WO2021172810A1 - 무선 통신 시스템에서 서비스를 선택하는 방법 및 장치 - Google Patents
무선 통신 시스템에서 서비스를 선택하는 방법 및 장치 Download PDFInfo
- Publication number
- WO2021172810A1 WO2021172810A1 PCT/KR2021/002070 KR2021002070W WO2021172810A1 WO 2021172810 A1 WO2021172810 A1 WO 2021172810A1 KR 2021002070 W KR2021002070 W KR 2021002070W WO 2021172810 A1 WO2021172810 A1 WO 2021172810A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- nwdaf
- analysis information
- information
- processing
- message
- 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
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
- H04L41/50—Network service management, e.g. ensuring proper service fulfilment according to agreements
- H04L41/5032—Generating service level reports
-
- 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
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
-
- 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
-
- 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
- H04L41/34—Signalling channels for network management communication
-
- 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
- H04L41/5058—Service discovery by the service manager
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/06—Generation of reports
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/12—Network monitoring probes
Definitions
- the present disclosure relates to a method and apparatus for selecting a service in a wireless communication system.
- the 5G communication system or the pre-5G communication system is called a 4G network after (Beyond 4G Network) communication system or an LTE (Long Term Evolution) system after (Post LTE) system.
- 5G communication systems are being considered for implementation in very high frequency (mmWave) bands (eg, 60 gigabytes (60 GHz) bands).
- mmWave very high frequency
- FD-MIMO Full Dimensional MIMO
- array antenna, analog beam-forming, and large scale antenna technologies are being discussed.
- an evolved small cell in the 5G communication system, an evolved small cell, an advanced small cell, a cloud radio access network (cloud RAN), an ultra-dense network (ultra-dense network) , Device to Device communication (D2D), wireless backhaul, moving network, cooperative communication, Coordinated Multi-Points (CoMP), and reception interference cancellation Technology development is underway.
- cloud RAN cloud radio access network
- ultra-dense network ultra-dense network
- D2D Device to Device communication
- wireless backhaul moving network
- cooperative communication Coordinated Multi-Points (CoMP)
- CoMP Coordinated Multi-Points
- FQAM Hybrid Frequency Shift Keying and Quadrature Amplitude Modulation
- SWSC Sliding Window Superposition Coding
- ACM Advanced Coding Modulation
- FBMC Filter Bank Multi Carrier
- NOMA Non Orthogonal Multiple Access
- SCMA Sparse Code Multiple Access
- IoT Internet of Things
- IoE Internet of Everything
- M2M Machine Type Communication
- MTC Machine Type Communication
- IoT an intelligent IT (Internet Technology) service that collects and analyzes data generated from connected objects and creates new values in human life can be provided.
- IoT is the field of smart home, smart building, smart city, smart car or connected car, smart grid, health care, smart home appliance, advanced medical service, etc. can be applied to
- 5G communication such as sensor network, machine to machine (M2M), and machine type communication (MTC) is being implemented by techniques such as beamforming, MIMO, and array antenna.
- M2M machine to machine
- MTC machine type communication
- cloud RAN cloud radio access network
- the present disclosure provides an apparatus and method for selecting a service in a wireless communication system.
- the disclosed embodiment provides an apparatus and method for effectively selecting a service in a wireless communication system.
- FIG. 1 illustrates a configuration of a mobile communication system and an entity located outside a network according to an embodiment of the present disclosure.
- NWDAF Network Data Analytics Function
- FIG. 3 is a sequence diagram illustrating a procedure in which an entity using NWDAF analysis information such as NF, AF, OAM, etc. discovers an NWDAF instance using a Network Repository Function (NRF) according to an embodiment of the present disclosure.
- NWDAF Network Repository Function
- FIG. 4 is a sequence diagram illustrating a procedure in which an NWDAF instance discovers another NWDAF instance according to an embodiment of the present disclosure.
- FIG. 5 illustrates an example of a method of configuring an NWDAF instance with a combination of detailed functions according to an embodiment of the present disclosure.
- FIG. 6 is a sequence diagram illustrating a procedure for discovering and selecting an NWDAF instance by using an NRF according to an embodiment of the present disclosure.
- FIG. 7 is a sequence diagram illustrating a procedure for discovering and selecting an NWDAF instance by utilizing feedback information of an entity using analysis information according to an embodiment of the present disclosure.
- FIG. 8 is a sequence diagram illustrating a method for an AF to discover an NWDAF according to an embodiment of the present disclosure.
- FIG. 9 is a sequence diagram illustrating a method of discovering and selecting an NWDAF for a data collection function according to an embodiment of the present disclosure.
- FIG. 10 is a sequence diagram illustrating a method for an NWDAF instance to discover and select another NWDAF for task offloading according to an embodiment of the present disclosure.
- FIG. 11 is a sequence diagram illustrating a method by which an NWDAF discovers and selects an NWDAF for task offloading according to an embodiment of the present disclosure.
- FIG. 12 is a sequence diagram illustrating a method of discovering and selecting an NWDAF instance for cooperative learning according to an embodiment of the present disclosure.
- FIG. 13 is a sequence diagram illustrating a method of discovering and selecting an NWDAF instance for analysis model delivery according to an embodiment of the present disclosure.
- FIG. 14 is a flowchart illustrating a method of operating a network entity according to an embodiment of the present disclosure.
- 15 is a block diagram illustrating a configuration of a network entity according to an embodiment of the present disclosure.
- a method of operating a Network Data Analytics Function (NWDAF) in a wireless communication system includes: receiving a request message for analysis information from a Network Function (NF); transmitting a discovery message for discovering another NWDAF to a Network Repository Function (NRF) based on the received request message; receiving, from the NRF, a response message to the discovery message; transmitting a message related to processing of the analysis information to the other NWDAF based on the information on the other NWDAF included in the received response message; receiving, from the other NWDAF, a response message to a message related to the processing of the analysis information; and generating the analysis information based on a result of processing on the analysis information performed by the NWDAF and a result of processing on the analysis information performed by the other NWDAF included in a response message received from the other NWDAF to do; may include.
- a network data analytics function (NWDAF) in a wireless communication system includes a transceiver; and controlling the transceiver to receive a request message for analysis information from a Network Function (NF), and based on the received request message, to transmit a discovery message for discovering another NWDAF to a Network Repository Function (NRF).
- NF Network Function
- NEF Network Repository Function
- Control the transceiver control the transceiver to receive a response message to the discovery message from the NRF, and based on the information on the other NWDAF included in the received response message, related to the processing of the analysis information control the transceiver to transmit a message to the other NWDAF, control the transceiver to receive, from the other NWDAF, a response message to a message related to the processing of the analysis information, the analysis information performed by the NWDAF and at least one processor configured to generate the analysis information based on a result of the processing and a result of processing on the analysis information performed by the other NWDAF included in the response message received from the other NWDAF.
- a method of operating a network data analytics function (NWDAF) in a wireless communication system includes the steps of receiving a request message for analysis information from a network function (NF); based on the steps of transmitting a discovery message for discovering at least one other NWDAF to a Network Repository Function (NRF), receiving a response message to the discovery message from the NRF, and the response message to the discovery message is the including information on at least one other NWDAF, transmitting a request message for processing the analysis information to the at least one other NWDAF based on the information on the at least one other NWDAF, the at least one receive a response message to the message related to the processing of the analysis information from another NWDAF of Including a result, based on the result of the processing on the analysis information performed by the NWDAF and the result of the processing on the analysis information performed by the at least one other NWDAF, the analysis information requested from the NF generating, and transmitting the generated analysis information to the NF.
- NDF Network Repository Function
- a network data analytics function (NWDAF) in a wireless communication system receives a request message for analysis information from a network function (NF) through a transceiver and the transceiver, and the transceiver unit transmits a discovery message for discovering at least one other NWDAF to a Network Repository Function (NRF) based on the request message for the analysis information, and responds to the discovery message from the NRF through the transceiver receiving a message, and a response message to the discovery message includes information on the at least one other NWDAF, and through the transceiver, processing of the analysis information based on the information on the at least one other NWDAF for transmitting a request message to the at least one other NWDAF, and receiving a response message to the message related to the processing of the analysis information from the at least one other NWDAF through the transceiver, and related to the processing of the analysis information
- the response message to the message includes a result of processing on the analysis information performed by the at least one other NWDA
- each block of the flowchart diagrams and combinations of the flowchart diagrams may be performed by computer program instructions.
- These computer program instructions may be embodied in a processor of a general purpose computer, special purpose computer, or other programmable data processing equipment, such that the instructions performed by the processor of the computer or other programmable data processing equipment are not described in the flowchart block(s). It creates a means to perform functions.
- These computer program instructions may also be stored in a computer-usable or computer-readable memory that may direct a computer or other programmable data processing equipment to implement a function in a particular manner, and thus the computer-usable or computer-readable memory.
- the instructions stored in the flow chart block(s) produce an article of manufacture containing instruction means for performing the function described in the flowchart block(s).
- the computer program instructions may also be mounted on a computer or other programmable data processing equipment, such that a series of operational steps are performed on the computer or other programmable data processing equipment to create a computer-executed process to create a computer or other programmable data processing equipment. It is also possible that instructions for performing the processing equipment provide steps for performing the functions described in the flowchart block(s).
- each block may represent a module, segment, or portion of code that includes one or more executable instructions for executing specified logical function(s). It should also be noted that in some alternative implementations it is also possible for the functions recited in blocks to occur out of order. For example, two blocks shown one after another may in fact be performed substantially simultaneously, or it is possible that the blocks are sometimes performed in the reverse order according to the corresponding function.
- the term ' ⁇ unit' used in this embodiment means software or hardware components such as FPGA (Field Programmable Gate Array) or ASIC (Application Specific Integrated Circuit), and ' ⁇ unit' performs certain roles do.
- '-part' is not limited to software or hardware.
- the ' ⁇ unit' may be configured to reside on an addressable storage medium or may be configured to refresh one or more processors.
- ' ⁇ ' denotes components such as software components, object-oriented software components, class components, and task components, and processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables.
- components and ' ⁇ units' may be combined into a smaller number of components and ' ⁇ units' or further separated into additional components and ' ⁇ units'.
- components and ' ⁇ units' may be implemented to play one or more CPUs in a device or secure multimedia card.
- ' ⁇ part' may include one or more processors.
- a term for identifying an access node used in the following description a term referring to a network entity (network entity), a term referring to messages, a term referring to an interface between network objects, and various identification information Reference terms and the like are exemplified for convenience of description. Accordingly, the present disclosure is not limited to the terms described below, and other terms referring to objects having equivalent technical meanings may be used.
- the present disclosure uses terms and names defined in the 3rd Generation Partnership Project Long Term Evolution (3GPP LTE) standard.
- 3GPP LTE 3rd Generation Partnership Project Long Term Evolution
- the present disclosure is not limited by the above terms and names, and may be equally applied to systems conforming to other standards.
- the present disclosure may be applied to 3GPP NR (New Radio: 5th generation mobile communication standard).
- eNB may be used interchangeably with gNB for convenience of description. That is, a base station described as an eNB may represent a gNB.
- the term terminal may refer to mobile phones, NB-IoT devices, sensors, as well as other wireless communication devices.
- the base station is a subject that performs resource allocation of the terminal, and may be at least one of gNode B, eNode B, Node B, a base station (BS), a radio access unit, a base station controller, or a node on a network.
- the terminal may include a user equipment (UE), a mobile station (MS), a cellular phone, a smart phone, a computer, or a multimedia system capable of performing a communication function. Of course, it is not limited to the above example.
