WO2022257366A1 - 网络切片自优化方法、基站及存储介质 - Google Patents

网络切片自优化方法、基站及存储介质 Download PDF

Info

Publication number
WO2022257366A1
WO2022257366A1 PCT/CN2021/132853 CN2021132853W WO2022257366A1 WO 2022257366 A1 WO2022257366 A1 WO 2022257366A1 CN 2021132853 W CN2021132853 W CN 2021132853W WO 2022257366 A1 WO2022257366 A1 WO 2022257366A1
Authority
WO
WIPO (PCT)
Prior art keywords
network slice
configuration information
resource configuration
base station
optimization
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/CN2021/132853
Other languages
English (en)
French (fr)
Inventor
郭华
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.)
ZTE Corp
Original Assignee
ZTE Corp
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 ZTE Corp filed Critical ZTE Corp
Priority to US18/562,567 priority Critical patent/US20240251298A1/en
Priority to JP2023567032A priority patent/JP7573124B2/ja
Priority to EP21944862.8A priority patent/EP4329358A4/en
Publication of WO2022257366A1 publication Critical patent/WO2022257366A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/40—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using virtualisation of network functions or resources, e.g. SDN or NFV entities
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/16—Central resource management; Negotiation of resources or communication parameters, e.g. negotiating bandwidth or QoS [Quality of Service]
    • H04W28/24—Negotiating SLA [Service Level Agreement]; Negotiating QoS [Quality of Service]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0893—Assignment of logical groups to network elements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0894—Policy-based network configuration management
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/5003—Managing SLA; Interaction between SLA and QoS
    • H04L41/5009—Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF]
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/5003—Managing SLA; Interaction between SLA and QoS
    • H04L41/5019—Ensuring fulfilment of SLA
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
    • H04L41/5003—Managing SLA; Interaction between SLA and QoS
    • H04L41/5019—Ensuring fulfilment of SLA
    • H04L41/5025—Ensuring fulfilment of SLA by proactively reacting to service quality change, e.g. by reconfiguration after service quality degradation or upgrade
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W28/00—Network traffic management; Network resource management
    • H04W28/02—Traffic management, e.g. flow control or congestion control
    • H04W28/0268—Traffic management, e.g. flow control or congestion control using specific QoS parameters for wireless networks, e.g. QoS class identifier [QCI] or guaranteed bit rate [GBR]

