turbine generator set in the n historical time periods is determined based on the historical operation data to obtain the theoretical capacity coefficient, including: for each historical time period, based on the theoretical power curve, determining the theoretical power average value of each wind speed interval; determining the expected theoretical power average value according to the theoretical power average value and frequency of each wind speed interval as the theoretical average power of the wind turbine generator set in the historical time period; determining the ratio of the theoretical average power of the wind turbine generator set in the historical time period to the rated power to obtain the theoretical capacity coefficient.
  • the actual power average value is an average value of actual power within the wind speed interval; and/or the theoretical power average value is a value obtained by interpolating in the theoretical power curve based on the average wind speed in each wind speed interval.
  • the historical operation data includes wind speed distribution parameters and rated wind speed.
  • the distribution parameters are used to describe the distribution probability of wind speed, wherein the ratio of the theoretical average power to the rated power of the wind turbine generator set in the n historical time periods is determined respectively according to the historical operation data to obtain the theoretical capacity factor, including: for each of the historical time periods, according to the wind speed distribution parameters, determining the expectation of the third power of the wind speed; determining the ratio of the expectation of the third power of the wind speed to the third power of the rated wind speed to obtain the theoretical capacity factor.
  • the wind speed distribution parameter includes a wind speed probability density function or a wind speed probability distribution function; or the wind speed distribution parameter includes a plurality of wind speed intervals and a frequency of each of the wind speed intervals.
  • the power generation performance evaluation method also includes: determining the estimated power generation of the wind turbine generator set in the target future time period based on the estimated power generation performance coefficient; determining the estimated profit generated by the wind turbine generator set adopting the candidate unit control strategy in the target future time period based on the estimated power generation, candidate unit control strategy and profit-related variables, wherein the profit-related variables are variables required to determine the power generation profit of the wind turbine generator set.
  • the revenue-related variables include the electricity price of the target future time period, a predetermined first relationship function and a second relationship function, the first relationship function being a relationship function between a power generation change and an adjustment amount of the unit control strategy, and the second relationship function being a relationship function between power generation and unit maintenance cost
  • determining the estimated revenue generated by the wind turbine generator set adopting the candidate unit control strategy in the target future time period based on the estimated power generation, the candidate unit control strategy and the revenue-related variables includes: determining the estimated power generation change corresponding to the candidate unit control strategy based on the adjustment amount of the candidate unit control strategy relative to the current unit control strategy and the first relationship function; determining the sum of the estimated power generation and the estimated power generation change as the estimated total power generation corresponding to the candidate unit control strategy; determining the estimated maintenance cost corresponding to the candidate unit control strategy based on the estimated total power generation and the second relationship function; determining the estimated revenue generated by the wind turbine generator set adopting the candidate unit control strategy in the target future time period based on the estimated total power generation
  • the power generation performance evaluation method further includes: adjusting the candidate unit control strategy based on the estimated benefit to obtain an optimized unit control strategy.
  • a device for evaluating power generation performance of a wind turbine generator set comprising: an acquisition unit configured to acquire historical operation data of the wind turbine generator set in n historical time periods, wherein n is a positive integer; a determination unit configured to determine, based on the historical operation data, an actual capacity factor and a theoretical capacity factor of the wind turbine generator set in the n historical time periods; and the determination unit is further configured to determine, based on the actual capacity factor and the theoretical capacity factor in the n historical time periods, an actual capacity factor and a theoretical capacity factor in the n historical time periods.
  • a theoretical capacity coefficient is used to determine the historical power generation performance coefficients of the wind turbine generator set in the n historical time periods respectively; a sorting unit is configured to obtain the power generation performance change trend according to the historical power generation performance coefficients in the n historical time periods; a prediction unit is configured to determine the estimated power generation performance coefficient of the wind turbine generator set in the target future time period according to the power generation performance change trend, and the estimated power generation performance coefficient is used to estimate the power generation performance of the target future time period.
  • the determination unit is further configured to: determine, based on the historical operation data, the ratio of the actual value to the rated value of the power generation index of the wind turbine generator set in the n historical time periods, to obtain the actual capacity coefficient, wherein the power generation index includes at least one of the power generation time, the online power and the power; determine, based on the historical operation data, the ratio of the theoretical average power to the rated power of the wind turbine generator set in the n historical time periods, to obtain the theoretical capacity coefficient.
  • the determination unit is further configured to: for each of the historical time periods, determine the actual power average value of each wind speed interval based on the actual power curve; determine the expected actual power average value based on the actual power average value and frequency of each wind speed interval as the actual average power of the wind turbine generator set in the historical time period; determine the ratio of the actual average power of the wind turbine generator set in the historical time period to the rated power to obtain the actual capacity factor.
  • the historical operation data also includes a theoretical power curve
  • the determination unit is further configured to: for each of the historical time periods, determine the theoretical power average value of each of the wind speed intervals based on the theoretical power curve; determine the expectation of the theoretical power average value according to the theoretical power average value and frequency of each of the wind speed intervals as the theoretical average power of the wind turbine generator set in the historical time period; determine the ratio of the theoretical average power of the wind turbine generator set in the historical time period to the rated power to obtain the theoretical capacity factor.
  • the actual power average value is an average value of actual power within the wind speed interval; and/or the theoretical power average value is a value obtained by interpolating in the theoretical power curve based on the average wind speed in each wind speed interval.
  • the historical operating data includes wind speed distribution parameters and rated wind speed
  • the wind speed distribution parameters are used to describe the distribution probability of the wind speed
  • the determination unit is further configured to: for each of the historical time periods, determine the expected third power of the wind speed according to the wind speed distribution parameters; determine the ratio of the expected third power of the wind speed to the third power of the rated wind speed to obtain the theoretical capacity coefficient.
  • the wind speed distribution parameter includes a wind speed probability density function or a wind speed probability distribution function; or the wind speed distribution parameter includes a plurality of wind speed intervals and a frequency of each of the wind speed intervals.
  • the power generation performance evaluation device also includes an estimation unit, which is configured to: determine the estimated power generation of the wind turbine generator set in the target future time period based on the estimated power generation performance coefficient; determine the estimated profit generated by the wind turbine generator set adopting the candidate unit control strategy in the target future time period based on the estimated power generation, candidate unit control strategies and profit-related variables, wherein the profit-related variables are variables required to determine the power generation profit of the wind turbine generator set.
  • an estimation unit which is configured to: determine the estimated power generation of the wind turbine generator set in the target future time period based on the estimated power generation performance coefficient; determine the estimated profit generated by the wind turbine generator set adopting the candidate unit control strategy in the target future time period based on the estimated power generation, candidate unit control strategies and profit-related variables, wherein the profit-related variables are variables required to determine the power generation profit of the wind turbine generator set.
  • the revenue-related variables include the electricity price of the target future time period, a predetermined first relationship function and a second relationship function, the first relationship function being a relationship function between a power generation change and an adjustment amount of the unit control strategy, the second relationship function being a relationship function between power generation and unit maintenance cost
  • the estimation unit is further configured to: determine an estimated power generation change corresponding to the candidate unit control strategy based on the adjustment amount of the candidate unit control strategy relative to the current unit control strategy and the first relationship function; determine the sum of the estimated power generation and the estimated power generation change as the estimated total power generation corresponding to the candidate unit control strategy; determine an estimated maintenance cost corresponding to the candidate unit control strategy based on the estimated total power generation and the second relationship function; and determine the estimated revenue generated by the wind turbine generator set adopting the candidate unit control strategy in the target future time period based on the estimated total power generation, the electricity price, and the estimated maintenance cost.
  • the power generation performance evaluation device further includes an optimization unit configured to adjust the candidate unit control strategy based on the estimated benefit to obtain an optimized unit control strategy.
  • a computer-readable storage medium is provided.
  • the at least one processor is prompted to perform the power generation performance evaluation method as described above.
  • a computer device comprising: at least one processor; and at least one memory storing computer executable instructions, wherein the computer executable instructions, when executed by the at least one processor, cause the at least one processor to execute the power generation performance evaluation method as described above.
  • the present disclosure uses the actual capacity factor that can reflect the actual power and combines it with the theoretical capacity factor to obtain the historical power generation performance factor, which can effectively evaluate the power generation performance of the unit itself, and can also use the further determined power generation performance change trend to reflect the power generation performance change of the unit itself.
  • the wind turbine generator set can effectively evaluate the power generation performance of the unit itself, and can also use the further determined power generation performance change trend to reflect the power generation performance change of the unit itself.
  • the energy coefficient can reflect the changes in the power generation performance of the wind turbine generator set from a more intuitive future perspective, thereby providing a basis for the active update of the subsequent control strategy and operation and maintenance strategy of the unit.
  • the present disclosure uses the historical operation data of the unit, without the need to install additional measurement devices, so the optimization cost is low and the portability is strong.
  • FIG1 is a flow chart showing a method for evaluating power generation performance of a wind turbine generator set according to an embodiment of the present disclosure
  • FIG2 is a schematic diagram showing a theoretical power curve according to an embodiment of the present disclosure
  • FIG3 is a schematic diagram showing an actual power curve according to an embodiment of the present disclosure.
  • FIG4 is a schematic flow chart showing a control strategy optimization solution according to a specific embodiment of the present disclosure.
  • FIG. 5 is a schematic flow chart showing a system for evaluating the power generation performance of a wind turbine generator set according to an embodiment of the present disclosure
  • FIG. 6 is a block diagram showing a device for evaluating power generation performance of a wind turbine generator set according to an embodiment of the present disclosure
  • FIG. 7 is a block diagram illustrating a computer device according to an embodiment of the present disclosure.
  • first, second, and third may be used herein to describe various members, components, regions, layers, or portions, these members, components, regions, layers, or portions should not be limited by these terms. Instead, these terms are only used to distinguish one member, component, region, layer, or portion from another member, component, region, layer, or portion. Therefore, without departing from the teachings of the examples described herein, the first member, first component, first region, first layer, or first portion referred to in the examples may also be referred to as the second member, second component, second region, second layer, or second portion.
  • FIG1 is a flow chart showing a method for evaluating power generation performance of a wind turbine generator system according to an embodiment of the present disclosure.
  • step S101 historical operation data of wind turbines in n historical periods are obtained.
  • n is a positive integer.
  • the length of each historical period can be set as needed, such as 1 month, 1 quarter, 1 year, and different historical periods can have common parts, such as for the same.
  • you need to use historical operation data in a certain historical period you can use the historical operation data with a timestamp in that historical period.
  • the above operating data is data reflecting the real-time operating status of the unit at different times, including, for example, wind speed, power, and power generation.
  • the historical operating data may be data obtained from SCADA (Supervisory Control And Data Acquisition); in another example, the historical operating data may be collected from various sensors installed on the wind turbine generator set.
  • step S102 actual capacity factors and theoretical capacity factors of the wind turbine generator set in n historical time periods are determined according to historical operation data.
  • the capacity factor is used to reflect the energy output of a wind turbine.
  • the actual capacity factor is used to reflect the actual energy output of a wind turbine, which may refer to the ratio of the actual power generation (actual power) of the wind turbine during the statistical period to the rated power generation (rated power) of the wind turbine.
  • the theoretical capacity factor is used to reflect the theoretical energy output of a wind turbine, which may refer to the ratio of the theoretical power generation (theoretical power) of the wind turbine during the statistical period to the rated power generation (rated power) of the wind turbine.
  • the actual power of a wind turbine is affected by both the unit's own power generation performance and environmental factors.
  • the theoretical power is the power of the unit under ideal conditions (that is, when the unit's own power generation performance is optimal), which reflects the influence of environmental factors. Therefore, the difference between the two is caused by the unit itself and can reflect the unit's own power generation performance. Furthermore, since both the actual capacity factor and the theoretical capacity factor introduce the fixed value of the rated power relative to the actual power and the theoretical power, the difference between the actual capacity factor and the theoretical capacity factor can also reflect the difference between the actual power and the theoretical power. On the one hand, it can meet the evaluation needs. On the other hand, the calculation methods of the actual capacity factor and the theoretical capacity factor are more diverse, ensuring the flexibility of the solution. By obtaining the historical operation data in n historical periods, the actual capacity factor and the theoretical capacity factor of each historical period can be calculated. The detailed calculation method will be introduced in detail later, so it will not be repeated here.
  • step S103 based on the actual capacity factor and the theoretical capacity factor in the n historical time periods, the historical power generation performance coefficients of the wind turbine generator set in the n historical time periods are determined.
  • the power generation performance coefficient is used to characterize the power generation performance of the wind turbine itself. For a historical period, the ratio of the actual capacity factor to the theoretical capacity factor of the wind turbine generator set during the period can be determined. This ratio is equal to the ratio of the actual power to the theoretical power. Taking it as the historical power generation performance coefficient during the historical period, a dimensionless performance coefficient can be obtained, which can eliminate the influence of environmental factors and is not limited by the rated power of the unit. It should be understood that the power generation performance of the unit itself tends to decrease with the increase of operating years, so the actual power is often less than the theoretical power, causing the above ratio to be less than 1, and the smaller the ratio, the greater the difference between the actual power and the theoretical power, and the worse the power generation performance of the unit itself. In other words, the larger the ratio, the better the power generation performance of the unit itself.
  • the ratio can also be converted to a power value, specifically by first calculating the average value of the theoretical power of n historical periods, and then multiplying the average value by the aforementioned ratio of each historical period to obtain the actual power of each historical period. Using the average value of the theoretical power of n historical periods as the conversion coefficient instead of the theoretical power of a certain year can unify the evaluation criteria.
  • the power generation performance change trend is obtained based on the historical power generation performance coefficients in n historical time periods.
  • the power generation performance change trend can be obtained by a fitting method, such as, but not limited to, linear fitting.
  • a fitting method such as, but not limited to, linear fitting.
  • step S105 based on the power generation performance change trend, the estimated power generation performance coefficient of the wind turbine generator set in the target future time period is determined.
  • the estimated power generation performance coefficient is used to estimate the power generation performance of the wind turbine generator set in the target future time period.
  • the generalized change trend can be converted into a clear point value in the future, thereby reflecting the power generation performance change results of the wind turbine generator set from a more intuitive future perspective, and providing a basis for the subsequent control strategy of the unit and the active update of the operation and maintenance strategy.
  • the above steps S101 to S104 can also be performed periodically to evaluate the power generation performance change trend of the wind turbine generator set; the entire power generation performance evaluation method disclosed in the present invention can also be performed periodically.
  • step S103 how to determine the historical power generation performance coefficient, that is, step S103, is specifically introduced.
  • step S103 includes: determining, according to the historical operation data, the ratio of the actual value to the rated value of the power generation index of the wind turbine generator set in n historical time periods, and obtaining the actual capacity factor, wherein the power generation index includes at least one of the power generation time, the grid-connected power and the power; determining, according to the historical operation data, the ratio of the theoretical average power to the rated power of the wind turbine generator set in n historical time periods, and obtaining the actual capacity factor; The ratio of the actual power rate to the rated power is used to obtain the theoretical capacity factor.
  • the actual capacity factor is the ratio of the actual power to the rated power.
  • the actual power generation time and the rated power generation time which are more easily obtained, can be used to calculate the ratio, or the actual grid-connected power and the rated grid-connected power can be used to calculate the ratio.
