WO2024109960A1 - Procédé, dispositif et produit-programme informatique pour communication sans fil - Google Patents

Procédé, dispositif et produit-programme informatique pour communication sans fil Download PDF

Info

Publication number
WO2024109960A1
WO2024109960A1 PCT/CN2024/072152 CN2024072152W WO2024109960A1 WO 2024109960 A1 WO2024109960 A1 WO 2024109960A1 CN 2024072152 W CN2024072152 W CN 2024072152W WO 2024109960 A1 WO2024109960 A1 WO 2024109960A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
federated learning
capability
data analytics
wireless communication
Prior art date
Application number
PCT/CN2024/072152
Other languages
English (en)
Inventor
Yuang FENG
Menghan WANG
Jinguo Zhu
Original Assignee
Zte Corporation
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Zte Corporation filed Critical Zte Corporation
Priority to PCT/CN2024/072152 priority Critical patent/WO2024109960A1/fr
Publication of WO2024109960A1 publication Critical patent/WO2024109960A1/fr

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition

Definitions

  • This document is directed generally to wireless communications, and in particular to 5 th generation (5G) communications or 6 th generation (6G) communications.
  • NWDAF Network Data Analytics Function
  • 5GC 5G Core
  • NF Network Function
  • This document relates to methods, systems, and computer program products for a wireless communication.
  • the wireless communication method includes: transmitting, by a first data analytics node to a repository node, a request for information of one or more second data analytics nodes; and receiving, by the first data analytics node from the repository node, the information of one or more second data analytics nodes based on Machine Learning, ML, capability information, wherein the ML capability information comprises information for different types of ML.
  • ML Machine Learning
  • the ML capability information comprises at least one of:
  • the ML capability information comprises at least one of:
  • the request for information of one or more second data analytics nodes comprises at least one of:
  • a response responding to the request for information of one or more second data analytics nodes comprise information of one or more selected data analytics nodes capable of performing as one or more Federated Learning clients in a determined type of ML.
  • a response responding to the request for information of one or more second data analytics nodes comprise information of one or more selected data analytics nodes capable of performing as one or more Federated Learning servers in a determined type of ML.
  • the wireless communication method further comprises: transmitting, by the first data analytics node to the repository node, a request for updating information of one or more capability types of one or more types of ML in the ML capability information.
  • the wireless communication method further comprises: transmitting, by the first data analytics node to the repository node, a network function profile comprising information of one or more capability types of ML in one or more types of ML for the first data analytics node.
  • a Vertical Federated Learning satisfies at least one of:
  • Vertical Federated Learning clients and Vertical Federated Learning servers exchange intermediate data
  • the intermediate data comprises at least one of a gradient or a loss computed by a data analytics node.
  • a Horizontal Federated Learning satisfies at least one of:
  • Horizontal Federated Learning clients having the same feature space and different sample spaces for a local model training
  • Horizontal Federated Learning clients and Horizontal Federated Learning servers exchange ML models
  • Horizontal Federated Learning clients and Horizontal Federated Learning servers refrain from exchanging intermediate data.
  • the types of ML comprise at least one of:
  • the wireless communication method includes: receiving, by a repository node from a first data analytics node, a request for information of one or more second data analytics nodes; and transmitting, by the repository node to the first data analytics node, the information of one or more second data analytics nodes based on Machine Learning, ML, capability information, wherein the ML capability information comprises information for different types of ML.
  • ML Machine Learning
  • the ML capability information comprises at least one of:
  • the ML capability information comprises at least one of:
  • the request for information of one or more second data analytics nodes comprises at least one of:
  • a response responding to the request for information of one or more second data analytics nodes comprise information of one or more selected data analytics nodes capable of performing as one or more Federated Learning clients in a determined type of ML.
  • a response responding to the request for information of one or more second data analytics nodes comprise information of one or more selected data analytics nodes capable of performing as one or more Federated Learning servers in a determined type of ML.
  • the wireless communication method further comprises: receiving, by the repository node from the first data analytics node, a request for updating information of one or more capability types of one or more types of ML in the ML capability information.
  • the wireless communication method further comprises: receiving, by the repository node from the first data analytics node, a network function profile comprising information of one or more capability types of ML in one or more types of ML for the first data analytics node.
  • a Vertical Federated Learning satisfies at least one of:
  • Vertical Federated Learning clients and Vertical Federated Learning servers exchange intermediate data
  • the intermediate data comprises at least one of a gradient or a loss computed by a data analytics node.