- the radio access network New RAN on the 5G mobile communication standard specified by 3GPP, a mobile communication standard standardization organization, and the packet core (5G System, or 5G Core Network) as the core network , or NG Core: Next Generation Core), but the main gist of the present disclosure can be applied to other communication systems having a similar technical background with slight modifications within the scope not significantly departing from the scope of the present disclosure, , this will be possible at the discretion of a person having technical knowledge skilled in the technical field of the present disclosure.
- the present disclosure provides a method for selecting a Network Data Analytics Function (NWDAF) instance in consideration of an analytic purpose and network situation in a mobile communication network.
- NWDAF Network Data Analytics Function
- the present disclosure relates to a method of discovering NWDAF, which is a network function that provides analysis information, according to a purpose and situation, and enabling the discovered NWDAF to be used in utilizing network analysis information in a mobile communication system.
- the network analysis information may be used by an NWDAF or an entity corresponding to the NWDAF located in the core network to collect information from devices located inside or outside the network, perform analysis, and deliver the results.
- the above-described network analysis information may include analysis information related to a terminal, wired/wireless network situation information, and analysis information related to a service used by each terminal, and predictive information related to a future time along with statistical analysis information of past and present situations. may include.
- the network analysis information may be generated using various types of algorithms. For example, a method of generating the optimal analysis information may vary depending on the purpose of use of the analysis information, the application situation, or the application target. In addition, depending on the performance and load situation of the NWDAF that generates the analysis information, a method of selecting the NWDAF instance that provides the analysis information may be required. Through this, an embodiment of the present disclosure proposes a method of selecting an optimal NWDAF instance so that the network analysis information can be provided at a time or situation suitable for the analysis information generation method selected for the purpose.
- network analysis information may be used in combination with analysis information. That is, the following analysis information may mean network analysis information.
- Various embodiments of the present disclosure may utilize NWDAF that provides network analysis information within a mobile communication system.
- the present disclosure includes a method of selecting an optimal NWDAF instance in consideration of a purpose of using the analysis information and a network situation when there are a plurality of NWDAF instances having different performance and detailed functions for providing analysis information.
- the selection of an optimal algorithm for generating the analysis information may be changed according to the purpose of using the network analysis information.
- it includes a method of selecting an optimal NWDAF instance in a specific situation by comprehensively considering the geographic location, delay, specification, and load information of the NWDAF instance according to the network and resource conditions.
- the number of terminals using a mobile communication network and the number of services and applications to support them are increasing exponentially.
- the design and operation of wireless networks and core networks are becoming increasingly sophisticated.
- new types of terminals such as factories, unmanned aerial vehicles, robots, automobiles, and airplanes are emerging.
- the number of these new types of terminals is expected to increase continuously, and in order to effectively support these purposes, the mobile communication network is also expected to continuously evolve services.
- the embodiment according to the present disclosure collects data generated in the past or current network in performing operations such as operation of wireless and core networks, guaranteeing service quality, and providing optimized services, to collect current network conditions and service-related information. can be analyzed and used. Utilization of such network analysis information can efficiently perform functions such as terminal mobility, network function performance, user service satisfaction, slice quality management, traffic path optimization, base station and core network energy consumption reduction, abnormal terminal and traffic detection, etc. We can provide information to support you. In addition, network analysis information may be utilized to supplement basic functions such as mobility management, session management, and policy management performed in the existing core network or to increase efficiency.
- the network analysis information may be expressed in the form of basically collecting and analyzing data generated in the network in the past, providing statistical or numerical values, or predicting a value for a specific future time point.
- analysis information such as analysis/prediction of a movement location or movement path of a specific terminal, analysis/prediction of load information of a specific network function, and the like may be provided.
- NWDAF can perform the function of providing such analysis information.
- the NWDAF may include detailed functions to perform an analysis function.
- NWDAF may perform functions such as network information collection, collection information storage, learning, model storage, and inference.
- each NWDAF instance may provide only a subset of the detailed functionality.
- the accuracy and performance of a model providing network analysis information may vary depending on the design and training data of the model. If a plurality of NWDAFs provide the same analysis information, but different algorithms for generating such analysis information, different results or performance may be provided. Therefore, in selecting the NWDAF instance, it is necessary to select the instance in consideration of the purpose of utilizing the analysis information and the required performance.
- the present disclosure provides a method for selecting an NWDAF instance in consideration of these characteristics. Through this, a method for obtaining accurate analysis information at an appropriate time or situation to fit the purpose in utilizing the network analysis information may be provided.
- FIG. 1 A configuration diagram in which each element interacts using a service based interface is shown in FIG. 1 .
- FIG. 1 illustrates a configuration of a mobile communication system and an entity located outside a network according to an embodiment of the present disclosure.
- AMF Access and Mobility Management Function
- AMF Access and Mobility Management Function
- functions provided by the AMF may include, for example, functions such as registration of a terminal, connection, reachability, mobility management, access confirmation/authentication, and mobility event generation.
- the Session Management Function may perform a PDU session management function of the terminal.
- SMF provides a session management function through establishment, modification, and release of a session and maintenance of a tunnel between UPF and AN necessary for this, IP address assignment and management function of the terminal, ARP proxy function, user plane selection and It can perform functions such as control, traffic processing control in UPF, charging data collection control, and the like.
- the Policy Control Function may play a role of determining and issuing policies for access/mobility and session management applied by AMF and SMF.
- the PCF may manage the behavior of the entire network, and may provide policies to be implemented to NFs (Network Functions) constituting the control plane.
- PCF can access UDR (Unified Data Repository) to access information related to policy decision.
- a Network Exposure Function may be in charge of a function of transmitting or receiving an event occurring in a mobile communication network and a supported function (capability) to the outside.
- NEF can perform functions such as safely provisioning information of external applications in the core network, conversion of internal/external information, and redistribution after storing functions received from other NFs in UDR.
- Unified Data Management UDM
- Unified Data Repository UDR
- UDM is, for example, generation of AKA authentication information for 3GPP security, processing of user identifier (User ID), reverse concealment of secured user identifier (Subscriber Concealed ID, SUPI), list management of NFs currently supporting UE, subscriber information (subscription) management, short message (SMS) management, etc.
- the UDR may, for example, perform a function of storing and providing subscriber information managed by the UDM, structured data for exposure, and application data related to the NEF or service.
- the UPF (User Plane Function) serves to process actual user data, and transmits a packet generated by the terminal to an external data network or a packet to deliver data introduced from an external data network to the terminal.
- the main functions provided by UPF include, for example, acting as an anchor between radio access technologies, providing connectivity to PDU sessions and external data networks, packet routing and forwarding, packet inspection, and user plane policy. Functions such as enforcement, traffic usage report generation, buffering, etc. may be included.
- the Network Data Analytics Function collects events or information occurring within the network and uses tools such as an analysis tool or machine learning to perform statistics related to specific information, prediction ( Prediction) and recommendation information can be delivered to NF, AF, and OAM.
- NWDAF may perform functions such as collection of data from NF/AF/OAM (Operation, Administration and Maintenance), NWDAF service registration and metadata exposure, and providing network analysis information to NF/AF.
- NWDAF analyzes data through intelligent technology such as machine learning based on the collected network data and provides the analysis result to other 5G core network functions (eg NF, AF, or OAM, etc.) It can help optimize functions and improve performance.
- NWDAF and NWDAF instance may be used interchangeably. That is, in the description to be described later, the operation method of the NWDAF instance may refer to the operation method of the NWDAF.
- the UCMF UE Radio Capability Management Function
- the UCMF provides mapping information between the ID of the radio access related function of the terminal allocated by the PLMN or allocated by the manufacturer and the actual function in the dictionary. ) in the form of storage and provision.
- the AF Application Function
- the AF may perform a function interworking with the core network of 3GPP to provide a service.
- AF can be largely divided into reliable (Trusted) and untrusted (Untrusted).
- reliable AF it is possible to utilize the services of network functions located inside the core network without a separate intermediate function such as NEF. have.
- Typical functions provided by AF include application influence on traffic routing, utilization of network information exposure function, interaction with policy framework for policy control, and IMS-related interaction. .
- operation, administration and maintenance may refer to a device for managing the entire mobile communication network including the base station and the core network.
- the OAM may perform functions related to operation, management, maintenance, provisioning, troubleshooting, and the like of a communication network.
- OAM may perform a function of monitoring and setting the functions of each base station or core network to operate smoothly according to design and policy.
- OAM is a concept that encompasses all management-related tools and procedures, and does not refer to a specific device, but may include all tools, software, and procedures used by a network manager for management.
- a terminal may be connected to a RAN (Radio Access Network) to access a core network device of the network.
- a core network of a network may include the functions described above.
- the above-described RAN may include 5G-RAN, and may mean a base station that provides a wireless communication function to a terminal.
- the UE may access the AMF through the base station and exchange control plane signaling messages with the 5G core network.
- the terminal may access the UPF through the base station and exchange data network (Data Network, DN) and user plane (User Plane) data.
- Data Network Data Network
- DN user plane
- FIG. 1 A high-level configuration diagram of entities constituting such a core network is shown in FIG. 1 .
- NWDAF consists of one architectural entity in the system configuration. However, when segmentation is actually performed to support the operation of NWDAF, NWDAF provides data collection, data storage/Lake, data learning/Training, and model storage (Model Library/Repository). , Inference Engine, and Interface may be composed of detailed functions, and each detailed component may be divided into more subdivided functions according to each role. The detailed configuration of the NWDAF is shown in FIG. 2 .
- NWDAF Network Data Analytics Function
- the NWDAF in FIG. 2 may include a data collection function for collecting data by being connected to an NF, AF, OAM, or UE to perform data collection.
- the data collection function may pass the collected data to a repository so that other detailed functions can use the collected data.
- the data learning function using the collected data can create a model by applying various analysis techniques such as machine learning, artificial intelligence, trend analysis, and statistical analysis.
- the generated model may be stored in a model repository. Models stored in the repository or currently trained models can be used by the inference engine to obtain specific analysis or prediction values.
- NWDAF Network NF
- AF AF
- OAM commonly referred to as Consumer NF
- NWDAF Service NF
- analysis platforms that manage the life cycle of each analysis information or provide resources and an execution environment for each analysis information model to operate may be additionally configured.
- the services constituting the NWDAF are described on the basis that they can be divided into the detailed functions described above, but the present disclosure is not limited that the NWDAF is composed only of the detailed functions described above.
- NWDAF instances that drive analysis information with real resources are not driven by internally executing all of the above-described functions, but may selectively generate other functions by combining each function as needed.
- an instance for the main purpose of data collection may be driven as an instance having only a data collection function and a data storage function.
- an instance providing a function to calculate and provide analysis information it may be created as an instance in the form of selectively performing only an inference function and an interface function.
- a plurality of NWDAF instances having various purposes may exist within the core network of the mobile communication system. And, for a user or an NF who wants to use NWDAF analysis information, the discovery of an NWDAF instance suitable for the purpose must be preceded.
- NWDAF instance selection may also be referred to as service instance selection or service selection.
- the NWDAF instance shown in FIG. 2 may include at least one service instance.
- a service instance collects data from NFs, a service instance that performs a data collection function, a service instance that performs a storage function, and performs a training and learning function.
- the purpose of selecting the NWDAF instance may be classified as follows.
- FIG. 3 In order to use the analysis information provided by the NWDAF, an example in which other NFs constituting the core network uses the NWDAF is shown in FIG. 3 .
- FIG. 3 is a sequence diagram illustrating a procedure in which an entity using NWDAF analysis information such as NF, AF, OAM, etc. discovers an NWDAF instance using NRF according to an embodiment of the present disclosure.