  • the actual power can also be calculated by other means, and then the actual power and the rated power can be used to calculate the ratio, which ensures the flexibility of the solution.
  • the theoretical power can be obtained through theoretical calculation. By using the theoretical average power in the historical period, the average level of the theoretical power can be used to characterize the theoretical power of the corresponding historical period, which ensures the reliability of the calculation results.
  • the present disclosure can provide two types of methods to determine the actual capacity factor and the theoretical capacity factor.
  • One method mainly uses the rated wind speed of the unit.
  • the derivation process of this method is as follows:
  • the power generation index used can be the power generation time, grid-connected power or power.
  • the actual capacity factor can be the ratio of the effective utilization hours of the unit in the year to the annual hours, or as shown in formula (1), it is the ratio of the actual annual grid-connected power E real of the unit to the rated annual grid-connected power E rate , or as shown in formula (2), it is the ratio of the actual average power P real of the unit in the year to the rated power P rate .
  • ICF Industry Capacity Factor
  • P ideal , f w (v), and Pe (v) are respectively the theoretical average power, rated power, wind speed probability density function, and power calculation function related to wind speed
  • ⁇ , C p , ⁇ , A, v r , v cin , and v cout are respectively the air density, power coefficient, efficiency coefficient, swept area, rated wind speed, cut-in wind speed, and cut-off wind speed.
  • P ideal is only related to wind speed, and the other parameters ( ⁇ , C p , ⁇ , A, v r ) are assumed to be consistent with the rated power P rate . Then the P ideal calculation formula can be written as shown in (5), and P rate can directly use the unit design value. Then the theoretical capacity factor ICF can be expressed by formula (6).
  • the historical operation data includes wind speed distribution parameters and rated wind speed
  • the wind speed distribution parameters are used to describe the distribution probability of wind speed.
  • the step of determining the theoretical capacity factor in n historical time periods in step S103 includes: for each historical period, determining the expectation of the third power of wind speed according to the wind speed distribution parameters; determining the ratio of the expectation of the third power of wind speed to the third power of rated wind speed to obtain the theoretical capacity factor.
  • wind speed distribution parameters can be described in two forms:
  • the wind speed distribution parameters include the wind speed probability density function fw (v) or the wind speed probability distribution function.
  • a special distribution type can be used to obtain a theoretical wind speed probability density function fw (v) or a wind speed probability distribution function F(v) to improve the feasibility of the calculation. It should be understood that the wind speed probability density function fw (v) is the first-order derivative of the wind speed probability distribution function F(v).
  • the wind speed distribution can follow the Rayleigh distribution, and the wind speed probability distribution function is obtained:
  • the wind speed probability distribution function can be obtained, there is no need to calculate the specific wind speed probability density function fw (v). Given the wind speed, the wind speed probability distribution function can be used, for example, using formula (7) to calculate the probability of the wind speed. Then, enough wind speed points can be taken and their probabilities calculated. The integral problem can be transformed into a differential problem, which helps to reduce the difficulty of calculation and save computing resources.
  • the wind speed distribution parameters include multiple wind speed intervals and the frequency fi of each wind speed interval.
  • the frequency fi of the wind speed interval refers to the percentage of the sum of the duration of the wind speed in a certain wind speed interval to the total duration of the statistical period.
  • the wind speed interval length can be determined from the cut-in wind speed v cin to the cut-out wind speed v cout , for example, 0.5 m/s as an interval. Perform probability statistics and obtain the frequency fi .
  • PR Physical Radio
  • Another method mainly uses the power curve of the unit.
  • FIG2 shows a theoretical power curve of a unit at a turbulence intensity of 0.1 (the turbulence intensity of 0.1 is selected here as a case reference value only, and the specific selected theoretical power curve can be determined according to the model design parameters), and FIG3 shows an actual power curve of the unit (by screening data, from the cut-in wind speed v cin to the cut-out wind speed v cout , with a determined wind speed interval length, such as 0.5 m/s, as an interval, and taking the average value of the actual power), and the frequency fi of each wind speed interval can be obtained, then the theoretical capacity factor ICF and the actual capacity factor CF can be calculated by formulas (9) and (10).
  • P ideal (i) is obtained by interpolating the average wind speed in each wind speed interval from the theoretical power curve
  • P real (i) is the average power in each wind speed interval
  • fi is the frequency of each wind speed interval
  • the historical operation data includes an actual power curve, multiple wind speed intervals, the frequency of each wind speed interval, and the rated power.
  • the step of determining the actual capacity factor in n historical time periods in step S103 includes: for each historical time period, based on the actual power curve, determining the actual power average value of each wind speed interval; determining the expectation of the actual power average value according to the actual power average value and frequency of each wind speed interval as the actual average power of the wind turbine generator set in the historical time period; determining the ratio of the actual average power of the wind turbine generator set in the historical time period to the rated power to obtain the actual capacity factor.
  • the actual power curve integrates the discrete data of the actual power detected during the operation of the unit.
  • the detection data can be directly used to reduce the difficulty of calculation.
  • the actual power average value is the average value of the actual power in the wind speed interval.
  • the average value can be calculated based on the detected data, which is faithful to the detection data and ensures the consistency of the scheme.
  • the historical operation data further includes a theoretical power curve.
  • the step of determining the theoretical capacity factor in n historical time periods in step S103 includes: for each historical time period, based on the theoretical power curve, line, determine the theoretical power average value in each wind speed interval; according to the theoretical power average value and frequency in each wind speed interval, determine the expectation of the theoretical power average value as the theoretical average power of the wind turbine in the historical period; determine the ratio of the theoretical average power of the wind turbine in the historical period to the rated power to obtain the theoretical capacity factor.
  • the theoretical power curve is a power curve obtained by theoretical calculation under the ideal design state of the unit. By combining the theoretical power curve to determine the theoretical average power of the historical period, the theoretical average power of each wind speed interval can be directly used to reduce the difficulty of calculation.
  • the theoretical power average value is based on the average wind speed in each wind speed interval. By interpolating the value obtained in the theoretical power curve, a specific value can be obtained from the theoretical continuous curve, which is convenient for value acquisition and can ensure the reliability of value acquisition.
  • step S105 further utilization of the estimated power generation performance coefficient determined in step S105 is introduced.
  • the power generation performance evaluation method further includes: determining the estimated power generation of the wind turbine generator set in the target future period according to the estimated power generation performance coefficient; determining the estimated revenue generated by the wind turbine generator set adopting the candidate unit control strategy in the target future period according to the estimated power generation, the candidate unit control strategy and the revenue-related variables, wherein the revenue-related variables are the variables required to determine the power generation revenue of the wind turbine generator set.
  • the estimated power generation performance coefficient can reflect the power generation performance of the wind turbine generator set in the target future period, and the estimated power generation in the target future period can be determined accordingly.
  • the control strategy adopted by the unit is embodied in the form of the values of multiple parameters such as the cut-out wind speed, rated power, and rated speed.
  • the difference between different control strategies lies in the different specific values of the parameters such as the cut-out wind speed, rated power, and rated speed. Accordingly, when adjusting the control strategy, the value of at least one of the parameters is adjusted, for example, the cut-out wind speed can be extended, the rated power can be adjusted, and the rated speed can be adjusted.
  • the power generation of the unit will also be different. By combining the estimated power generation and the candidate unit control strategy, a more accurate power generation can be estimated.
  • the estimated revenue that can be brought by adopting a clear candidate unit control strategy can be determined, making the estimated result clearer and more intuitive, which helps to provide a clear basis for the subsequent control strategy of the unit and the active update of the operation and maintenance strategy.
  • the number of target future time periods can be at least one, so that the estimated revenue of at least one target future time period can be clarified as needed.
  • the sum of these multiple estimated revenues can also be calculated to understand the overall estimated revenue.
  • the revenue-related variables include the electricity price in the target future period, a predetermined first relationship function and a second relationship function.
  • the first relationship function is a relationship function between the power generation change and the unit control strategy adjustment amount, and the unit control strategy adjustment amount is the aforementioned cut-out wind speed, rated power, rated speed, and rated power.
  • the first relationship function reflects how much the power generation will change relative to the current power generation after a certain amount of adjustment is made to the parameters therein based on the current unit control strategy. Since the unit control strategy is not adjusted when determining the estimated power generation, the prediction is the amount of power that can be produced by the unit continuing to use the current unit control strategy.
  • the amount of power generation change that can be brought about by adopting the candidate unit control strategy can be determined in combination with the first relationship function.
  • the candidate unit control strategy can be embodied in the form of the adjustment amount of the control parameter, or in the form of the value of the control parameter, and the present disclosure does not limit this.
  • the second relationship function is the relationship function between power generation and unit maintenance cost.
  • the above-mentioned method of determining the estimated revenue generated by the wind turbine generator set adopting the candidate unit control strategy in the target future period according to the estimated power generation, the candidate unit control strategy and the revenue-related variables includes: determining the estimated power generation change corresponding to the candidate unit control strategy according to the adjustment amount of the candidate unit control strategy relative to the current unit control strategy and the first relationship function; determining the sum of the estimated power generation and the estimated power generation change as the estimated total power generation corresponding to the candidate unit control strategy; determining the estimated maintenance cost corresponding to the candidate unit control strategy according to the estimated total power generation and the second relationship function; determining the estimated revenue generated by the wind turbine generator set adopting the candidate unit control strategy in the target future period according to the estimated total power generation, the electricity price and the estimated maintenance cost.
  • the difference between the estimated power generation revenue and the estimated maintenance cost can be obtained, thereby obtaining the estimated revenue.
  • the calculation process has clear logic and ensures the reliability of the estimated results.
  • the first relationship function can be obtained through preliminary simulation calculations, reflecting the relationship between the change in power generation and the adjustment amount of the unit control strategy, and as mentioned above, the control strategy adopted by the unit is embodied in the form of values of multiple parameters, so accordingly, the candidate unit control strategy can reflect the unit control strategy adjustment amount in the form of value adjustment amounts of specific parameters.
  • the value adjustment amount here can be an absolute value or a relative value, as long as it can reflect the adjustment situation;
  • the second relationship function can be obtained by integrating historical power generation and maintenance costs, and as time goes by, the historical power generation and maintenance cost data will gradually increase, so the second relationship function can be continuously updated to improve the accuracy of the second relationship function.
  • the power generation performance evaluation method further includes: adjusting the candidate unit control strategy based on the estimated revenue to obtain the optimized unit control strategy.
  • Each candidate unit control strategy can determine the corresponding estimated revenue using the above method. Benefit, one can be selected from multiple candidate unit control strategies as the optimized unit control strategy to realize the active update of the subsequent control strategy and operation and maintenance strategy of the unit.
  • multiple candidate unit control strategies can be listed in advance, the estimated benefits are calculated respectively, and then one is selected; it can also be given an initial value of a candidate unit control strategy, and then the estimated benefit meets the preset conditions as the goal, for example, but not limited to, with the estimated benefit maximization as the goal, the candidate unit control strategy is iteratively calculated to obtain the optimized unit control strategy. Further, the user can also set the target benefit, and require the estimated benefit corresponding to the optimized unit control strategy to meet the target benefit.
  • the optimized unit control strategy can be determined for each target future time period, and when the iterative calculation method is used to determine the optimized unit control strategy, the sum of the estimated benefits of multiple target future time periods can be taken as the goal to meet the preset conditions and calculated together to take into account the overall benefit.
  • FIG4 shows a schematic flow chart of the specific embodiment.
  • the specific embodiment uses the estimated power generation performance coefficient, the second relationship function between power generation and unit maintenance cost, the target benefit set by the user, the preset operating life of the wind turbine unit, the annual grid electricity price, the initial value of the candidate unit control strategy, and the first relationship function between the power generation change and the unit control strategy adjustment amount as input, takes the estimated benefit maximization as the objective function, performs optimization and optimization, continuously adjusts the candidate unit control strategy, and requires that the estimated benefit corresponding to the optimized unit control strategy must meet the target benefit, so as to obtain the best control strategy for unit operation within the set operating life that should be met while taking into account the target benefit, maintenance cost, the current power generation capacity of the unit, and the grid electricity price of each year.
  • each adjustment of the control strategy such as extension of the cut-out wind speed, change of rated power, rated speed, etc.
  • the first relationship function of the power generation caused by the adjustment of the control strategy can be obtained through the early simulation calculation.
  • the simulation calculation shows that when the cut-out wind speed is extended by 0.5m/s, the rated power is adjusted by 5% and the rated speed is increased by 5% under the consideration of storms.
  • the change in the power generation of the unit caused by the adjustment of the control strategy such as speed adjustment of 0.5% is shown in Table 1 below.
  • the adjustment amount (0.5m/s, 5%, 0.5%) is only an example value. In actual simulation, it can be set according to the specific model.
  • ⁇ E is the power generation change
  • ⁇ C is the unit control strategy adjustment
  • f( ⁇ E, ⁇ c) is the first relationship function between the power generation change and the unit control strategy adjustment, which can be obtained by first summarizing the relationship between the power generation E+ ⁇ E and the unit control strategy C+ ⁇ C.
  • the calculation formula for the estimated revenue during the operation of the unit for m years can be obtained as shown in the following formula (13) and formula (14), where G is the estimated total revenue for m years, Price i is the annual electricity price, and E i is the estimated total power generation per year.
  • the average value of theoretical power can be taken from the average value of theoretical power in the historical period previously obtained, or the target future period can be further estimated.
  • Power determine the average value of the theoretical power of each historical period and the target future period, hour is the preset number of power generation hours per year.
  • Set the objective function max(G) continuously adjust the control strategy, add to the power generation capacity of the unit itself each year, comprehensively consider the unit maintenance cost, optimize the best unit control strategy, and maximize the objective function.
  • the power generation performance evaluation method of the wind turbine generator set can be executed by the field-level controller of the wind farm, can be executed by the controller of the wind turbine generator set, and can also be executed by developing an independent power generation performance evaluation system.
  • the independent power generation performance evaluation system it can specifically include a wind turbine generator set power generation performance evaluator and a wind turbine generator set parameter optimizer.
  • the wind turbine generator set power generation performance evaluator is used to evaluate the historical power generation performance coefficient, the power generation performance change trend, and the estimated power generation performance coefficient.
  • the wind turbine generator set parameter optimizer is used to determine the estimated power generation and optimize the unit control strategy based on the estimated power generation performance coefficient.
  • FIG6 is a block diagram showing a device for evaluating power generation performance of a wind turbine generator system according to an embodiment of the present disclosure.
  • a wind turbine generator set power generation performance evaluation device 600 includes an acquisition unit 601 , a determination unit 602 , a sorting unit 603 , and a prediction unit 604 .
  • the acquisition unit 601 can acquire the historical operation data of the wind turbine generator set in n historical time periods, where n is a positive integer.
  • the above operation data is data reflecting the real-time operation status of the unit at different times, such as wind speed, power, and power generation.
  • the historical operation data can be data obtained from SCADA; in another example, the historical operation data can be collected from various sensors set on the wind turbine generator set.
  • the determination unit 602 may determine the actual capacity factor and the theoretical capacity factor of the wind turbine generator set in n historical time periods respectively according to the historical operation data.
  • the capacity factor is used to reflect the energy output of a wind turbine.
  • the actual capacity factor is used to reflect the actual energy output of a wind turbine. It can refer to the ratio of the actual power generation (actual power) of a wind turbine during a statistical period to the rated power generation (rated power) of the wind turbine.
  • the theoretical capacity factor is used to reflect the theoretical energy output of a wind turbine. It can refer to the ratio of the theoretical power generation (theoretical power) of a wind turbine during a statistical period to the rated power generation (rated power) of the wind turbine. rate) ratio.
  • the actual power of a wind turbine is affected by both the unit's own power generation performance and environmental factors.