  • a Horizontal Federated Learning satisfies at least one of:
  • Horizontal Federated Learning clients having the same feature space and different sample spaces for a local model training
  • Horizontal Federated Learning clients and Horizontal Federated Learning servers exchange ML models
  • Horizontal Federated Learning clients and Horizontal Federated Learning servers refrain from exchanging intermediate data.
  • the types of ML comprise at least one of:
  • the first data analytics node includes a communication unit and a processor.
  • the processor is configured to: transmit, via the communication unit to a repository node, a request for information of one or more second data analytics nodes; and receive, via the communication unit from the repository node, the information of one or more second data analytics nodes based on Machine Learning, ML, capability information, wherein the ML capability information comprises information for different types of ML.
  • ML Machine Learning
  • the repository node includes a communication unit and a processor.
  • the processor is configured to: receive, via the communication unit from a first data analytics node, a request for information of one or more second data analytics nodes; and transmit, via the communication unit to the first data analytics node, the information of one or more second data analytics nodes based on Machine Learning, ML, capability information, wherein the ML capability information comprises information for different types of ML.
  • ML Machine Learning
  • the present disclosure relates to a computer program product comprising a computer-readable program medium code stored thereupon, the code, when executed by a processor, causing the processor to implement a wireless communication method recited in any one of foregoing methods.
  • the present disclosure is not limited to the exemplary embodiments and applications described and illustrated herein. Additionally, the specific order and/or hierarchy of steps or operations in the methods disclosed herein are merely exemplary approaches. Based upon design preferences, the specific order or hierarchy of steps or operations of the disclosed methods or processes can be re-arranged while remaining within the scope of the present disclosure. Thus, those of ordinary skill in the art will understand that the methods and techniques disclosed herein present various steps or operations in a sample order, and the present disclosure is not limited to the specific order or hierarchy presented unless expressly stated otherwise.
  • FIG. 1 shows a schematic diagram of a network according to an embodiment of the present disclosure.
  • FIG. 2 shows a schematic diagram of a procedure according to an embodiment of the present disclosure.
  • FIG. 3 shows a schematic diagram of a procedure according to an embodiment of the present disclosure.
  • FIG. 4 shows a schematic diagram of a procedure according to an embodiment of the present disclosure.
  • FIG. 5 shows a schematic diagram of a procedure according to an embodiment of the present disclosure.
  • FIG. 6 shows a schematic diagram of a procedure according to an embodiment of the present disclosure.
  • FIG. 7 shows a schematic diagram of a procedure according to an embodiment of the present disclosure.
  • FIG. 8 shows a schematic diagram of a procedure according to an embodiment of the present disclosure.
  • FIGs. 9A and 9B show a schematic diagram of a procedure according to an embodiment of the present disclosure.
  • FIG. 10 shows an example of a schematic diagram of a wireless communication terminal according to an embodiment of the present disclosure.
  • FIG. 11 shows an example of a schematic diagram of a wireless communication node according to an embodiment of the present disclosure.
  • FIGs. 12 to 13 show flowcharts of wireless communication methods according to some embodiments of the present disclosure.
  • the Federated Learning (FL) capability per analytic ID is not distinguished by the Vertical Federated Learning (VFL) or the Horizontal Federated Learning (HFL) .
  • the FL capability per analytic ID indicates FL capability types that the NWDAF willing to be in the FL process.
  • the FL capability per analytic ID include at least one of the following: FL client, FL server and/or FL client and server.
  • the HFL and the VFL are different, in the HLF, the NWDAF clients have the same feature spaces but different sample spaces for the model training. In the VFL, the NWDAF clients have different feature spaces but the same sample spaces.
  • the client and the server exchange ML models in the HFL but intermediate data (e.g., gradient and/or loss computed by the client and/or server) in the VFL. Therefore, some NWDAFs may be willing to be a HFL client or a HFL server but not willing to be a VFL client or a VFL server, vice versa. Therefore, in some embodiments of the present disclosure, an indicator may be added into the NF profile of the NWDAF to indicate whether the NWDAF willing to join the HFL or the VFL.
  • the NWDAF in the middle layer can be seen as the FL client with respect to upper layers and the FL server with respect to lower layers.
  • an NWDAF can become client and server simultaneously in one FL process.
  • a second indicator may be added in the NF profile of the NWDAF to indicate whether an NWDAF wish to be NWDAF client and server simultaneously in multi-layer FL process.
  • an FL process is taken as examples to facilitate the description, but the present disclosure is not limited thereto.
  • Another machine learning (ML) process may be used in different embodiments of the present disclosure.
  • FIG. 1 shows the 5G architecture for supporting the 5G Local Area Network (LAN) Virtual Network (VN) group service according to an embodiment of the present disclosure.
  • the N19 interface is introduced to support the traffic local switching within one User Plane Function (UPF) or among multiple UPFs serving one specific VN group.
