Client registration and selection for federated machine learning
A Permissioned Distributed Ledger network architecture addresses the challenge of secure UE registration and selection for federated machine learning in wireless communication systems, enhancing security and efficiency for future networks like 6G by authenticating and managing UE profiles and data access.
Patent Information
- Application Number
- PCT/EP2024/054184
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-02-09
- Filing Date
- 2024-02-19
- Publication Date
- 2024-11-21
AI Technical Summary
Current wireless communication systems lack secure and efficient methods for registering and selecting User Equipment (UE) for federated machine learning, particularly in distributed networks where privacy and security concerns are paramount, such as in future 6G networks.
The implementation of a Permissioned Distributed Ledger (PDL) network architecture that facilitates secure registration and selection of UE by authenticating and authorizing network functions, storing UE profile information, and managing block addresses for secure data access and storage, ensuring secure distribution and collection of sensitive ML model information.
This solution provides a secure and efficient framework for UE registration and selection, optimizing data access and storage while ensuring privacy and integrity, particularly beneficial for future wireless communication networks like 6G.
Smart Images

Figure EP2024054184_21112024_PF_FP_ABST
Abstract
Description
CLIENT REGISTRATION AND SELECTION FOR FEDERATED MACHINE LEARNINGTECHNICAL FIELD
[0001] The present disclosure relates to wireless communications, and more specifically to network architectures and methods that support the registration and selection of User Equipment (UE) for use in federated machine learning.BACKGROUND
[0002] A wireless communications system may include one or multiple network communication devices, such as base stations, which may support wireless communications for one or multiple user communication devices, which may be otherwise known as user equipment (UE), or other suitable terminology. The wireless communications system may support wireless communications with one or multiple user communication devices by utilizing resources of the wireless communication system (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers, or the like). Additionally, the wireless communications system may support wireless communications across various radio access technologies including third generation (3G) radio access technology, fourth generation (4G) radio access technology, fifth generation (5G) radio access technology, among other suitable radio access technologies beyond 5G (e.g., sixth generation (6G)).SUMMARY
[0003] An article “a” before an element is unrestricted and understood to refer to “at least one” of those elements or “one or more” of those elements. The terms “a,” “at least one,” “one or more,” and “at least one of one or more” may be interchangeable. As used herein, including in the claims, “or” as used in a list of items (e.g., a list of items prefaced by a phrase such as “at least one of’ or “one or more of’ or “one or both of’) indicates an inclusive list such that, for example, a list of at least one of A, B, or C means A or B or C or AB or AC or BC or ABC (i.e., A and B and C). Also, as used herein, the phrase “based on” shall not be construed as a reference to a closed set of conditions. For example, an example step that isdescribed as “based on condition A” may be based on both a condition A and a condition B without departing from the scope of the present disclosure. In other words, as used herein, the phrase “based on” shall be constmed in the same manner as the phrase “based at least in part on. Further, as used herein, including in the claims, a “set” may include one or more elements.
[0004] Some implementations of the method and apparatuses described herein include a network entity, the network entity comprising at least one memory and at least one processor coupled with the at least one memory and configured to cause the network entity to receive, from each of a plurality of first network functions associated with respective User Equipments (UEs), a registration request comprising UE profile information of the UE, said UE profile information indicating at least (i) a UE identifier and (ii) one or more capabilities of, and / or an availability of, the UE for training a machine learning (ML) model.
[0005] The at least one processor is further configured to cause the network entity to: authenticate and authorize each of the first network functions; send the UE profile information to a second network function; receive, from the second network function, one or more confirmation responses comprising one or more block addresses of the UE profile information as stored in a permissioned distributed ledger (PDL); and store each of the one or more block addresses in a database in association with a respective profile of one or more corresponding UE(s).
[0006] The at least one processor is further configured to cause the network entity to: receive, from a third network function, a ML client selection request, the ML client selection request including: a ML Model Identifier and / or type and / or one or more desired UE capabilities.