Definitions

  • the present application relates to the field of communication technologies, and in particular to a network slicing self-optimization method, a base station and a storage medium.
  • 5G Fifth Generation
  • network slicing technology in 5G networks is able to select the characteristics required for each slice, such as low latency, high throughput, connection density, spectrum efficiency, traffic capacity, and network efficiency, it contributes to improving efficiency in creating products and services.
  • 5G network slicing technology is mainly used in various vertical industries that have high demand for network communications, such as Internet of Vehicles, emergency communications, and industrial Internet.
  • network communications such as Internet of Vehicles, emergency communications, and industrial Internet.
  • it is necessary to optimize each network slice in real time.
  • vertical industries due to the limited scale and the industry itself does not have the ability to optimize network operation and maintenance, a lot of manual work is required, and the operation and maintenance costs are high.
  • Embodiments of the present application provide a network slicing self-optimization method, a base station, and a storage medium.
  • the embodiment of the present application provides a network slicing self-optimization method, which is applied to a first base station, the first base station is connected to a server, and the server is connected to a second base station, and the network slicing self-optimization method includes : Obtain optimization policy information and index thresholds sent by the server, where the optimization policy information includes first network slice resource configuration information and a parameter optimization model, and the first network slice resource configuration information and the parameter optimization model are both From the second base station; obtain a service level agreement SLA index according to the first network slice resource configuration information and the parameter optimization model; when the SLA index does not meet the index threshold, adjust the first network slice resource Configure information so that the SLA index meets the index threshold.
  • the embodiment of the present application provides a method for self-optimization of network slicing, which is applied to a second base station, where the second base station is connected to a server, and the server is connected to the first base station.
  • the method for self-optimization of network slicing includes: Obtaining the task threshold sent by the server; obtaining local network slice resource configuration information and a parameter optimization model; obtaining first network slice resource configuration information according to the task threshold, the local network slice resource configuration information and the parameter optimization model; sending the first network slice resource configuration information and the parameter optimization model to the first base station through the server, so that the first base station optimizes the model according to the first network slice resource configuration information and the parameter optimization model Obtaining a service level agreement (SLA) index, and enabling the first base station to adjust resource configuration information of the first network slice when the SLA index does not meet the index threshold, so that the SLA index meets the index threshold.
  • SLA service level agreement
  • an embodiment of the present application provides a base station, including a memory, a processor, and a computer program stored on the memory and operable on the processor.
  • the processor executes the computer program, it implements the A self-optimizing method for network slicing.
  • the embodiment of the present application provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, implements the network slicing self-optimization method provided in the embodiment of the present application. Additional features and advantages of the application will be set forth in the description which follows, and, in part, will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
  • FIG. 1 is a schematic structural diagram of a network slicing optimization system for performing a network slicing self-optimization method provided by an embodiment of the present application;
  • FIG. 2 is a schematic flowchart of a network slice self-optimization method provided in an embodiment of the present application
  • FIG. 3 is a schematic diagram of a specific implementation process of step S200 in FIG. 2;
  • FIG. 4 is a schematic diagram of a specific implementation process of step S300 in FIG. 2;
  • FIG. 5 is a schematic diagram of a specific implementation process included after step S200 in FIG. 2;
  • FIG. 6 is a schematic diagram of a specific flow for forming optimization strategy information provided by an embodiment of the present application.
  • FIG. 7 is a schematic flowchart of a network slice self-optimization method provided by an embodiment of the present application.
  • FIG. 8 is a schematic diagram of a specific implementation process of step S900 in FIG. 7;
  • FIG. 9 is a schematic structural diagram of a base station provided by an embodiment of the present application.
  • the embodiment of the present application provides a self-optimization method for network slicing.
  • the server obtains the index threshold and the optimization strategy information from the second base station.
  • the optimization strategy information includes the first network slice resource configuration information and the parameter optimization model, so that the first network slice can be used.
  • the resource configuration information of the first network slice of the second base station and the parameter optimization model obtain the SLA indicator of the service level agreement.
  • the SLA indicator can indicate the performance of the current network slice, and can also indicate the optimization effect of the current network slice. Therefore, other base stations can be obtained through the server
  • the optimization strategy information is used as a data sample to optimize the local base station, thereby expanding the data sample and improving the optimization efficiency and effect.
  • the index threshold is used as the task standard issued by the server to judge the optimization effect of the current base station.
  • the SLA index does not meet the index threshold, it can be considered that the optimization effect of the network slice of the current base station has not yet reached the standard, and the network slice needs to be optimized. Therefore, By adjusting the resource configuration information of the first network slice, the SLA index meets the index threshold, that is, the optimization effect of the network slice of the current base station meets the requirement, and the optimization task is completed. Therefore, through the indicator threshold issued by the server and the SLA indicator representing the current network slicing performance, the configuration parameters of the first base station are adjusted for optimization operations, realizing the self-optimization function of wireless network slicing, reducing the workload of manual optimization, and improving network optimization efficiency.
  • FIG. 1 shows a network slice optimization system 100 for implementing a network slice self-optimization method.
  • the network slice optimization system 100 includes: a server 110, a first base station 120 and a second base station 130, wherein the server 110 communicates with the second base station respectively.
  • a base station 120 is connected to a second base station 130 .
  • the server 110 can be a wireless sub-slice manager, which includes a wireless sub-slice management system (RAN-NSSMF), and the RAN-NSSMF is responsible for completing the resource application of the wireless sub-slice and the wireless The lifecycle of subslices is managed.
  • RAN-NSSMF wireless sub-slice management system
  • the first base station 120 and the second base station 130 connected to the server 110 may be base stations within the coverage of the wireless sub-slice, the first base station 120 is a base station that needs to use the data of other base stations for self-optimization, and the second base station 130 is a base station that can A base station that does not rely on other base station data for optimization. Therefore, under the coordination of the server 110, the first base station 120 can use the optimized data sent by the second base station 130 to the server 110 as the input of machine learning, realize the horizontal federated learning of the base station, and achieve the self-optimization function of the base station.
  • the server 110 is also configured to respond to the instantiation information, determine the base station to be optimized that needs horizontal federated learning optimization and the instantiation configuration data according to the instantiation information, and send the instantiation configuration data to the base station to be optimized.
  • the server 110 is also used to receive the feedback result of the instantiated configuration data from the base station to be optimized, and determine the instantiated base station to be optimized according to the feedback result, so as to facilitate subsequent network slice self-optimization processing of the base station to be optimized.
  • the server 110 can also be connected to a slice management system (Network Slice Management Function, NSMF), that is, a third-party slice management system, wherein the instantiation information can be initiated by NSMF or manually input, and the instantiation information can be used for
  • NSMF Network Slice Management Function
  • the server sends an instantiation operation to instantiate the network slice of the base station, so as to facilitate subsequent network slice optimization tasks.
  • the server 110 can also receive slice optimization task parameters input from the outside, and send the slice optimization task parameters to a designated base station.
  • the slice optimization task parameters can be data related to network slice configuration, and can include optimization algorithm , SLA task indicators and optimization thresholds.
  • the server 110 can also select a base station within the coverage area of the server 110 as the first base station 120 or the second base station 130 through the participant selection algorithm as the first base station 120 or the second base station 130 for delivering the optimization task.
  • the data samples of the preferred base station can meet the task requirements of local network slicing optimization, can not rely on the data samples of other base stations, and can maximize the expansion of other base stations
  • the network slicing optimization task based on data samples is required to provide data samples for the first base station 120 to improve the optimization effect and efficiency of the first base station 120 .
  • the network slicing optimization system 100 described in the embodiment of the present application for performing the network slice self-optimization method is to illustrate the technical solution of the embodiment of the present application more clearly, and does not constitute a limitation to the technical solution provided in the embodiment of the present application.
  • Those skilled in the art know that with the evolution of the network slice optimization system 100 and the emergence of new application scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
  • FIG. 1 does not constitute a limitation to the embodiment of the present application, and may include more or less components than those shown in the illustration, or combine certain components. , or different component arrangements.
  • FIG. 2 shows a flow chart of a network slicing self-optimization method provided in an embodiment of the present application.
  • the network slicing self-optimization method can be applied to a first base station, for example, the first base station shown in FIG. 1, the path Obtaining methods include but are not limited to the following steps:
  • Step S100 obtaining optimization policy information and index thresholds sent by the server, wherein the optimization policy information includes first network slice resource configuration information and a parameter optimization model, the first network slice resource configuration information and the parameter optimization model
  • the models are all from the second base station.
  • the first base station obtains the optimization policy information and the index threshold through the server, wherein the index threshold is used as a standard condition for the base station to complete the optimization task, and the optimization policy information includes the first network slice resource configuration information and parameter optimization model, and the optimization
  • the policy information that is, the resource configuration information of the first network slice and the parameter optimization model come from the second base station, so that the first base station can use the resource configuration information of the first network slice and the parameter optimization model of the second base station to perform subsequent optimization processing to realize the first
  • the horizontal federated learning between the base station and the second base station expands the data samples for the first base station to optimize the network slice, improving the optimization effect and efficiency.
  • the first base station obtains the optimized strategy information of the second base station through the server, that is, the first network slice resource configuration information and the parameter optimization model, and optimizes the network slice.
  • the optimization of network slicing is not effective. It is necessary to set up a centralized point to obtain the data of relevant base stations for network slicing optimization, but it may include user Privacy data, and a large amount of data interaction between the centralized point and the base station is required, which increases the communication overhead and affects the stability of the network.
  • the first base station uses the resource configuration information and parameter model of the first network slice after the optimization process of the second base station to perform subsequent optimization processing on the network slice, which realizes the horizontal federated learning of the base station and eliminates the need to set a centralized point to obtain related base stations.
  • the step of collecting data avoids a large amount of data interaction between the set centralized point and the base station, thereby reducing the communication overhead between the server and the base station, and improving the stability of the network.
  • Step S200 obtaining a service level agreement (SLA) index according to the resource configuration information of the first network slice and the parameter optimization model;
  • SLA service level agreement
  • Step S300 when the SLA indicator does not meet the indicator threshold, adjust the resource configuration information of the first network slice so that the SLA indicator meets the indicator threshold.