  • UPF User Plane Function
  • UE User Equipment
  • RAN Radio Access Network
  • 5G it is a New Radio (NR) base station.
  • NR New Radio
  • AMF Access and Mobility Management function
  • This function includes the following functionalities: Registration management, Connection management, Reachability management and/or Mobility Management. This function also performs the access authentication and access authorization.
  • the AMF is the Non-Access-Stratum (NAS) security termination and handles the Session Management (SM) NAS between the UE and the SMF (Session Management Function) , etc.
  • NAS Non-Access-Stratum
  • SM Session Management
  • SMF Session Management Function
  • SMF Session Management Function
  • This function includes the following functionalities: session establishment, modification and release, UE Internet Protocol (IP) address allocation and management (including optional authorization functions) , selection and control of uplink (UP) function, downlink data notification, etc.
  • IP Internet Protocol
  • the SMF controls the UPF via the N4 association.
  • the SMF provides Packet Detection Rule (PDR) to the UPF to instruct how to detect user data traffic, Forwarding Action Rule (FAR) , QoS Enforcement Rule (QER) and Usage Reporting Rule (URR) to instruct the UPF how to perform the user data traffic forwarding, QoS handling and usage reporting for the user data traffic detected by using the PDR.
  • PDR Packet Detection Rule
  • FAR Forwarding Action Rule
  • QER QoS Enforcement Rule
  • URR Usage Reporting Rule
  • UPF User Plane Function
  • This function includes the following functionalities: serving as an anchor point for intra-/inter-radio access technology (RAT) mobility, packet routing and forwarding, traffic usage reporting, Quality of service (QoS) handling for the user plane, downlink packet buffering and downlink data notification triggering, etc.
  • the GTP-U tunnel is used over the N3 interface between the RAN and the UPF.
  • the GTP-U tunnel is per PDU session.
  • the UPF binds the downlink traffic to QoS flows within the GTP-U tunnel of the PDU session by using the FARs received from the SMF.
  • the RAN transfer the user plane traffic to QoS flows identified by the UE.
  • PCF Policy Control Function
  • the PCF provides QoS policy rules to control plane functions to enforce the rules.
  • the PCF (s) transform (s) the Application Function (AF) requests into policies that apply to PDU Sessions.
  • UDM Unified Data Management
  • the UDM performs the generation of the 3GPP Authentication and Key Agreement (AKA) Authentication Credential, access authorization based on subscription data, UE's Serving NF Registration Management (e.g., storing serving the AMF for the UE and/or storing serving SMF for UE's PDU Session) and Subscription management, etc.
  • the UDM accesses the Unified Data Repository (UDR) to retrieve the UE subscription data and store the UE context in the UDR.
  • UDR Unified Data Repository
  • the NWDAF is a 5GC NF located on the control plane and performs statistical data analysis (i.e., the distribution information of the datasets) and machine learning-related tasks in 5G System (5GS) .
  • the NWDAF may interact with at least one of the following different entities for different purposes:
  • AMF Access Management Function
  • SMF Session Management Function
  • UPF User Plane Function
  • PCF Policy Management Function
  • UDM Network Slice Admission Control Function
  • NSACF Network Slice Admission Control Function
  • AF Analytics Function
  • NEF Network Exposure Function
  • OAM Operations, Administration and Maintenance
  • DCCF Data Collection Coordination Function
  • ADRF Analytics Data Repository Function
  • NFs e.g., from the Network Repository Function (NRF) for the NF-related information
  • NRF Network Repository Function
  • NWDAF may be deployed in a Public Land Mobile Network (PLMN) .
  • PLMN Public Land Mobile Network
  • An NWDAF may contain at least one of the following logical functions:
  • a logical function in the NWDAF which performs inference, derives analytics information (i.e., derives statistics and/or predictions based on the Analytics Consumer request) and exposes analytics service (i.e., Nnwdaf_AnalyticsSubscription or Nnwdaf_AnalyticsInfo) ; and/or
  • MTLF Model Training logical function
  • the DCCF is also an NF on the control plane of 5GC.
  • the DCCF coordinates the collection and distribution of data requested by NF consumers. It prevents data sources from having to handle multiple subscriptions for the same data and sends multiple notifications containing the same information due to uncoordinated requests from data consumers.
  • the DCCF is applicable to:
  • NWDAFs that request data from a Data Source (e.g., for use in computing analytics) .
  • FIG. 2 and FIG. 4 illustrate data collection architectures by the NWDAF to enable data analysis and model training.
  • FIG. 3 and FIG. 5 show possible network data analytics exposure architectures for any NF consumer who subscribes or requests the analytics.
  • the FL type in the NWDAF profile in the 5GC may indicate:
  • the FL type in the NWDAF profile in the 5GC may indicate:
  • An NWDAF containing the MTLF supporting FL as a server shall additionally include the FL capability type (i.e., the FL server) , Time interval supporting FL as FL capability information during the registration in the NRF.
  • the FL capability type i.e., the FL server
  • Time interval supporting FL as FL capability information during the registration in the NRF.
  • An NWDAF containing the MTLF supporting FL as a client shall additionally include the FL capability type (i.e., FL client) , Time interval supporting FL as FL capability information during the registration in the NRF.
  • an NWDAF containing the MTLF supporting FL as a client may also include NF type (s) where data can be collected as the input for local model training.