[0007] The at least one processor is further configured to cause the network entity to: authenticate and authorize the third network function; select one or more UE profiles from the database based on the ML client selection request, and obtain the associated block address or addresses; fetch one or more UE identifiers from the second network function using the obtained block address or addresses; and send to the third network function a ML client selection including the fetched UE identifiers.
[0008] In some implementations each UE profile in the database may indicate at least one or more capabilities of, and / or an availability of, the corresponding UE(s) for training a ML model.
[0009] In some implementations, the at least one processor may be further configured to cause the network entity to: temporarily store the UE identifiers received in the registration requests from the first network functions, and optionally to delete said UE identifiers after sending the UE profile information to the second network function or after receiving the confirmation response from the second network function.
[0010] In some implementations, the at least one processor is configured to cause the network entity to: group the profile information received from the first network functions according to the capabilities of, and / or the availabilities of, the respective UE for training a ML model; send each group of profile information in a respective request to the second network function; and receive, for each group, a respective confirmation response from the second network function comprising one or more block addresses of the group of profile information in the PDL.
[0011] In some implementations, the selection request comprising the selected one or more block addresses may further comprise the capabilities of, and / or the availabilities of, the corresponding UE(s) for training a ML model.
[0012] In some implementations, the second network function may be associated with one of a plurality of nodes of a PDL network, and may be configured to add the UE profile information to a blockchain block and distribute said block to the plurality of nodes of the PDL network.
[0013] In some implementations, the at least one processor may be further configured to cause the network entity to: after receiving a confirmation response from the second network function comprising one or more block addresses of UE profile information in the PDL, send a confirmation response to one or more corresponding first network functions, optionally comprising said one or more block addresses.
[0014] In some implementations, the at least one processor may be further configured to cause the network entity to: receive, from the third network function, a request to train a ML model, the request comprising (i) one or more UE identifiers and (ii) a ML model identifier and ML model parameters, or one or more block addresses of the ML model identifier andparameters as stored in a PDL; and send, to the first network functions associated with said one or more UE identifiers, a training request comprising the ML model identifier and parameters or the one or more block addresses of the ML model identifier and parameters in the PDL.
[0015] Some implementations of the method and apparatuses described herein include a method performed by a network entity, the method comprising: receiving from each of a plurality of first network functions associated with respective User Equipments (UEs), a registration request comprising UE profile information of the UE, said UE profde information indicating at least (i) a UE identifier and (ii) one or more capabilities of, and / or an availability of, the UE for training a machine learning (ML) model.
[0016] The method further comprises: authenticating and authorizing each of the first network functions; sending the UE profile information to a second network function; receiving, from the second network function, one or more confirmation responses comprising one or more block addresses of the UE profile information as stored in a permissioned distributed ledger (PDL); and storing each of the one or more block addresses in a database in association with a respective profile of one or more corresponding UE(s).
[0017] The method further comprises: receiving from a third network function a ML client selection request, the ML client selection request including a ML Model Identifier and / or type and / or one or more desired UE capabilities; authenticating and authorizing the third network function; selecting one or more UE profiles from the database based on the ML client selection request, and obtaining the associated block address or addresses; fetching one or more UE identifiers from the second network function using the obtained block address or addresses; and sending to the third network function a ML client selection including the fetched UE identifiers.
[0018] In some implementations, each UE profile in the database may indicate at least one or more capabilities of, and / or an availability of, the corresponding UE(s) for training a ML model.
[0019] In some implementations, the method may comprise: temporarily storing the UE identifiers received in the registration requests from the first network functions, andoptionally deleting said UE identifiers after sending the UE profile information to the second network function or after receiving the confirmation response from the second network function.
[0020] In some implementations, the method may comprise: grouping the profile information received from the first network functions according to the capabilities of, and / or the availabilities of, the respective UE for training a ML model; sending each group of profile information in a respective request to the second network function; and receiving, for each group, a respective confirmation response from the second network function comprising one or more block addresses of the group of profile information in the PDL.
