Search

CN-122003883-A - Mechanism for service layer support for federal learning groups

CN122003883ACN 122003883 ACN122003883 ACN 122003883ACN-122003883-A

Abstract

Methods and systems for service layer support for federal learning groups are described herein. In one aspect, a method performed by an application enabler server may include receiving a first request to form a Federal Learning (FL) group, sending one or more requests corresponding to assistance with FL operations to a core network, receiving a response to the one or more requests from the core network, and sending a response to the first request, the response including one of an FL group identifier, an FL client list associated with the FL group, a validity time or schedule of the FL group, or a combination thereof.

Inventors

  • LIU LU
  • D. Sid
  • Q.LI
  • C nurse Latin

Assignees

  • 交互数字专利控股公司

Dates

Publication Date
20260508
Application Date
20240808
Priority Date
20230810

Claims (20)

  1. 1. A method performed by an application enabler server, comprising: receiving a request to form a Federal Learning (FL) group; Assigning at least one UE to the FL group; Transmitting a request to a core network to obtain one or more UEs of the FL group, wherein the request may include filter criteria including QoS requirements, access type, FL operation transfer time, UE location and mobility information, or a combination thereof; receiving a response from the core network with a list of one or more UEs, and A response to the request for forming the FL group is transmitted, the response indicating a state corresponding to the FL group.
  2. 2. The method of claim 1, wherein the response to the request to form the FL group comprises a status of the request to form the FL group, a FL group identifier, one or more UE identifiers selected for the FL group, scheduling of FL operations, or a combination thereof.
  3. 3. The method of claim 1, wherein the request to form the FL group comprises a FL server identifier, a FL group identifier, a FL policy, a FL client list, a FL client capability requirement, a number of clients to be part of the FL group, a quality of service requirement, a geographic location, or a combination thereof.
  4. 4. The method of claim 1, sending a notification to the at least one UE indicating that the at least one UE is selected as part of the FL set, and A response is received from the at least one UE, the response indicating that the UE is capable of participating in FL operations.
  5. 5. The method of claim 1, wherein assigning UEs to the FL group may result from finding UEs from a list of UEs received from the core network.
  6. 6. The method of claim 1, further comprising: a plurality of UEs are discovered from a FL client pool, wherein the at least one UE is assigned to the FL group based on the discovery.
  7. 7. The method of claim 1, further comprising: a FL group identifier is assigned to the FL group.
  8. 8. A method performed by an application enabler server, comprising: Transmitting a location-based group creation request to a group management server; Receiving a response to the location-based group creation request, the response including at least a list of UEs meeting location criteria, federal Learning (FL) criteria, or both; transmitting FL group creation request based on the UE list, and A response to the FL group creation request is received, the response including information corresponding to the FL group.
  9. 9. The method of claim 8, wherein the response to the location-based group creation request further comprises a status of the request, a group identifier, or both.
  10. 10. The method of claim 8, wherein the information corresponding to the FL group comprises a status of the FL group creation request, a FL group identifier, one or more FL client identifiers, scheduling of FL operations, or a combination thereof.
  11. 11. The method of claim 8, wherein the location-based group creation request comprises a FL server identifier, a FL group identifier, a FL policy, a FL client list, a FL client capability requirement, a number of clients to be part of the FL group, a quality of service requirement of the FL group, a geographic location of the FL group, or a combination thereof.
  12. 12. The method of claim 8, wherein the application enabler server is pre-provisioned with one or more FL policies.
  13. 13. The method of claim 12, wherein the one or more FL policies include a server identifier, a FL configuration identifier, a FL role, an application identifier, a Machine Learning (ML) model or algorithm, a ML application type, one or more FL capabilities, FL security information, FL user information, FL history information, or a combination thereof.
  14. 14. The method of claim 8 wherein the FL group creation request is sent to an Application Data Analysis Enable (ADAE) server.
  15. 15. An apparatus, comprising: One or more processors; Memory, and A set of instructions stored in the memory, which when executed by the one or more processors, cause: receiving a request to form a Federal Learning (FL) group; Assigning at least one UE to the FL group; transmitting a notification to the at least one UE, the notification indicating a selection of the at least one UE as part of the FL group; transmitting a request for a quality of service metric for one or more UEs of the FL group to a core network; receiving the quality of service metrics for the one or more UEs, and A response to the request for forming the FL group is sent, the response indicating a state corresponding to the FL group.
  16. 16. The apparatus of claim 15, wherein the response to the request to form the FL group comprises a status of the request to form the FL group, a FL group identifier, one or more FLUE identifiers selected for the FL group, a schedule of FL operations, or a combination thereof.
  17. 17. The apparatus of claim 15, wherein the request to form the FL group comprises a FL server identifier, a FL group identifier, a FL policy, a FL client list, a FL client capability requirement, a number of clients to be part of the FL group, a quality of service requirement of the FL group, a geographic location of the FL group, or a combination thereof.
  18. 18. The device of claim 15, wherein the request to form the FL group is received from a VAL server.
  19. 19. The apparatus of claim 18, wherein the set of instructions, when executed by the one or more processors, further cause: Authenticating the VAL server.
  20. 20. The apparatus of claim 15, wherein the set of instructions, when executed by the one or more processors, further cause: a plurality of UEs are discovered from a FL client pool, wherein the at least one UE is assigned to the FL group based on the discovery.