  • the theoretical power is the power of the unit under ideal conditions (that is, when the unit's own power generation performance is optimal), which reflects the influence of environmental factors. Therefore, the difference between the two is caused by the unit itself and can reflect the unit's own power generation performance. Furthermore, since both the actual capacity factor and the theoretical capacity factor introduce the fixed value of the rated power relative to the actual power and the theoretical power, the difference between the actual capacity factor and the theoretical capacity factor can also reflect the difference between the actual power and the theoretical power. On the one hand, it can meet the evaluation needs. On the other hand, the calculation methods of the actual capacity factor and the theoretical capacity factor are more diverse, ensuring the flexibility of the solution. By obtaining the historical operation data in n historical periods, the actual capacity factor and the theoretical capacity factor of each historical period can be calculated. The detailed calculation method will be introduced in detail later, so it will not be repeated here.
  • the determination unit 602 may also determine the historical power generation performance coefficients of the wind turbine generator sets in the n historical time periods respectively based on the actual capacity coefficients and the theoretical capacity coefficients in the n historical time periods.
  • the power generation performance coefficient is used to characterize the power generation performance of the wind turbine generator set itself.
  • the determination unit 602 can determine the ratio of the actual capacity coefficient to the theoretical capacity coefficient of the wind turbine generator set during the period, and the ratio is equal to the ratio of the actual power to the theoretical power. Taking it as the historical power generation performance coefficient during the historical period, a dimensionless performance coefficient can be obtained, which can eliminate the influence of environmental factors and is not limited by the rated power of the unit.
  • the power generation performance of the unit itself tends to decrease with the increase of the operating years, so the actual power is often less than the theoretical power, causing the above ratio to be less than 1, and the smaller the ratio, the greater the difference between the actual power and the theoretical power, and the worse the power generation performance of the unit itself. In other words, the larger the ratio, the better the power generation performance of the unit itself.
  • the determination unit 602 can also convert the ratio to a power value, specifically by first calculating the average value of the theoretical power of n historical periods, and then multiplying the average value by the aforementioned ratio of each historical period to obtain the actual power of each historical period. Using the average value of the theoretical power of n historical periods as a conversion coefficient instead of the theoretical power of a certain year can unify the evaluation criteria.
  • the sorting unit 603 may obtain the power generation performance change trend according to the historical power generation performance coefficients in the n historical time periods.
  • the power generation performance change trend may be obtained by a fitting method, such as, but not limited to, linear fitting.
  • the prediction unit 604 can determine the estimated power generation performance coefficient of the wind turbine generator set in the target future period according to the power generation performance change trend.
  • the estimated power generation performance coefficient is used to predict the wind turbine generator set in the target future period.
  • the power generation performance in the coming period is estimated.
  • the generalized change trend can be converted into a clear point value in the future, thereby reflecting the power generation performance change results of the wind turbine generator set from a more intuitive future perspective, and providing a basis for the subsequent control strategy and active update of the operation and maintenance strategy of the unit. It should be understood that as time goes by, the above steps S101 to S104 can also be performed periodically to evaluate the power generation performance change trend of the wind turbine generator set; the entire power generation performance evaluation device 600 of the present disclosure can also be run periodically.
  • the determination unit 602 can also determine the ratio of the actual value of the power generation index of the wind turbine generator set in n historical time periods to the rated value according to the historical operation data, and obtain the actual capacity coefficient, wherein the power generation index includes at least one of the power generation time, the online power and the power; according to the historical operation data, determine the ratio of the theoretical average power of the wind turbine generator set in n historical time periods to the rated power, and obtain the theoretical capacity coefficient.
  • the actual capacity coefficient is the ratio of the actual power to the rated power. To calculate the actual capacity coefficient, the ratio can be calculated using the more easily accessible actual power generation time and the rated power generation time, or the actual online power and the rated online power.
  • the actual power can also be calculated by other means, and then the actual power and the rated power are used to calculate the ratio, which ensures the flexibility of the scheme.
  • the theoretical power can be obtained by theoretical calculation.
  • the average level of the theoretical power can be used to characterize the theoretical power of the corresponding historical time period, which ensures the reliability of the calculation result.
  • the historical operation data includes an actual power curve, multiple wind speed intervals, the frequency of each wind speed interval, and the rated power.
  • the determination unit 602 can also determine the actual power average value of each wind speed interval for each historical period based on the actual power curve; determine the expectation of the actual power average value according to the actual power average value and frequency of each wind speed interval as the actual average power of the wind turbine generator set in the historical period; determine the ratio of the actual average power of the wind turbine generator set in the historical period to the rated power to obtain the actual capacity factor.
  • the actual power curve integrates the discrete data of the actual power detected during the operation of the unit.
  • the detection data can be used directly to reduce the difficulty of calculation.
  • the actual power average value is the average value of the actual power in the wind speed interval.
  • the average value can be calculated based on the detected data, which is faithful to the detection data and ensures the consistency of the scheme.
  • the historical operation data also includes a theoretical power curve.
  • the determination unit 602 can also determine, for each historical period, a theoretical power average value for each wind speed interval based on the theoretical power curve; determine an expectation of the theoretical power average value according to the theoretical power average value and frequency of each wind speed interval as the theoretical average power of the wind turbine generator set in the historical period; determine the expected theoretical power average value of the wind turbine generator set in the historical period; The ratio of the theoretical average power to the rated power is used to obtain the theoretical capacity factor.
  • the theoretical power curve is a power curve obtained by theoretical calculation under the ideal design state of the unit.
  • the theoretical average power of each wind speed interval can be directly used, which helps to reduce the difficulty of calculation and save computing resources.
  • the theoretical power average value is based on the average wind speed in each wind speed interval.
  • the historical operation data includes wind speed distribution parameters and rated wind speed, and the wind speed distribution parameters are used to describe the distribution probability of wind speed.
  • the determination unit 602 can also determine the expectation of the third power of wind speed for each historical period according to the wind speed distribution parameters; determine the ratio of the third power of wind speed expectation to the third power of rated wind speed to obtain the theoretical capacity factor.
  • the theoretical capacity factor can be determined with the help of wind speed distribution parameters and rated wind speed, which ensures the simplicity and reliability of the calculation.
  • the wind speed distribution parameters include multiple wind speed intervals and the frequency of each wind speed interval, and do not involve integration problems.
  • Statistical data can be used directly for calculation, which helps to reduce the difficulty of calculation.
  • the power generation performance evaluation device further includes an estimation unit (not shown in the figure), which can determine the estimated power generation of the wind turbine generator set in the target future period according to the estimated power generation performance coefficient; determine the estimated revenue generated by the wind turbine generator set adopting the candidate unit control strategy in the target future period according to the estimated power generation, the candidate unit control strategy and the revenue-related variables, wherein the revenue-related variables are the variables required to determine the power generation revenue of the wind turbine generator set.
  • the estimated power generation performance coefficient can reflect the power generation performance of the wind turbine generator set in the target future period, and the estimated power generation in the target future period can be determined accordingly.
  • the control strategy adopted by the unit is embodied in the form of the values of multiple parameters such as the cut-out wind speed, rated power, and rated speed.
  • the difference between different control strategies lies in the different specific values of the parameters such as the cut-out wind speed, rated power, and rated speed. Accordingly, when adjusting the control strategy, the value of at least one of the parameters is adjusted, for example, the cut-out wind speed can be extended, the rated power can be adjusted, and the rated speed can be adjusted.
  • the power generation of the unit will also be different.
  • the estimated power generation and the candidate unit control strategy By combining the estimated power generation and the candidate unit control strategy, a more accurate power generation can be estimated.
  • the estimated benefits that can be brought by adopting a clear candidate unit control strategy can be determined, making the estimated results clearer and more intuitive, which is helpful for the subsequent control strategy of the unit and the proactive operation and maintenance strategy.
  • the number of target future time periods may be at least one, so as to clarify the estimated revenue of at least one target future time period as needed.
  • the sum of the multiple estimated revenues may also be calculated to understand the overall estimated revenue.
  • the revenue-related variables include the electricity price of the target future period, a predetermined first relationship function, and a second relationship function.
  • the first relationship function is a relationship function between the power generation change and the unit control strategy adjustment amount.
  • the unit control strategy adjustment amount is the adjustment amount of the value of at least one of the aforementioned multiple control parameters such as the cut-out wind speed, rated power, and rated speed.
  • the first relationship function reflects how much the power generation will change relative to the current power generation after a certain amount of adjustment is made to the parameters based on the current unit control strategy. Since the unit control strategy is not adjusted when determining the estimated power generation, the prediction is the amount of power that can be produced by the unit continuing to use the current unit control strategy.
  • the power generation change that can be brought about by adopting the candidate unit control strategy can be determined in combination with the first relationship function.
  • the candidate unit control strategy can be embodied in the form of the adjustment amount of the control parameter, or in the form of the value of the control parameter, and the present disclosure does not limit this.
  • the second relationship function is a relationship function between the power generation and the unit maintenance cost.
  • the estimation unit can also determine the estimated power generation change corresponding to the candidate unit control strategy based on the adjustment amount of the candidate unit control strategy relative to the current unit control strategy and the first relationship function; determine the sum of the estimated power generation and the estimated power generation change as the estimated total power generation corresponding to the candidate unit control strategy; determine the estimated maintenance cost corresponding to the candidate unit control strategy based on the estimated total power generation and the second relationship function; determine the estimated revenue generated by the wind turbine generator set adopting the candidate unit control strategy in the target future period based on the estimated total power generation, electricity price, and estimated maintenance cost.
  • the difference between the estimated power generation income and the estimated maintenance cost can be obtained, thereby obtaining the estimated revenue.
  • the calculation process is logically clear, ensuring the reliability of the estimation result.
  • the first relationship function can be obtained through preliminary simulation calculations, reflecting the relationship between the change in power generation and the adjustment amount of the unit control strategy, and as mentioned above, the control strategy adopted by the unit is embodied in the form of values of multiple parameters, so accordingly, the candidate unit control strategy can reflect the unit control strategy adjustment amount in the form of value adjustment amounts of specific parameters.
  • the value adjustment amount here can be an absolute value or a relative value, as long as it can reflect the adjustment situation;
  • the second relationship function can be obtained by integrating historical power generation and maintenance costs, and as time goes by, the historical power generation and maintenance cost data will gradually increase, so the second relationship function can be continuously updated to improve the accuracy of the second relationship function.
  • the power generation performance evaluation device also includes an optimization unit (not shown in the figure), which can adjust the candidate unit control strategy based on the estimated benefit to obtain the optimized unit control strategy.
  • Each candidate unit control strategy can use the optimization unit to determine the corresponding estimated benefit.
  • one of the multiple candidate unit control strategies can be selected as the optimized unit control strategy to achieve the active update of the subsequent control strategy and operation and maintenance strategy of the unit.
  • the candidate unit control strategy when selecting one from multiple candidate unit control strategies, it can be to list multiple candidate unit control strategies in advance, calculate the estimated benefits respectively, and then select one from them; it can also be to first give an initial value of a candidate unit control strategy, and then take the estimated benefit satisfying the preset conditions as the goal, for example, but not limited to, with the goal of maximizing the estimated benefit, the candidate unit control strategy is iteratively calculated to obtain the optimized unit control strategy.
  • an optimized unit control strategy can be determined separately for each target future time period, and when using an iterative calculation method to determine the optimized unit control strategy, the sum of the estimated benefits of multiple target future time periods that meet the preset conditions can be taken as the target and calculated together to take into account the overall benefit.
  • the acquisition unit 601, determination unit 602, sorting unit 603, and prediction unit 604 of the present disclosure can be attributed to the wind turbine power generation performance evaluator, and the estimation unit and optimization unit can be attributed to the wind turbine parameter optimizer.
  • the power generation performance evaluation method of the wind turbine generator set according to the embodiment of the present disclosure can be written as a computer program and stored on a computer-readable storage medium.
  • the instructions corresponding to the computer program are executed by the processor, the power generation performance evaluation method of the wind turbine generator set as described above can be implemented.
  • Examples of computer-readable storage media include: read-only memory (ROM), random access programmable read-only memory (PROM), electrically erasable programmable read-only memory (EEPROM), random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), flash memory, non-volatile memory, CD-ROM, CD-R, CD+R, CD-RW, CD+RW, DVD-ROM, DVD-R, DVD+R, DVD-RW, DVD+RW, DVD-RAM, BD-ROM, BD-R, BD-R LTH, BD-RE, Blu-ray or optical disk storage, hard disk drive (HDD), solid state drive (SSD), card storage (such as, Multimedia Card, Secure Digital (SD) card or Extreme Digital (XD) card), magnetic tape, floppy disk, magneto-optical data storage device, optical data storage device, hard disk, solid state disk and any other device configured to store the computer program and any associated data, data files and data structures in a non-transitory manner and
  • the computer program and any associated data files and data structures are stored in a non-transitory manner.
  • Data, data files and data structures are distributed across networked computer systems so that a computer program and any associated data, data files and data structures are stored, accessed and executed in a distributed manner by one or more processors or computers.
  • FIG. 7 is a block diagram illustrating a computer device according to an embodiment of the present disclosure.
  • a computer device 700 includes at least one memory 701 and at least one processor 702, wherein the at least one memory 701 stores a set of computer executable instructions, and when the set of computer executable instructions is executed by the at least one processor 702, a method for evaluating power generation performance of a wind turbine generator set according to an exemplary embodiment of the present disclosure is executed.
  • the computer device 700 may be a PC, a tablet device, a personal digital assistant, a smart phone, or other device capable of executing the above-mentioned instruction set.
  • the computer device 700 is not necessarily a single electronic device, but may also be any device or circuit collection capable of executing the above-mentioned instructions (or instruction sets) individually or in combination.
  • the computer device 700 may also be part of an integrated control system or a system manager, or may be configured as a portable electronic device interconnected with a local or remote (e.g., via wireless transmission) interface.
  • processor 702 may include a central processing unit (CPU), a graphics processing unit (GPU), a programmable logic device, a dedicated processor system, a microcontroller, or a microprocessor.
  • the processor may also include an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, etc.
  • the processor 702 may execute instructions or codes stored in the memory 701, which may also store data. Instructions and data may also be sent and received over a network via a network interface device, which may employ any known transmission protocol.
  • the memory 701 may be integrated with the processor 702, for example, by placing RAM or flash memory within an integrated circuit microprocessor or the like.
  • the memory 701 may include a separate device, such as an external disk drive, a storage array, or any other storage device that can be used by a database system.
  • the memory 701 and the processor 702 may be operatively coupled, or may communicate with each other, such as through an I/O port, a network connection, etc., so that the processor 702 can read files stored in the memory.
  • the computer device 700 may also include a video display (such as a liquid crystal display) and a user interaction interface (such as a keyboard, a mouse, a touch input device, etc.) All components of the computer device 700 may be connected to each other via a bus and/or a network.
  • a video display such as a liquid crystal display
  • a user interaction interface such as a keyboard, a mouse, a touch input device, etc.
  • the method and device described in this disclosure are aimed at wind turbines already in operation in a wind farm. No additional measuring devices need to be installed, and the measurement data generated by the real-time operation of the in-service wind turbines can be transferred.
  • SCADA data including wind speed distribution, real-time power of the unit, etc., by eliminating the influence of the external environment and only considering the influence of the unit itself, evaluates the power generation performance of the wind turbine during its operation. According to the historical power generation performance coefficient obtained by the evaluation, the changes in the power generation performance of the unit itself during the operation period of the unit can be clarified, and the power generation performance change trend of the unit can be obtained, and then the future power generation performance of the unit can be speculated.
  • the present disclosure can also combine the speculation results, comprehensively consider the maintenance cost and the on-grid electricity price, and give the corresponding optimized unit control strategy according to the target income set by the user, which can cope with different scenarios such as maintaining the existing power generation status, accelerating production to obtain maximum income, and decommissioning and replacement, so that the unit can meet the user's expectations.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Evolutionary Computation (AREA)
  • General Physics & Mathematics (AREA)
  • Geometry (AREA)
  • Computer Hardware Design (AREA)
  • Chemical & Material Sciences (AREA)
  • Mechanical Engineering (AREA)
  • Combustion & Propulsion (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Sustainable Energy (AREA)
  • Sustainable Development (AREA)
  • Artificial Intelligence (AREA)
  • Wind Motors (AREA)