[0021] In some implementations, the selection request comprising the selected one or more block addresses may further comprise the capabilities of, and / or the availabilities of, the corresponding UE(s) for training a ML model.
[0022] In some implementations, the second network function may be associated with one of a plurality of nodes of a PDL network, and may be configured to add the UE profile information to a blockchain block and distribute said block to the plurality of nodes of the PDL network.
[0023] In some implementations, the method may further comprise, after receiving a confirmation response from the second network function comprising one or more block addresses of UE profile information in the PDL, sending a confirmation response to one or more corresponding first network functions, optionally comprising said one or more block addresses.
[0024] In some implementations, the method may further comprise: receiving, from the third network function, a request to train a ML model, the request comprising (i) one or more UE identifiers and (ii) a ML model identifier and ML model parameters, or one or more block addresses of the ML model identifier and parameters as stored in a PDL; and sending, to the first network functions associated with said one or more UE identifiers, a training request comprising the ML model identifier and parameters or the one or more block addresses of the ML model identifier and parameters in the PDL.
[0025] Some implementations of the method and apparatuses described herein include a User Equipment (UE), the UE comprising at least one memory and at least one processor coupled with the at least one memory and configured to cause the UE to: send, to a first network function, a registration request comprising profile information of the UE, said profile information indicating at least (i) an identifier of the UE and (ii) one or more capabilities of, and / or an availability of, the UE for training a machine learning (ML) model; and receive, from the first network function, a confirmation response comprising one or more block addresses of profile information associated with the UE as stored in a permissioned distributed ledger (PDL).
[0026] In some implementations, the processor is further configured to cause the UE to: receive, from a second network function, a request to train a ML model; and perform training of the ML model using local data so as to produce a trained version of the ML model.
[0027] Some implementations of the method and apparatuses described herein include a processor, the processor comprising at least one memory and at least one controller coupled with the at least one memory and configured to cause the processor to: send, to a first network function, a registration request comprising profile information of the User Equipment (UE), said profile information indicating at least (i) an identifier of the UE and (ii) one or more capabilities of, and / or an availability of, the UE for training a machine learning (ML) model; and receive, from the first network function, a confirmation response comprising one or more block addresses of profile information associated with the UE as stored in a permissioned distributed ledger (PDL).
[0028] In some implementations, the processor is further configured to cause the UE to: receive, from a second network function, a request to train a ML model; and perform training of the ML model using local data so as to produce a trained version of the ML model.BRIEF DESCRIPTION OF THE DRAWINGS
[0029] Figure 1 illustrates an example of a wireless communications system in accordance with aspects of the present disclosure.
[0030] Figure 2 illustrates a network architecture for registering and selecting User Equipment (UE) for use in federated machine learning in accordance with aspects of the present disclosure.
[0031] Figure 3 illustrates a procedure for registering and selecting UE for use in federated machine learning in accordance with aspects of the present disclosure.
[0032] Figure 4 illustrates an example of a user equipment 400 in accordance with aspects of the present disclosure.
[0033] Figure 5 illustrates an example of a processor 500 in accordance with aspects of the present disclosure.
[0034] Figure 6 illustrates an example of a network equipment (NE) 600 in accordance with aspects of the present disclosure.
[0035] Figure 7 is a flowchart illustrating a method 700 performed by a NE in accordance with aspects of the present disclosure.
[0036] Figure 8 is a flowchart illustrating a method 800 performed by a UE in accordance with aspects of the present disclosure.DETAILED DESCRIPTION
[0037] The 3rd Generation Partnership Project (3 GPP) is an umbrella term for a number of standards organizations which develop protocols for mobile telecommunications technologies, including radio access, core network and service capabilities, which provide a complete system description for mobile telecommunications.