  • the SLA index corresponding to the optimized network slice is obtained, and the SLA index can represent the current network slice.
  • Performance which means the availability of the current network slice.
  • the index threshold issued by the server is obtained.
  • the index threshold corresponds to the SLA index, and the index threshold represents the SLA index corresponding to the network slice that successfully completes the optimization task, that is, the optimization task goal.
  • the first network slice resource configuration information is configuration data or policy data related to the network slice, and the network slice is adjusted and optimized by adjusting the first network slice resource configuration information.
  • the adjusted SLA index is obtained by using the adjusted resource configuration information of the first network slice and the parameter optimization model. If the adjusted SLA index still does not meet the index threshold, it is necessary to continue to optimize the network slice, that is, the first network slice needs to be optimized.
  • the slice resource configuration information continues to be adjusted so that the adjusted SLA index meets the index threshold, that is, the adjusted network slice can achieve the optimization task goal. Therefore, by adjusting the resource configuration information of the first network slice, the SLA index meets the index threshold, that is, the optimization effect of the network slice of the current base station meets the requirements, and the optimization task is completed.
  • the resource configuration information of the first network slice from the second base station is adjusted to optimize the operation, and the horizontal federated learning is used to optimize the wireless network slice, reducing Manually optimize workload and improve network optimization efficiency.
  • the first base station will keep adjusting the resource configuration information of the first network slice until the SLA indicator meets the indicator threshold.
  • the number of iterations of SLA can be limited by setting the upper limit of the number of adjustments, that is, the number of adjustments of the resource configuration information of the first network slice is limited.
  • the number of adjustments of the resource configuration information of the first network slice reaches If the upper limit is adjusted, the resource configuration information of the first network slice after the last adjustment is retained, and the resource configuration information of the first network slice after the last adjustment is used as the optimization result, and the optimization process of the network slice is terminated.
  • the first network slice resource configuration information may include at least one of a resource reservation policy, a quality of service configuration policy, or a 5G quality of service indicator, and may also be a 3rd Generation Partnership Project (3rd Generation Partnership Project, 3GPP)
  • the set of parameters related to the SLA index defined in the specification is not specifically limited in this embodiment.
  • the resource configuration information of the first network slice may be the maximum resource reservation ratio parameter in the resource reservation policy, and optimize the network slice by adjusting the maximum resource reservation ratio parameter so that the SLA index meets the index threshold.
  • the resource configuration information of the first network slice may be a quality of service configuration policy, and the network slice may be optimized by adjusting the priority of network traffic in the quality of service configuration policy, so that the SLA index meets the index threshold.
  • the first base station may perform the first network slice resource configuration information according to the gap relationship between the corresponding SLA index and the index threshold adjusted by the first network slice resource configuration information.
  • Adjustment, for example, the resource configuration information of the first network slice can be the maximum resource reservation ratio parameter, after increasing the maximum resource reservation ratio parameter, the gap between the adjusted SLA and the index threshold increases, and then continue in the opposite direction Adjust the parameter of the maximum resource reservation ratio, that is, reduce the parameter of the maximum resource reservation ratio; for another example, after increasing the parameter of the maximum resource reservation ratio, the gap between the adjusted SLA index and the index threshold is narrowed, then maintain the first
  • the adjustment direction of the network slicing resource configuration information reduces the adjustment step, thereby improving the optimization efficiency of the network slicing by the first base station.
  • step S200 in the embodiment shown in FIG. 2 also includes but is not limited to the following steps:
  • Step S210 input the resource configuration information of the first network slice into the parameter optimization model for optimization prediction, and obtain the service level agreement (SLA) index.
  • SLA service level agreement
  • the first network slice resource configuration information and parameter optimization model are from the second base station, and the first network slice resource configuration information and parameter optimization model are data after optimization processing by the second base station, and the first base station passes the server
  • the issued resource configuration information of the first network slice is used as the input parameter of the parameter optimization model, and the optimization prediction of the network slice is carried out to obtain the SLA index.
  • Slicing processing increases the data samples for optimization processing by the first base station, improves the optimization effect of the first base station, makes it easier for the SLA index corresponding to the adjusted network slice to reach the index threshold, completes the optimization task, and improves optimization efficiency.
  • step S300 in the embodiment shown in FIG. 2 also includes but is not limited to the following steps:
  • Step S310 acquiring local second network slice resource configuration information
  • Step S320 adjusting the resource configuration information of the first network slice according to the resource configuration information of the second network slice.
  • the first base station obtains the first network slice resource configuration information and parameter optimization model from the second base station through the server, and uses the first network slice resource configuration information and parameter optimization model optimized by the second base station in the The network slice is optimized in the first base station. Due to the different environmental conditions of each base station, different base stations may need to optimize the content differently. After using the data optimized and processed by other base stations, expand their own data samples and perform optimization processing. For example, the resource configuration information of the first network slice For reference, it is also necessary to adjust according to the local network slice resource configuration information of the base station, so that the SLA index corresponding to the network slice in the base station locally meets the index threshold.
  • the local second network slice resource configuration information of the base station is acquired, wherein the second network slice resource configuration information corresponds to the first network slice resource configuration information, and the first network slice resource configuration information is configured according to the local second network slice resource configuration information
  • the configuration information is adjusted so that the local network slicing optimization processing of the base station conforms to the current environmental conditions of the base station, the SLA index of the local base station can meet the index threshold, complete the optimization task, improve the optimization effect and efficiency of network slicing, and improve the stability of the network.
  • the local second network slice resource configuration information of the base station corresponds to the first network slice resource configuration information from the second base station
  • the second network slice resource configuration information may include resource reservation policy, quality of service configuration policy Or at least one of the 5G service quality indicators, and can also be a set of parameters related to SLA indicators defined in the 3rd Generation Partnership Project (3GPP) specification, and specific parameters of the second network slice resource configuration information
  • 3GPP 3rd Generation Partnership Project
  • step S200 in the embodiment shown in FIG. 2 it also includes but is not limited to the following steps:
  • Step S330 when the SLA indicator satisfies the indicator threshold, report the resource configuration information of the first network slice and the parameter optimization model to the server.
  • the SLA index can be obtained according to the resource configuration information of the first network slice and the parameter optimization model, and the SLA index and the index threshold are judged, and the network slice is detected according to the current resource configuration information of the first network slice and the parameter optimization model. Optimization processing, whether it can meet the optimization task target issued by the server.
  • the SLA index meets the index threshold it can be considered that after the base station locally uses the current first network slice resource configuration information and optimization model to optimize the network slice, the optimized network slice can reach the optimization task goal, that is, the optimization task is completed. The adjustment of the resource configuration information of the first network slice and the optimization of the network slice are terminated.
  • the first base station may also report the optimization failure as an optimization result to the server, so that the server can know the optimization processing progress of the first base station in time and improve optimization efficiency.
  • the first base station can send the first network slice resource configuration information and The parameter optimization model is broadcast to other base stations, so that other base stations will supplement the first network slice resource configuration information and parameter optimization model adjusted by the first base station to their own data samples, thereby assisting other base stations to complete network slice optimization task, and improve the optimization efficiency and optimization effect of the base station.
  • the first base station can monitor its own SLA index.
  • the SLA index does not meet the index threshold, even if the SLA index of the first base station once met the index threshold, the first base station can report the information of starting self-optimization to the server, and adjust The current first network slice resource configuration information enables SLA indicators that meet the indicator threshold to be obtained according to the adjusted first network slice resource configuration information and parameter optimization model, thereby realizing the real-time self-optimization function of the first base station and reducing manual Optimize workload and improve optimization efficiency.
  • FIG. 6 shows that the optimization strategy information is specifically obtained by the following steps:
  • Step S610 acquiring the task threshold sent by the server
  • Step S620 obtaining local network slice resource configuration information and the parameter optimization model
  • Step S630 obtaining candidate SLA indicators according to the local network slice resource configuration information and the parameter optimization model
  • Step S640 when the candidate SLA indicator does not meet the task threshold, adjust the resource configuration information of the local network slice so that the candidate SLA indicator meets the task threshold;
  • Step S650 if the candidate SLA index satisfies the task threshold, determine the adjusted resource configuration information of the local network slice as the first network slice resource configuration information;
  • Step S660 obtaining the optimization strategy information according to the resource configuration information of the first network slice and the parameter optimization model.
  • the optimization policy information can be obtained through processing by the base station.
  • the base station obtains the task threshold sent by the server, as well as the local network slice resource configuration information and parameter optimization model, where the task threshold represents the optimization task goal that the SLA index corresponding to the network slice needs to achieve.
  • the base station uses the local network slice resource configuration information and the parameter optimization model to obtain candidate SLA indicators, and uses the candidate SLA indicators to represent the corresponding performance of the network slice optimized according to the local network slice resource configuration information.
  • the candidate SLA index does not meet the task threshold, that is, the network slice optimized using the current local network slice resource configuration information does not meet the optimization task goal, the candidate SLA index needs to be adjusted so that the candidate SLA index meets the task threshold.
  • the candidate SLA indicators are obtained from the local network slice resource configuration information and the parameter optimization model. Therefore, the local network slice resource configuration information is adjusted, and the network slice is optimized using the adjusted local network slice resource configuration information, so that after optimization The candidate SLA indicators of meet the task threshold, so the local data of the base station can be used to complete the self-optimization task.
  • the candidate SLA index meets the task threshold, that is, the network slice obtained by using the adjusted local network slice resource configuration information and the parameter optimization model can complete the optimization task goal
  • the adjusted local The network slice resource configuration information is determined as the first network slice resource configuration information
  • the optimization strategy information is obtained according to the first network slice resource configuration information and the parameter optimization model, so that the optimization result of the local base station can be shared with other base stations through the server, that is, the optimization strategy information , to assist other base stations to complete optimization tasks, reduce the communication overhead between the server and the base station, increase the data samples of other base stations, and improve the optimization effect and efficiency.