  • An NWDAF containing the MTLF may indicate to support both FL server (s) and FL client (s) in the FL capability for the specific Analytics ID.
  • Some protocols do not include information about the VFL or the HFL, and whether an NWDAF willing to be a client and server simultaneously in the multi-layer FL process.
  • Some embodiments of the present disclosure provide information about whether an NWDAF support the client or server of the VFL or the HFL, and whether an NWDAF willing to be a client and server simultaneously in the multi-layer FL process.
  • FIG. 6 illustrates an example of the NWDAF FL capability per analytic in some embodiments of the present disclosure.
  • the FL process was may include different categories: VFL, HFL, Multi-layer Vertical Federated Learning (M-VFL) , Multi-layer Horizontal Federated Learning (M-HFL) .
  • M-VFL Multi-layer Vertical Federated Learning
  • M-HFL Multi-layer Horizontal Federated Learning
  • the NWDAF clients have the same feature spaces but different samples for the local model training.
  • the NWDAF clients have different feature spaces but the same sample spaces for the local model training.
  • the client and the server exchange ML models in the HFL but intermediate data (e.g., gradient and/or loss computed by the client and/or server) in the VFL.
  • intermediate data e.g., gradient and/or loss computed by the client and/or server
  • an NWDAF willing to be an FL client and an FL server simultaneously indicates that the NWDAF is located in the middle of the multi-layer FL process. Therefore, the upper layer may be a client and the lower layer may be a server in one FL process. In some embodiments, the NWDAF willing to be an FL client and server indicates that the NWDAF may be a server or a client, but may not want to be a client and a server simultaneously. In some embodiments, when the NWDAF does not want to be a client and a server simultaneously, the NWDAF may be placed at the top or the bottom layers in the hierarchical FL process.
  • an NWDAF corresponds to ML (e.g., FL) capability information.
  • the ML capability information includes information of one or more capability types of one or more types of ML.
  • the one or more types of ML may include at least one of HFL, VFL, M-HFL and/or M-VFL.
  • the one or more capability types may include at least one of: a Federated Learning client, a Federated Learning server, a Federated Learning client and server, or a Federated Learning client and server simultaneously.
  • the ML capability information for an NWDAF may include at least one of:
  • an indication indicating the NWDAF is capable of or willing to perform as a M-HFL client and server simultaneously.
  • FIG. 7 illustrates a schematic diagram of an NWDAF registration procedure according to an embodiment of the present disclosure.
  • the procedure may include at least one of the following operations.
  • the NWDAF sends a request (e.g., the Nnrf_NFManagement_NFRegister Request) to the NRF to inform the NRF of its NF profile when the NF service consumer becomes operative for the first time.
  • a request e.g., the Nnrf_NFManagement_NFRegister Request
  • the NF profile may include its ML (e.g., FL) capability information, which covers the ML (e.g., FL) capability in at least one types of ML (e.g., FL) (e.g., VFL, HFL, M-VFL and/or M-HFL) (see FIG. 6) .
  • ML e.g., FL
  • the NRF stores the NF profile of the NWDAF and marks the NWDAF available.
  • the NRF acknowledges that the NWDAF Registration is accepted via a response (e.g., the Nnrf_NFManagement_NFRegister response) .
  • FIG. 8 illustrates a schematic diagram of an NWDAF updating the NF profile procedure according to an embodiment of the present disclosure.
  • the procedure may include at least one of the following operations.
  • the NWDAF sends a request (e.g., the Nnrf_NFManagement_NFUpdate Request) to the NRF to inform the NRF of its updated NF profile (e.g., with the updated capacity) .
  • the request e.g., the Nnrf_NFManagement_NFUpdate Request
  • the NWDAF sends the request (e.g., the Nnrf_NFManagement_NFUpdate Request) to the NRF to inform the NRF of its updated NF profile when triggered after a scaling operation.
  • the NF profile may include its updated ML (e.g., FL) capability information.
  • the updated ML (e.g., FL) capability information covers the ML (e.g., FL) capability in at least one types of ML (e.g., FL) (e.g., VFL, HFL, M-VFL, and/or M-HFL) .
  • the NRF updates the NF profile of the NWDAF.
  • the NRF acknowledges that the NWDAF Update is accepted via a response (e.g., the Nnrf_NFManagement_NFUpdate response) .
  • the NWDAF service consumer could discover the server NWDAF through the NRF to initiate the FL process.
  • the server NWDAF can discover the client NWDAF with the suitable FL capability through the NRF for the local model training.
  • FIGs. 9A and 9B illustrates a schematic diagram of a procedure in 5GC according to an embodiment of the present disclosure.
  • the procedure may include at least one of the following operations.
  • Steps 1 to 3 are the NWDAF registration procedure.
  • the server NWDAF sends a request (e.g., the Nnrf_NFManagement_NFRegister Request message) to the NRF to inform the NRF of its NF profile when the NF service consumer becomes operative for the first time.
  • a request e.g., the Nnrf_NFManagement_NFRegister Request message
  • the NF profile may include its FL capability information, which covers the FL capability in at least one types of FL (e.g., VFL, HFL, M-VFL and/or /M-HFL) (see FIG. 6) .
  • FL e.g., VFL, HFL, M-VFL and/or /M-HFL
  • the NRF stores the NF profiles of the NWDAFs and marks the NWDAFs available.
  • the NRF acknowledges that the NWDAF Registration are accepted via responses (e.g., the Nnrf_NFManagement_NFRegister responses) .
  • Steps 4 to 6 are the NWDAF Discovery procedure.