- NWDAF analysis information such as NF, AF, OAM, etc.
- the AMF may subscribe to the mobility analysis information (Mobility Analytics) of the terminal provided by the NWDAF.
- This usage method is a general matter of a general service-based architecture, and each NF uses NRF or local policy to select an NWDAF instance that provides the required network analysis information and to use the service. can If an entity that intends to use NWDAF is outside the core network, such as untrusted AF, NWDAF service may be available through NEF.
- an NWDAF instance is discovered to use a function provided by another NWDAF instance, as shown in FIG. 4 .
- FIG. 4 is a sequence diagram illustrating a procedure in which an NWDAF instance discovers another NWDAF instance according to an embodiment of the present disclosure.
- an NWDAF instance by decomposing the functions constituting the NWDAF and selectively selecting each function as described above, a method in which the NWDAF instance discovers another NWDAF instance will be used.
- a method in which the NWDAF instance discovers another NWDAF instance will be used.
- a first embodiment of the present disclosure may include a method of configuring an NWDAF instance through a combination of detailed functions.
- the existing NWDAF can be distinguished as a single NF type for NFs constituting the core network.
- NWDAF which is modeled as a single function, can be decomposed into detailed functions. These detailed functions may be referred to as service instances.
- Representative decomposable detailed functions include data collection, data storage/Lake, data learning/Training, model library/Repository, inference engine, interface ( interface) may exist.
- Data collection collects network data such as events that occur from other NFs, AFs, or OAMs existing in the core network, so that NWDAF can play a role in collecting information to understand the current situation and learn data.
- the data store may serve as a store for storing data collected by the data collection function.
- a data store may also serve to pass data to be made available to a data learning or inference engine.
- Data learning is a function of learning and modeling given network information by utilizing the data collected by a model that generates analysis values using data such as machine learning, artificial intelligence, and statistical/analytic algorithms. can be performed.
- the model storage may perform a storage function to store the results of data training or to store and use other model developers or purchased models.
- the inference engine may perform a function of calculating and returning a request for analysis information using the data model.
- the interface can serve to provide a window to communicate with entities using analysis information such as NF, AF, and OAM existing in the core network.
- a method of configuring an NWDAF instance through a combination of the detailed functions of the above-described NWDAF and efficiently operating the NWDAF instances may be provided. An example of this is shown in FIG. 5 .
- FIG. 5 illustrates an example of a method of configuring an NWDAF instance with a combination of detailed functions according to an embodiment of the present disclosure.
- NWDAF Instance 1 of FIG. 5 is an instance that performs the main role of data collection, and consists of a combination of a function to collect data from NF, AF, OAM, etc. and a function to store it.
- NWDAF Instance 2 can play a role of training a model by utilizing the data collected from NWDAF Instance 1, and storing the trained model in the model repository so that it can be used by other entities.
- NWDAF Instance 3 communicates with entities such as NF, AF, and OAM that use analysis information to receive a request for analysis information, calculates and returns the requested analysis information, and an interface and an inference engine. can be configured.
- NWDAF Instance 4 can perform the function of providing an analysis information model related to on-line learning that collects data generated from the network in real time and reflects it in the model, rather than the model already provided.
- NWDAF Instance 4 may be configured with a combination of detailed functions of an interface, an inference engine, and model learning. That is, NWDAF instance 4 may be configured as a combination of NWDAF instance 2 and NWDAF instance 3 described above.
- the present disclosure may include a method of storing detailed functions constituting an NWDAF instance in the NRF, and an NF or other NWDAF that wants to select an NWDAF efficiently selects an instance.
- a unit providing the detailed functions of the NWDAF described above in the present disclosure may be referred to as a module of the NWDAF.
- NWDAF Instance 1 may include a data collection module and a data storage module.
- NWDAF Instance 1 may include a data collection module and a data storage module.
- FIG. 6 A procedure according to the present disclosure is illustrated in FIG. 6 .
- a module that may be included in the above-described NWDAF instance may be referred to as a service instance.
- FIG. 6 is a sequence diagram illustrating a procedure for discovering and selecting an NWDAF instance by using an NRF according to an embodiment of the present disclosure.
- an NWDAF instance may be created or a configuration may be changed. That is, NWDAF instance provisioning may be performed.
- the NWDAF instance may be registered with the NRF.
- NF Type In order to register the NWDAF instance as an NF in the NRF, NF Type, NF Instance ID, Names of supported services, PLMN ID and additional information may be registered in the NRF using the Nnrf_NFmanagement_NFRegister service.
- a list of modules constituting the NWDAF instance may be additionally registered with the NRF. In this process, when the module configuration of the existing NWDAF is updated or the state of each module is changed, Nnrf_NFmanagement_NFupdate may be used.
- NFs, AFs, and OAMs that want to use the service provided by the NWDAF may request the NRF for a list of NWDAF instances suitable for the purpose by using the Nnrf_NFDiscovery_Request service provided by the NRF.
- Service Name NF type of target NF, NF type of service consumer, and additional information may be used as the used NWDAF discovery condition.
- Consumer NFs may include information that can be used for the above-described discovery condition in a discovery request and deliver it to the NRF.
- the Consumer NFs may additionally provide the NRF with a list of modules or modules required according to the purpose of the Consumer NF as a filter. That is, the Consumer NF may request the NWDAF instance composed of the required modules from the NRF.
- the NRF may select a set of NWDAF instances corresponding to the NF discovery request received in step 605 .
- a list of modules additionally delivered in step 605 may be used.
- the NRF may return the set of NWDAF instances selected in step 607 to the Consumer NF.
- a second embodiment of the present disclosure may include a method for selecting an instance or model using an objective score through feedback.
- the second embodiment of the present disclosure may provide a method of selecting an NWDAF instance that meets a purpose and can provide a high level of satisfaction with analysis information when a plurality of NWDAF instances exist.
- the NF using the analysis information provided by the NWDAF may perform evaluation on the analysis information provided.
- the satisfaction level according to the value of the analysis information may vary according to the purpose of using the network analysis information. Although the analysis information has the same accuracy, the decision using the analysis information may vary depending on the purpose of use or the policy of the communication operator.
- two analysis models may provide predictive analysis values at 90 km/h and 110 km/h, respectively. Both pieces of analysis information may have the same accuracy (or error). However, if the AMF reflects the set value of the terminal using the information that the terminal's moving speed is 110 km/h, there may be a slight waste of resources, but there is no decrease in the quality that the user feels, so the terminal's moving speed is 90 km/h. Higher satisfaction can be obtained than when the information /h is used. The difference between these analysis information results is that the analysis model running or the data collected by each NWDAF instance may be different.
- the present disclosure may include a method used when selecting an NWDAF by receiving feedback on accuracy and satisfaction of such analysis information.
- the subject providing evaluation information such as the accuracy and satisfaction of the analysis information may be the NWDAF instance itself (self-feedback) that provides the analysis information.
- FIG. 7 A procedure for implementing the second embodiment of the present disclosure is shown in FIG. 7 .
- FIG. 7 is a sequence diagram illustrating a procedure for discovering and selecting an NWDAF instance by utilizing feedback information of an entity using analysis information according to an embodiment of the present disclosure.
- the NF may request a specific NWDAF instance to provide analysis information.
- the service used may be Nnwdaf_AnalyticsSubscription_subscribe or Nnwdaf_AnalyticsInfo_Request.
- the NWDAF instance may transmit a response message to the NF in response to the request received from the NF in step 701 .
- the NWDAF instance may include a Subscription Correlation ID related to the Subscription in Nnwdaf_AnalyticsSubscription_subscribe Response and transmit it to the NF.
- the NWDAF may provide the analysis information requested in step 701 .
- the NF may make a specific decision using the analysis information provided from the NWDAF instance, or refer to the analysis information to make the specific decision.
- an NF eg Consumer NF
- the AMF or NSSF utilizes the slice load level provided by the NWDAF to select a slice instance corresponding to the S-NSSAI requested by the specific UE.
- Service Experience Analytics provided by SMF Using analysis information (Network Performance Analytics) to determine policies and time related to BDT (Background Data Transfer), AM (Access and Mobility Management) or SM (Session management) using analysis information related to abnormal behavior of the terminal related policy decision, PCF or AMF decides service area restriction using expected UE behavior of UE, AMF uses expected UE behavior of UE to determine registration cycle, Determining the DRX cycle, the minimum connection maintenance time, etc. may be included.
- Network Performance Analytics Analysis information to determine policies and time related to BDT (Background Data Transfer), AM (Access and Mobility Management) or SM (Session management) using analysis information related to abnormal behavior of the terminal related policy decision
- PCF or AMF decides service area restriction using expected UE behavior of UE, AMF uses expected UE behavior of UE to determine registration cycle, Determining the DRX cycle, the minimum connection maintenance time, etc. may be included.
- the SMF or PCF determines the optimal DNAI (Data Network Access Identifier) for a specific application, the PCF determines related to the Radio/Frequency Selection Priority (RFSP) index, and NWDAF is involved in the determination related to the detection and utilization of a new application through the NEF or PCF.
- RFSP Radio/Frequency Selection Priority
- the NF eg, Consumer NF
- the network operator may quantify the accuracy and satisfaction of the provided analysis information and feed it back to the NWDAF instance.
- Feedback information may include information such as Consumer NF type, applied service, application target, accuracy, and satisfaction of the analysis information provided from NWDAF, and the NF provides such feedback information to NWDAF. can be sent to the instance.
- the NF eg, Consumer NF
- the analysis information target period (Analytics Target Period)
- the preferred level of accuracy (Preferred level of accuracy)
- the analysis information response time time when analytics are) needed
- filter information included upon request may be selectively included in the feedback information.
- the information included in the feedback information may include only some combinations of the above-described information according to the characteristics of the analysis information.
- feedback information referred to as Nnwdaf_AnalyticsSubscription_Feedback may be transmitted to the NWDAF instance, and when the analysis information request service is used, feedback information referred to as Nnwdaf_AnalyticsInfo_Request_Feedback is NWDAF It can be sent to an instance.
- the NWDAF instance may collect the feedback information provided in step 709 .
- the NWDAF instance may make a decision to update the NFProfile in the NRF. For example, if the above-mentioned cumulative accepted result passes a certain threshold, and the accuracy or satisfaction of the analysis information exceeds or falls below a certain value, such as 90%, the NWDAF instance makes a decision to update the NFProfile in the NRF.
- a certain period when a specific time such as 24 hours has elapsed, the NWDAF instance may update the NFProfile of the NWDAF instance in the NRF. Values such as the above-described specific threshold or specific period may be determined according to an internal policy.
- the NWDAF instance may request the NRF by configuring the NFprofile or factors including the new information.
- Nnrf_NFManagement_NFUpdate may be used.
- the transmitted information may include information on Consumer NF type, applied service, applied target, accuracy, and satisfaction (Score).
- the Consumer NF type may mean a target using analysis information
- the applied service may mean a service related to a decision performed by the Consumer NF by using the analysis information.
- the application target may refer to a target to which a decision is applied (eg, a UE or a specific NF, or a traffic forwarding path, etc.).
- an evaluation result may be transmitted to the NRF.
- the analysis information target time (Analytics Target Period)
- the preferred level of accuracy and the analysis information response time (time when analytics) are selectively transmitted in step 709 . are needed)
- filter information included upon request may be provided to the NRF along with cumulative evaluation or feedback results.
- the NRF that has received these additional parameters can store the received parameters in NFProfile.
- a new consumer NF who wants to use the analysis information of the NWDAF may request a list of NWDAF instances that provide specific analysis information to the NRF.
- the new Consumer NF may deliver the Target NF type, consumer NF type, and Analytic ID to the NRF as the conditions for discovery of the NWDAF instance.