  • the specific parameters of the local network slice resource configuration information are the same as the specific parameters of the first network slice resource configuration information, and since the specific parameters related to the first network slice resource configuration information have been described in the above embodiments, in order to avoid Redundancy, which will not be specifically described in this embodiment.
  • FIG. 7 shows a flow chart of a network slicing self-optimization method provided by an embodiment of the present application.
  • the network slicing self-optimization method can be applied to a second base station, such as the second base station shown in FIG. 1, the path Obtaining methods include but are not limited to the following steps:
  • Step S700 acquiring the task threshold sent by the server
  • Step S800 obtaining local network slice resource configuration information and a parameter optimization model
  • Step S900 obtaining first network slice resource configuration information according to the task threshold, the local network slice resource configuration information and the parameter optimization model;
  • Step S1000 sending the first network slice resource configuration information and the parameter optimization model to the first base station through the server, so that the first base station uses the first network slice resource configuration information and the The parameter optimization model obtains the service level agreement SLA index, and makes the first base station adjust the resource configuration information of the first network slice when the SLA index does not meet the index threshold, so that the SLA index meets the index threshold.
  • the second base station can determine the optimization task target of the network slice by acquiring the task threshold of the server. Obtain the local network slice resource configuration information and parameter optimization model of the base station, and optimize the network slice without relying on the optimized data of other base stations.
  • the base station can perform optimization prediction according to the task threshold, local network slice resource configuration information and parameter optimization model, and obtain optimized first network slice resource configuration information.
  • the optimized first network slice resource configuration information and parameter optimization model are sent to the first base station through the server.
  • the first base station can obtain the SLA index corresponding to the currently optimized network slice according to the resource configuration information and parameter optimization model of the first network slice optimized by the second base station, and make the first base station fail to meet the SLA index
  • the first base station obtains the index threshold value from the server, that is, when the current optimization process of the first base station has not yet reached the optimization task target issued by the server, it can adjust the resource configuration information of the first network slice so that The SLA index meets the index threshold, and the optimization task of the first base station is completed.
  • the resource configuration information and parameter optimization model of the first network slice of the second base station can expand the data samples for network slice optimization processing by the first base station under the coordination of the server, and help the first base station complete the self-optimization task of wireless network slices , reduce the workload of manual optimization, improve the optimization effect and efficiency.
  • step S900 in the embodiment shown in FIG. 8 also includes but is not limited to the following steps:
  • Step S910 obtaining candidate SLA indicators according to the local network slice resource configuration information and the parameter optimization model
  • Step S920 when the candidate SLA indicator does not meet the task threshold, adjust the resource configuration information of the local network slice so that the candidate SLA indicator meets the task threshold;
  • Step S930 if the candidate SLA index satisfies the task threshold, determine the adjusted resource configuration information of the local network slice as the first network slice resource configuration information.
  • the network slice is optimized using the local network slice resource configuration information and the parameter optimization model.
  • the local network slice resource configuration information can be used as an input parameter to input the local network slice resource configuration information into the parameter optimization model
  • the optimization prediction is carried out in the network slice, and the candidate SLA index corresponding to the optimized network slice is obtained.
  • the candidate SLA index does not meet the task threshold, it can be considered that the currently optimized network slice of the second base station does not meet the optimization task target of the server, and the resource configuration information of the local network slice needs to be adjusted.
  • the local network slice resource configuration information is the configuration data or policy data related to the network slice.
  • the network slice By adjusting the local network slice resource configuration information, the network slice can be adjusted and optimized, the performance of the network slice can be improved, and the corresponding candidate SLA indicators can be improved. According to the adjusted local network slice resource configuration information and parameter optimization model, the adjusted candidate SLA index is obtained. If the adjusted candidate SLA index still does not meet the task threshold, it is necessary to continue to adjust the local network slice resource configuration information until The candidate SLA index can meet the task threshold, that is, the network slice after optimization processing according to the adjusted local network slice resource configuration information and parameter optimization model meets the optimization task goal of the server and completes the optimization task.
  • the local network slice resource configuration information corresponding to the candidate SLA indicator is determined as the first network slice resource configuration information, so as to be assisted by the server.
  • the first base station performs self-optimization processing on the network slice. Therefore, the second base station optimizes the network slice by using the local data of the base station, that is, the local network slice resource configuration information and the parameter optimization model, through the task threshold issued by the server, until the optimized network slice reaches the optimization task target of the server.
  • the local network slice resource configuration information corresponding to the network slice that completes the optimization task goal is determined as the first network slice resource configuration information, and the first network slice resource configuration information is used to provide data samples for the network slice optimization of the first base station to assist the first network slice resource configuration information.
  • the base station performs self-optimization of network slicing, realizes horizontal federated learning, realizes the self-optimization function of network slicing, reduces the workload of manual optimization, and improves the efficiency of network optimization.
  • the second base station will keep adjusting the resource configuration information of the local network slice until the candidate SLA indicator meets the task threshold.
  • the number of adjustment times for local network slice resource configuration information reaches adjustment If the maximum number of times is set, the last adjusted local network slice resource configuration information is retained, and the last adjusted local network slice resource configuration information is used as the optimization result to terminate the network slice optimization process.
  • the local network slice resource configuration information may include at least one of resource reservation policy, service quality configuration policy, or 5G service quality indicator, and may also be a 3rd Generation Partnership Project (3rd Generation Partnership Project, 3GPP) specification
  • the set of parameters related to the SLA index defined in which is not specifically limited in this embodiment.
  • the local network slice resource configuration information may be the maximum resource reservation ratio parameter in the resource reservation policy, and the network slice is optimized by adjusting the maximum resource reservation ratio parameter, so that the adjusted SLA index meets the index threshold.
  • the local network slice resource configuration information may be a quality of service configuration policy, and the network slice may be optimized by adjusting the network traffic priority in the quality of service configuration policy, so that the adjusted SLA index meets the index threshold.
  • the first base station can adjust the resource configuration information of the local network slice according to the adjusted gap relationship between the candidate SLA indicator and the task threshold, for example, the local network slice
  • the resource configuration information can be the maximum resource reservation ratio parameter. After reducing the maximum resource reservation ratio parameter, the gap between the adjusted candidate SLA and the task threshold increases, and then continue to adjust the maximum resource reservation ratio parameter in the opposite direction. That is, increase the maximum resource reservation ratio parameter; for another example, after reducing the maximum resource reservation ratio parameter, the gap between the adjusted candidate SLA index and the task threshold is narrowed, and the adjustment direction of the local network slice resource configuration information is maintained. The adjustment step is reduced, thereby improving the optimization efficiency of the second base station for network slicing.
  • FIG. 9 shows a base station 900 provided by an embodiment of the present application.
  • the base station 900 includes but is not limited to:
  • memory 910 for storing programs
  • the processor 920 is configured to execute the program stored in the memory 910, and when the processor 920 executes the computer program stored in the memory 910, the processor 920 is configured to execute the above-mentioned network slice self-optimization method.
  • the processor 920 and the memory 910 may be connected through a bus or in other ways.
  • the memory 910 can be used to store non-transitory software programs and non-transitory computer-executable programs, such as the network slicing self-optimization method described in any embodiment of the present application.
  • the processor 920 executes the non-transitory software programs and instructions stored in the memory 910 to implement the above-mentioned network slicing self-optimization method.
  • the memory 910 may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application program required by at least one function; the data storage area may store and execute the above-mentioned network slicing self-optimization method.
  • the memory 910 may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices.
  • the memory 910 may include remote memories located remotely relative to the processor 920, and these remote memories may be connected to the processor 920 through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.
  • the non-transitory software programs and instructions required to implement the above self-optimization method for network slicing are stored in the memory 910, and when executed by one or more processors 920, the self-optimization method for network slicing provided by any embodiment of the present application is executed.
  • the embodiment of the present application also provides a storage medium storing computer-executable instructions, and the computer-executable instructions are used to execute the above-mentioned network slicing self-optimization method.
  • the storage medium stores computer-executable instructions, and the computer-executable instructions are executed by one or more control processors, for example, executed by a processor in the above-mentioned network device, so that the above-mentioned one or more A processor executes the network slicing self-optimization method provided by any embodiment of the present application.
  • the embodiment of the present application includes: obtaining the optimization strategy information and index threshold sent by the server, wherein the optimization strategy information includes the first network slice resource configuration information and parameter optimization model, and the first network slice resource configuration information and parameter optimization model are both from the second
  • the base station obtains the service level agreement SLA index according to the first network slice resource configuration information and the parameter optimization model; when the SLA index does not meet the index threshold, adjusts the first network slice resource configuration information so that the SLA index meets the index threshold.
  • the server obtains the index threshold, the first network slice resource configuration information and the parameter optimization model, and uses the second base station's first network slice resource configuration information and the parameter optimization model to obtain the service level agreement SLA index , the SLA index can represent the performance of the current network slice, and can also represent the optimization effect of the current network slice. Therefore, the optimization policy information of other base stations can be obtained through the server as a data sample, and the local base station can be optimized to expand the data sample of the local base station. , to improve optimization efficiency and optimization effect.
  • the index threshold is used as the task standard issued by the server to judge the optimization effect of the current base station.
  • the SLA index does not meet the index threshold, it can be considered that the optimization effect of the network slice of the current base station has not yet reached the standard. Therefore, by adjusting the first network slice resource
  • the information is configured so that the SLA index meets the index threshold, that is, the optimization effect of the network slice of the current base station meets the requirements, and the optimization task is completed. Therefore, through the indicator threshold issued by the server and the SLA indicator representing the current network slicing performance, the configuration parameters of the first base station are adjusted for optimization operations, realizing the self-optimization function of wireless network slicing, reducing the workload of manual optimization, and improving network optimization efficiency.
  • Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cartridges, tape, magnetic disk storage or other magnetic storage devices, or can Any other medium used to store desired information and which can be accessed by a computer.
  • communication media typically embody computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media .