Abstract

本公开提供一种风力发电机组的发电性能评估方法和装置。发电性能评估方法包括：获取风力发电机组分别在n个历史时段内的历史运行数据；根据历史运行数据，确定实际容量系数和理论容量系数；基于实际容量系数和理论容量系数，确定历史发电性能系数，得到发电性能变化趋势；根据发电性能变化趋势，确定目标未来时段的预估发电性能系数。

Description

风力发电机组的发电性能评估方法和装置 技术领域
本公开涉及风力发电技术领域，更具体地，涉及一种风力发电机组的发电性能评估方法和装置。
背景技术
随着市场上的风力发电机组的装机容量与运行年限的增长，目前大批量机组即将达到设计年限，或是由于电价政策的改变等原因面临着升级更新的问题。在风力发电机组整个生命周期过程中，其控制策略以及运维策略的改变，一般是由于大部件失效被动引起的。为了提高风力发电机组整体收益，将控制策略以及运维策略等更新由被动转为主动，需要评估已运行风力发电机组的发电性能，作为后续机组去向的判断依据。
现有的风力发电机组发电性能评估，多从功率曲线或功率特性、故障率等进行，判断机组发电性能的变化趋势。但是通过这些方法进行评估时，影响机组发电性能的因素除了风机本身以外，还有外部的环境影响，而一般风机本身引起的发电性能变化相对缓和，环境影响造成的发电性能变化相对明显，所以对于风力发电机组发电性能在一定时间内的改变，机组本身引起的发电性能的变化将被掩盖，并且这些环境影响均有一定的波动性，因而难以判断在长时间内风力发电机组本身引起的发电性能变化。
发明内容
因此，如何可靠评估风力发电机组本身引起的发电性能变化，至关重要。
在一个总的方面，提供一种风力发电机组的发电性能评估方法，包括：获取所述风力发电机组分别在n个历史时段内的历史运行数据，所述n为正整数；根据所述历史运行数据，确定所述风力发电机组分别在所述n个历史时段内的实际容量系数和理论容量系数；基于所述n个历史时段内的实际容量系数和理论容量系数，确定所述风力发电机组分别在所述n个历史时段内的历史发电性能系数；根据所述n个历史时段内的历史发电性能系数，得到 发电性能变化趋势；根据所述发电性能变化趋势，确定所述风力发电机组在目标未来时段的预估发电性能系数，所述预估发电性能系数用于对所述目标未来时段的发电性能进行预估。
可选地，所述根据所述历史运行数据，确定所述风力发电机组分别在所述n个历史时段内的实际容量系数和理论容量系数，包括：根据所述历史运行数据，分别确定在所述n个历史时段内所述风力发电机组的发电指标的实际值与额定值的比值，得到所述实际容量系数，其中，所述发电指标包括发电时长、上网电量和功率中的至少一个；根据所述历史运行数据，分别确定在所述n个历史时段内所述风力发电机组的理论平均功率与额定功率的比值，得到所述理论容量系数。
可选地，在所述发电指标包括功率的情况下，所述历史运行数据包括实际功率曲线、多个风速区间、每个所述风速区间的频率、额定功率，所述根据所述历史运行数据，分别确定在所述n个历史时段内所述风力发电机组的发电指标的实际值与额定值的比值，得到所述实际容量系数，包括：对于每个所述历史时段，基于所述实际功率曲线，确定每个所述风速区间的实际功率平均值；根据每个所述风速区间的所述实际功率平均值和频率，确定所述实际功率平均值的期望，作为所述风力发电机组在所述历史时段的实际平均功率；确定所述风力发电机组在所述历史时段的所述实际平均功率与所述额定功率的比值，得到所述实际容量系数。
可选地，所述历史运行数据还包括理论功率曲线，所述根据所述历史运行数据，分别确定在所述n个历史时段内所述风力发电机组的理论平均功率与额定功率的比值，得到所述理论容量系数，包括：对于每个所述历史时段，基于所述理论功率曲线，确定每个所述风速区间的理论功率平均值；根据每个所述风速区间的所述理论功率平均值和频率，确定所述理论功率平均值的期望，作为所述风力发电机组在所述历史时段的所述理论平均功率；确定所述风力发电机组在所述历史时段的所述理论平均功率与所述额定功率的比值，得到所述理论容量系数。
可选地，所述实际功率平均值是所述风速区间内的实际功率的平均值；和/或所述理论功率平均值是基于每个所述风速区间的平均风速，通过在所述理论功率曲线中进行插值得到的值。
可选地，所述历史运行数据包括风速分布参数和额定风速，所述风速分 布参数用于描述风速的分布概率，其中，所述根据所述历史运行数据，分别确定在所述n个历史时段内所述风力发电机组的理论平均功率与额定功率的比值，得到所述理论容量系数，包括：对于每个所述历史时段，根据所述风速分布参数，确定风速的三次幂的期望；确定所述风速的三次幂的期望与所述额定风速的三次幂的比值，得到所述理论容量系数。
可选地，所述风速分布参数包括风速概率密度函数或风速概率分布函数；或所述风速分布参数包括多个风速区间及每个所述风速区间的频率。
可选地，所述发电性能评估方法还包括：根据所述预估发电性能系数，确定所述风力发电机组在所述目标未来时段的预估发电量；根据所述预估发电量、候选机组控制策略和收益相关变量，确定所述风力发电机组在所述目标未来时段采用所述候选机组控制策略所产生的预估收益，其中，所述收益相关变量是确定所述风力发电机组的发电收益所需使用的变量。
可选地，所述收益相关变量包括所述目标未来时段的电价、预先确定的第一关系函数和第二关系函数，所述第一关系函数是发电变化量与机组控制策略调整量的关系函数，所述第二关系函数是发电量与机组维修成本的关系函数，其中，所述根据所述预估发电量、候选机组控制策略和收益相关变量，确定所述风力发电机组在所述目标未来时段采用所述候选机组控制策略所产生的预估收益，包括：根据所述候选机组控制策略相对于当前机组控制策略的调整量和所述第一关系函数，确定与所述候选机组控制策略对应的预估发电变化量；确定所述预估发电量与所述预估发电变化量的和，作为所述候选机组控制策略对应的预估发电总量；根据所述预估发电总量和所述第二关系函数，确定与所述候选机组控制策略对应的预估维修成本；根据所述预估发电总量、所述电价、所述预估维修成本，确定所述风力发电机组在所述目标未来时段采用所述候选机组控制策略所产生的所述预估收益。
可选地，所述发电性能评估方法还包括：基于所述预估收益，调整所述候选机组控制策略，得到优化机组控制策略。
在另一总的方面，提供一种风力发电机组的发电性能评估装置，包括：获取单元，被配置为获取所述风力发电机组分别在n个历史时段内的历史运行数据，所述n为正整数；确定单元，被配置为根据所述历史运行数据，确定所述风力发电机组分别在所述n个历史时段内的实际容量系数和理论容量系数；所述确定单元还被配置为基于所述n个历史时段内的实际容量系数和 理论容量系数，确定所述风力发电机组分别在所述n个历史时段内的历史发电性能系数；整理单元，被配置为根据所述n个历史时段内的历史发电性能系数，得到发电性能变化趋势；预测单元，被配置为根据所述发电性能变化趋势，确定所述风力发电机组在目标未来时段的预估发电性能系数，所述预估发电性能系数用于对所述目标未来时段的发电性能进行预估。
可选地，所述确定单元还被配置为：根据所述历史运行数据，分别确定在所述n个历史时段内所述风力发电机组的发电指标的实际值与额定值的比值，得到所述实际容量系数，其中，所述发电指标包括发电时长、上网电量和功率中的至少一个；根据所述历史运行数据，分别确定在所述n个历史时段内所述风力发电机组的理论平均功率与额定功率的比值，得到所述理论容量系数。
可选地，在所述发电指标包括功率的情况下，所述历史运行数据包括实际功率曲线、多个风速区间、每个所述风速区间的频率、额定功率，所述确定单元还被配置为：对于每个所述历史时段，基于所述实际功率曲线，确定每个所述风速区间的实际功率平均值；根据每个所述风速区间的所述实际功率平均值和频率，确定所述实际功率平均值的期望，作为所述风力发电机组在所述历史时段的实际平均功率；确定所述风力发电机组在所述历史时段的所述实际平均功率与所述额定功率的比值，得到所述实际容量系数。
可选地，所述历史运行数据还包括理论功率曲线，所述确定单元还被配置为：对于每个所述历史时段，基于所述理论功率曲线，确定每个所述风速区间的理论功率平均值；根据每个所述风速区间的所述理论功率平均值和频率，确定所述理论功率平均值的期望，作为所述风力发电机组在所述历史时段的所述理论平均功率；确定所述风力发电机组在所述历史时段的所述理论平均功率与所述额定功率的比值，得到所述理论容量系数。
可选地，所述实际功率平均值是所述风速区间内的实际功率的平均值；和/或所述理论功率平均值是基于每个所述风速区间的平均风速，通过在所述理论功率曲线中进行插值得到的值。
可选地，所述历史运行数据包括风速分布参数和额定风速，所述风速分布参数用于描述风速的分布概率，所述确定单元还被配置为：对于每个所述历史时段，根据所述风速分布参数，确定风速的三次幂的期望；确定所述风速的三次幂的期望与所述额定风速的三次幂的比值，得到所述理论容量系数。
可选地，所述风速分布参数包括风速概率密度函数或风速概率分布函数；或所述风速分布参数包括多个风速区间及每个所述风速区间的频率。
可选地，所述发电性能评估装置还包括预估单元，被配置为：根据所述预估发电性能系数，确定所述风力发电机组在所述目标未来时段的预估发电量；根据所述预估发电量、候选机组控制策略和收益相关变量，确定所述风力发电机组在所述目标未来时段采用所述候选机组控制策略所产生的预估收益，其中，所述收益相关变量是确定所述风力发电机组的发电收益所需使用的变量。
可选地，所述收益相关变量包括所述目标未来时段的电价、预先确定的第一关系函数和第二关系函数，所述第一关系函数是发电变化量与机组控制策略调整量的关系函数，所述第二关系函数是发电量与机组维修成本的关系函数，所述预估单元还被配置为：根据所述候选机组控制策略相对于当前机组控制策略的调整量和所述第一关系函数，确定与所述候选机组控制策略对应的预估发电变化量；确定所述预估发电量与所述预估发电变化量的和，作为所述候选机组控制策略对应的预估发电总量；根据所述预估发电总量和所述第二关系函数，确定与所述候选机组控制策略对应的预估维修成本；根据所述预估发电总量、所述电价、所述预估维修成本，确定所述风力发电机组在所述目标未来时段采用所述候选机组控制策略所产生的所述预估收益。
可选地，所述发电性能评估装置还包括优化单元，被配置为基于所述预估收益，调整所述候选机组控制策略，得到优化机组控制策略。
在另一总的方面，提供一种计算机可读存储介质，当所述计算机可读存储介质中的指令被至少一个处理器运行时，促使所述至少一个处理器执行如上所述的发电性能评估方法。
在另一总的方面，提供一种计算机设备，包括：至少一个处理器；至少一个存储计算机可执行指令的存储器，其中，所述计算机可执行指令在被所述至少一个处理器运行时，促使所述至少一个处理器执行如上所述的发电性能评估方法。
本公开通过使用能够反映实际功率的实际容量系数，并结合理论容量系数得到历史发电性能系数，能够有效评估机组自身的发电性能，还可利用进一步确定出的发电性能变化趋势来反映机组自身的发电性能变化。此外，通过根据发电性能变化趋势来确定风力发电机组在目标未来时段的预估发电性 能系数，能够用更直观的未来视角体现风力发电机组的发电性能变化，从而为机组后续的控制策略以及运维策略的主动更新提供依据。同时，本公开使用机组的历史运行数据，无需额外安装测量装置，因而优化成本低，可迁移性强。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
图1是示出根据本公开的实施例的风力发电机组的发电性能评估方法的流程图；
图2是示出根据本公开的实施例的理论功率曲线的示意图；
图3是示出根据本公开的实施例的实际功率曲线的示意图；
图4是示出根据本公开的一个具体实施例的控制策略优化方案的示意流程图；
图5是示出根据本公开的实施例的风力发电机组的发电性能评估系统的示意流程图；