- a service Related service
- accuracy, and satisfaction related to the utilization of analysis information may be provided to the NRF as filter information. That is, in an embodiment of the present disclosure, filter information may refer to information about a condition used to classify specific information.
- the NRF may generate a set of NWDAF instances satisfying a condition by using the information provided in step 715 .
- the NRF may additionally deliver a specific related service related to each instance and related accuracy and satisfaction while returning a set of NWDAF instances to the new Consumer NF.
- steps 701 to 709 of FIG. 7 may be replaced with steps 801 to 817 of FIG. 8 .
- FIG. 8 is a sequence diagram illustrating a method for an AF to discover an NWDAF according to an embodiment of the present disclosure.
- the AF may transmit an Nnef_AnalyticsExposure_Subscribe or Nnwdaf_AnalyticsExposure_Fetch message to the NEF in order to request the NWDAF to provide analysis information.
- the NEF may request the NWDAF to provide analysis information.
- the NWDAF may transmit a response message to the NEF in the same manner as in step 703.
- the NEF may deliver the response message received from the NWDAF to the AF. And, in the same way as in step 705, in step 809, the NWDAF may provide the requested analysis information to the NEF.
- the NEF may deliver the analysis information received from the NWDAF to the AF.
- the AF may make a specific decision using the analysis information provided from the NWDAF, or refer to the analysis information to make the specific decision.
- the AF may transmit feedback information including information quantifying the accuracy and satisfaction of the provided analysis information to the NEF. And, in the same way as in step 709, the NEF may deliver feedback information to the NWDAF in step 817.
- a third embodiment of the present disclosure may include a method for discovering and selecting an NWDAF instance for sharing collected data.
- the basic operating method of the NWDAF may include collecting data generated in a network on a large scale, and generating a model necessary for operation and management from the collected data. Based on such a model, a method of obtaining or predicting statistical information related to a specific phenomenon or behavior of an object may be used.
- the model used or trained may be a model utilizing a technique such as machine learning, artificial intelligence, or deep learning as well as various statistical models.
- the priority may be to collect data to create or utilize a model.
- the NF that provides data may create a load that must collect and report duplicate data.
- a method of configuring an instance for collecting data by separating detailed functions of NWDAF, and sharing and using the collected data by a plurality of NWDAF instances may be used.
- the NF providing the data can communicate with the NWDAF responsible for the collection of a single target, and each NWDAF may not have to collect and store all of the numerous network data that occur innumerably. Therefore, through this, the load for data collection and processing of NF and NWDAF may be reduced, and there may be an effect of reducing the number of signaling messages for delivery of collected data.
- NWDAF expressed as a single entity may be divided into various detailed functions as described above, and the present disclosure may include a method of configuring an NWDAF instance by separating functions for data collection.
- Existing NWDAF provides only two services, and these two services are the analytics information subscription (Nnwdaf_Analytics_Subscription) and the analytics information request (Nnwdaf_AnalyticsInfo) service. Therefore, a detailed function instance for data collection cannot be found by utilizing the existing service-based interface.
- the present disclosure describes a method for enabling specific NWDAF instances to share data collection function.
- a data collection function related to data collection and a new service interface may be defined in NWDAF in relation to data storage.
- the name of the newly defined interface may be referred to as Nnwdaf_DataCollection.
- the above-described service interface may mean a new service for a specific NF to perform a request for collected or later collected data.
- the interface provided by the above-described service may include a subscription (Subscribe), a notification (Notify), a notification cancel (Unsubscribe), a request (Request or Fetch), and a response (Response).
- subscription may mean requesting notification of data when a periodic or specific condition is satisfied with respect to newly collected data or an event.
- the subscription service may not receive further notices through unsubscription.
- the request interface is an interface for temporarily bringing existing data, and when a request for specific data is received, data can be delivered to the requester through a response.
- additional factors such as event to be collected, condition, time, period, etc. may be requested together.
- This request may mean a request to notify the location of the terminal when the terminal is located in TAI1 and TAI2 from 12:00 to 14:00 for the terminal having UE ID1.
- the procedure for the present disclosure is illustrated in FIG. 9 .
- FIG. 9 is a sequence diagram illustrating a method of discovering and selecting an NWDAF for a data collection function according to an embodiment of the present disclosure.
- the NF that wants to use the NWDAF DataCollection service may request an NWDAF instance that provides the Nnwdaf_DataCollection service by using the NRF.
- the NF may be an NWDAF instance that intends to perform data collection through another NWDAF instance.
- NF can explicitly convey the data storage and data collection requirements by providing the module name as an additional argument.
- the NRF that has received the NWDAF instance request from the NF may return the NWDAF providing the requested function to the NF.
- the NF may call the interface provided by the DataCollection service to the NWDAF.
- the callable interface may include an interface such as a subscription, a notification, a notification unsubscribe, a request or a fetch, and a response.
- a subscription such as a subscription, a notification, a notification unsubscribe, a request or a fetch, and a response.
- FIG. 9 a procedure using a subscription is shown, and information on data name, collection period, target or filters is included as additional factors. can be transmitted.
- the NWDAF when a condition for specific target data is satisfied using the above-described additional factor, the NWDAF may be requested to notify the corresponding data.
- a request Request or Fetch
- similar request factors may be included and requested from the NWDAF.
- a response message to the interface call transmitted in step 905 may be transmitted from the NWDAF to the NF.
- the response message transmitted to the NF may include a subscription ID (Subscription ID) and the like.
- step 909 the NWDAF instance receiving the request from the NF in step 905 may notify the NF of the collected data when collecting data or an event satisfying the condition.
- the NF may perform a related service using the data notified from the NWDAF.
- the other NWDAF instance may generate analysis information using the notified data.
- the NF can deliver feedback on the data collection accuracy and satisfaction of the NWDAF instance that has received the current data to the NWDAF. Through such feedback transfer, it is possible to selectively assist in the selection of NWDAF instances with respect to specific data collection. For example, there may be a plurality of NWDAF instances providing the DataCollection service. At this time, since each data collection NWDAF instance has a different data collection period and a different data collection target, the collected data may be different according to the purpose of each NF. Accordingly, feedback data for assisting in NWDAF instance selection according to each purpose may be accumulated.
- a fourth embodiment of the present disclosure may include a NWDAF instance registration and discovery method for task offloading.
- network data since network data covers a large number of terminals and a wide area of a country unit, a large amount of data may be generated at a very high rate.
- NWDAF For data generated from such national mobile communication networks, it may be difficult for a single NWDAF to collect all data and perform calculations for analysis.
- the NWDAF needs to delegate the calculation to a plurality of NWDAFs by distributing the work for a specific analysis information request.
- delegation of such calculations may be referred to as task offloading.
- the task offloading means that a plurality of NWDAF instances divide and process the requested network analysis information request, and, if necessary, a specific NWDAF performs a task of integrating the results received from the distributed NWDAF instances.
- various criteria such as a criterion for dividing the integrated analysis information into small analysis information, may exist by region, by terminal, by analysis information, by instance, and by network function (NF). According to such various criteria, the network analysis information request may be distributed and processed to a plurality of NWDAF instances.
- a plurality of NWDAF instances for each region participate to generate analysis information, and display the integrated result. You can create and deliver the result to the requesting NF.
- a method of performing job offloading according to the present disclosure may be divided into two main types.
- the first method is a method in which an NWDAF that has received a request for analysis information requests analysis information from another NWDAF again.
- the procedure according to this first method is shown in FIG. 10 .
- the NWDAF instance may mean NWDAF.
- FIG. 10 is a sequence diagram illustrating a method for an NWDAF instance to discover and select another NWDAF for task offloading according to an embodiment of the present disclosure.
- the NF may request analysis information from the NWDAF instance 1.
- AF or OAM may request analysis information from NWDAF instance 1.
- the NWDAF instance 1 may determine to calculate by offloading the work on the requested analysis information to another NWDAF. As a criterion for NWDAF instance 1 to make this decision, the time when analytics information is needed, the current load level of the NWDAF, the current resource capacity of the NWDAF, and the analysis accuracy are considered. can be NWDAF instance 1 may make a decision related to offloading in consideration of the above-mentioned criteria.
- the NWDAF instance 1 that has decided to distribute the analysis information calculation related work may send an Nnrf_NFDiscovery request to the NRF to find another NWDAF instance to distribute the work.
- the request target may include whether the discovery target NWDAF supports an analytics information identifier (Analytics ID) for offloading tasks.
- the NWDAF instance 1 may additionally transmit whether the NWDAF interface and the inference engine module are included in the target-related factor filter. By additionally passing NWDAF's interface and whether an inference engine module is included, you can let NRF find an NWDAF instance that supports task offloading.
- the NWDAF instance 1 includes a type of target NWDAF, a name of supported services, an analytics ID or a list of modules, etc.
- An Nnrf_NFDiscovery request may be sent to the NRF.
- the NRF receiving the request may return an NWDAF instance corresponding to the request.
- the NRF may transmit a response message including information on an NWDAF instance set capable of offloading a task to the NWDAF instance 1 .
- step 1009 when a new NWDAF instance 2 for task offloading is discovered, the NWDAF instance 1 may request analysis information from the instance 2 .
- the target, time, and accuracy of the requested analysis information may be the same as that of the NWDAF instance 1 requested in step 1001, or may include a small range.
- NWDAF instance 1 when NWDAF instance 1 receives a request for analysis information on the expected movement path for terminals 1 to 100, in step 1009, NWDAF instance 1 moves the terminal corresponding to 50 to 100 in NWDAF instance 2 You can request analysis information for path prediction.
- a method of dividing a job may include a method of dividing a requested object or a method of dividing a requested area or a specific time zone. Additionally, when specific analysis information is a combination of other analysis information, NWDAF instance 1 may request analysis information different from that requested in step 1001 from NWDAF instance 2 .
- NWDAF instance 1 and NWDAF instance 2 may each process a request for analysis information. At this time, NWDAF instance 1 may perform calculations except for the part in which the work is offloaded. In the example of step 1009, NWDAF instance 1 may calculate only analysis information corresponding to terminals 0 to 55.
- the NWDAF instance 1 may receive the result calculated by the NWDAF instance 2 from the NWDAF instance 2 .
- the NWDAF instance 1 may generate the analysis information requested in operation 1001 .
- the NWDAF instance 1 may deliver the final analysis information generated in step 1017 to the analysis information requester. That is, the NWDAF instance 1 may deliver the final analysis information to the NF.
- a second method of performing task offloading according to the present disclosure is to define a service for new task offloading in NWDAF.
- This method has the advantage of being able to divide (or offload) the calculation of analysis information more precisely by passing factors related to offloading, compared to requesting analysis information to NWDAF.
- an Nnwdaf_TaskOffloading service may be defined in the present disclosure.
- the Nnwdaf_TaskOffloading service may provide an interface of a request and a response.
- the request interface is an interface used to request task offloading to a specific NWDAF instance.
- the request interface is an analytics information identifier (Analytics ID), an analytics model identifier (Analytics Model ID), a target, and reporting information. ), filter information, analytics model, and the like.
- the NWDAF instance receiving the analysis information offloading request may determine whether the request is executed, and accordingly, the NWDAF instance receiving the analysis information offloading request may return information indicating whether the request is approved or rejected. In case of refusal, reasons for refusal of the request such as lack of resources or lack of data may be included.
- a procedure for the above-described embodiment of the present disclosure is shown in FIG. 11 .
- FIG. 11 is a sequence diagram illustrating a method by which NWDAF discovers and selects NWDAF for task offloading according to an embodiment of the present disclosure.