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Quality & Reliability (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

一种网络切片自优化方法、基站及存储介质，网络切片自优化方法应用于第一基站，第一基站与服务器连接，服务器与第二基站连接，该方法包括：获取服务器发送的优化策略信息和指标阈值，其中，优化策略信息包括第一网络切片资源配置信息和参数优化模型，第一网络切片资源配置信息和参数优化模型均来自第二基站(S100)；根据第一网络切片资源配置信息和参数优化模型得到服务等级协议SLA指标(S200)；当SLA指标不满足指标阈值，调节第一网络切片资源配置信息，使得SLA指标满足指标阈值(S300)。

Description

网络切片自优化方法、基站及存储介质
相关申请的交叉引用
本申请基于申请号为202110635730.9、申请日为2021年06月08日的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本申请涉及通信技术领域，尤其涉及一种网络切片自优化方法、基站及存储介质。
背景技术
目前，第五代(5th Generation,5G)无线通信技术已是目前业界的热点。由于5G网络中的网络切片技术能够选择每个切片所需的特性，例如低延迟、高吞吐量、连接密度、频谱效率、流量容量和网络效率，有助于提高创建产品和服务方面的效率，提升客户体验，5G网络切片技术主要应用在车联网、应急通信、工业互联网等各种对网络通信有高需求的垂直行业。为了保证网络切片能够正常运行，需要对各个网络切片进行实时优化。但是在垂直行业中，由于规模受限，且行业本身对网络运维并不具备优化能力，需要投入大量人工工作，运维成本高。
发明内容
以下是对本文详细描述的主题的概述。本概述并非是为了限制权利要求的保护范围。
本申请实施例提供了一种网络切片自优化方法、基站及存储介质。
第一方面，本申请实施例提供了一种网络切片自优化方法，应用于第一基站，所述第一基站与服务器连接，所述服务器与第二基站连接，所述网络切片自优化方法包括：获取所述服务器发送的优化策略信息和指标阈值，其中，所述优化策略信息包括第一网络切片资源配置信息和参数优化模型，所述第一网络切片资源配置信息和所述参数优化模型均来自所述第二基站；根据所述第一网络切片资源配置信息和所述参数优化模型得到服务等级协议SLA指标；当所述SLA指标不满足所述指标阈值，调节所述第一网络切片资源配置信息，使得所述SLA指标满足所述指标阈值。
第二方面，本申请实施例提供一种网络切片自优化方法，应用于第二基站，所述第二基站与服务器连接，所述服务器与第一基站连接，所述网络切片自优化方法包括：获取所述服务器发送的任务阈值；获取本地网络切片资源配置信息和参数优化模型；根据所述任务阈值、所述本地网络切片资源配置信息和所述参数优化模型得到第一网络切片资源配置信息；将所述第一网络切片资源配置信息和所述参数优化模型通过所述服务器发送至所述第一基站，使得所述第一基站根据所述第一网络切片资源配置信息和所述参数优化模型得到服务等级协议SLA指标，并使得所述第一基站在所述SLA指标不满足指标阈值的情况下，调节所述第一网络切片资源配置信息，使得所述SLA指标满足所述指标阈值。
第三方面，本申请实施例提供一种基站，包括存储器、处理器及存储在存储器上并可在 处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现本申请实施例提供的网络切片自优化方法。
第四方面，本申请实施例提供一种计算机可读存储介质，存储有计算机程序，所述计算机程序被处理器执行时，实现本申请实施例提供的网络切片自优化方法。本申请的其它特征和优点将在随后的说明书中阐述，并且，部分地从说明书中变得显而易见，或者通过实施本申请而了解。本申请的目的和其他优点可通过在说明书、权利要求书以及附图中所特别指出的结构来实现和获得。
附图说明
附图用来提供对本申请技术方案的进一步理解，并且构成说明书的一部分，与本申请的实施例一起用于解释本申请的技术方案，并不构成对本申请技术方案的限制。
图1是本申请实施例提供的用于执行网络切片自优化方法的网络切片优化系统的结构示意图；
图2是本申请实施例提供的一种网络切片自优化方法的流程示意图；
图3是图2中步骤S200的具体实现过程示意图；
图4是图2中步骤S300的具体实现过程示意图；
图5是图2中步骤S200后还包括的一种具体实现过程示意图；
图6是本申请实施例提供的优化策略信息形成的具体流程示意图；
图7是本申请实施例提供的一种网络切片自优化方法的流程示意图；
图8是图7中步骤S900的具体实现过程示意图；
图9是本申请实施例提供的一种基站的结构示意图。
具体实施方式
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本申请，并不用于限定本申请。
需要说明的是，虽然在模块示意图中进行了功能模块划分，在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于模块中的模块划分，或流程图中的顺序执行所示出或描述的步骤。说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。
本申请实施例提供了一种网络切片自优化方法，通过服务器获取指标阈值和来自于第二基站的优化策略信息，优化策略信息包括第一网络切片资源配置信息和参数优化模型，从而能够利用第二基站的第一网络切片资源配置信息和参数优化模型得出服务等级协议SLA指标，SLA指标能够表示当前网络切片的性能，也可以表示当前网络切片的优化效果，因此，能够通过服务器获取其他基站的优化策略信息作为数据样本，对本地基站进行优化，从而扩大数据样本，提高优化效率和优化效果。指标阈值作为服务器下发的任务标准，用于判断当前基站的优化效果，当SLA指标不满足指标阈值，可以认为，当前基站的网络切片的优化效果尚未达标，需要对网络切片进行优化，因此，通过调节第一网络切片资源配置信息，使得SLA指标满足指标阈值，即，使得当前基站的网络切片的优化效果满足要求，完成优化任务。所 以，通过服务器下发的指标阈值和代表当前网络切片性能的SLA指标，调节第一基站的配置参数进行优化操作，实现无线网络切片的自优化功能，减少人工优化工作量，提高网络优化效率。
为便于理解，下面结合附图对本申请实施例提供的网络切片自优化方法的应用场景进行介绍。
图1示出了一种用于执行网络切片自优化方法的网络切片优化系统100，该网络切片优化系统100包括：服务器110、第一基站120和第二基站130，其中，服务器110分别与第一基站120和第二基站130连接。服务器110可以是无线子切片管理器，无线子切片管理器中包括有无线子切片管理系统(RAN Network Slice Subnet Management Function，RAN-NSSMF)，RAN-NSSMF负责完成无线子切片的资源申请以及对无线子切片的生命周期进行管理。而与服务器110连接的第一基站120和第二基站130可以是无线子切片覆盖范围内的基站，第一基站120是需要利用其他基站的数据进行自优化的基站，而第二基站130是能够不依赖于其他基站数据进行优化的基站。从而，在服务器110的协调下，第一基站120能够利用第二基站130向服务器110发送的优化后的数据作为机器学习的输入，实现基站的横向联邦学习，达到基站自优化功能。
需要说明的是，服务器110还用于响应于实例化信息，根据实例化信息确定需要进行横向联邦学习优化的待优化基站以及与实例化配置数据，并将实例化配置数据发送至待优化基站。服务器110还用于接收来自于待优化基站对实例化配置数据的反馈结果，并根据反馈结果确定完成实例化的待优化基站，以便于对待优化基站进行后续的网络切片自优化处理。
需要说明的是，服务器110还可以与切片管理系统(Network Slice Management Function，NSMF)即第三方切片管理系统连接，其中，实例化信息可以是由NSMF发起的或由人工输入的，实例化信息用于服务器下发实例化操作使得基站的网络切片实例化，以便于后续网络切片的优化任务。
需要说明的是，服务器110还可以接收外部输入的切片优化任务参数，并将切片优化任务参数下发至指定基站，例如，切片优化任务参数可以是与网络切片配置相关的数据，可以包括优化算法、SLA任务指标和优化阈值。其中，服务器110还可以通过参与者选择算法选取服务器110覆盖范围内的基站作为下发优化任务的第一基站120或第二基站130，换句话说，服务器110可以根据数据样本的质量和数量等参数，从覆盖范围内的基站选择出优选基站作为第二基站130，优选基站的数据样本能够满足本地网络切片优化的任务需求，能够不依赖其他基站的数据样本，并且能够最大化满足其他基站扩大数据样本而进行网络切片优化任务的需求，即能够为第一基站120提供数据样本，提高第一基站120的优化效果和优化效率。
本申请实施例描述的用于执行网络切片自优化方法的网络切片优化系统100是为了更加清楚的说明本申请实施例的技术方案，并不构成对于本申请实施例提供的技术方案的限定，本领域技术人员可知，随着网络切片优化系统100的演变和新应用场景的出现，本申请实施例提供的技术方案对于类似的技术问题，同样适用。
本领域技术人员可以理解的是，图1中示出的网络切片优化系统100的结构并不构成对本申请实施例的限定，可以包括比图示更多或更少的部件，或者组合某些部件，或者不同的部件布置。
基于上述网络切片优化系统100的结构，提出本申请实施例的网络切片自优化方法的各个实施例。
参见图2，图2示出了本申请实施例提供的网络切片自优化方法的流程图，该网络切片自优化方法可以应用于第一基站，例如图1中所示的第一基站，该路径获取方法包括但不限于有以下步骤：
步骤S100，获取所述服务器发送的优化策略信息和指标阈值，其中，所述优化策略信息包括第一网络切片资源配置信息和参数优化模型，所述第一网络切片资源配置信息和所述参数优化模型均来自所述第二基站。
可以理解的是，第一基站通过服务器获取优化策略信息和指标阈值，其中，指标阈值是作为基站完成优化任务的标准条件，优化策略信息包括第一网络切片资源配置信息和参数优化模型，而优化策略信息即第一网络切片资源配置信息和参数优化模型来自于第二基站，从而第一基站能够利用第二基站的第一网络切片资源配置信息和参数优化模型进行后续的优化处理，实现第一基站与第二基站的横向联邦学习，扩大了第一基站对网络切片进行优化处理的数据样本，提高优化效果和优化效率。第一基站通过服务器获取第二基站完成优化后的优化策略信息，即第一网络切片资源配置信息和参数优化模型，对网络切片进行优化处理。目前，由于部分基站存在网络切片的数据量少，数据质量差的问题，对网络切片的优化处理效果不好，需要设置集中点获取相关基站的数据进行网络切片优化处理，但其中可能包含有用户隐私数据，并且，集中点和基站之间需要进行大量数据的交互，提高了通信开销，影响网络的稳定性。而第一基站利用第二基站完成优化处理后的第一网络切片资源配置信息和参数模型对网络切片进行后续的优化处理，实现了基站的横向联邦学习，免去了需要设置集中点获取相关基站的数据的步骤，避免设置的集中点与基站之间进行大量数据的交互，从而减少了服务器与基站之间的通信开销，提高了网络的稳定性。