图6是示出根据本公开的实施例的风力发电机组的发电性能评估装置的框图；
图7是示出根据本公开的实施例的计算机设备的框图。
具体实施方式
提供下面的具体实施方式以帮助读者获得对在此描述的方法、设备和/或系统的全面理解。然而，在理解本申请的公开之后，在此描述的方法、设备和/或系统的各种改变、修改和等同物将是清楚的。例如，在此描述的操作的顺序仅是示例，并且不限于在此阐述的那些顺序，而是除了必须以特定的顺序发生的操作之外，可如在理解本申请的公开之后将是清楚的那样被改变。此外，为了更加清楚和简明，本领域已知的特征的描述可被省略。
在此描述的特征可以以不同的形式来实现，而不应被解释为限于在此描述的示例。相反，已提供在此描述的示例，以仅示出实现在此描述的方法、设备和/或系统的许多可行方式中的一些可行方式，所述许多可行方式在理解本申请的公开之后将是清楚的。
如在此使用的，术语“和/或”包括相关联的所列项中的任何一个以及任何两个或更多个的任何组合。
尽管在此可使用诸如“第一”、“第二”和“第三”的术语来描述各种构件、组件、区域、层或部分，但是这些构件、组件、区域、层或部分不应被这些术语所限制。相反，这些术语仅用于将一个构件、组件、区域、层或部分与另一构件、组件、区域、层或部分进行区分。因此，在不脱离示例的教导的情况下，在此描述的示例中所称的第一构件、第一组件、第一区域、第一层或第一部分也可被称为第二构件、第二组件、第二区域、第二层或第二部分。
在说明书中，当元件(诸如，层、区域或基底)被描述为“在”另一元件上、“连接到”或“结合到”另一元件时，该元件可直接“在”另一元件上、直接“连接到”或“结合到”另一元件，或者可存在介于其间的一个或多个其他元件。相反，当元件被描述为“直接在”另一元件上、“直接连接到”或“直接结合到”另一元件时，可不存在介于其间的其他元件。
在此使用的术语仅用于描述各种示例，并不将用于限制公开。除非上下文另外清楚地指示，否则单数形式也意在包括复数形式。术语“包含”、“包括”和“具有”说明存在叙述的特征、数量、操作、构件、元件和/或它们的组合，但不排除存在或添加一个或多个其他特征、数量、操作、构件、元件和/或它们的组合。
除非另有定义，否则在此使用的所有术语(包括技术术语和科学术语)具有与由本公开所属领域的普通技术人员在理解本公开之后通常理解的含义相同的含义。除非在此明确地如此定义，否则术语(诸如，在通用词典中定义的术语)应被解释为具有与它们在相关领域的上下文和本公开中的含义一致的含义，并且不应被理想化或过于形式化地解释。
此外，在示例的描述中，当认为公知的相关结构或功能的详细描述将引起对本公开的模糊解释时，将省略这样的详细描述。
图1是示出根据本公开的实施例的风力发电机组的发电性能评估方法的流程图。
参照图1，在步骤S101，获取风力发电机组分别在n个历史时段内的历史运行数据。n为正整数。每个历史时段的长度可以按需设置，例如为1个月、1个季度、1年，并且不同历史时段之间可以有公共部分，例如对于同一 年，可以同时获取每个月、每个季度、一整年的历史运行数据，当然，对于这种情况，往往不必重复获取相同的数据，只要能够将数据与所属的历史时段对应起来即可。例如，可统一获取n个历史时段内的所有历史运行数据，并且每个历史运行数据都附有时间戳，在需要使用某个历史时段内的历史运行数据时，可使用时间戳处于该历史时段内的历史运行数据。
上述运行数据是反映机组在不同时刻的实时运行情况的数据，例如包括风速、功率、发电量。作为示例，历史运行数据可以是从SCADA(Supervisory Control And Data Acquisition，数据采集与监视控制系统)获取的数据；另一个示例中，历史运行数据可以是从风力发电机组上设置的各个传感器采集得到。
在步骤S102，根据历史运行数据，确定风力发电机组分别在n个历史时段内的实际容量系数和理论容量系数。
容量系数用于反映风力发电机组的能量输出情况。上述实际容量系数用于反映风力发电机组的实际的能量输出情况，其可以是指统计周期内风电机组实际发电量(实际功率)和该机组额定发电量(额定功率)的比值。上述理论容量系数用于反映风力发电机组的理论上的能量输出情况，其可以是指统计周期内风电机组理论发电量(理论功率)和该机组额定发电量(额定功率)的比值。
风电机组的实际功率同时受到机组自身发电性能和环境因素的影响，理论功率则是在理想状态下(也就是机组自身发电性能最优的情况下)机组的功率，体现了环境因素的影响，所以二者之间的差异由机组自身引起，可以体现机组自身的发电性能。进一步地，由于相对于实际功率和理论功率，实际容量系数和理论容量系数均引入了额定功率这一确定的值，因而实际容量系数和理论容量系数的差异也可以反映实际功率和理论功率的差异，一方面能够满足评估需要，另一方面，实际容量系数和理论容量系数的计算方式更多样，保障了方案的灵活性。通过获取的n个历史时段内的历史运行数据，可以计算得到各个历史时段的实际容量系数和理论容量系数。关于详细的计算方式，将在后文中详细介绍，此处不再赘述。
在步骤S103，基于n个历史时段内的实际容量系数和理论容量系数，确定风力发电机组分别在n个历史时段内的历史发电性能系数。
发电性能系数用于表征风力发电机组自身的发电性能。作为示例，针对 一个历史时段，可确定在该时段内风力发电机组的实际容量系数与理论容量系数的比值，该比值等于实际功率与理论功率的比值，将之作为该历史时段内的历史发电性能系数，能够得到一个无量纲的性能系数，既可除去环境因素的影响，又不受机组的额定功率限制。应理解，机组自身的发电性能往往会随着运行年限的增长而降低，所以实际功率往往会小于理论功率，造成上述比值小于1，并且该比值越小，表明实际功率与理论功率的差异越大，机组自身的发电性能越差。换言之，该比值越大，表明机组自身的发电性能越好。
此外，也可将该比值转换到功率值，具体是先计算出n个历史时段的理论功率的平均值，再将该平均值与各个历史时段的前述比值相乘，即可得到每个历史时段的实际功率。使用n个历史时段的理论功率的平均值作为转换系数，而不是某一年的理论功率，可统一评判标准。
在步骤S104，根据n个历史时段内的历史发电性能系数，得到发电性能变化趋势。作为示例，可通过拟合的方法得到发电性能变化趋势，例如，但不限于，线性拟合。如前所述，不同历史时段之间可以有公共部分，例如对于同一年，可以同时获取每个月、每个季度、一整年的历史运行数据，进而得到机组在每个月、每个季度、一整年的历史发电性能系数，再基于这些历史发电性能系数，拟合发电性能变化趋势。
在步骤S105，根据发电性能变化趋势，确定风力发电机组在目标未来时段的预估发电性能系数。预估发电性能系数用于对风力发电机组在目标未来时段的发电性能进行预估。通过应用发电性能变化趋势，确定预估发电性能系数，能够将概括性的变化趋势转换为未来明确的点值，从而用更直观的未来视角体现风力发电机组的发电性能变化结果，为机组后续的控制策略以及运维策略的主动更新提供了依据。应理解，随着时间的推移，还可以周期性地执行上述步骤S101至步骤S104，以评估风电机组的发电性能变化趋势；还可周期性地执行本公开的整个发电性能评估方法。
接下来对如何确定历史发电性能系数，也就是步骤S103，进行具体介绍。
可选地，步骤S103包括：根据历史运行数据，分别确定在n个历史时段内风力发电机组的发电指标的实际值与额定值的比值，得到实际容量系数，其中，发电指标包括发电时长、上网电量和功率中的至少一个；根据历史运行数据，分别确定在n个历史时段内风力发电机组的理论平均功率与额定功 率的比值，得到理论容量系数。如前所述，实际容量系数是实际功率与额定功率的比值，为计算实际容量系数，可以使用更容易获取的实际发电时长和额定发电时长来计算比值，或者实际上网电量和额定上网电量来计算比值，也可以通过其他方式计算实际功率，再使用实际功率与额定功率来计算比值，保障了方案的灵活性。对于理论容量系数，理论功率可经由理论计算得到。通过使用所针对的历史时段内的理论平均功率，能够用理论功率的平均水平来表征相应历史时段的理论功率，保障了计算结果的可靠性。
具体来说，根据在历史运行数据中主要使用的数据不同，本公开可提供两类方法来确定实际容量系数和理论容量系数。
一种方法主要使用机组的额定风速。该方法的推导过程如下：
对于实际容量系数CF(Capacity Factor)，所使用的发电指标可为发电时长、上网电量或功率，以历史时段的长度为1年为例，实际容量系数可为机组运行年有效利用小时数与全年小时数的比值，或如公式(1)所示，为机组实际运行年上网电量Ereal与额定年上网电量Erate的比值，或如公式(2)所示，为机组年实际平均功率Preal与额定功率Prate的比值。

对于理论容量系数ICF(Ideal Capacity Factor)，可仅考虑风速这一环境因素。如公式(3)～(6)所示，Pideal、fw(v)、Pe(v)分别为理论平均功率、额定功率、风速概率密度函数、与风速相关的功率计算函数；ρ、Cp、η、A、vr、vcin、vcout分别为空气密度、功率系数、效率系数、扫风面积、额定风速、切入风速、切除风速。其中Pideal仅跟风速有关，默认其余参数(ρ、Cp、η、A、vr)与额定功率Prate一致，则Pideal计算公式又可写为(5)所示，Prate可直接采用机组设计值。则理论容量系数ICF可由公式(6)表示。



基于上述推导过程，可选地，历史运行数据包括风速分布参数和额定风速，风速分布参数用于描述风速的分布概率，步骤S103中确定在n个历史时段内的理论容量系数的步骤包括：对于每个历史时段，根据风速分布参数，确定风速的三次幂的期望；确定风速的三次幂的期望与额定风速的三次幂的比值，得到理论容量系数。通过利用理论平均功率Pideal与额定功率Prate一致的内容，可借助风速分布参数和额定风速vr来确定理论容量系数ICF，保障了计算的简洁和可靠。
可选地，参照公式(6)，风速分布参数可采用两种形式来描述：
(1)风速分布参数包括风速概率密度函数fw(v)或风速概率分布函数，可利用特殊的分布类型来得到理论上的风速概率密度函数fw(v)或风速概率分布函数F(v)，提高计算的可行性。应理解，风速概率密度函数fw(v)是风速概率分布函数F(v)的一阶导数。
作为示例，假设获取到的风速数据仅有平均风速vave，风速分布可遵从瑞利分布，得到风速概率分布函数：
对于能够得到风速概率分布函数的情况，不必再计算具体的风速概率密度函数fw(v)，给定风速，即可利用风速概率分布函数，例如利用公式(7)，算出该风速的概率，进而取足够多的风速点并计算其概率，可将积分问题化为微分问题，有助于降低计算难度，节约计算资源。
(2)风速分布参数包括多个风速区间及每个风速区间的频率fi。风速区间的频率fi是指对于统计的时段，某个风速区间内的风速出现的时长之和占统计时段总时长的百分比，参照公式(6)，此时同样不涉及积分问题，可以直接使用统计数据进行计算，降低计算难度。作为示例，假设获取到的风速数据较充足(符合统计学大样本定义，即样本量n≥30)，可从切入风速vcin到切出风速vcout，以确定的风速区间长度为间隔，例如以0.5m/s为一间隔，进 行概率统计，得到频率fi。
进一步地，可定义PR(Performance Radio)为机组的历史发电性能系数，如公式(8)所示，表征机组除去风速影响后的发电性能。
另一种方法主要使用机组的功率曲线。
作为示例，如图2所示为某机组在湍流强度0.1的理论功率曲线(此处选取了湍流强度0.1，仅为案例参考值，具体选取的理论功率曲线可根据机型设计参数定)，如图3所示为该机组的实际功率曲线(通过筛选数据，从切入风速vcin到切出风速vcout，以确定的风速区间长度，例如0.5m/s，为一间隔，取实际功率的平均值得到)，并且可以得到各风速区间的频率fi，则理论容量系数ICF、实际容量系数CF可以通过公式(9)、(10)计算。