  • the NWDAF containing the MTLF may determine the ML model requires the VFL or the HFL based on the Analytic ID, Service Area/Data Network Access Identifier (DNAI) or data may not be obtained directly from the data producer NF (e.g., due to privacy reasons) .
  • DNAI Service Area/Data Network Access Identifier
  • a first NWDAF containing the MTLF may determine whether it can perform as the FL Server NWDAF in the determined type of FL (i.e., VFL, HFL, M-VFL or M-HFL) . In some embodiments, if the first NWDAF containing the MTLF cannot perform as the FL Server NWDAF in the determined type of FL (i.e., VFL, HFL, M-VFL or M-HFL) , the first NWDAF may send a request (e.g., the Nnrf_NFDiscovery_Request) to the NRF to discover the NWDAF able to serve as the FL Server NWDAF.
  • a request e.g., the Nnrf_NFDiscovery_Request
  • the NRF authorizes the NF service discovery and sends a response (e.g., the Nnrf_NFDiscovery_RequestResponse) to the first NWDAF.
  • the response e.g., the Nnrf_NFDiscovery_RequestResponse
  • the response comprises information of other NWDAF (s) able to serve as the FL Server NWDAF.
  • the NRF transmits the information of other NWDAF (s) able to serve as the FL Server NWDAF in the determined type of FL based on the ML capability information received from the NWDAFs (e.g., via the procedure in Aspect 2 or 3) .
  • the first NWDAF selects the FL Server NWDAF from the information of other NWDAF (s) able to serve as the FL Server NWDAF received from the NRF based on at least one of the following: the Analytic ID of the ML model required, Model filter information, FL capability Type (e.g., FL server in the determined type of FL (VFL, HFL, M-VFL or M-HFL) ) , and/or whether the selected FL Server NWDAF is currently executing an FL procedure for the Analytics ID, the Time Period of Interest and/or the Service Area.
  • the Analytic ID of the ML model required e.g., Model filter information
  • FL capability Type e.g., FL server in the determined type of FL (VFL, HFL, M-VFL or M-HFL)
  • the selected FL Server NWDAF sends a request (the Nnrf_NFDiscovery_Request) to the NRF to discover other NWDAF (s) containing the MTLF as FL Client NWDAF (s) (Step 4) .
  • the first NWDAF containing the MTLF can perform as the FL Server NWDAF in the determined type of FL (i.e., VFL, HFL, M-VFL or M-HFL)
  • the first NWDAF e.g., the FL server NWDAF
  • may send a request e.g., the Nnrf_NFDiscovery_Request
  • the NRF may send a request (e.g., the Nnrf_NFDiscovery_Request) to the NRF to discover other NWDAF (s) containing the MTLF as FL Client NWDAF (s) (Step 4) .
  • the NRF authorizes the NF service discovery.
  • the NRF sends a response (e.g., the Nnrf_NFDiscovery_RequestResponse) to the requested NWDAF.
  • the response e.g., the Nnrf_NFDiscovery_RequestResponse
  • the response comprises other NWDAF (s) containing the MTLF as FL Client NWDAF (s) .
  • the NRF transmits the information of other NWDAF (s) able to serve as the FL Client NWDAF (s) in the determined type of FL based on the ML capability information received from the NWDAFs (e.g., via the procedure in Aspect 2 or 3) .
  • the first NWDAF selects the FL Client NWDAF (s) from the information of other NWDAF (s) able to serve as the FL Client NWDAF (s) received from the NRF based on at least one of the following criteria: the Analytic ID of the ML model required, the FL capability Type (e.g., the FL client in the determined type of FL (VFL, HFL, M-VFL or M-HFL) ) , the Service Area and/or the NF type (s) of data sources from which the FL Client NWDAF is able to collect data for the FL training, the Time Period of Interest and/or the ML Model Interoperability Indicator.
  • the FL capability Type e.g., the FL client in the determined type of FL (VFL, HFL, M-VFL or M-HFL
  • the Time Period of Interest and/or the ML Model Interoperability In
  • the FL Server NWDAF sends a request (e.g., the FL preparation request) to the FL Client NWDAF (s) using a service (e.g., the Nnwdaf_MLModelTraining_Subscribe or the Nnwdaf_MLModelTrainingInfo_Request service) with the ML Preparation Flag, to check if the FL Client NWDAF (s) can meet the ML model training requirement (e.g., Analytics ID, ML Model Interoperability information, Available data requirement (alist of Event IDs of the local data for training, Available data requirement may also include the dataset statistical properties, the time window of the data samples and the minimum number of data samples) and/or Availability time requirement (time span needed for the FL process) , etc. ) .
  • a service e.g., the Nnwdaf_MLModelTraining_Subscribe or the Nnwdaf_MLModelTrainingInfo_Request service
  • the ML Preparation Flag e.g.,
  • FL Client NWDAF checks if it can meet the ML model training requirement and/or can successfully download the model if the model information is provided in the request and decides whether to join the FL process based on implementation.
  • Example criteria used by FL Client NWDAF (s) may be based on its availability, computation and communication capability and/or ML Model Interoperability information.
  • FL Client NWDAF (s) invokes a response (e.g., the Nnwdaf_MLModelTraining_Subscribe response service operation or Nnwdaf_MLModelTrainingInfo_Request response service operation) to indicate the FL Server NWDAF if FL Client NWDAF (s) will join the FL procedure.
  • FL Client NWDAF (s) may contain the reason in the response message if it cannot join the FL process.
  • the FL Server NWDAF conducts selection of FL Client NWDAF (s) .
  • the federated learning process may include different categories: Vertical Federated Learning (VFL) , Horizontal Federated Learning (HFL) , Multi-layer Vertical Federated Learning (M-VFL) , and Multi-layer Horizontal federated learning (M-HFL) .
  • VFL Vertical Federated Learning
  • HFL Horizontal Federated Learning
  • M-VFL Multi-layer Vertical Federated Learning
  • M-HFL Multi-layer Horizontal federated learning