步骤S200，根据所述第一网络切片资源配置信息和所述参数优化模型得到服务等级协议SLA指标；
步骤S300，当所述SLA指标不满足所述指标阈值，调节所述第一网络切片资源配置信息，使得所述SLA指标满足所述指标阈值。
可以理解的是，利用来自于第二基站的第一网络切片资源配置信息和参数优化模型，对网络切片进行优化后，得到优化后的网络切片对应的SLA指标，SLA指标能够表示当前网络切片的性能，即表示当前网络切片的可用性。在第一基站进行优化处理前，获取服务器下发的指标阈值，指标阈值与SLA指标对应，指标阈值表示的是成功完成优化任务的网络切片对应的SLA指标，即优化任务目标。当第一基站完成优化处理后的网络切片得到的SLA指标不满足指标阈值，则可以认为第一基站当前的网络切片未到达优化任务目标，需要第一基站继续对网络切片进行优化处理。第一网络切片资源配置信息是与网络切片相关的配置数据或策略数据，通过调节第一网络切片资源配置信息，实现对网络切片的调节和优化。利用调节后的第一网络切片资源配置信息和参数优化模型得到调节后的SLA指标，若调节后的SLA指标仍不满足指标阈值，则需要对网络切片继续进行优化处理，即需要对第一网络切片资源配置信息继续进行调节，使得调节后的SLA指标满足指标阈值，即使得调节后的网络切片能够达到优化任务目标。因此，通过调节第一网络切片资源配置信息，使得SLA指标满足指标阈值，即，使得当前基站的网络切片的优化效果满足要求，完成优化任务。所以，通过服务 器下发的指标阈值和代表当前网络切片性能的SLA指标，调节来自于第二基站的第一网络切片资源配置信息进行优化操作，实现利用横向联邦学习对无线网络切片进行优化，减少人工优化工作量，提高网络优化效率。
需要说明的是，当SLA指标不满足指标阈值，第一基站会保持对第一网络切片资源配置信息的调节，直至SLA指标满足指标阈值。为了避免优化处理时间长，提高优化效率，可以通过设置调整次数上限对SLA的迭代次数进行限制，即限制第一网络切片资源配置信息的调节次数，在第一网络切片资源配置信息的调节次数达到调整次数上限，则保留最后一次调节后的第一网络切片资源配置信息，以最后一次调节后的第一网络切片资源配置信息作为优化结果，终止对网络切片的优化处理。
需要说明的是，第一网络切片资源配置信息可以包括资源预留策略、服务质量配置策略或5G服务质量指示符中至少一种，还可以是第三代合作计划(3rd Generation Partnership Project，3GPP)规范中的定义的与SLA指标相关的参数集合，本实施例并不对此作具体限制。例如，第一网络切片资源配置信息可以是资源预留策略中的最大资源预留比例参数，通过调节最大资源预留比例参数对网络切片进行优化处理，使得SLA指标满足指标阈值。又如，第一网络切片资源配置信息可以是服务质量配置策略，可以通过调节服务质量配置策略中的网络流量优先级对网络切片进行优化处理，使得SLA指标满足指标阈值。
需要说明的是，在SLA指标不满足指标阈值的情况下，第一基站可以根据第一网络切片资源配置信息调节后对应的SLA指标与指标阈值的差距关系，对第一网络切片资源配置信息进行调节，例如，第一网络切片资源配置信息可以是最大资源预留比例参数，在将最大资源预留比例参数增大后，得到调节后的SLA与指标阈值的差距增大，则向反方向继续调节最大资源预留比例参数，即减小最大资源预留比例参数；又如，在将最大资源预留比例参数增大后，得到调节后的SLA指标与指标阈值的差距缩小，则维持第一网络切片资源配置信息的调节方向，缩小调节步幅，从而，提高第一基站对网络切片的优化效率。
参照图3，图2所示实施例中的步骤S200还包括但不限于有以下步骤：
步骤S210，将所述第一网络切片资源配置信息输入至所述参数优化模型进行优化预测，得到服务等级协议SLA指标。
可以理解的是，第一网络切片资源配置信息与参数优化模型均来自于第二基站，第一网络切片资源配置信息与参数优化模型为第二基站完成优化处理后的数据，第一基站通过服务器下发的第一网络切片资源配置信息作为参数优化模型的输入参数，进行网络切片的优化预测，得到SLA指标，即，利用第二基站完成优化处理后的数据样本，在第一基站内对网络切片进行处理，增大了第一基站进行优化处理的数据样本，提高第一基站的优化效果，使得调节后的网络切片对应的SLA指标能够更容易达到指标阈值，完成优化任务，提高优化效率。
参照图4，图2所示实施例中的步骤S300还包括但不限于有以下步骤：
步骤S310，获取本地的第二网络切片资源配置信息；
步骤S320，根据所述第二网络切片资源配置信息调节所述第一网络切片资源配置信息。
可以理解的是，第一基站通过服务器获取来自于第二基站的第一网络切片资源配置信息和参数优化模型，并利用第二基站优化处理后的第一网络切片资源配置信息和参数优化模型在第一基站内对网络切片进行优化处理。由于各个基站的环境条件不同，不同基站所需要进行优化的内容有可能不同，在利用其它基站优化处理后的数据，扩大自身的数据样本，进行 优化处理，例如，以第一网络切片资源配置信息作为参考，还需要根据基站本地的网络切片资源配置信息进行调节，使得在基站本地内网络切片对应的SLA指标满足指标阈值。因此，获取基站本地的第二网络切片资源配置信息，其中，第二网络切片资源配置信息与第一网络切片资源配置信息相对应，根据本地的第二网络切片资源配置信息对第一网络切片资源配置信息进行调节，使得基站本地的网络切片优化处理符合当前基站的环境条件，本地基站的SLA指标能够满足指标阈值，完成优化任务，提高网络切片的优化效果和优化效率，提高网络的稳定性。
需要说明的是，基站本地的第二网络切片资源配置信息与来自于第二基站的第一网络切片资源配置信息相对应，第二网络切片资源配置信息可以包括资源预留策略、服务质量配置策略或5G服务质量指示符中至少一种，还可以是第三代合作计划(3rd Generation Partnership Project，3GPP)规范中的定义的与SLA指标相关的参数集合，第二网络切片资源配置信息的具体参数与第一网络切片资源配置信息的具体参数相同，而由于第一网络切片资源配置信息相关的具体参数已在上述实施例中说明，为避免冗余，本实施例不再对此作具体说明。
参照图5，图2所示实施例中的步骤S200之后，还包括但不限于有以下步骤：
步骤S330，当所述SLA指标满足所述指标阈值，将所述第一网络切片资源配置信息和所述参数优化模型上报至所述服务器。
可以理解的是，根据第一网络切片资源配置信息和参数优化模型可以得到SLA指标，通过SLA指标与指标阈值进行判断，检测根据当前的第一网络切片资源配置信息和参数优化模型对网络切片进行优化处理，是否能满足服务器下发的优化任务目标。当SLA指标满足指标阈值，可以认为，基站本地利用当前的第一网络切片资源配置信息和优化模型对网络切片进行优化处理后，优化处理后的网络切片能够达到优化任务目标，即优化任务完成，终止对第一网络切片资源配置信息的调节和对网络切皮的优化处理。将当前满足指标阈值对应的第一网络切片资源配置信息和参数优化模型上报至服务器中，向服务器反馈优化结果，因此，能够有效减少基站与服务器之间大量数据的交互，减少通信开销，提高优化效率。
需要说明的是，当SLA指标不满足指标阈值，第一基站还可以将优化未成功作为优化结果上报至服务器，从而使得服务器能够及时了解第一基站的优化处理进度，提高优化效率。
需要说明的是，在第一基站根据调节后的第一网络切片资源配置信息和参数优化模型得到的SLA指标满足指标阈值的情况下，第一基站可以通过服务器将第一网络切片资源配置信息和参数优化模型广播至其他基站，使得其他基站将来自于第一基站调节后的第一网络切片资源配置信息和参数优化模型，补充至自己的数据样本之中，从而协助其他基站完成网络切片的优化任务，提高基站的优化效率和优化效果。
需要说明的是，第一基站可以监控自身的SLA指标，当SLA指标不满足指标阈值，即使第一基站的SLA指标曾经满足指标阈值，第一基站可以向服务器上报启动自优化的信息，并调节当前的第一网络切片资源配置信息，使得根据调节后的第一网络切片资源配置信息和参数优化模型，能够得到满足指标阈值的SLA指标，从而实现第一基站实时自优化的功能，减少了人工优化工作量，提高优化效率。
参照图6，图6示出了优化策略信息具体由以下步骤得到：
步骤S610，获取所述服务器发送的任务阈值；
步骤S620，获取本地网络切片资源配置信息和所述参数优化模型；
步骤S630，根据所述本地网络切片资源配置信息和所述参数优化模型得到候选SLA指标；
步骤S640，当所述候选SLA指标不满足所述任务阈值，调节所述本地网络切片资源配置信息，使得所述候选SLA指标满足所述任务阈值；
步骤S650，在所述候选SLA指标满足所述任务阈值的情况下，将调节后的所述本地网络切片资源配置信息确定为所述第一网络切片资源配置信息；
步骤S660，根据所述第一网络切片资源配置信息和所述参数优化模型得到所述优化策略信息。
可以理解的是，优化策略信息可以通过基站处理得到。基站通过获取服务器发送的任务阈值，以及本地网络切片资源配置信息和参数优化模型，其中，任务阈值则表示网络切片对应的SLA指标所需要达到的优化任务目标。基站利用本地网络切片资源配置信息和参数优化模型得到候选SLA指标，通过候选SLA指标表示根据本地网络切片资源配置信息优化处理后的网络切片对应的性能。当候选SLA指标不满足任务阈值，即利用当前的本地网络切片资源配置信息优化处理的网络切片未达到优化任务目标，需要调节候选SLA指标，使得候选SLA指标满足任务阈值。而候选SLA指标由本地网络切片资源配置信息和参数优化模型得到，因此，对本地网络切片资源配置信息进行调节，利用调节后的本地网络切片资源配置信息对网络切片进行优化处理，使得优化处理后的候选SLA指标满足任务阈值，因此，能够利用基站本地的数据完成自优化任务。
可以理解的是，在候选SLA指标满足任务阈值，即利用调节后的本地网络切片资源配置信息和参数优化模型得到的网络切片能够完成优化任务目标，可以认为，优化任务完成，将调节后的本地网络切片资源配置信息确定为第一网络切片资源配置信息，并根据第一网络切片资源配置信息和参数优化模型得到优化策略信息，从而能够通过服务器向其他基站共享本地基站的优化结果即优化策略信息，协助其他基站完成优化任务，减少服务器与基站之间通信开销，能够增大其他基站的数据样本，提高优化效果和优化效率。
需要说明的是，本地网络切片资源配置信息的具体参数与第一网络切片资源配置信息的具体参数相同，而由于第一网络切片资源配置信息相关的具体参数已在上述实施例中说明，为避免冗余，本实施例不再对此作具体说明。