- the NF may request analysis information from the NWDAF instance 1.
- AF or OAM may request analysis information from NWDAF instance 1.
- NWDAF instance 1 may determine that another NWDAF (or NWDAF instance) calculates the requested analysis information by offloading the job.
- the criteria for NWDAF instance 1 to make this decision may include the time when analytics information is needed, the current load level of the NWDAF, the current resource capacity of the NWDAF, and the accuracy of analysis. have.
- the NWDAF instance 1 that has decided to distribute the analysis information calculation related work may send an Nnrf_NFDiscovery request to the NRF to find another NWDAF instance to distribute the work to.
- whether the NWDAF instance to which tasks are distributed supports the Nnwdaf_TaskOffloading service may be included in the Nnrf_NFDiscovery request.
- the NRF may return NWDAF instances supporting the Nnwdaf_TaskOffloading service to NWDAF instance 1 .
- the NRF may transmit a response message including information on an NWDAF instance set supporting the Nnwdaf_TaskOffloading service to the NWDAF instance 1 .
- NWDAF instance 1 may request the newly discovered NWDAF instance 2 to offload a specific task by using Nnwdaf_TaskOffloading_Request.
- the analysis information identifier to be offloaded (Analytics ID), the analysis information model identifier (Analytics Model ID), the target, reporting information, filter information, etc. may be included.
- the analysis information identifier and the analysis model identifier may be selectively included in the specific task offloading request described above.
- NWDAF instance 1 may pass the model (Analytic Model) itself so that NWDAF instance 2 can calculate it.
- NWDAF instance 1 and NWDAF instance 2 may each process an analysis information request.
- NWDAF instance 1 may perform calculations except for the part in which the work is offloaded. That is, the NWDAF instance 1 may perform calculations on the analysis information except for the part in which the task is offloaded to the NWDAF instance 2 .
- the NWDAF instance 2 may transmit the calculation result to the NWDAF instance 1 .
- the NWDAF instance 2 may transmit a failure indication to the NWDAF instance 2.
- the NWDAF instance 2 may also transmit the reason (cause) of the operation failure to the NWDAF instance 1.
- the NWDAF instance 1 may generate the analysis information requested in operation 1101 based on the result calculated in operation 1111 and the calculation result received from the NWDAF instance 2 in operation 1113 .
- the NWDAF instance 1 may deliver the final analysis information generated in step 1117 to the analysis information requester. For example, the NWDAF instance 1 may transmit the final analysis information generated in step 1117 to the NF.
- a fifth embodiment of the present disclosure may include an NWDAF instance discovery and selection method for federated learning.
- the NWDAF instance may use federated learning that requires sharing of learned factors according to the type of the analysis model.
- Cooperative learning may refer to a method of increasing learning efficiency by sharing the results of learning independently by multiple instances and sharing common learning factors. Therefore, it may be necessary to negotiate in advance on the learning model to be used and the factors to be shared between instances.
- a service for negotiation related to this inter-instance cooperation model and factors to be shared is provided. This service may be referred to as Nnwdaf_FederatedLearning_Association.
- a procedure for performing the above-described cooperative learning is shown in FIG. 12 .
- FIG. 12 is a sequence diagram illustrating a method of discovering and selecting an NWDAF instance for cooperative learning according to an embodiment of the present disclosure.
- the NWDAF instance 1 may determine to perform federated learning.
- the NWDAF instance 1 for cooperative learning may send an Nnrf_NFDiscovery request to the NRF to find another NWDAF instance to share a learning factor with.
- whether a target NWDAF instance to share a learning factor supports the Nnwdaf_FederatedLearning_Association service may be included in the Nnrf_NFDiscovery request.
- the NRF may return instances of NWDAF that support the Nnwdaf_FederatedLearning_Association service.
- the NRF may transmit a response message including information on an NWDAF instance set supporting the Nnwdaf_FederatedLearning_Association service to the NWDAF instance 1 .
- NWDAF instance 1 may use Nnwdaf_FederatedLearning_Association_Reqeust to request the newly discovered NWDAF instance 2 to share learning factors for a specific model.
- Factors transmitted upon request may include an analysis information identifier for cooperative learning, an analysis model identifier, a list of factors to be shared, filter information on a reporting cycle, and the like.
- the analysis information identifier and the analysis model identifier may be selectively included in the learning factor sharing request for the specific model described above.
- NWDAF instance 1 may pass the model (Analytic Model) itself so that NWDAF instance 2 can calculate it.
- NWDAF instance 1 and NWDAF instance 2 may each perform learning.
- the NWDAF instance 2 may report the learned factor to the NWDAF instance 1 at the period agreed in step 1207 .
- the NWDAF instance 1 may adjust the factors received from the NWDAF instance 2 and its own factors to calculate an integrated factor and apply it to the model.
- a sixth embodiment of the present disclosure may include a method of registering and discovering an NWDAF instance for delivery of an analysis model.
- various methods such as self-learning of an analysis model that can be run in NWDAF, purchasing a commercial model, and sharing from another instance may be used.
- various models may be selectively used in providing the same analysis information. Accordingly, when receiving the analysis information request, the NWDAF may select a model for calculating the analysis information and calculate the analysis information. At this time, if there is no analysis information model required, NWDAF may receive the analysis information model from the model repository or another NWDAF instance.
- an Nnwdaf_Model_Transfer service may be defined in the present disclosure.
- a procedure for implementing the NWDAF instance registration and discovery method for the above-described analysis model delivery is shown in FIG. 13 .
- steps 601 and 603 of FIG. 6 may be performed before step 1301 to be described later is performed.
- NWDAF instance 1 may perform provisioning for NWDAF instance 1 and may register with NRF.
- the NWDAF instance 1 may recognize that a model for calculation of analysis information is required, and may determine to receive a model for calculation of analysis information from another NWDAF instance.
- NWDAF instance 1 may send an Nnrf_NFDiscovery request to NRF to find another NWDAF instance that supports model delivery.
- whether the target NWDAF instance supporting model transfer supports the Nnwdaf_Model_Transfer service may be included in the Nnrf_NFDiscovery request.
- information on whether to search for a dedicated NWDAF instance for model distribution, such as a model repository, may be additionally transmitted.
- the NRF receiving the request may return NWDAF instances supporting the Nnwdaf_Model_Transfer service.
- the NRF may transmit a response message including information on an NWDAF instance set supporting the Nnwdaf_Model_Transfer service to the NWDAF instance 1 .
- the NWDAF instance 1 may request the transfer of a specific analysis model to the newly discovered NWDAF instance 2 using Nnwdaf_Model_Transfer_Reqeust.
- Factors passed upon request may include an analysis information identifier, an analysis model, and the like.
- the analysis information identifier and the analysis model identifier may be selectively included in the delivery request for the specific analysis model described above.
- NWDAF instance 2 may transmit the requested model to NWDAF instance 1 .
- the network entity performing the operation method as shown in FIG. 14 may mean NWDAF (or NWDAF instance).
- NWDAF or NWDAF instance
- the NWDAF may receive a request message for analysis information.
- the NWDAF may receive a request message for analysis information from NF, AF, or OAM.
- a request message for the above-described analysis information Nnwdaf_AnalyticsSubscription_Subscribe or Nnwdaf_AnalyticsInfo_Request may be used.
- the NWDAF may determine to offload the processing of the requested analysis information to another NWDAF based on the above-described request message for the analysis information.
- the NWDAF may decide to learn cooperatively with another NWDAF.
- the NWDAF may decide to receive an analysis information model from another NWDAF.
- the analysis information model may mean a model for calculating the requested analysis information.
- the NWDAF may transmit a discovery message for discovering another NWDAF to the NRF.
- the discovery message for discovering another NWDAF includes a type of another NWDAF, a name of a supported service, an identifier of analysis information, information related to whether other NWDAF supports offloading, or a module included in another NWDAF.
- a module included in another NWDAF may mean an interface or an inference engine module.
- the NWDAF may transmit a list of modules included in another NWDAF to the NRF.
- the NWDAF may receive a response message to the discovery message from the NRF.
- the response message to the above-described discovery message may include information on other NWDAFs.
- information on other NWDAF may include information on an NWDAF instance set capable of offloading processing for analysis information.
- the NWDAF may transmit a message related to processing of the analysis information to another NWDAF based on the information on the other NWDAF included in the response message.
- the NWDAF may request analysis information from another NWDAF based on a request message for analysis information received from the NF in step 1401 .
- the target, time, and accuracy of the analysis information requested from another NWDAF in step 1407 are the same as or less than the target, time, and accuracy of the analysis information requested by the NF from the NWDAF in step 1401. can
- the NWDAF may transmit a message requesting offloading of a task related to processing of analysis information to another NWDAF.
- the offloading request message includes an identifier of analysis information, an identifier of a model for processing analysis information, a target for which analysis information is used, information related to reporting of analysis information, filter information related to selection of analysis information, etc. may include
- the NWDAF may receive a response message to the message related to the processing of the analysis information.
- the response message to the message related to the processing of the above-described analysis information is a result of processing on analysis information performed by another NWDAF, an indicator indicating whether offloading fails, or information on a cause of failure and the like.
- the NWDAF may generate analysis information.
- the NWDAF may generate the analysis information based on the result of the processing on the analysis information performed by the NWDAF and the result of the processing on the analysis information performed by the other NWDAF.
- the result of processing on the analysis information performed by another NWDAF may be included in the response message of step 1409 .
- the NWDAF may transmit the generated analysis information to an NF, AF or OAM requesting the analysis information.
- the NWDAF may transmit a discovery message for discovering another NWDAF performing federated learning to the NRF. Then, the NWDAF may receive a response message to the above-described discovery message from the NRF. In addition, the NWDAF may transmit a message requesting sharing of a parameter used for cooperative learning to another NWDAF.
- the parameters used for the above-described cooperative learning may include an identifier of analysis information, an identifier of a model for learning analysis information, a list of shared parameters, or a reporting period for cooperative learning.
- the NWDAF When the NWDAF sends a discovery message to the NRF to discover another NWDAF that performs cooperative learning, the NWDAF determines the result of learning about the parameters used for cooperative learning performed by the NWDAF, and cooperative learning performed by the other NWDAF.
- a shared parameter may be generated based on the result of learning about the parameter used for .
- the result of learning on the parameter used for cooperative learning performed by another NWDAF may be included in a response message to a message requesting sharing of the parameter used for cooperative learning.
- the NWDAF may transmit a discovery message to the NRF to discover another NWDAF carrying the analysis information model.
- the NWDAF may transmit a message requesting delivery of the analysis information model to another NWDAF.
- the message requesting delivery of the analysis information model may include an identifier of the analysis information or an identifier of the analysis information model.
- FIG. 15 is a block diagram illustrating a configuration of a network entity according to an embodiment of the present disclosure.
- '... wealth' '...
- a term such as 'group' means a unit for processing at least one function or operation, which may be implemented as hardware or software, or a combination of hardware and software.
- the configuration of the network entities shown in FIG. 15 may represent the configuration of the network entities shown in FIG. 1 .
- the configuration of the network entity shown in FIG. 15 may mean the structure of the NWDAF.
- the present invention is not limited thereto, and the configuration of the network entity shown in FIG. 15 may mean the configuration of AMF, SMF, PCF, or the like.
- the network entity may include a transceiver 1510 , a controller 1520 , and a storage 1530 .
- the controller may be defined as a circuit or an application specific integrated circuit or at least one processor.
- the above-described network entity may be referred to as a core network object.
- the transceiver 1510 may transmit/receive signals to and from other network entities.