  • the FL capability per analytic ID includes FL client, FL server, or FL client and server in this four categories.
  • the FL capability further includes FL client and server simultaneously.
  • the NWDAF performs at least one of:
  • the NRF receives the request and match the on-going type Federated learning (e.g., VFL, HFL, M-VFL, M-HFL) to the FL capability information of each NWDAF and returns a list of available NWDAF which is capable to be a FL server in the on-going type of federated learning; and/or
  • the on-going type Federated learning e.g., VFL, HFL, M-VFL, M-HFL
  • the NRF receives the request and match the on-going type Federated learning (e.g., VFL, HFL, M-VFL, M-HFL) to the FL capability information of each NWDAF and returns a list of available NWDAF, which is capable to be a FL client in the on-going type of federated learning.
  • the on-going type Federated learning e.g., VFL, HFL, M-VFL, M-HFL
  • FIG. 10 relates to a diagram of a wireless communication terminal 30 according to an embodiment of the present disclosure.
  • the wireless communication terminal 30 may be a tag, a mobile phone, a laptop, a tablet computer, an electronic book or a portable computer system and is not limited herein.
  • the wireless communication terminal 30 may be used to implement the UE described in this disclosure.
  • the wireless communication terminal 30 may include a processor 300 such as a microprocessor or Application Specific Integrated Circuit (ASIC) , a storage unit 310 and a communication unit 320.
  • the storage unit 310 may be any data storage device that stores a program code 312, which is accessed and executed by the processor 300.
  • Embodiments of the storage unit 310 include but are not limited to a subscriber identity module (SIM) , read-only memory (ROM) , flash memory, random-access memory (RAM) , hard-disk, and optical data storage device.
  • SIM subscriber identity module
  • ROM read-only memory
  • RAM random-access memory
  • the communication unit 320 may a transceiver and is used to transmit and receive signals (e.g., messages or packets) according to processing results of the processor 300.
  • the communication unit 320 transmits and receives the signals via at least one antenna 322 or via wiring.
  • the storage unit 310 and the program code 312 may be omitted and the processor 300 may include a storage unit with stored program code.
  • the processor 300 may implement any one of the steps or operations in exemplified embodiments on the wireless communication terminal 30, e.g., by executing the program code 312.
  • the communication unit 320 may be a transceiver.
  • the communication unit 320 may as an alternative or in addition be combining a transmitting unit and a receiving unit configured to transmit and to receive, respectively, signals to and from a wireless communication node.
  • the wireless communication terminal 30 may be used to perform the operations of the UE described in this disclosure.
  • the processor 300 and the communication unit 320 collaboratively perform the operations described in this disclosure. For example, the processor 300 performs operations and transmit or receive signals, message, and/or information through the communication unit 320.
  • FIG. 11 relates to a diagram of a wireless communication node 40 according to an embodiment of the present disclosure.
  • the wireless communication node 40 may be a satellite, a base station (BS) , a gNB, a network entity, a Domain Name System (DNS) server, a Mobility Management Entity (MME) , Serving Gateway (S-GW) , Packet Data Network (PDN) Gateway (P-GW) , a radio access network (RAN) , a next generation RAN (NG-RAN) , a data network, a core network, a communication node in the core network, or a Radio Network Controller (RNC) , and is not limited herein.
  • BS base station
  • gNB a network entity
  • DNS Domain Name System
  • MME Mobility Management Entity
  • S-GW Serving Gateway
  • PDN Packet Data Network Gateway
  • RAN radio access network
  • NG-RAN next generation RAN
  • RNC Radio Network Controller
  • the wireless communication node 40 may include (perform) at least one network function such as an access and mobility management function (AMF) , a session management function (SMF) , a user place function (UPF) , a policy control function (PCF) , an application function (AF) , etc.
  • the wireless communication node 40 may be used to implement the NWDAF or the NRF described in this disclosure.
  • the wireless communication node 40 may include a processor 400 such as a microprocessor or ASIC, a storage unit 410 and a communication unit 420.
  • the storage unit 410 may be any data storage device that stores a program code 412, which is accessed and executed by the processor 400.
  • the storage unit 410 examples include but are not limited to a SIM, ROM, flash memory, RAM, hard-disk, and optical data storage device.
  • the communication unit 420 may be a transceiver and is used to transmit and receive signals (e.g., messages or packets) according to processing results of the processor 400. In an embodiment, the communication unit 420 transmits and receives the signals via at least one antenna 422 or via wiring.
  • the storage unit 410 and the program code 412 may be omitted.
  • the processor 400 may include a storage unit with stored program code.
  • the processor 400 may implement any steps or operations described in exemplified embodiments on the wireless communication node 40, e.g., via executing the program code 412.
  • the communication unit 420 may be a transceiver.
  • the communication unit 420 may as an alternative or in addition be combining a transmitting unit and a receiving unit configured to transmit and to receive, respectively, signals, messages, or information to and from a wireless communication node or a wireless communication terminal.
  • the wireless communication node 40 may be used to perform the operations of the NWDAF or the NRF described in this disclosure.