参见图7，图7示出了本申请实施例提供的网络切片自优化方法的流程图，该网络切片自优化方法可以应用于第二基站，例如图1中所示的第二基站，该路径获取方法包括但不限于有以下步骤：
步骤S700，获取所述服务器发送的任务阈值；
步骤S800，获取本地网络切片资源配置信息和参数优化模型；
步骤S900，根据所述任务阈值、所述本地网络切片资源配置信息和所述参数优化模型得到第一网络切片资源配置信息；
步骤S1000，将所述第一网络切片资源配置信息和所述参数优化模型通过所述服务器发送至所述第一基站，使得所述第一基站根据所述第一网络切片资源配置信息和所述参数优化模型得到服务等级协议SLA指标，并使得所述第一基站在所述SLA指标不满足指标阈值的情况下，调节所述第一网络切片资源配置信息，使得所述SLA指标满足所述指标阈值。
可以理解的是，第二基站可以通过获取服务器的任务阈值以确定网络切片的优化任务目 标。获取基站的本地网络切片资源配置信息和参数优化模型，不依赖其他基站优化后的数据对网络切片进行优化处理。基站可以根据任务阈值、本地网络切片资源配置信息和参数优化模型进行优化预测，得到优化处理后的第一网络切片资源配置信息。将优化处理后的第一网络切片资源配置信息和参数优化模型通过服务器发送至第一基站。从而，第一基站能够根据第二基站优化处理后的第一网络切片资源配置信息和参数优化模型，得出当前优化处理后的网络切片对应的SLA指标，并且使得第一基站在SLA指标不满足第一基站从服务器中获取的指标阈值的情况下，即在第一基站当前优化处理仍未达到服务器下发的优化任务目标的情况下，能够对第一网络切片资源配置信息进行调节，以使SLA指标满足指标阈值，完成第一基站的优化任务。第二基站的第一网络切片资源配置信息和参数优化模型能够在服务器的协调下，扩大第一基站对网络切片优化处理的数据样本，有助于第一基站完成对无线网络切片的自优化任务，减少人工优化工作量，提高优化效果和优化效率。
参照图8，图8所示实施例中的步骤S900还包括但不限于有以下步骤：
步骤S910，根据所述本地网络切片资源配置信息和所述参数优化模型得到候选SLA指标；
步骤S920，当所述候选SLA指标不满足所述任务阈值，调节所述本地网络切片资源配置信息，使得所述候选SLA指标满足所述任务阈值；
步骤S930，在所述候选SLA指标满足所述任务阈值的情况下，将调节后的所述本地网络切片资源配置信息确定为所述第一网络切片资源配置信息。
可以理解的是，利用本地网络切片资源配置信息和参数优化模型对网络切片进行优化处理，换句话说，本地网络切片资源配置信息可以作为输入参数，将本地网络切片资源配置信息输入至参数优化模型中进行优化预测，得到优化处理后的网络切片对应的候选SLA指标。当候选SLA指标不满足任务阈值，可以认为，第二基站当前优化处理后的网络切片未达到服务器的优化任务目标，需要对本地网络切片资源配置信息进行调节。本地网络切片资源配置信息是与网络切片相关的配置数据或策略数据，通过调节本地网络切片资源配置信息，能够对网络切片进行调节和优化，提高网络切片的性能，提高与其对应的候选SLA指标。根据调节后的本地网络切片资源配置信息和参数优化模型，得到调节后的候选SLA指标，若调节后的候选SLA指标仍未满足任务阈值，则需要继续对本地网络切片资源配置信息进行调节，直至候选SLA指标能够满足任务阈值，即根据调节后的本地网络切片资源配置信息和参数优化模型进行优化处理后的网络切片满足服务器的优化任务目标，完成优化任务。在候选SLA指标满足任务阈值的情况下，将该候选SLA指标对应的本地网络切片资源配置信息，即调节后的本地网络切片资源配置信息，确定为第一网络切片资源配置信息，以通过服务器协助第一基站对网络切片进行自优化处理。所以，第二基站通过服务器下发的任务阈值，利用基站本地的数据，即本地网络切片资源配置信息和参数优化模型对网络切片进行优化处理，直至优化后的网络切片达到服务器的优化任务目标。将完成优化任务目标的网络切片对应的本地网络切片资源配置信息，确定为第一网络切片资源配置信息，通过第一网络切片资源配置信息为第一基站的网络切片优化提供数据样本，协助第一基站进行网络切片自优化，实现横向联邦学习，实现对网络切片的自优化功能，减少人工优化工作量，提高网络优化效率。
需要说明的是，当候选SLA指标不满足任务阈值，第二基站会保持对本地网络切片资源配置信息的调节，直至候选SLA指标满足任务阈值。为了避免优化处理时间长，提高优化效 率，可以通过设置调整次数上限对候选SLA的迭代次数进行限制，即限制本地网络切片资源配置信息的调节次数，在本地网络切片资源配置信息的调节次数达到调整次数上限，则保留最后一次调节后的本地网络切片资源配置信息，以最后一次调节后的本地网络切片资源配置信息作为优化结果，终止对网络切片的优化处理。
需要说明的是，本地网络切片资源配置信息可以包括资源预留策略、服务质量配置策略或5G服务质量指示符中至少一种，还可以是第三代合作计划(3rd Generation Partnership Project，3GPP)规范中的定义的与SLA指标相关的参数集合，本实施例并不对此作具体限制。例如，本地网络切片资源配置信息可以是资源预留策略中的最大资源预留比例参数，通过调节最大资源预留比例参数对网络切片进行优化处理，使得调节后的SLA指标满足指标阈值。又如，本地网络切片资源配置信息可以是服务质量配置策略，可以通过调节服务质量配置策略中的网络流量优先级对网络切片进行优化处理，使得调节后的SLA指标满足指标阈值。
需要说明的是，在候选SLA指标不满足任务阈值的情况下，第一基站可以根据调节后的候选SLA指标与任务阈值的差距关系，对本地网络切片资源配置信息进行调节，例如，本地网络切片资源配置信息可以是最大资源预留比例参数，在将最大资源预留比例参数缩小后，得到调节后的候选SLA与任务阈值的差距增大，则向反方向继续调节最大资源预留比例参数，即增大最大资源预留比例参数；又如，在将最大资源预留比例参数缩小后，得到调节后的候选SLA指标与任务阈值的差距缩小，则维持本地网络切片资源配置信息的调节方向，缩小调节步幅，从而，提高第二基站对网络切片的优化效率。
参见图9，图9示出了本申请实施例提供的基站900。该基站900包括但不限于：
存储器910，用于存储程序；
处理器920，用于执行存储器910存储的程序，当处理器920执行存储器910存储的计算机程序时，处理器920用于执行上述的网络切片自优化方法。
处理器920和存储器910可以通过总线或者其他方式连接。
存储器910作为一种非暂态计算机可读存储介质，可用于存储非暂态软件程序以及非暂态性计算机可执行程序，如本申请任意实施例描述的网络切片自优化方法。处理器920通过运行存储在存储器910中的非暂态软件程序以及指令，从而实现上述的网络切片自优化方法。
存储器910可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储执行上述的网络切片自优化方法。此外，存储器910可以包括高速随机存取存储器，还可以包括非暂态存储器，比如至少一个磁盘存储器件、闪存器件、或其他非暂态固态存储器件。在一些实施方式中，存储器910可包括相对于处理器920远程设置的远程存储器，这些远程存储器可以通过网络连接至该处理器920。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
实现上述的网络切片自优化方法所需的非暂态软件程序以及指令存储在存储器910中，当被一个或者多个处理器920执行时，执行本申请任意实施例提供的网络切片自优化方法。
本申请实施例还提供了一种存储介质，存储有计算机可执行指令，计算机可执行指令用于执行上述的网络切片自优化方法。
在一实施例中，该存储介质存储有计算机可执行指令，该计算机可执行指令被一个或多个控制处理器执行，比如，被上述网络设备中的一个处理器执行，可使得上述一个或多个处理器执行本申请任意实施例提供的网络切片自优化方法。
本申请实施例包括：获取服务器发送的优化策略信息和指标阈值，其中，优化策略信息包括第一网络切片资源配置信息和参数优化模型，第一网络切片资源配置信息和参数优化模型均来自第二基站；根据第一网络切片资源配置信息和参数优化模型得到服务等级协议SLA指标；当SLA指标不满足指标阈值，调节第一网络切片资源配置信息，使得SLA指标满足指标阈值。根据本申请实施例提供的方案，通过服务器获取指标阈值、第一网络切片资源配置信息和参数优化模型，利用第二基站的第一网络切片资源配置信息和参数优化模型得出服务等级协议SLA指标，SLA指标能够表示当前网络切片的性能，也可以表示当前网络切片的优化效果，因此，能够通过服务器获取其他基站的优化策略信息作为数据样本，对本地基站进行优化，从而扩大本地基站的数据样本，提高优化效率和优化效果。指标阈值作为服务器下发的任务标准，用于判断当前基站的优化效果，当SLA指标不满足指标阈值，可以认为，当前基站的网络切片的优化效果尚未达标，因此，通过调节第一网络切片资源配置信息，使得SLA指标满足指标阈值，即使得当前基站的网络切片的优化效果满足要求，完成优化任务。所以，通过服务器下发的指标阈值和代表当前网络切片性能的SLA指标，调节第一基站的配置参数进行优化操作，实现无线网络切片的自优化功能，减少人工优化工作量，提高网络优化效率。
以上所描述的实施例仅仅是示意性的，其中作为分离部件说明的单元可以是或者也可以不是物理上分开的，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
本领域普通技术人员可以理解，上文中所公开方法中的全部或某些步骤、系统可以被实施为软件、固件、硬件及其适当的组合。某些物理组件或所有物理组件可以被实施为由处理器，如中央处理器、数字信号处理器或微处理器执行的软件，或者被实施为硬件，或者被实施为集成电路，如专用集成电路。这样的软件可以分布在计算机可读介质上，计算机可读介质可以包括计算机存储介质(或非暂时性介质)和通信介质(或暂时性介质)。如本领域普通技术人员公知的，术语计算机存储介质包括在用于存储信息(诸如计算机可读指令、数据结构、程序模块或其他数据)的任何方法或技术中实施的易失性和非易失性、可移除和不可移除介质。计算机存储介质包括但不限于RAM、ROM、EEPROM、闪存或其他存储器技术、CD-ROM、数字多功能盘(DVD)或其他光盘存储、磁盒、磁带、磁盘存储或其他磁存储装置、或者可以用于存储期望的信息并且可以被计算机访问的任何其他的介质。此外，本领域普通技术人员公知的是，通信介质通常包括计算机可读指令、数据结构、程序模块或者诸如载波或其他传输机制之类的调制数据信号中的其他数据，并且可包括任何信息递送介质。
以上是对本申请的若干实施进行了具体说明，但本申请并不局限于上述实施方式，熟悉本领域的技术人员在不违背本申请精神的。共享条件下还可作出种种等同的变形或替换，这些等同的变形或替换均包括在本申请权利要求所限定的范围内。