Description

Mechanism for service layer support for federal learning groups Cross Reference to Related Applications The present application claims the benefit of U.S. provisional application No. 63/518,652 entitled "MECHANISMS FOR SERVICE LAYER Support of FEDERATED LEARNING Groups," filed on 8/10 of 2023, the contents of which are incorporated herein by reference in their entirety for any and all purposes. Background An application layer architecture. Applications are becoming increasingly more complex, and various mechanisms have been devised to assist in developing applications more rapidly. One such mechanism is to introduce different functional layers within (or adjacent to) the application layer to separate functions that are accessible via an application programming interface or API. FIG. 1 illustrates an example of a generalized application layer architecture that separates application development into three distinct layers, an application-specific layer, a vertical application enabler layer, and a service layer. At the bottom of the application stack is a service layer that provides common services to all applications. Services may include security aspects of location management, group management, configuration management, and application development. Above the service layer is a vertical application enabler layer, which is a layer that manages services for a particular vertical application (such as autonomous driving vehicles, drones, ioT, games, etc.). At the top of the application stack is an application-specific layer that serves a particular application within the vertical application. This layer contains application-specific customized logic or business logic and may be provided by various service providers in the vertical application domain. The goal of this three-tiered approach is to abstract the common services of all applications to the vertical application enabler and service tier to simplify application development, thereby deploying the applications more quickly. The architecture shown in fig. 1 is based on a client-server communication model. One or more client applications on the device may communicate with one or more server applications on the application server. Note that a server application may reside in one or more application servers. The client application and the server application of each layer communicate with each other between the device and the application server. The application-specific client and server may communicate with the client and server applications, respectively, at any of the lower layers. For example, an application-specific client may communicate with the client application at a vertical application enabler or service layer. The network between the client and server applications provides a communication medium. The network may be a cellular network such as a mobile operator network, or the network may be a broadband service provider network that provides access to the internet for client and server applications. Notably, the architecture shown in FIG. 1 can also be applied to the publish-subscribe and subscribe-notify modes of communication. It is also worth noting that for decentralized deployments where devices communicate directly with other devices, the server functionality may reside on the device, rather than on the application server. For this case, the devices may communicate with each other such that one device may act as a client and the other device may act as a server. A Data Analysis Enabled Service (ADAES) architecture is applied. The 3GPP defines an Application Data Analysis Enabling Service (ADAES) available to an application to access analysis related to the application. The ADAES architecture is shown in fig. 2. As shown in the figure, ADAE clients communicate with ADAE servers over 3GPP networks using ADAE-UU interfaces. The ADAE client resides on a User Equipment (UE), and the ADAE server may reside on an Application Server (AS) or an Application Function (AF). The figure also shows ADAE that the clients and servers are part of a Service Enabler Architecture Layer (SEAL), which may be similar to the service layer shown in fig. 1. The ADAE layer supports application layer analysis to generate VAL servers and VAL clients. The generated analysis may include statistics or predictions associated with the analysis ID. Various analysis IDs are currently supported, application performance, slice-specific and UE-to-UE application performance, location accuracy, service APIs, slice usage patterns, and edge load analysis. Data collection is also managed by the ADAE layer to enable derivation of the corresponding analysis. Finally, ADAE servers can access core network services through the N33, N6, and ADAE-OAM interfaces, as shown in fig. 2. An Edge Enabler Layer (EEL). Edge computing architecture allows communication and computing services to reside closer to end devices to reduce end-to-end latency and offload networks. Thus, the edge enabler layer may be