  • the processor 400 and the communication unit 420 collaboratively perform the operations described in this disclosure. For example, the processor 400 performs operations and transmit or receive signals through the communication unit 420.
  • a wireless communication method is also provided according to an embodiment of the present disclosure.
  • the wireless communication method may be performed by using a wireless communication node (e.g., an NWDAF) .
  • the wireless communication node may be implemented by using the wireless communication node 40 described in this disclosure, but is not limited thereto.
  • the wireless communication method includes transmitting, by a first data analytics node to a repository node, a request for information of one or more second data analytics nodes; and receiving, by the first data analytics node from the repository node, the information of one or more second data analytics nodes based on Machine Learning, ML, capability information, wherein the capability information comprises information for different types of ML.
  • ML Machine Learning
  • the wireless communication method may be performed by using a wireless communication node (e.g., an NRF) .
  • the wireless communication node may be implemented by using the wireless communication node 40 described in this disclosure, but is not limited thereto.
  • the wireless communication method includes receiving, by a repository node from a first data analytics node, a request for information of one or more second data analytics nodes; and transmitting, by the repository node to the first data analytics node, the information of one or more second data analytics nodes based on Machine Learning, ML, capability information, wherein the capability information comprises information for different types of ML.
  • ML Machine Learning
  • the data analytics node used in the present disclosure may indicate the NWDAF described above.
  • the repository node used in the present disclosure may indicate the NRF described above.
  • a and/or B and/or C includes any and all combinations of one or more of A, B, and C, including A, B, C, A and B, A and C, B and C, and a combination of A and B and C.
  • A/B/C includes any and all combinations of one or more of A, B, and C, including A, B, C, A and B, A and C, B and C, and a combination of A and B and C.
  • any reference to an element herein using a designation such as “first, “ “second, “ and so forth does not generally limit the quantity or order of those elements. Rather, these designations can be used herein as a convenient means of distinguishing between two or more elements or instances of an element. Thus, a reference to first and second elements does not mean that only two elements can be employed, or that the first element must precede the second element in some manner.
  • any one of the various illustrative logical blocks, units, processors, means, circuits, methods and functions described in connection with the aspects disclosed herein can be implemented by electronic hardware (e.g., a digital implementation, an analog implementation, or a combination of the two) , firmware, various forms of program or design code incorporating instructions (which can be referred to herein, for convenience, as "software” or a “software unit” ) , or any combination of these techniques.
  • a processor, device, component, circuit, structure, machine, unit, etc. can be configured to perform one or more of the functions described herein.
  • IC integrated circuit
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA field programmable gate array
  • the logical blocks, units, and circuits can further include antennas and/or transceivers to communicate with various components within the network or within the device.
  • a general-purpose processor can be a microprocessor, but in the alternative, the processor can be any conventional processor, controller, or state machine.
  • a processor can also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other suitable configuration to perform the functions described herein. If implemented in software, the functions can be stored as one or more instructions or code on a computer-readable medium. Thus, the steps or operations of a method or algorithm disclosed herein can be implemented as software stored on a computer-readable medium.
  • Computer-readable media includes both computer storage media and communication media including any medium that can be enabled to transfer a computer program or code from one place to another.
  • a storage media can be any available media that can be accessed by a computer.
  • such computer-readable media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer.
  • unit refers to software, firmware, hardware, and any combination of these elements for performing the associated functions described herein. Additionally, for purpose of discussion, the various units are described as discrete units; however, as would be apparent to one of ordinary skill in the art, two or more units may be combined to form a single unit that performs the associated functions according to embodiments of the present disclosure.
  • memory or other storage may be employed in embodiments of the present disclosure.
  • memory or other storage may be employed in embodiments of the present disclosure.
  • any suitable distribution of functionality between different functional units, processing logic elements or domains may be used without detracting from the present disclosure.
  • functionality illustrated to be performed by separate processing logic elements, or controllers may be performed by the same processing logic element, or controller.
  • references to specific functional units are only references to a suitable means for providing the described functionality, rather than indicative of a strict logical or physical structure or organization.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