其中，Pideal(i)由各风速区间的平均风速于理论功率曲线插值得到，Preal(i)为各风速区间功率平均值，fi为各风速区间的频率。
可选地，在发电指标包括功率的情况下，历史运行数据包括实际功率曲线、多个风速区间、每个风速区间的频率、额定功率，步骤S103中确定在n个历史时段内的实际容量系数的步骤包括：对于每个历史时段，基于实际功率曲线，确定每个风速区间的实际功率平均值；根据每个风速区间的实际功率平均值和频率，确定实际功率平均值的期望，作为风力发电机组在历史时段的实际平均功率；确定风力发电机组在历史时段的实际平均功率与额定功率的比值，得到实际容量系数。实际功率曲线整合了机组运行中检测到的实际功率的离散数据，通过结合实际功率曲线来确定历史时段的实际平均功率，能够直接使用检测数据，降低计算难度。作为示例，实际功率平均值是风速区间内的实际功率的平均值，可基于检测到的数据求取平均值，忠于检测数据，保证了方案的一致性。
可选地，历史运行数据还包括理论功率曲线，步骤S103中确定在n个历史时段内的理论容量系数的步骤包括：对于每个历史时段，基于理论功率曲 线，确定每个风速区间的理论功率平均值；根据每个风速区间的理论功率平均值和频率，确定理论功率平均值的期望，作为风力发电机组在历史时段的理论平均功率；确定风力发电机组在历史时段的理论平均功率与额定功率的比值，得到理论容量系数。理论功率曲线是机组在设计的理想状态下经理论计算得到的功率曲线，通过结合理论功率曲线来确定历史时段的理论平均功率，能够直接使用各个风速区间的理论平均功率，降低计算难度。作为示例，理论功率平均值是基于每个风速区间的平均风速，通过在理论功率曲线中进行插值得到的值，可实现从理论的连续曲线中取得特定值，既便于取值，又可保障取值可靠。
接下来对步骤S105中确定的预估发电性能系数的进一步利用进行介绍。
在一些实施例中，在步骤S105之后，根据本公开的实施例的发电性能评估方法还包括：根据预估发电性能系数，确定风力发电机组在目标未来时段的预估发电量；根据预估发电量、候选机组控制策略和收益相关变量，确定风力发电机组在目标未来时段采用候选机组控制策略所产生的预估收益，其中，收益相关变量是确定风力发电机组的发电收益所需使用的变量。预估发电性能系数能够反映风力发电机组在目标未来时段的发电性能，可据此确定目标未来时段的预估发电量。机组所采取的控制策略以切出风速、额定功率、额定转速等多个参数的取值的形式体现，不同的控制策略之间的区别就在于切出风速、额定功率、额定转速等参数的具体取值不同，相应地，调整控制策略时，调整的就是这其中至少一个参数的取值，例如可以延长切出风速、调整额定功率、调整额定转速等。采取不同的控制策略时，机组的发电量也会有所不同。通过结合预估发电量和候选机组控制策略，能够预估出更准确的发电量，再结合收益相关变量，可确定出采用明确的候选机组控制策略所能带来的预估收益，使得预估结果更清楚直观，有助于为机组后续的控制策略以及运维策略的主动更新提供清晰的依据。应理解，目标未来时段的数量可为至少一个，以便按需明确至少一个目标未来时段的预估收益。当目标未来时段的数量为多个时，还可计算这多个预估收益的总和，以了解整体的预估收益。
可选地，收益相关变量包括目标未来时段的电价、预先确定的第一关系函数和第二关系函数。第一关系函数是发电变化量与机组控制策略调整量的关系函数，机组控制策略调整量就是前述的切出风速、额定功率、额定转速 等多个控制参数中的至少一个参数的取值的调整量，第一关系函数反映了在基于当前的机组控制策略对其中的参数做出一定量的调整后，发电量会相对于当前的发电量产生多少变化。由于确定预估发电量时没有对机组控制策略进行调整，所以预测的是机组继续沿用当前的机组控制策略所能产出的电量，此时通过对照候选机组控制策略与当前机组控制策略之间的调整量，就能够结合第一关系函数确定采用候选机组控制策略所能带来的发电变化量。作为示例，候选机组控制策略可以控制参数的调整量的形式体现，也可以控制参数的取值的形式体现，本公开对此不作限制。第二关系函数是发电量与机组维修成本的关系函数。其中，上述的根据预估发电量、候选机组控制策略和收益相关变量，确定风力发电机组在目标未来时段采用候选机组控制策略所产生的预估收益，包括：根据候选机组控制策略相对于当前机组控制策略的调整量和第一关系函数，确定与候选机组控制策略对应的预估发电变化量；确定预估发电量与预估发电变化量的和，作为候选机组控制策略对应的预估发电总量；根据预估发电总量和第二关系函数，确定与候选机组控制策略对应的预估维修成本；根据预估发电总量、电价、预估维修成本，确定风力发电机组在目标未来时段采用候选机组控制策略所产生的预估收益。通过逐步确定候选机组控制策略引起的预估发电变化量、预估发电总量、预估维修成本，并结合电价和预估发电总量确定预估发电收入，能够得到预估发电收入与预估维修成本的差值，从而得到预估收益，计算过程逻辑清晰，保障了预估结果的可靠性。
应理解，第一关系函数可通过前期仿真计算得到，反映了发电变化量与机组控制策略调整量的关系，并且如前所述，机组所采取的控制策略以多个参数的取值的形式体现，所以相应地，候选机组控制策略可以具体参数的取值调整量的形式体现机组控制策略调整量，这里的取值调整量可以是绝对值，也可以是相对值，只要可以反映调整情况即可；第二关系函数可结合历史上的发电量和维修成本整合得到，并且随着时间的推移，历史上的发电量和维修成本数据会逐渐增加，因此可以不断更新第二关系函数，提升第二关系函数的准确性。
可选地，根据本公开的实施例的发电性能评估方法还包括：基于预估收益，调整候选机组控制策略，得到优化机组控制策略。每个候选机组控制策略都能够利用上述方法确定出对应的预估收益，有鉴于此，通过基于预估收 益，可从多个候选机组控制策略中选择一个，作为优化机组控制策略，实现机组后续的控制策略以及运维策略的主动更新。应理解，从多个候选机组控制策略中选择一个时，可以是提前列举多个候选机组控制策略，分别计算预估收益，再从中选择一个；也可以是先给定一个候选机组控制策略的初始值，然后以预估收益满足预设条件为目标，例如，但不限于，以预估收益最大化为目标，对候选机组控制策略进行迭代计算，得到优化机组控制策略。进一步地，还可由用户设置目标收益，并要求优化机组控制策略对应的预估收益需满足目标收益。还应理解，当目标未来时段的数量为多个时，可针对每个目标未来时段，分别确定优化机组控制策略，并且在采用迭代计算的方法来确定优化机组控制策略时，可将多个目标未来时段的预估收益总和满足预设条件作为目标，一起计算，以兼顾整体收益。
接下来介绍从预估发电性能系数到优化机组控制策略的一个具体实施例。
图4示出了该具体实施例的示意流程图。参照图4，总体来说，该具体实施例以预估发电性能系数、发电量与机组维修成本之间的第二关系函数、用户设定的目标收益、风电机组的预设运行年限、每年的电网电价、候选机组控制策略的初始值、发电变化量与机组控制策略调整量的第一关系函数作为输入，以预估收益最大化作为目标函数，进行优化寻优，不断进行候选机组控制策略的调整，并要求优化机组控制策略对应的预估收益需满足目标收益，从而在兼顾目标收益、维修成本、机组当前的发电能力、每一年的电网电价的情况下，在设定应满足的运行年限内，得到机组运行最佳控制策略。
具体来说，关于发电量与机组维修成本之间的第二关系函数，随着机组发电量增加，相应的机组运维成本会随之增加，因此二者存在正相关的关系，可由机组已运行的SCADA数据中每年的发电量与每年的维修成本进行拟合得到。如下公式(11)所示，其中E为发电量，M为机组维修成本，f(E,M)为发电量与机组维修成本之间的第二关系函数，通过以下公式(11)，可根据设置的发电量推算所需的机组维修成本。
E＝f(E,M)×M              (11)
关于候选机组控制策略，控制策略每一次调整，如切出风速延长、额定功率、额定转速的改变等，均会引起的机组发电量的改变。控制策略的调整引起的发电量的第一关系函数可通过前期仿真计算获取，如仿真计算切出风速每延长0.5m/s，在考虑暴风等的情况下，执行额定功率每调整5％，额定转 速每调整0.5％等控制策略调整，引起的机组的发电量的变化值，如下表1所示，通过仿真库计算，可以得到发电变化量与机组控制策略调整量的关系。其中调整量(0.5m/s、5％、0.5％)仅为示例值，实际仿真时，可根据具体机型具体设置。
表1
总结如下公式(12)所示，ΔE为发电变化量，ΔC为机组控制策略调整量，f(ΔE,Δc)为发电变化量与机组控制策略调整量的之间第一关系函数，可通过先总结发电量E+ΔE与机组控制策略C+ΔC之间的关系得到。通过以下公式(12)，可计算得到机组控制策略调整量对应引起的发电量的变化值。
ΔE＝f(ΔE,Δc)×ΔC          (12)
综上所述，在该具体实施例中，可以得到机组运行m年内，预估收益的计算公式如下公式(13)和公式(14)所示，G为m年的预估收益总量，Pricei为每年的电价，Ei为每年的预估发电总量，为理论功率的平均值，可以取此前获取的历史时段的理论功率的平均值，也可以进一步预估目标未来时段的 功率，确定各个历史时段和目标未来时段整体的理论功率的平均值，hour为预设每年的发电小时数。设定目标函数max(G)，不断调整控制策略，在每一年的机组本身的发电能力上添加，综合考虑机组维修成本，优化得到最佳的机组控制策略，使得目标函数最大。