- the transceiver 1510 may provide an interface for communicating with other devices in the network. That is, the transceiver 1510 may convert a bit string transmitted from the network entity to another device into a physical signal and convert a physical signal received from the other device into a bit string. That is, the transceiver 1510 may transmit and receive signals.
- the transceiver 1510 may be referred to as a modem, a transmitter, a receiver, a communication unit, or a communication module.
- the transceiver 1510 may enable the network entity to communicate with other devices or systems through a backhaul connection (eg, wired backhaul or wireless backhaul) or another connection method or through a network.
- a backhaul connection eg, wired backhaul or wireless backhaul
- the storage unit 1530 may store data such as a basic program, an application program, and setting information for an operation of a network entity.
- the storage unit 1530 may be configured as a volatile memory, a non-volatile memory, or a combination of a volatile memory and a non-volatile memory.
- the storage unit 1530 may store at least one of information transmitted/received through the transceiver 1510 and information generated through the control unit 1520 .
- the storage unit 1530 may store information required for service detection according to the above-described embodiment.
- the controller 1520 may control the overall operation of the network entity according to the embodiment proposed in the present disclosure.
- the controller 1520 may control a signal flow between blocks to perform an operation according to the procedure described above with reference to FIGS. 1 to 14 .
- the controller 1520 may control components of a network entity to select an NWDAF instance in the wireless communication system according to an embodiment of the present disclosure.
- a method of operating a network data analytics function (NWDAF) in a wireless communication system includes the steps of receiving a request message for analysis information from a network function (NF); based on the steps of transmitting a discovery message for discovering at least one other NWDAF to a Network Repository Function (NRF), receiving a response message to the discovery message from the NRF, and the response message to the discovery message is the including information on at least one other NWDAF, transmitting a request message for processing the analysis information to the at least one other NWDAF based on the information on the at least one other NWDAF, the at least one receive a response message to the message related to the processing of the analysis information from another NWDAF of Including a result, based on the result of the processing on the analysis information performed by the NWDAF and the result of the processing on the analysis information performed by the at least one other NWDAF, the analysis information requested from the NF generating, and transmitting the generated analysis information to the NF.
- NDF Network Repository Function
- the request message for processing the analysis information may include at least one of an identifier of the analysis information, a target for which the analysis information is used, or filter information for classification of the analysis information.
- the step of transmitting a discovery message for discovering at least one other NWDAF to the NRF based on the request message for the analysis information includes: Based on the request message for the analysis information, the analysis information and transmitting a discovery message for discovering at least one other NWDAF that provides a model for processing to the NRF.
- the receiving of the response message to the discovery message comprises receiving, from the NRF, a response message including information on at least one other NWDAF that provides a model for processing the analysis information.
- the method of operation of the NWDAF includes transmitting a message requesting provision of a model for processing the analysis information to at least one other NWDAF that provides a model for processing the analysis information, and The method further comprising the step of receiving information on a model for processing the analysis information from at least one NWDAF that provides a model for processing the analysis information, requesting to provide a model for processing the analysis information
- the message may include an identifier of the analysis information and an identifier of a model for processing the analysis information.
- the method of operating the NWDAF may further include performing provisioning for the NWDAF, and transmitting a message for registration of the NWDAF to the NRF.
- the operation method of the NWDAF based on the request message for the analysis information received from the NF, determining to offload the processing for the analysis information to the at least one other NWDAF A method comprising further steps.
- the discovery message for discovering the at least one other NWDAF includes: a type of the at least one other NWDAF, a name of a supported service, an identifier of the analysis information, and offloading of the at least one other NWDAF It may include at least one of information related to whether support is provided or information about a module included in the at least one other NWDAF.
- a network data analytics function (NWDAF) in a wireless communication system receives a request message for analysis information from a network function (NF) through a transceiver and the transceiver, and the transceiver unit transmits a discovery message for discovering at least one other NWDAF to a Network Repository Function (NRF) based on the request message for the analysis information, and responds to the discovery message from the NRF through the transceiver receiving a message, and a response message to the discovery message includes information on the at least one other NWDAF, and through the transceiver, processing of the analysis information based on the information on the at least one other NWDAF for transmitting a request message to the at least one other NWDAF, and receiving a response message to the message related to the processing of the analysis information from the at least one other NWDAF through the transceiver, and related to the processing of the analysis information
- the response message to the message includes a result of processing on the analysis information performed by the at least one other NWDA
- the request message for processing the analysis information may include at least one of an identifier of the analysis information, a target for which the analysis information is used, or filter information for classification of the analysis information.
- the at least one processor the at least one processor
- a discovery message for searching for at least one other NWDAF that provides a model for processing the analysis information may be transmitted to the NRF.
- the at least one processor may receive, from the NRF through the transceiver, a response message including information on at least one other NWDAF that provides a model for processing the analysis information. have.
- the at least one processor through the transceiver, at least one other NWDAF that provides a model for processing the analysis information, a message requesting to provide a model for processing the analysis information transmits, through the transceiver, receives information on a model for processing the analysis information from at least one NWDAF that provides a model for processing the analysis information, and a model for processing the analysis information
- the message requesting provision may include an identifier of the analysis information and an identifier of a model for processing the analysis information.
- the at least one processor may perform provisioning for the NWDAF and transmit a message for registration of the NWDAF to the NRF.
- the at least one processor determines to offload the processing for the analysis information to the at least one other NWDAF based on the request message for the analysis information received from the NF. and the discovery message for discovering the at least one other NWDAF is related to the type of the at least one other NWDAF, the name of a supported service, an identifier of the analysis information, and whether offloading of the at least one other NWDAF is supported. It may include at least one of information or information about a module included in the at least one other NWDAF.
- the present disclosure relates to a communication technique that converges a 5G communication system for supporting a higher data rate after a 4G system with IoT technology, and a system thereof.
- the present disclosure provides intelligent services (eg, smart home, smart building, smart city, smart car or connected car, healthcare, digital education, retail business, security and safety related services, etc.) based on 5G communication technology and IoT-related technology. ) can be applied to
- An embodiment of the present disclosure includes a method for dividing NWDAF into detailed functions and efficiently discovering and selecting them. Through this, calculation efficiency of analysis information and resources required for calculation may be efficiently managed. In addition, the cost of creating, managing, and maintaining the model can be reduced by delivering the model used to calculate the analytic information or supporting collaborative learning. Through this, in terms of using the analysis information, optimized analysis information having a high level of accuracy and satisfaction according to circumstances may be delivered at an appropriate time.
- a computer-readable storage medium or computer program product storing one or more programs (software modules) may be provided.
- One or more programs stored in a computer-readable storage medium or computer program product are configured for execution by one or more processors in an electronic device (device).
- One or more programs include instructions for causing an electronic device to execute methods according to embodiments described in a claim or specification of the present disclosure.
- Such programs include random access memory, non-volatile memory including flash memory, read only memory (ROM), electrically erasable programmable ROM (EEPROM: Electrically Erasable Programmable Read Only Memory), magnetic disc storage device, Compact Disc-ROM (CD-ROM), Digital Versatile Discs (DVDs), or any other form of It may be stored in an optical storage device or a magnetic cassette. Alternatively, it may be stored in a memory composed of a combination of some or all thereof. In addition, each configuration memory may be included in plurality.
- the program accesses through a communication network composed of a communication network such as the Internet, Intranet, Local Area Network (LAN), Wide LAN (WLAN), or Storage Area Network (SAN), or a combination thereof. It may be stored in an attachable storage device that can be accessed. Such a storage device may be connected to a device implementing an embodiment of the present disclosure through an external port. In addition, a separate storage device on the communication network may be connected to the device implementing the embodiment of the present disclosure.
- a communication network such as the Internet, Intranet, Local Area Network (LAN), Wide LAN (WLAN), or Storage Area Network (SAN), or a combination thereof. It may be stored in an attachable storage device that can be accessed.
- Such a storage device may be connected to a device implementing an embodiment of the present disclosure through an external port.
- a separate storage device on the communication network may be connected to the device implementing the embodiment of the present disclosure.
- computer program product or “computer readable medium” refers to a medium such as a memory, a hard disk installed in a hard disk drive, and a signal as a whole. used for These “computer program products” or “computer-readable recording media” are means for providing a method for selecting an NWDAF instance according to the present disclosure.
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (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
Description
Claims (15)
- 무선 통신 시스템에서 NWDAF(Network Data Analytics Function)의 동작 방법에 있어서,NF(Network Function)로부터 분석 정보에 대한 요청 메시지를 수신하는 단계;상기 분석 정보에 대한 요청 메시지에 기초하여, 적어도 하나의 다른 NWDAF를 탐색하기 위한 탐색 메시지를 NRF(Network Repository Function)에게 전송하는 단계;상기 NRF로부터, 상기 탐색 메시지에 대한 응답 메시지를 수신하고, 상기 탐색 메시지에 대한 응답 메시지는 상기 적어도 하나의 다른 NWDAF에 대한 정보를 포함하는 단계;상기 적어도 하나의 다른 NWDAF에 대한 정보에 기초하여, 상기 분석 정보의 처리를 위한 요청 메시지를 상기 적어도 하나의 다른 NWDAF에게 전송하는 단계;상기 적어도 하나의 다른 NWDAF로부터, 상기 분석 정보의 처리와 관련된 메시지에 대한 응답 메시지를 수신하고, 상기 분석 정보의 처리와 관련된 메시지에 대한 응답 메시지는 상기 적어도 하나의 다른 NWDAF에 의해 수행된 분석 정보에 대한 처리의 결과를 포함하는 단계;상기 NWDAF에 의해 수행된 분석 정보에 대한 처리의 결과와, 상기 적어도 하나의 다른 NWDAF에 의해 수행된 분석 정보에 대한 처리의 결과에 기초하여, 상기 NF로부터 요청된 분석 정보를 생성하는 단계; 및상기 생성된 분석 정보를 상기 NF에게 전송하는 단계;를 포함하는 방법.
- 제1항에 있어서,상기 분석 정보의 처리를 위한 요청 메시지는,상기 분석 정보의 식별자, 상기 분석 정보가 이용되는 대상 또는 상기 분석 정보의 분류를 위한 필터 정보 중 적어도 하나를 포함하는 방법.
- 제1항에 있어서,상기 분석 정보에 대한 요청 메시지에 기초하여, 적어도 하나의 다른 NWDAF를 탐색하기 위한 탐색 메시지를 NRF에게 전송하는 단계는,상기 분석 정보에 대한 요청 메시지에 기초하여, 상기 분석 정보의 처리를 위한 모델을 제공하는 적어도 하나의 다른 NWDAF를 탐색하기 위한 탐색 메시지를 상기 NRF에게 전송하는 단계;를 포함하는 방법.
- 제3항에 있어서,상기 탐색 메시지에 대한 응답 메시지를 수신하는 단계는,상기 NRF로부터, 상기 분석 정보의 처리를 위한 모델을 제공하는 적어도 하나의 다른 NWDAF에 대한 정보를 포함하는 응답 메시지를 수신하는 단계;를 포함하는 방법.
- 제4항에 있어서,상기 분석 정보의 처리를 위한 모델을 제공하는 적어도 하나의 다른 NWDAF에게, 상기 분석 정보의 처리를 위한 모델의 제공을 요청하는 메시지를 전송하는 단계; 및상기 분석 정보의 처리를 위한 모델을 제공하는 적어도 하나의 NWDAF로부터, 상기 분석 정보의 처리를 위한 모델에 대한 정보를 수신하는 단계;를 더 포함하고,상기 분석 정보의 처리를 위한 모델의 제공을 요청하는 메시지는, 상기 분석 정보의 식별자 및 상기 분석 정보의 처리를 위한 모델의 식별자를 포함하는 방법.