Claims (11)

  1. 一种网络切片自优化方法，应用于第一基站，所述第一基站与服务器连接，所述服务器与第二基站连接，所述网络切片自优化方法包括：
    获取所述服务器发送的优化策略信息和指标阈值，其中，所述优化策略信息包括第一网络切片资源配置信息和参数优化模型，所述第一网络切片资源配置信息和所述参数优化模型均来自所述第二基站；
    根据所述第一网络切片资源配置信息和所述参数优化模型得到服务等级协议SLA指标；
    当所述SLA指标不满足所述指标阈值，调节所述第一网络切片资源配置信息，使得所述SLA指标满足所述指标阈值。
  2. 根据权利要求1所述的网络切片自优化方法，其中，所述根据所述第一网络切片资源配置信息和所述参数优化模型得到服务等级协议SLA指标，包括：
    将所述第一网络切片资源配置信息输入至所述参数优化模型进行优化预测，得到服务等级协议SLA指标。
  3. 根据权利要求1所述的网络切片自优化方法，其中，所述调节所述第一网络切片资源配置信息，包括：
    获取本地的第二网络切片资源配置信息；
    根据所述第二网络切片资源配置信息调节所述第一网络切片资源配置信息。
  4. 根据权利要求1所述的网络切片自优化方法，其中，所述根据所述第一网络切片资源配置信息和所述参数优化模型得到服务等级协议SLA指标之后，所述网络切片自优化方法还包括：
    当所述SLA指标满足所述指标阈值，将所述第一网络切片资源配置信息和所述参数优化模型上报至所述服务器。
  5. 根据权利要求1所述的网络切片自优化方法，其中，所述优化策略信息由以下步骤得到：
    获取所述服务器发送的任务阈值；
    获取本地网络切片资源配置信息和所述参数优化模型；
    根据所述本地网络切片资源配置信息和所述参数优化模型得到候选SLA指标；
    当所述候选SLA指标不满足所述任务阈值，调节所述本地网络切片资源配置信息，使得所述候选SLA指标满足所述任务阈值；
    在所述候选SLA指标满足所述任务阈值的情况下，将调节后的所述本地网络切片资源配置信息确定为所述第一网络切片资源配置信息；
    根据所述第一网络切片资源配置信息和所述参数优化模型得到所述优化策略信息。
  6. 根据权利要求1至5任意一项所述的网络切片自优化方法，其中，所述第一网络切片资源配置信息包括资源预留策略、服务质量配置策略或5G服务质量 指示符中的至少一种。
  7. 一种网络切片自优化方法，应用于第二基站，所述第二基站与服务器连接，所述服务器与第一基站连接，所述网络切片自优化方法包括：
    获取所述服务器发送的任务阈值；
    获取本地网络切片资源配置信息和参数优化模型；
    根据所述任务阈值、所述本地网络切片资源配置信息和所述参数优化模型得到第一网络切片资源配置信息；
    将所述第一网络切片资源配置信息和所述参数优化模型通过所述服务器发送至所述第一基站，使得所述第一基站根据所述第一网络切片资源配置信息和所述参数优化模型得到服务等级协议SLA指标，并使得所述第一基站在所述SLA指标不满足指标阈值的情况下，调节所述第一网络切片资源配置信息，使得所述SLA指标满足所述指标阈值。
  8. 根据权利要求7所述的网络切片自优化方法，其中，所述根据所述任务阈值、所述本地网络切片资源配置信息和所述参数优化模型得到第一网络切片资源配置信息，包括：
    根据所述本地网络切片资源配置信息和所述参数优化模型得到候选SLA指标；
    当所述候选SLA指标不满足所述任务阈值，调节所述本地网络切片资源配置信息，使得所述候选SLA指标满足所述任务阈值；
    在所述候选SLA指标满足所述任务阈值的情况下，将调节后的所述本地网络切片资源配置信息确定为所述第一网络切片资源配置信息。
  9. 根据权利要求7或8所述的网络切片自优化方法，其中，所述本地网络切片资源配置信息包括资源预留策略、服务质量配置策略或5G服务质量指示符中的至少一种。
  10. 一种基站，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其中，所述处理器执行所述计算机程序时实现如权利要求1至9中任意一项所述的网络切片自优化方法。
  11. 一种计算机可读存储介质，其中，存储有计算机程序，所述计算机程序被处理器执行时，实现如权利要求1至9任意一项所述的网络切片自优化方法。
PCT/CN2021/132853 2021-06-08 2021-11-24 网络切片自优化方法、基站及存储介质 Ceased WO2022257366A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
US18/562,567 US20240251298A1 (en) 2021-06-08 2021-11-24 Network slice self-optimization method, base station, and storage medium
JP2023567032A JP7573124B2 (ja) 2021-06-08 2021-11-24 ネットワークスライス自己最適化方法、基地局、及び記憶媒体
EP21944862.8A EP4329358A4 (en) 2021-06-08 2021-11-24 METHOD FOR SELF-OPTIMIZATION OF NETWORK SLICES, BASE STATION AND STORAGE MEDIUM

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110635730.9A CN115460623A (zh) 2021-06-08 2021-06-08 网络切片自优化方法、基站及存储介质
CN202110635730.9 2021-06-08

Publications (1)

Publication Number Publication Date
WO2022257366A1 true WO2022257366A1 (zh) 2022-12-15

Family

ID=84294599

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/132853 Ceased WO2022257366A1 (zh) 2021-06-08 2021-11-24 网络切片自优化方法、基站及存储介质

Country Status (5)

Country Link
US (1) US20240251298A1 (zh)
EP (1) EP4329358A4 (zh)
JP (1) JP7573124B2 (zh)
CN (1) CN115460623A (zh)
WO (1) WO2022257366A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115623602A (zh) * 2022-12-19 2023-01-17 浪潮通信信息系统有限公司 资源重选方法及装置
CN115835256A (zh) * 2023-02-17 2023-03-21 中汽研汽车工业工程(天津)有限公司 一种面向汽车制造场景的智能网关资源配置与计算方法

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102893801B1 (ko) * 2021-11-30 2025-12-01 한국전자통신연구원 모바일 코어 시스템과 연동하는 연합학습 장치 및 방법
CN119031476A (zh) * 2023-05-18 2024-11-26 中兴通讯股份有限公司 网络切片的资源配置方法、基站及存储介质

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112668877A (zh) * 2020-12-25 2021-04-16 西安电子科技大学 结合联邦学习和强化学习的事物资源信息分配方法及系统
US10992396B1 (en) * 2020-02-07 2021-04-27 Verizon Patent And Licensing Inc. Systems and methods for mapping resource blocks to network slices
CN112887120A (zh) * 2019-11-30 2021-06-01 华为技术有限公司 一种信息处理方法及装置

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108632063B (zh) * 2017-03-20 2021-01-05 华为技术有限公司 管理网络切片实例的方法、装置和系统
GB2574247A (en) * 2018-05-31 2019-12-04 Nec Corp Communication system
US11026106B2 (en) * 2018-11-09 2021-06-01 Huawei Technologies Co., Ltd. Method and system of performance assurance with conflict management in provisioning a network slice service
US11700628B2 (en) * 2019-03-11 2023-07-11 Intel Corporation Multi-slice support for MEC-enabled 5G deployments
US11336538B2 (en) * 2019-11-27 2022-05-17 Netsia, Inc. Slice assurance within a mobile network
US11310104B2 (en) * 2019-12-02 2022-04-19 At&T Intellectual Property I, L.P. Management of persistent network slices by a distributed learning system in a 5G or other next generation wireless network
US20230244952A1 (en) * 2020-09-04 2023-08-03 Qualcomm Incorporated Interface for over the air model aggregation in federated system

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112887120A (zh) * 2019-11-30 2021-06-01 华为技术有限公司 一种信息处理方法及装置
US10992396B1 (en) * 2020-02-07 2021-04-27 Verizon Patent And Licensing Inc. Systems and methods for mapping resource blocks to network slices
CN112668877A (zh) * 2020-12-25 2021-04-16 西安电子科技大学 结合联邦学习和强化学习的事物资源信息分配方法及系统

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
HUAWEI: "Add use case and potential solutions of cross-slice resource optimization analysis", 3GPP DRAFT; S5-203202, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. SA WG5, no. e-meeting; 20200525 - 20200603, 15 May 2020 (2020-05-15), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France , XP051886566 *
LI QIYAO: "The Research on Intelligent Reconfiguration Mechanism of Network Slice", CHINESE MASTER'S THESES FULL-TEXT DATABASE, INFORMATION SCIENCE & TECHNOLOGY, no. 7, 15 July 2020 (2020-07-15), XP093012313 *
See also references of EP4329358A4 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115623602A (zh) * 2022-12-19 2023-01-17 浪潮通信信息系统有限公司 资源重选方法及装置
CN115835256A (zh) * 2023-02-17 2023-03-21 中汽研汽车工业工程(天津)有限公司 一种面向汽车制造场景的智能网关资源配置与计算方法

Also Published As

Publication number Publication date
EP4329358A4 (en) 2024-10-09
CN115460623A (zh) 2022-12-09
US20240251298A1 (en) 2024-07-25
JP7573124B2 (ja) 2024-10-24
EP4329358A1 (en) 2024-02-28
JP2024515333A (ja) 2024-04-08

Similar Documents

Publication Publication Date Title
WO2022257366A1 (zh) 网络切片自优化方法、基站及存储介质
CN112512058B (zh) 网络优化方法、服务器、客户端设备、网络设备和介质
EP3843337B1 (en) Slice information processing method and apparatus
CN113596863B (zh) 确定用户面功能及信息提供的方法、设备及介质
US20210235277A1 (en) Method and apparatus for dynamically allocating radio resources in a wireless communication system
US10966122B2 (en) Method and migration managing module for managing a migration of a service
CN110417565A (zh) 一种模型更新方法、装置及系统
US11057309B2 (en) Management method, management unit, and system
EP3565182A1 (en) Network slicing management method, and management unit and system
CN110572687A (zh) 直播回源聚合的方法、装置、系统、设备及存储介质
US11356328B2 (en) Service management method and apparatus, and storage medium
US10362549B2 (en) Method and apparatus for setting up interface between access points
US12273251B2 (en) Data analysis apparatus management and control method and communication apparatus
GB2625419A (en) Methods and apparatus for supporting AI/ML model life cycle management in wireless communication networks
US10802896B2 (en) Rest gateway for messaging
US12356248B2 (en) System and method for delivering quality of service
CN113453252A (zh) 通信方法及装置
CN118055459A (zh) 基于5g与tsn融合的资源预留方法、装置及系统
CN115699823A (zh) 支持无线通信网络中收集和分析网络数据的移动性的方法和设备
US20240305554A1 (en) Information advertisement method, controller and storage medium
US10932273B2 (en) Facilitating communication of radio resource quality to a mobile application
WO2025218763A1 (zh) 一种服务质量信息的处理方法、设备、介质和程序产品
CN115426413B (zh) 基于5g的边缘节点调度方法、装置、介质及设备
GB2629475A (en) Method and apparatus for autoscaling in a network
CN118540378B (zh) 算力节点选择方法、设备、装置及存储介质

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: 21944862

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023567032

Country of ref document: JP

WWE Wipo information: entry into national phase

Ref document number: 18562567

Country of ref document: US

Ref document number: 2021944862

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2021944862

Country of ref document: EP

Effective date: 20231120

NENP Non-entry into the national phase

Ref country code: DE