根据本公开的实施例的风力发电机组的发电性能评估方法，可由风电场的场级控制器执行，也可以由风力发电机组的控制器执行，还可以开发独立的发电性能评估系统来执行。对于独立的发电性能评估系统，具体可包括风电机组发电性能评估器和风电机组参数优化器，参照图5，风电机组发电性能评估器用于评估历史发电性能系数、发电性能变化趋势、预估发电性能系数，风电机组参数优化器用于根据预估发电性能系数确定预估发电量、优化机组控制策略。
图6是示出根据本公开的实施例的风力发电机组的发电性能评估装置的框图。
参照图6，风力发电机组的发电性能评估装置600包括获取单元601、确定单元602、整理单元603、预测单元604。
获取单元601可获取风力发电机组分别在n个历史时段内的历史运行数据，n为正整数。上述运行数据是反映机组在不同时刻的实时运行情况的数据，例如包括风速、功率、发电量。作为示例，历史运行数据可以是从SCADA获取的数据；另一个示例中，历史运行数据可以是从风力发电机组上设置的各个传感器采集得到。
确定单元602可根据历史运行数据，确定风力发电机组分别在n个历史时段内的实际容量系数和理论容量系数。
容量系数用于反映风力发电机组的能量输出情况。上述实际容量系数用于反映风力发电机组的实际的能量输出情况，其可以是指统计周期内风电机组实际发电量(实际功率)和该机组额定发电量(额定功率)的比值。上述理论容量系数用于反映风力发电机组的理论上的能量输出情况，其可以是指统计周期内风电机组理论发电量(理论功率)和该机组额定发电量(额定功 率)的比值。
风电机组的实际功率同时受到机组自身发电性能和环境因素的影响，理论功率则是在理想状态下(也就是机组自身发电性能最优的情况下)机组的功率，体现了环境因素的影响，所以二者之间的差异由机组自身引起，可以体现机组自身的发电性能。进一步地，由于相对于实际功率和理论功率，实际容量系数和理论容量系数均引入了额定功率这一确定的值，因而实际容量系数和理论容量系数的差异也可以反映实际功率和理论功率的差异，一方面能够满足评估需要，另一方面，实际容量系数和理论容量系数的计算方式更多样，保障了方案的灵活性。通过获取的n个历史时段内的历史运行数据，可以计算得到各个历史时段的实际容量系数和理论容量系数。关于详细的计算方式，将在后文中详细介绍，此处不再赘述。
确定单元602还可基于n个历史时段内的实际容量系数和理论容量系数，确定风力发电机组分别在n个历史时段内的历史发电性能系数。
发电性能系数用于表征风力发电机组自身的发电性能。作为示例，针对一个历史时段，确定单元602可确定在该时段内风力发电机组的实际容量系数与理论容量系数的比值，该比值等于实际功率与理论功率的比值，将之作为该历史时段内的历史发电性能系数，能够得到一个无量纲的性能系数，既可除去环境因素的影响，又不受机组的额定功率限制。应理解，机组自身的发电性能往往会随着运行年限的增长而降低，所以实际功率往往会小于理论功率，造成上述比值小于1，并且该比值越小，表明实际功率与理论功率的差异越大，机组自身的发电性能越差。换言之，该比值越大，表明机组自身的发电性能越好。
此外，确定单元602也可将该比值转换到功率值，具体是先计算出n个历史时段的理论功率的平均值，再将该平均值与各个历史时段的前述比值相乘，即可得到每个历史时段的实际功率。使用n个历史时段的理论功率的平均值作为转换系数，而不是某一年的理论功率，可统一评判标准。
整理单元603可根据n个历史时段内的历史发电性能系数，得到发电性能变化趋势。作为示例，可通过拟合的方法得到发电性能变化趋势，例如，但不限于，线性拟合。
预测单元604可根据发电性能变化趋势，确定风力发电机组在目标未来时段的预估发电性能系数，预估发电性能系数用于对风力发电机组在目标未 来时段的发电性能进行预估。通过应用发电性能变化趋势，确定预估发电性能系数，能够将概括性的变化趋势转换为未来明确的点值，从而用更直观的未来视角体现风力发电机组的发电性能变化结果，为机组后续的控制策略以及运维策略的主动更新提供了依据。应理解，随着时间的推移，还可以周期性地执行上述步骤S101至步骤S104，以评估风电机组的发电性能变化趋势；还可周期性地运行本公开的整个发电性能评估装置600。
可选地，确定单元602还可根据历史运行数据，分别确定在n个历史时段内风力发电机组的发电指标的实际值与额定值的比值，得到实际容量系数，其中，发电指标包括发电时长、上网电量和功率中的至少一个；根据历史运行数据，分别确定在n个历史时段内风力发电机组的理论平均功率与额定功率的比值，得到理论容量系数。如前所述，实际容量系数是实际功率与额定功率的比值，为计算实际容量系数，可以使用更容易获取的实际发电时长和额定发电时长来计算比值，或者实际上网电量和额定上网电量来计算比值，也可以通过其他方式计算实际功率，再使用实际功率与额定功率来计算比值，保障了方案的灵活性。对于理论容量系数，理论功率可经由理论计算得到。通过使用所针对的历史时段内的理论平均功率，能够用理论功率的平均水平来表征相应历史时段的理论功率，保障了计算结果的可靠性。
可选地，在发电指标包括功率的情况下，历史运行数据包括实际功率曲线、多个风速区间、每个风速区间的频率、额定功率，确定单元602还可对于每个历史时段，基于实际功率曲线，确定每个风速区间的实际功率平均值；根据每个风速区间的实际功率平均值和频率，确定实际功率平均值的期望，作为风力发电机组在历史时段的实际平均功率；确定风力发电机组在历史时段的实际平均功率与额定功率的比值，得到实际容量系数。实际功率曲线整合了机组运行中检测到的实际功率的离散数据，通过结合实际功率曲线来确定历史时段的实际平均功率，能够直接使用检测数据，降低计算难度。作为示例，实际功率平均值是风速区间内的实际功率的平均值，可基于检测到的数据求取平均值，忠于检测数据，保证了方案的一致性。
可选地，历史运行数据还包括理论功率曲线，确定单元602还可对于每个历史时段，基于理论功率曲线，确定每个风速区间的理论功率平均值；根据每个风速区间的理论功率平均值和频率，确定理论功率平均值的期望，作为风力发电机组在历史时段的理论平均功率；确定风力发电机组在历史时段 的理论平均功率与额定功率的比值，得到理论容量系数。理论功率曲线是机组在设计的理想状态下经理论计算得到的功率曲线，通过结合理论功率曲线来确定历史时段的理论平均功率，能够直接使用各个风速区间的理论平均功率，有助于降低计算难度，节约计算资源。作为示例，理论功率平均值是基于每个风速区间的平均风速，通过在理论功率曲线中进行插值得到的值，可实现从理论的连续曲线中取得特定值，既便于取值，又可保障取值可靠。
可选地，历史运行数据包括风速分布参数和额定风速，风速分布参数用于描述风速的分布概率，确定单元602还可对于每个历史时段，根据风速分布参数，确定风速的三次幂的期望；确定风速的三次幂的期望与额定风速的三次幂的比值，得到理论容量系数。通过利用理论平均功率与额定功率一致的内容，可借助风速分布参数和额定风速来确定理论容量系数，保障了计算的简洁和可靠。
可选地，风速分布参数包括风速概率密度函数或风速概率分布函数，可利用特殊的分布类型来得到理论上的风速概率密度函数或风速概率分布函数，提高计算的可行性。
可选地，风速分布参数包括多个风速区间及每个风速区间的频率，不涉及积分问题，可以直接使用统计数据进行计算，有助于降低计算难度。
可选地，发电性能评估装置还包括预估单元(图中未示出)，可根据预估发电性能系数，确定风力发电机组在目标未来时段的预估发电量；根据预估发电量、候选机组控制策略和收益相关变量，确定风力发电机组在目标未来时段采用候选机组控制策略所产生的预估收益，其中，收益相关变量是确定风力发电机组的发电收益所需使用的变量。预估发电性能系数能够反映风力发电机组在目标未来时段的发电性能，可据此确定目标未来时段的预估发电量。机组所采取的控制策略以切出风速、额定功率、额定转速等多个参数的取值的形式体现，不同的控制策略之间的区别就在于切出风速、额定功率、额定转速等参数的具体取值不同，相应地，调整控制策略时，调整的就是这其中至少一个参数的取值，例如可以延长切出风速、调整额定功率、调整额定转速等。采取不同的控制策略时，机组的发电量也会有所不同。通过结合预估发电量和候选机组控制策略，能够预估出更准确的发电量，再结合收益相关变量，可确定出采用明确的候选机组控制策略所能带来的预估收益，使得预估结果更清楚直观，有助于为机组后续的控制策略以及运维策略的主动 更新提供清晰的依据。应理解，目标未来时段的数量可为至少一个，以便按需明确至少一个目标未来时段的预估收益。当目标未来时段的数量为多个时，还可计算这多个预估收益的总和，以了解整体的预估收益。
可选地，收益相关变量包括目标未来时段的电价、预先确定的第一关系函数和第二关系函数。第一关系函数是发电变化量与机组控制策略调整量的关系函数，机组控制策略调整量就是前述的切出风速、额定功率、额定转速等多个控制参数中的至少一个参数的取值的调整量，第一关系函数反映了在基于当前的机组控制策略对其中的参数做出一定量的调整后，发电量会相对于当前的发电量产生多少变化。由于确定预估发电量时没有对机组控制策略进行调整，所以预测的是机组继续沿用当前的机组控制策略所能产出的电量，此时通过对照候选机组控制策略与当前机组控制策略之间的调整量，就能够结合第一关系函数确定采用候选机组控制策略所能带来的发电变化量。作为示例，候选机组控制策略可以控制参数的调整量的形式体现，也可以控制参数的取值的形式体现，本公开对此不作限制。第二关系函数是发电量与机组维修成本的关系函数。预估单元还可根据候选机组控制策略相对于当前机组控制策略的调整量和第一关系函数，确定与候选机组控制策略对应的预估发电变化量；确定预估发电量与预估发电变化量的和，作为候选机组控制策略对应的预估发电总量；根据预估发电总量和第二关系函数，确定与候选机组控制策略对应的预估维修成本；根据预估发电总量、电价、预估维修成本，确定风力发电机组在目标未来时段采用候选机组控制策略所产生的预估收益。通过逐步确定候选机组控制策略引起的预估发电变化量、预估发电总量、预估维修成本，并结合电价和预估发电总量确定预估发电收入，能够得到预估发电收入与预估维修成本的差值，从而得到预估收益，计算过程逻辑清晰，保障了预估结果的可靠性。应理解，第一关系函数可通过前期仿真计算得到，反映了发电变化量与机组控制策略调整量的关系，并且如前所述，机组所采取的控制策略以多个参数的取值的形式体现，所以相应地，候选机组控制策略可以具体参数的取值调整量的形式体现机组控制策略调整量，这里的取值调整量可以是绝对值，也可以是相对值，只要可以反映调整情况即可；第二关系函数可结合历史上的发电量和维修成本整合得到，并且随着时间的推移，历史上的发电量和维修成本数据会逐渐增加，因此可以不断更新第二关系函数，提升第二关系函数的准确性。
可选地，发电性能评估装置还包括优化单元(图中未示出)，可基于预估收益，调整候选机组控制策略，得到优化机组控制策略。每个候选机组控制策略都能够利用优化单元确定出对应的预估收益，有鉴于此，通过基于预估收益，可从多个候选机组控制策略中选择一个，作为优化机组控制策略，实现机组后续的控制策略以及运维策略的主动更新。应理解，从多个候选机组控制策略中选择一个时，可以是提前列举多个候选机组控制策略，分别计算预估收益，再从中选择一个；也可以是先给定一个候选机组控制策略的初始值，然后以预估收益满足预设条件为目标，例如，但不限于，以预估收益最大化为目标，对候选机组控制策略进行迭代计算，得到优化机组控制策略。还应理解，当目标未来时段的数量为多个时，可针对每个目标未来时段，分别确定优化机组控制策略，并且在采用迭代计算的方法来确定优化机组控制策略时，可将多个目标未来时段的预估收益总和满足预设条件作为目标，一起计算，以兼顾整体收益。
需说明的是，对应于前述的发电性能评估系统，本公开的获取单元601、确定单元602、整理单元603、预测单元604可归于风电机组发电性能评估器，预估单元和优化单元可归于风电机组参数优化器。
根据本公开的实施例的风力发电机组的发电性能评估方法可被编写为计算机程序并被存储在计算机可读存储介质上。当所述计算机程序对应的指令被处理器执行时，可实现如上所述的风力发电机组的发电性能评估方法。计算机可读存储介质的示例包括：只读存储器(ROM)、随机存取可编程只读存储器(PROM)、电可擦除可编程只读存储器(EEPROM)、随机存取存储器(RAM)、动态随机存取存储器(DRAM)、静态随机存取存储器(SRAM)、闪存、非易失性存储器、CD-ROM、CD-R、CD+R、CD-RW、CD+RW、DVD-ROM、DVD-R、DVD+R、DVD-RW、DVD+RW、DVD-RAM、BD-ROM、BD-R、BD-R LTH、BD-RE、蓝光或光盘存储器、硬盘驱动器(HDD)、固态硬盘(SSD)、卡式存储器(诸如，多媒体卡、安全数字(SD)卡或极速数字(XD)卡)、磁带、软盘、磁光数据存储装置、光学数据存储装置、硬盘、固态盘以及任何其他装置，所述任何其他装置被配置为以非暂时性方式存储计算机程序以及任何相关联的数据、数据文件和数据结构并将所述计算机程序以及任何相关联的数据、数据文件和数据结构提供给处理器或计算机使得处理器或计算机能执行所述计算机程序。在一个示例中，计算机程序以及任何相关联的数 据、数据文件和数据结构分布在联网的计算机系统上，使得计算机程序以及任何相关联的数据、数据文件和数据结构通过一个或多个处理器或计算机以分布式方式存储、访问和执行。
图7是示出根据本公开的实施例的计算机设备的框图。
参照图7，计算机设备700包括至少一个存储器701和至少一个处理器702，所述至少一个存储器701中存储有计算机可执行指令集合，当计算机可执行指令集合被至少一个处理器702执行时，执行根据本公开的示例性实施例的风力发电机组的发电性能评估方法。
作为示例，计算机设备700可以是PC计算机、平板装置、个人数字助理、智能手机、或其他能够执行上述指令集合的装置。这里，计算机设备700并非必须是单个的电子设备，还可以是任何能够单独或联合执行上述指令(或指令集)的装置或电路的集合体。计算机设备700还可以是集成控制系统或系统管理器的一部分，或者可被配置为与本地或远程(例如，经由无线传输)以接口互联的便携式电子设备。
在计算机设备700中，处理器702可包括中央处理器(CPU)、图形处理器(GPU)、可编程逻辑装置、专用处理器系统、微控制器或微处理器。作为示例而非限制，处理器还可包括模拟处理器、数字处理器、微处理器、多核处理器、处理器阵列、网络处理器等。
处理器702可运行存储在存储器701中的指令或代码，其中，存储器701还可以存储数据。指令和数据还可经由网络接口装置而通过网络被发送和接收，其中，网络接口装置可采用任何已知的传输协议。
存储器701可与处理器702集成为一体，例如，将RAM或闪存布置在集成电路微处理器等之内。此外，存储器701可包括独立的装置，诸如，外部盘驱动、存储阵列或任何数据库系统可使用的其他存储装置。存储器701和处理器702可在操作上进行耦合，或者可例如通过I/O端口、网络连接等互相通信，使得处理器702能够读取存储在存储器中的文件。
此外，计算机设备700还可包括视频显示器(诸如，液晶显示器)和用户交互接口(诸如，键盘、鼠标、触摸输入装置等)。计算机设备700的所有组件可经由总线和/或网络而彼此连接。
本公开所描述的方法和装置针对的是风电场中已运行的风电机组，无需安装额外的测量装置，可迁移强。主要基于在役风电机组实时运行所产生的 SCADA数据，包括风速分布、机组实时功率等，通过剔除外部环境的影响，仅考虑机组本身的影响，对风电机组已运行期间的发电性能进行评估，根据评估得到的历史发电性能系数，可以明晰机组已运行时期机组本身的发电性能的变化，并且得到机组的发电性能变化趋势，进而对机组未来的发电性能进行推测。进一步地，本公开还可结合推测结果，综合考虑维修成本、上网电价，根据用户设定的目标收益，给出相应的优化机组控制策略，可应对维持现有发电状态、加速生产以获取最大收益、退役替换等不同场景，使机组达到用户期望。
以上对本公开的具体实施方式进行了详细描述，虽然已表示和描述了一些实施例，但本领域技术人员应该理解，在不脱离由权利要求及其等同物限定其范围的本公开的原理和精神的情况下，可对这些实施例进行修改和变型，这些修改和变型也应在本公开的权利要求的保护范围内。

Claims (13)