- 제1항에 있어서,상기 NWDAF에 대한 프로비저닝(provisioning)을 수행하는 단계; 및상기 NWDAF의 등록을 위한 메시지를 상기 NRF에게 전송하는 단계;를 더 포함하는 방법.
- 제1항에 있어서,상기 NF로부터 수신된 분석 정보에 대한 요청 메시지에 기초하여, 상기 분석 정보에 대한 처리를 상기 적어도 하나의 다른 NWDAF에게 오프로딩(offloading)하는 것을 결정하는 단계;를 더 포함하는 방법.
- 제6항에 있어서,상기 적어도 하나의 다른 NWDAF를 탐색하기 위한 탐색 메시지는,상기 적어도 하나의 다른 NWDAF의 유형, 지원되는 서비스의 이름, 상기 분석 정보의 식별자, 상기 적어도 하나의 다른 NWDAF의 오프로딩 지원 여부와 관련된 정보, 또는 상기 적어도 하나의 다른 NWDAF에 포함된 모듈에 대한 정보 중 적어도 하나를 포함하는 방법.
- 무선 통신 시스템에서 NWDAF(Network Data Analytics Function)에 있어서,송수신부; 및상기 송수신부를 통해, NF(Network Function)로부터 분석 정보에 대한 요청 메시지를 수신하고,상기 송수신부를 통해, 상기 분석 정보에 대한 요청 메시지에 기초하여, 적어도 하나의 다른 NWDAF를 탐색하기 위한 탐색 메시지를 NRF(Network Repository Function)에게 전송하고,상기 송수신부를 통해, 상기 NRF로부터, 상기 탐색 메시지에 대한 응답 메시지를 수신하고, 상기 탐색 메시지에 대한 응답 메시지는 상기 적어도 하나의 다른 NWDAF에 대한 정보를 포함하고,상기 송수신부를 통해, 상기 적어도 하나의 다른 NWDAF에 대한 정보에 기초하여, 상기 분석 정보의 처리를 위한 요청 메시지를 상기 적어도 하나의 다른 NWDAF에게 전송하고,상기 송수신부를 통해, 상기 적어도 하나의 다른 NWDAF로부터, 상기 분석 정보의 처리와 관련된 메시지에 대한 응답 메시지를 수신하고, 상기 분석 정보의 처리와 관련된 메시지에 대한 응답 메시지는 상기 적어도 하나의 다른 NWDAF에 의해 수행된 분석 정보에 대한 처리의 결과를 포함하고,상기 NWDAF에 의해 수행된 분석 정보에 대한 처리의 결과와, 상기 적어도 하나의 다른 NWDAF에 의해 수행된 분석 정보에 대한 처리의 결과에 기초하여, 상기 NF로부터 요청된 분석 정보를 생성하고,상기 송수신부를 통해, 상기 생성된 분석 정보를 상기 NF에게 전송하는 적어도 하나의 프로세서;를 포함하는 NWDAF.
- 제9항에 있어서,상기 분석 정보의 처리를 위한 요청 메시지는,상기 분석 정보의 식별자, 상기 분석 정보가 이용되는 대상 또는 상기 분석 정보의 분류를 위한 필터 정보 중 적어도 하나를 포함하는 NWDAF.
- 제9항에 있어서,상기 적어도 하나의 프로세서는,상기 송수신부를 통해, 상기 분석 정보에 대한 요청 메시지에 기초하여, 상기 분석 정보의 처리를 위한 모델을 제공하는 적어도 하나의 다른 NWDAF를 탐색하기 위한 탐색 메시지를 상기 NRF에게 전송하는 NWDAF.
- 제11항에 있어서,상기 적어도 하나의 프로세서는,상기 송수신부를 통해, 상기 NRF로부터, 상기 분석 정보의 처리를 위한 모델을 제공하는 적어도 하나의 다른 NWDAF에 대한 정보를 포함하는 응답 메시지를 수신하는 NWDAF.
- 제12항에 있어서,상기 적어도 하나의 프로세서는,상기 송수신부를 통해, 상기 분석 정보의 처리를 위한 모델을 제공하는 적어도 하나의 다른 NWDAF에게, 상기 분석 정보의 처리를 위한 모델의 제공을 요청하는 메시지를 전송하고,상기 송수신부를 통해, 상기 분석 정보의 처리를 위한 모델을 제공하는 적어도 하나의 NWDAF로부터, 상기 분석 정보의 처리를 위한 모델에 대한 정보를 수신하고,상기 분석 정보의 처리를 위한 모델의 제공을 요청하는 메시지는, 상기 분석 정보의 식별자 및 상기 분석 정보의 처리를 위한 모델의 식별자를 포함하는 NWDAF.
- 제9항에 있어서,상기 적어도 하나의 프로세서는,상기 NWDAF에 대한 프로비저닝(provisioning)을 수행하고,상기 NWDAF의 등록을 위한 메시지를 상기 NRF에게 전송하는 NWDAF.
- 제9항에 있어서,상기 적어도 하나의 프로세서는,상기 NF로부터 수신된 분석 정보에 대한 요청 메시지에 기초하여, 상기 분석 정보에 대한 처리를 상기 적어도 하나의 다른 NWDAF에게 오프로딩(offloading)하는 것을 결정하고,상기 적어도 하나의 다른 NWDAF를 탐색하기 위한 탐색 메시지는,상기 적어도 하나의 다른 NWDAF의 유형, 지원되는 서비스의 이름, 상기 분석 정보의 식별자, 상기 적어도 하나의 다른 NWDAF의 오프로딩 지원 여부와 관련된 정보, 또는 상기 적어도 하나의 다른 NWDAF에 포함된 모듈에 대한 정보 중 적어도 하나를 포함하는 NWDAF.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US17/904,938 US12388717B2 (en) | 2020-02-26 | 2021-02-18 | Method and device for selecting service in wireless communication system |
| EP21759594.1A EP4099635A4 (en) | 2020-02-26 | 2021-02-18 | METHOD AND DEVICE FOR SERVICE SELECTION IN A WIRELESS COMMUNICATION SYSTEM |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| KR1020200023832A KR20210108785A (ko) | 2020-02-26 | 2020-02-26 | 무선 통신 시스템에서 서비스를 선택하는 방법 및 장치 |
| KR10-2020-0023832 | 2020-02-26 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2021172810A1 true WO2021172810A1 (ko) | 2021-09-02 |
Family
ID=77491393
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/KR2021/002070 Ceased WO2021172810A1 (ko) | 2020-02-26 | 2021-02-18 | 무선 통신 시스템에서 서비스를 선택하는 방법 및 장치 |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US12388717B2 (ko) |
| EP (1) | EP4099635A4 (ko) |
| KR (1) | KR20210108785A (ko) |
| WO (1) | WO2021172810A1 (ko) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114302429A (zh) * | 2021-12-27 | 2022-04-08 | 中国联合网络通信集团有限公司 | Nwdaf网元的确定方法、装置、设备及存储介质 |
| WO2023061615A1 (en) * | 2021-10-12 | 2023-04-20 | Lenovo International Coöperatief U.A. | Deriving analytics for mobility events |
| WO2023125879A1 (zh) * | 2021-12-30 | 2023-07-06 | 维沃移动通信有限公司 | 数据处理的方法、装置及通信设备 |
| CN116567608A (zh) * | 2022-01-28 | 2023-08-08 | 华为技术有限公司 | 一种通信方法及装置 |
| EP4228220A1 (en) * | 2022-02-11 | 2023-08-16 | Nokia Solutions and Networks Oy | Network data analytics function accuracy enhancement |
| WO2023153719A1 (en) * | 2022-02-10 | 2023-08-17 | Samsung Electronics Co., Ltd. | Method and apparatus to support federated machine learning in wireless communication system |
| US20230308903A1 (en) * | 2022-03-25 | 2023-09-28 | Lg Electronics Inc. | Communication related to federated learning |
| WO2023214806A1 (en) * | 2022-05-06 | 2023-11-09 | Samsung Electronics Co., Ltd. | Method and apparatus for supporting federated learning in wireless communication system |
| WO2024032883A1 (en) * | 2022-08-10 | 2024-02-15 | Nokia Technologies Oy | Analytics control |
| SE2251018A1 (en) * | 2022-09-05 | 2024-03-06 | Telia Co Ab | Methods and apparatuses for enhancing end-user experience of a subscriber moving from a home network to a visited network |
| WO2024147105A1 (en) * | 2023-01-05 | 2024-07-11 | Telefonaktiebolaget Lm Ericsson (Publ) | Method and apparatus for federated learning in a network |
| WO2024167241A1 (ko) * | 2023-02-10 | 2024-08-15 | 엘지전자 주식회사 | 연합 학습 |
| EP4476939A4 (en) * | 2022-02-11 | 2025-12-24 | Qualcomm Inc | NETWORK-ASSISTED INFORMATION |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20220130159A (ko) * | 2020-03-02 | 2022-09-26 | 엘지전자 주식회사 | Smf 노드를 선택하기 위한 방안 |
| US11902104B2 (en) | 2020-03-04 | 2024-02-13 | Intel Corporation | Data-centric service-based network architecture |
| CN113573331B (zh) * | 2020-04-29 | 2023-09-01 | 华为技术有限公司 | 一种通信方法、装置及系统 |
| BR112022024375A2 (pt) * | 2020-06-29 | 2022-12-27 | Intel Corp | Uma ou mais mídias legíveis por computador não transitórias e aparelho de uma rede de dados de borda |
| WO2022033671A1 (en) * | 2020-08-12 | 2022-02-17 | Nokia Technologies Oy | Calculation transfer between network data analytics functions |
| US11963200B2 (en) * | 2021-03-09 | 2024-04-16 | Amdocs Development Limited | System, method, and computer program for resource orchestration in a 5G network based on user equipment behavior analystics |
| JP7653522B2 (ja) * | 2021-07-29 | 2025-03-28 | 京セラ株式会社 | 通信制御方法、ユーザ装置、チップセット、プログラム、ネットワーク装置及び移動通信システム |
| CN116866203A (zh) * | 2022-03-28 | 2023-10-10 | 中国移动通信有限公司研究院 | 信息获取方法、装置及网络设备、终端 |
| KR20230155805A (ko) * | 2022-05-04 | 2023-11-13 | 삼성전자주식회사 | 이동 통신 시스템에서 연합 기계 학습 수행을 관리하기 위한 방법 및 장치 |
| KR102939883B1 (ko) * | 2023-06-09 | 2026-03-13 | 에스케이텔레콤 주식회사 | Nf 장치, nf에서 수행되는 시그널링 제어 방법 |
| WO2025022440A1 (en) * | 2023-07-23 | 2025-01-30 | Jio Platforms Limited | Method and system for monitoring a network load associated with one or more network functions |
| WO2025095376A1 (ko) * | 2023-11-01 | 2025-05-08 | 엘지전자 주식회사 | 에너지 소비 관리 방법 |
| WO2025169363A1 (ja) * | 2024-02-07 | 2025-08-14 | 株式会社Nttドコモ | ネットワーク構成要素及び無線通信方法 |
| WO2025174480A1 (en) * | 2024-02-13 | 2025-08-21 | Qualcomm Incorporated | Aerial user equipment data collection |
| WO2025175172A1 (en) * | 2024-02-15 | 2025-08-21 | Interdigital Patent Holdings, Inc. | Enhanced member wtru selection using application function feedback |
| US12413486B1 (en) | 2024-03-11 | 2025-09-09 | T-Mobile Usa, Inc. | Telecommunications system to timely send producer network function status notifications to consumer network functions |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180262924A1 (en) * | 2017-03-10 | 2018-09-13 | Huawei Technologies Co., Ltd. | System and Method of Network Policy Optimization |
| WO2019158737A1 (en) * | 2018-02-16 | 2019-08-22 | NEC Laboratories Europe GmbH | Network data analytics for oam |
| WO2019158777A1 (en) * | 2018-02-19 | 2019-08-22 | NEC Laboratories Europe GmbH | Network data analytics functionality enhancement and new service consumers |
| KR20190132898A (ko) * | 2018-05-21 | 2019-11-29 | 삼성전자주식회사 | 무선 통신 시스템에서 데이터 수집 및 분석 기능을 활용하는 방법 및 장치 |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140280338A1 (en) * | 2013-03-14 | 2014-09-18 | Cisco Technology, Inc. | Distributed network analytics |
| JP2020530703A (ja) * | 2017-08-11 | 2020-10-22 | コンヴィーダ ワイヤレス, エルエルシー | 通信ネットワークにおけるネットワークデータ分析 |
| EP4322505A3 (en) | 2018-02-06 | 2024-04-17 | Telefonaktiebolaget LM Ericsson (publ) | Method and apparatus for a network function |
| CN110324170B (zh) * | 2018-03-30 | 2021-07-09 | 华为技术有限公司 | 数据分析设备、多模型共决策系统及方法 |
| WO2019225929A1 (en) | 2018-05-21 | 2019-11-28 | Samsung Electronics Co., Ltd. | Method and apparatus for utilizing data collection and analysis function in wireless communication system |