Un procédé de communication sans fil est divulgué. Le procédé consiste à transmettre, par un premier nœud d'analyse de données à un nœud de référentiel, une demande d'informations d'un ou de plusieurs seconds nœuds d'analyse de données ; et recevoir, par le premier nœud d'analyse de données en provenance du nœud de référentiel, les informations d'un ou de plusieurs seconds nœuds d'analyse de données sur la base d'informations de capacité d'apprentissage machine, ML, les informations de capacité ML comprenant des informations pour différents types de ML.
PCT/CN2024/072152 2024-01-12 2024-01-12 Procédé, dispositif et produit-programme informatique pour communication sans fil WO2024109960A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2024/072152 WO2024109960A1 (fr) 2024-01-12 2024-01-12 Procédé, dispositif et produit-programme informatique pour communication sans fil

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2024/072152 WO2024109960A1 (fr) 2024-01-12 2024-01-12 Procédé, dispositif et produit-programme informatique pour communication sans fil

Publications (1)

Publication Number Publication Date
WO2024109960A1 true WO2024109960A1 (fr) 2024-05-30

Family

ID=91195220

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2024/072152 WO2024109960A1 (fr) 2024-01-12 2024-01-12 Procédé, dispositif et produit-programme informatique pour communication sans fil

Country Status (1)

Country Link
WO (1) WO2024109960A1 (fr)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190222489A1 (en) * 2018-04-09 2019-07-18 Intel Corporation NETWORK DATA ANALYTICS FUNCTION (NWDAF) INFLUENCING FIFTH GENERATION (5G) QUALITY OF SERVICE (QoS) CONFIGURATION AND ADJUSTMENT
CN110677299A (zh) * 2019-09-30 2020-01-10 中兴通讯股份有限公司 网络数据采集方法、装置和系统
CN110798360A (zh) * 2019-11-06 2020-02-14 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
CN112398900A (zh) * 2019-08-13 2021-02-23 国际商业机器公司 移动网络中存储和保留信息
CN113573331A (zh) * 2020-04-29 2021-10-29 华为技术有限公司 一种通信方法、装置及系统
CN114189885A (zh) * 2021-09-27 2022-03-15 阿里巴巴达摩院(杭州)科技有限公司 网元信息处理方法、设备及存储介质

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190222489A1 (en) * 2018-04-09 2019-07-18 Intel Corporation NETWORK DATA ANALYTICS FUNCTION (NWDAF) INFLUENCING FIFTH GENERATION (5G) QUALITY OF SERVICE (QoS) CONFIGURATION AND ADJUSTMENT
CN112398900A (zh) * 2019-08-13 2021-02-23 国际商业机器公司 移动网络中存储和保留信息
CN110677299A (zh) * 2019-09-30 2020-01-10 中兴通讯股份有限公司 网络数据采集方法、装置和系统
CN110798360A (zh) * 2019-11-06 2020-02-14 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
CN113573331A (zh) * 2020-04-29 2021-10-29 华为技术有限公司 一种通信方法、装置及系统
CN114189885A (zh) * 2021-09-27 2022-03-15 阿里巴巴达摩院(杭州)科技有限公司 网元信息处理方法、设备及存储介质

Similar Documents

Publication Publication Date Title
US10581984B2 (en) Methods and apparatus for providing information associated with network function (NF) instances of a 5G mobile network
EP3884707B1 (fr) Sélection d'un identifiant de tranche de réseau
EP3456090B1 (fr) Connexion à des réseaux centraux mobiles virtualisés
US10638306B2 (en) Methods and apparatus for use in reducing signal latency in a mobile network with use of localized unified data management (UDM) entities
CN109756423A (zh) 策略更新的方法和装置
EP3669560B1 (fr) Procédé d'exécution d'un service pour un consommateur de service, et noeud de réseau et produit de programme d'ordinateur correspondants
CN112350841B (zh) 一种管理数据的获取方法及装置
US11991660B2 (en) Apparatus, methods, and computer programs
WO2022033115A1 (fr) Procédé de communication et appareil de communication
US11558813B2 (en) Apparatus and method for network automation in wireless communication system
EP3913982A1 (fr) Découpage de réseau en tranches à l'aide d'un noeud de réseau d'accès radio
WO2021083612A1 (fr) Procédés et appareil de demande et de fourniture de données d'analyses de réseau
WO2024109960A1 (fr) Procédé, dispositif et produit-programme informatique pour communication sans fil
WO2022170510A1 (fr) Procédé, dispositif et produit-programme informatique servant à une communication sans fil
EP4068824A1 (fr) Application et assurance de la sécurité utilisant une structure de commande de politique et un renforcement de la sécurité de la fonction d'analyse dans un réseau de communication
WO2023193128A1 (fr) Procédé de sélection de réseau sur la base d'informations de tranche
WO2023279386A1 (fr) Procédé, dispositif et produit programme informatique pour communication sans fil
US20240098674A1 (en) Method, device and computer program product for wireless communication
US20230422142A1 (en) Collaboration Between Mobile Network Operators for Mobile Edge Computing Applications
WO2023137761A1 (fr) Procédé de libération de ressource de tranche
EP4210302A1 (fr) Appareil, procédés et programmes informatiques
US20240022465A1 (en) Roaming aspects for network data analytics functions
EP4135413A1 (fr) Agencement de réseau de communication et procédé de sélection de composant de réseau
WO2023137750A1 (fr) Procédé de libération de ressource de tranche
US20240022948A1 (en) On demand cell-site information collection in a cloud 5g environment