  1. 一种风力发电机组的发电性能评估方法，其特征在于，包括：
    获取所述风力发电机组分别在n个历史时段内的历史运行数据，所述n为正整数；
    根据所述历史运行数据，确定所述风力发电机组分别在所述n个历史时段内的实际容量系数和理论容量系数；
    基于所述n个历史时段内的实际容量系数和理论容量系数，确定所述风力发电机组分别在所述n个历史时段内的历史发电性能系数；
    根据所述n个历史时段内的历史发电性能系数，得到发电性能变化趋势；
    根据所述发电性能变化趋势，确定所述风力发电机组在目标未来时段的预估发电性能系数，所述预估发电性能系数用于对所述目标未来时段的发电性能进行预估。
  2. 如权利要求1所述的发电性能评估方法，其特征在于，所述根据所述历史运行数据，确定所述风力发电机组分别在所述n个历史时段内的实际容量系数和理论容量系数，包括：
    根据所述历史运行数据，分别确定在所述n个历史时段内所述风力发电机组的发电指标的实际值与额定值的比值，得到所述实际容量系数，其中，所述发电指标包括发电时长、上网电量和功率中的至少一个；
    根据所述历史运行数据，分别确定在所述n个历史时段内所述风力发电机组的理论平均功率与额定功率的比值，得到所述理论容量系数。
  3. 如权利要求2所述的发电性能评估方法，其特征在于，在所述发电指标包括功率的情况下，所述历史运行数据包括实际功率曲线、多个风速区间、每个所述风速区间的频率、额定功率，所述根据所述历史运行数据，分别确定在所述n个历史时段内所述风力发电机组的发电指标的实际值与额定值的比值，得到所述实际容量系数，包括：
    对于每个所述历史时段，基于所述实际功率曲线，确定每个所述风速区间的实际功率平均值；
    根据每个所述风速区间的所述实际功率平均值和频率，确定所述实际功率平均值的期望，作为所述风力发电机组在所述历史时段的实际平均功率；
    确定所述风力发电机组在所述历史时段的所述实际平均功率与所述额定 功率的比值，得到所述实际容量系数。
  4. 如权利要求3所述的发电性能评估方法，其特征在于，所述历史运行数据还包括理论功率曲线，所述根据所述历史运行数据，分别确定在所述n个历史时段内所述风力发电机组的理论平均功率与额定功率的比值，得到所述理论容量系数，包括：
    对于每个所述历史时段，基于所述理论功率曲线，确定每个所述风速区间的理论功率平均值；
    根据每个所述风速区间的所述理论功率平均值和频率，确定所述理论功率平均值的期望，作为所述风力发电机组在所述历史时段的所述理论平均功率；
    确定所述风力发电机组在所述历史时段的所述理论平均功率与所述额定功率的比值，得到所述理论容量系数。
  5. 如权利要求4所述的发电性能评估方法，其特征在于，
    所述实际功率平均值是所述风速区间内的实际功率的平均值；和/或
    所述理论功率平均值是基于每个所述风速区间的平均风速，通过在所述理论功率曲线中进行插值得到的值。
  6. 如权利要求2所述的发电性能评估方法，其特征在于，所述历史运行数据包括风速分布参数和额定风速，所述风速分布参数用于描述风速的分布概率，其中，所述根据所述历史运行数据，分别确定在所述n个历史时段内所述风力发电机组的理论平均功率与额定功率的比值，得到所述理论容量系数，包括：
    对于每个所述历史时段，根据所述风速分布参数，确定风速的三次幂的期望；
    确定所述风速的三次幂的期望与所述额定风速的三次幂的比值，得到所述理论容量系数。
  7. 如权利要求6所述的发电性能评估方法，其特征在于，
    所述风速分布参数包括风速概率密度函数；或
    所述风速分布参数包括多个风速区间及每个所述风速区间的频率。
  8. 如权利要求1至7中任一项所述的发电性能评估方法，其特征在于，所述发电性能评估方法还包括：
    根据所述预估发电性能系数，确定所述风力发电机组在所述目标未来时 段的预估发电量；
    根据所述预估发电量、候选机组控制策略和收益相关变量，确定所述风力发电机组在所述目标未来时段采用所述候选机组控制策略所产生的预估收益，其中，所述收益相关变量是确定所述风力发电机组的发电收益所需使用的变量。
  9. 如权利要求8所述的发电性能评估方法，其特征在于，所述收益相关变量包括所述目标未来时段的电价、预先确定的第一关系函数和第二关系函数，所述第一关系函数是发电变化量与机组控制策略调整量的关系函数，所述第二关系函数是发电量与机组维修成本的关系函数，
    其中，所述根据所述预估发电量、候选机组控制策略和收益相关变量，确定所述风力发电机组在所述目标未来时段采用所述候选机组控制策略所产生的预估收益，包括：
    根据所述候选机组控制策略相对于当前机组控制策略的调整量和所述第一关系函数，确定与所述候选机组控制策略对应的预估发电变化量；
    确定所述预估发电量与所述预估发电变化量的和，作为所述候选机组控制策略对应的预估发电总量；
    根据所述预估发电总量和所述第二关系函数，确定与所述候选机组控制策略对应的预估维修成本；
    根据所述预估发电总量、所述电价、所述预估维修成本，确定所述风力发电机组在所述目标未来时段采用所述候选机组控制策略所产生的所述预估收益。
  10. 如权利要求8所述的发电性能评估方法，其特征在于，所述发电性能评估方法还包括：
    基于所述预估收益，调整所述候选机组控制策略，得到优化机组控制策略。
  11. 一种风力发电机组的发电性能评估装置，其特征在于，包括：
    获取单元，被配置为获取所述风力发电机组分别在n个历史时段内的历史运行数据，所述n为正整数；
    确定单元，被配置为根据所述历史运行数据，确定所述风力发电机组分别在所述n个历史时段内的实际容量系数和理论容量系数；
    所述确定单元还被配置为基于所述n个历史时段内的实际容量系数和理 论容量系数，确定所述风力发电机组分别在所述n个历史时段内的历史发电性能系数；
    整理单元，被配置为根据所述n个历史时段内的历史发电性能系数，得到发电性能变化趋势；
    预测单元，被配置为根据所述发电性能变化趋势，确定所述风力发电机组在目标未来时段的预估发电性能系数，所述预估发电性能系数用于对所述目标未来时段的发电性能进行预估。
  12. 一种计算机可读存储介质，其特征在于，当所述计算机可读存储介质中的指令被至少一个处理器运行时，促使所述至少一个处理器执行如权利要求1至10中任一项所述的发电性能评估方法。
  13. 一种计算机设备，其特征在于，包括：
    至少一个处理器；
    至少一个存储计算机可执行指令的存储器，
    其中，所述计算机可执行指令在被所述至少一个处理器运行时，促使所述至少一个处理器执行如权利要求1至10中任一项所述的发电性能评估方法。
PCT/CN2023/117205 2022-11-30 2023-09-06 风力发电机组的发电性能评估方法和装置 Ceased WO2024114018A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
CA3261632A CA3261632A1 (en) 2022-11-30 2023-09-06 METHOD AND APPARATUS FOR EVALUATING THE PERFORMANCE OF ENERGY GENERATION FOR A WIND TURBINE GENERATION SYSTEM
EP23896175.9A EP4629125A4 (en) 2022-11-30 2023-09-06 METHOD AND APPARATUS FOR EVALUATING THE PERFORMANCE OF ENERGY GENERATION FOR A WIND TURBINE GENERATION SYSTEM
AU2023399270A AU2023399270A1 (en) 2022-11-30 2023-09-06 Power-generation performance evaluation method and apparatus for wind generating set
US18/880,986 US20260004020A1 (en) 2022-11-30 2023-09-06 Power-generation performance evaluation method and apparatus for wind generating set

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202211525160.9A CN116266247A (zh) 2022-11-30 2022-11-30 风力发电机组的发电性能评估方法和装置
CN202211525160.9 2022-11-30

Publications (1)

Publication Number Publication Date
WO2024114018A1 true WO2024114018A1 (zh) 2024-06-06

Family

ID=86744283

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/117205 Ceased WO2024114018A1 (zh) 2022-11-30 2023-09-06 风力发电机组的发电性能评估方法和装置

Country Status (7)

Country Link
US (1) US20260004020A1 (zh)
EP (1) EP4629125A4 (zh)
CN (1) CN116266247A (zh)
AU (1) AU2023399270A1 (zh)
CA (1) CA3261632A1 (zh)
CL (1) CL2025000124A1 (zh)
WO (1) WO2024114018A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118657546A (zh) * 2024-08-19 2024-09-17 国网浙江省电力有限公司宁波供电公司 一种基于人工智能的电网成本分析方法及系统
CN120073701A (zh) * 2025-02-26 2025-05-30 中国电力科学研究院有限公司 中长期尺度下风电实际容量系数评估方法、系统及设备
CN120522563A (zh) * 2025-07-24 2025-08-22 华南理工大学 一种风力发电机的发电性能评估方法、系统、设备及介质

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116266247A (zh) * 2022-11-30 2023-06-20 新疆金风科技股份有限公司 风力发电机组的发电性能评估方法和装置
CN116881667A (zh) * 2023-08-11 2023-10-13 华能国际电力江苏能源开发有限公司清洁能源分公司 一种风力发电机效益分析方法
CN117311159B (zh) * 2023-10-30 2024-10-22 上海新华控制技术集团科技有限公司 控制系统的自适应调节方法、装置、存储介质及电子设备
CN119982376B (zh) * 2025-03-04 2026-04-03 武汉华源电力设计院有限公司 一种风力发电机组的轴流风机节能控制方法

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160223600A1 (en) * 2015-02-03 2016-08-04 Envision Energy (Jiangsu) Co., Ltd. Power generation performance evaluation method and apparatus for power generator set
CN109345113A (zh) * 2018-09-29 2019-02-15 北京拾易技术有限公司 风电机组性能评估方法及介质
CN111400845A (zh) * 2018-12-27 2020-07-10 北京金风科创风电设备有限公司 风电机组的发电性能评估方法和装置
CN113204886A (zh) * 2021-05-12 2021-08-03 华能昌邑风力发电有限公司 一种风力发电机的发电性能评估方法
CN114510815A (zh) * 2021-11-19 2022-05-17 西安热工研究院有限公司 一种风电机组功率特性评估方法及系统
CN114881379A (zh) * 2022-07-12 2022-08-09 东方电气风电股份有限公司 风电场应发电量估测方法、装置、设备及存储介质
CN116266247A (zh) * 2022-11-30 2023-06-20 新疆金风科技股份有限公司 风力发电机组的发电性能评估方法和装置

Family Cites Families (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103514353A (zh) * 2012-06-29 2014-01-15 国际商业机器公司 新增风机的功率预测方法和系统
CN106022543A (zh) * 2016-06-28 2016-10-12 华电国际宁夏新能源发电有限公司 一种风功率及电量诊断系统
US10598157B2 (en) * 2017-02-07 2020-03-24 International Business Machines Corporation Reducing curtailment of wind power generation
CN108470233B (zh) * 2018-02-01 2020-05-15 华北电力大学 一种智能电网的需求响应能力评估方法和计算设备
JP7267815B2 (ja) * 2019-04-09 2023-05-02 三菱重工業株式会社 風車群発電量評価装置、風車群発電量評価方法、およびプログラム
CN110826899B (zh) * 2019-10-31 2023-01-31 三一重能股份有限公司 一种风力发电机组的性能评估方法、装置、设备及存储介质
CN111273109B (zh) * 2020-03-18 2021-03-12 珠海格力电器股份有限公司 一种能源转换效率测试方法、装置及用电系统
CN114117887B (zh) * 2021-10-28 2024-07-02 华能利津风力发电有限公司 风电机组的在线发电性能的实时评估方法、系统及介质

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160223600A1 (en) * 2015-02-03 2016-08-04 Envision Energy (Jiangsu) Co., Ltd. Power generation performance evaluation method and apparatus for power generator set
CN109345113A (zh) * 2018-09-29 2019-02-15 北京拾易技术有限公司 风电机组性能评估方法及介质
CN111400845A (zh) * 2018-12-27 2020-07-10 北京金风科创风电设备有限公司 风电机组的发电性能评估方法和装置
CN113204886A (zh) * 2021-05-12 2021-08-03 华能昌邑风力发电有限公司 一种风力发电机的发电性能评估方法
CN114510815A (zh) * 2021-11-19 2022-05-17 西安热工研究院有限公司 一种风电机组功率特性评估方法及系统
CN114881379A (zh) * 2022-07-12 2022-08-09 东方电气风电股份有限公司 风电场应发电量估测方法、装置、设备及存储介质
CN116266247A (zh) * 2022-11-30 2023-06-20 新疆金风科技股份有限公司 风力发电机组的发电性能评估方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4629125A4 *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118657546A (zh) * 2024-08-19 2024-09-17 国网浙江省电力有限公司宁波供电公司 一种基于人工智能的电网成本分析方法及系统
CN120073701A (zh) * 2025-02-26 2025-05-30 中国电力科学研究院有限公司 中长期尺度下风电实际容量系数评估方法、系统及设备
CN120522563A (zh) * 2025-07-24 2025-08-22 华南理工大学 一种风力发电机的发电性能评估方法、系统、设备及介质

Also Published As

Publication number Publication date
EP4629125A1 (en) 2025-10-08
CL2025000124A1 (es) 2025-05-09
US20260004020A1 (en) 2026-01-01
AU2023399270A1 (en) 2025-01-23
CN116266247A (zh) 2023-06-20
CA3261632A1 (en) 2025-04-23
EP4629125A4 (en) 2026-03-25

Similar Documents

Publication Publication Date Title
WO2024114018A1 (zh) 风力发电机组的发电性能评估方法和装置
US12112391B2 (en) Methods and systems for machine-learning for prediction of grid carbon emissions
JP7664708B2 (ja) 太陽光発電出力予測装置、電力系統制御システム、需給制御システム、日射強度予測装置、学習装置、太陽光発電出力予測方法および太陽光発電出力予測プログラム
JP6599763B2 (ja) 電力需要予測装置および電力需要予測プログラム
KR102912893B1 (ko) 풍력 발전 단지의 전력 제어 방법 및 장치
CN118249348A (zh) 电力负荷预测方法、装置、电子设备和介质
US20180284706A1 (en) Gas turbine dispatch optimizer
JP5833267B1 (ja) 発電量予測制御装置、発電量予測方法および発電量予測プログラム
CN116839173A (zh) 一种能耗优化方法、装置、存储介质和电子设备
US9739908B2 (en) Utility usage forecasting
CN119990413B (zh) 一种智慧工厂能效优化方法、系统、电子设备及存储介质
CN117540853B (zh) 多模型风电预测方法、装置、计算机设备及存储介质
CN119482395A (zh) 电力系统的负荷预测方法、装置及电子设备
CN119539564A (zh) 上网电量评估的方法及装置、电子设备和存储介质
TW201824044A (zh) 運轉計畫擬訂裝置、運轉計畫擬訂方法及記憶媒體
Singh et al. A novel dynamic imbalance volume forecasting model for balancing market optimization
CN119671241A (zh) 电场发电功率预测的风险评估方法及装置
CN116451066A (zh) 风速订正模型的训练方法、风电场的风速订正方法和装置
US20260092594A1 (en) System and method for estimating wind farm power output
CN115478985B (zh) 风力发电机组发电量评估系统及方法
CN119496141B (zh) 水电站的调度方法、装置、设备、存储介质及程序产品
KR102857702B1 (ko) 에너지 변환효율계수에 기초한 태양광 발전 설비의 이상 상태 탐지 및 발전량 예측 방법
CN117578428B (zh) 风机功率递归预测方法、装置、计算机设备和存储介质
JP6213166B2 (ja) 未知パラメータ推定方法、未知パラメータプログラム及び未知パラメータ推定装置
CN121882336A (zh) 基于海陆资源特性的辐照预测方法及系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23896175

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 18880986

Country of ref document: US

WWE Wipo information: entry into national phase

Ref document number: AU2023399270

Country of ref document: AU

ENP Entry into the national phase

Ref document number: 2023399270

Country of ref document: AU

Date of ref document: 20230906

Kind code of ref document: A

WWE Wipo information: entry into national phase

Ref document number: 2023896175

Country of ref document: EP

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2023896175

Country of ref document: EP

Effective date: 20250630

WWP Wipo information: published in national office

Ref document number: 2023896175

Country of ref document: EP

WWP Wipo information: published in national office

Ref document number: 18880986

Country of ref document: US