| US11140048B2 (en) * | 2019-01-11 | 2021-10-05 | Huawei Technologies Co., Ltd. | Sharable storage method and system for network data analytics |
| WO2020200487A1 (en) * | 2019-04-03 | 2020-10-08 | Telefonaktiebolaget Lm Ericsson (Publ) | Technique for facilitating use of machine learning models |
| WO2021023388A1 (en) * | 2019-08-08 | 2021-02-11 | Nokia Technologies Oy | Configuring network analytics |
| WO2021032495A1 (en) * | 2019-08-16 | 2021-02-25 | Telefonaktiebolaget Lm Ericsson (Publ) | Methods, apparatus and machine-readable media relating to machine-learning in a communication network |
| CN110569288A (zh) | 2019-09-11 | 2019-12-13 | 中兴通讯股份有限公司 | 一种数据分析方法、装置、设备和存储介质 |
| CN110677299B (zh) * | 2019-09-30 | 2024-06-28 | 中兴通讯股份有限公司 | 网络数据采集方法、装置和系统 |
| CN115022176B (zh) | 2019-11-06 | 2023-08-22 | 腾讯科技(深圳)有限公司 | Nwdaf网元的选择方法、装置、电子设备及可读存储介质 |
| CN114902622B (zh) * | 2020-01-03 | 2024-03-26 | 华为技术有限公司 | 用于确定模型以数字化地分析输入数据的网络实体 |
| KR20230120871A (ko) * | 2022-02-10 | 2023-08-17 | 삼성전자주식회사 | 무선 통신 시스템 내 연합 학습 지원 방법 및 장치 |
-
2020
- 2020-02-26 KR KR1020200023832A patent/KR20210108785A/ko active Pending
-
2021
- 2021-02-18 EP EP21759594.1A patent/EP4099635A4/en not_active Withdrawn
- 2021-02-18 WO PCT/KR2021/002070 patent/WO2021172810A1/ko not_active Ceased
- 2021-02-18 US US17/904,938 patent/US12388717B2/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20180262924A1 (en) * | 2017-03-10 | 2018-09-13 | Huawei Technologies Co., Ltd. | System and Method of Network Policy Optimization |
| WO2019158737A1 (en) * | 2018-02-16 | 2019-08-22 | NEC Laboratories Europe GmbH | Network data analytics for oam |
| WO2019158777A1 (en) * | 2018-02-19 | 2019-08-22 | NEC Laboratories Europe GmbH | Network data analytics functionality enhancement and new service consumers |
| KR20190132898A (ko) * | 2018-05-21 | 2019-11-29 | 삼성전자주식회사 | 무선 통신 시스템에서 데이터 수집 및 분석 기능을 활용하는 방법 및 장치 |
Non-Patent Citations (1)
| Title |
|---|
| ZTE: "[draft] Reply LS on RAN related parameters collected from UE", 3GPP DRAFT; R3-190277 [DRAFT] REPLY LS ON RAN RELATED PARAMETERS COLLECTED FROM UE, 3RD GENERATION PARTNERSHIP PROJECT (3GPP), MOBILE COMPETENCE CENTRE ; 650, ROUTE DES LUCIOLES ; F-06921 SOPHIA-ANTIPOLIS CEDEX ; FRANCE, vol. RAN WG3, no. Athens, Greece; 20190225 - 20190301, R3-190277 [draft] Reply LS on RAN related paramete, 15 February 2019 (2019-02-15), Mobile Competence Centre ; 650, route des Lucioles ; F-06921 Sophia-Antipolis Cedex ; France, XP051604220 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2023061615A1 (en) * | 2021-10-12 | 2023-04-20 | Lenovo International Coöperatief U.A. | Deriving analytics for mobility events |
| EP4618648A3 (en) * | 2021-10-12 | 2025-11-12 | Lenovo (Singapore) Pte. Ltd. | Deriving analytics for mobility events |
| GB2638297A (en) * | 2021-10-12 | 2025-08-20 | Lenovo Singapore Pte Ltd | Deriving analytics for mobility events |
| CN114302429B (zh) * | 2021-12-27 | 2023-04-28 | 中国联合网络通信集团有限公司 | Nwdaf网元的确定方法、装置、设备及存储介质 |
| CN114302429A (zh) * | 2021-12-27 | 2022-04-08 | 中国联合网络通信集团有限公司 | Nwdaf网元的确定方法、装置、设备及存储介质 |
| WO2023125879A1 (zh) * | 2021-12-30 | 2023-07-06 | 维沃移动通信有限公司 | 数据处理的方法、装置及通信设备 |
| CN116567608A (zh) * | 2022-01-28 | 2023-08-08 | 华为技术有限公司 | 一种通信方法及装置 |
| EP4473723A1 (en) | 2022-02-10 | 2024-12-11 | Samsung Electronics Co., Ltd. | Method and apparatus to support federated machine learning in wireless communication system |
| WO2023153719A1 (en) * | 2022-02-10 | 2023-08-17 | Samsung Electronics Co., Ltd. | Method and apparatus to support federated machine learning in wireless communication system |
| EP4473723A4 (en) * | 2022-02-10 | 2025-05-14 | Samsung Electronics Co., Ltd. | Method and apparatus for supporting federated machine learning in a wireless communication system |
| EP4228220A1 (en) * | 2022-02-11 | 2023-08-16 | Nokia Solutions and Networks Oy | Network data analytics function accuracy enhancement |
| EP4476939A4 (en) * | 2022-02-11 | 2025-12-24 | Qualcomm Inc | NETWORK-ASSISTED INFORMATION |
| US12526669B2 (en) | 2022-02-11 | 2026-01-13 | Nokia Solutions And Networks Oy | Network data analytics function accuracy enhancement |
| US20230308903A1 (en) * | 2022-03-25 | 2023-09-28 | Lg Electronics Inc. | Communication related to federated learning |
| WO2023214806A1 (en) * | 2022-05-06 | 2023-11-09 | Samsung Electronics Co., Ltd. | Method and apparatus for supporting federated learning in wireless communication system |
| WO2024032883A1 (en) * | 2022-08-10 | 2024-02-15 | Nokia Technologies Oy | Analytics control |
| US12513055B2 (en) | 2022-08-10 | 2025-12-30 | Nokia Technologies Oy | Analytics control |
| SE2251018A1 (en) * | 2022-09-05 | 2024-03-06 | Telia Co Ab | Methods and apparatuses for enhancing end-user experience of a subscriber moving from a home network to a visited network |
| WO2024147105A1 (en) * | 2023-01-05 | 2024-07-11 | Telefonaktiebolaget Lm Ericsson (Publ) | Method and apparatus for federated learning in a network |
| WO2024167241A1 (ko) * | 2023-02-10 | 2024-08-15 | 엘지전자 주식회사 | 연합 학습 |
Also Published As
| Publication number | Publication date |
|---|---|
| EP4099635A4 (en) | 2023-07-26 |
| EP4099635A1 (en) | 2022-12-07 |
| KR20210108785A (ko) | 2021-09-03 |
| US12388717B2 (en) | 2025-08-12 |
| US20230090022A1 (en) | 2023-03-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021172810A1 (ko) | 무선 통신 시스템에서 서비스를 선택하는 방법 및 장치 | |
| WO2022005037A1 (ko) | 무선 통신 네트워크에서 네트워크 분석 정보 제공 방법 및 장치 | |
| WO2020184929A1 (en) | Method and apparatus for managing the mobility of device in a network | |
| WO2021066352A1 (en) | Apparatus and method for network configuration | |
| WO2021045531A1 (en) | Apparatus and method for network automation in wireless communication system | |
| US11855864B2 (en) | Method and apparatus for collecting network traffic in wireless communication system | |
| WO2021137624A1 (en) | Method and apparatus for registering with network slice in wireless communication system | |
| WO2021235902A1 (ko) | 무선 통신 네트워크에서 네트워크 데이터 수집 및 분석을 위한 이동성 지원 방법 및 장치 | |
| WO2023101304A1 (ko) | 무선 통신 시스템에서 통신을 수행하는 방법 및 장치 | |
| WO2016129957A1 (en) | Methods and apparatuses for processing ue context of ue | |
| EP4458050A1 (en) | Communication method and device for xr service in wireless communication system | |
| WO2021158001A1 (ko) | 무선 통신 시스템에서 서비스 수요 정보 분석을 통한 자원 관리 방법 및 장치 | |
| WO2023191505A1 (en) | Monitoring for application ai/ml-based services and operations | |
| WO2020130245A1 (en) | Network connection method and apparatus | |
| EP4274177A1 (en) | Method for evaluating action impact over mobile network performance | |
| WO2024035095A1 (en) | External exposure of control plane to user plane switch parameter | |
| WO2021066485A1 (en) | Improvements in and relating to dynamic path switching | |
| WO2021002666A1 (en) | Improvements in and relating to minimisation of drive test in a telecommunication network | |
| WO2022203360A1 (en) | Communication method and device for supporting authentication of unmanned aerial vehicle in wireless communication system | |
| Shah et al. | Toward network-slicing-enabled edge computing: A cloud-native approach for slice mobility | |
| WO2023101303A1 (ko) | 무선 통신 시스템에서 통신을 수행하는 방법 및 장치 | |
| WO2023068854A1 (ko) | 무선 통신 시스템에서 트래픽에 대한 서비스 품질 관리 방법 및 장치 | |
| WO2024151069A1 (ko) | 무선 통신 시스템에서 ai/ml 애플리케이션을 위한 정보를 핸들링하기 위한 방법 및 장치 | |
| EP4175352A1 (en) | Information transmission method and device, storage medium, and electronic device | |
| WO2021075762A1 (ko) | 무선 통신 시스템에서 데이터 패킷을 송수신하는 방법 및 장치 |
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: 21759594 Country of ref document: EP Kind code of ref document: A1 |
|
| ENP | Entry into the national phase |
Ref document number: 2021759594 Country of ref document: EP Effective date: 20220831 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| WWG | Wipo information: grant in national office |
Ref document number: 17904938 Country of ref document: US |
|
| WWW | Wipo information: withdrawn in national office |
Ref document number: 2021759594 Country of ref document: EP |