[0038] Network Data Analytics Function (NWDAF) is a 5G 3GPP standard method used to collect data from user equipment (UEs), network functions (NFs), operations, administration, and maintenance (0AM) systems, etc. from the 5G Core (5GC), Cloud, and Edge networks that can be used for analytics. The NWDAF is located within the 5G core network domain. The NWDAF may provide data analytics to allow communication service providers to improve customer experiences and to increase network efficiency and generate new sources of revenue. Via open APIs the NWDAF may also be exposed to external users such as streaming services, financial institutions including banks, etc.
[0039] Typically, the NWDAF makes use of one or more Machine Learning (ML) models the building of which is an iterative process. A ML model can be identified by its ID and can be provided by the network or operator, a telco vendor, edge provider or anapplication provider and can be applicable for mobile devices in the 5G system, e.g., image recognition, localization, performance, speech recognition, and video processing, as well as for optimizing performance of the network elements / communi cation aspects. A ML model can be trained for example for deriving the UE location pattern for a given time and area, the performance for a given cell / network access or for a UE or the load of a network entity. ML models at the network side are stored at network functions serving as ML model repositories using the ML model ID. Lor external ML models, there is no provisioning of how the ID is configured and where the ML models are stored.
[0040] In the current 3 GPP architecture (up to Release 18) the NWDAE provides analytic output to one or more Analytics Consumer NEs based on data collected from one or more Data Producer NFs. Analytics Consumer NFs subscribe to the NWDAE to receive analytics data therefrom.
[0041] In Release 17 the NWDAF is split into an Analytics Logical Function (AnLF) and a Model Training Function (MTLF). The AnLF is responsible for collecting analytics requests from consumers and for returning responses. The MTLF is responsible for training ML models based on data received from the Data Producer NFs (or DCCF). According to this architecture, a single AnLF may act as an “aggregator”, calculating an aggregate model (where a model may be defined by a set of model parameters) from model data received from the multiple MTLFs. The model aggregator provides updated model parameters to each MTLF that each MTLF uses to re-train its own model thus allowing every local model training function to have a trained model using data from multiple sources.
[0042] This type of shared ML model training is known as “federated learning” or FL. Release 18 defines two types of federated learning, namely horizontal and vertical federated learning. Horizontal federated learning (HFL), or sample-based federated learning, is introduced where data sets share the same feature space but have different samples. This might arise where different MTLFs create models for the same feature set but for a different group of users, e.g. UEs. Vertical federated learning (VFL) might arise where different UEs are creating models based on different feature sets for the same or different groups of users.
[0043] As described above, current 3 GPP specifications allow for FL of ML models between NWDAFs. For example, an FL Server NWDAF can provide an ML model to FL Client NWDAFs for further training using local data. Afterwards, each FL Client NWDAFprovides their trained ML model information or the weights of a trained model back to the FL Server NWDAF, which aggregates all the local ML model information and updates the global ML model. The process may be repeated until the desired accuracy is reached or the upper bound for training time expires.
[0044] UEs may be involved in application related analytics whereby the UE position or other local data cannot be shared with the network due to privacy concerns. Nevertheless, as described in TR 23.700-80, AI / ML training can still benefit from the local data. To support this, certain enhancements were introduced atNEF to assist the selection / recommendation of FL client UE considering network conditions, i.e., QoS, wireless links performance, etc.
[0045] Federated Learning of NWDAFs is further described in TS 23.228 and TR 23.700-80. FL is a distributed procedure, which may involve untrusted or vulnerable entities such as UE. There is therefore a need to ensure that the FL process is sufficiently secure for the distribution and collection of sensitive ML model information.
[0046] According to aspects of the present disclosure, there are provided network architectures and methods that facilitate the secure registration and selection of UE for FL, through the use of a Permissioned Distributed Ledger (PDL). In this way, the FL process, including data access and storage, can be dealt with securely. The present solution may be particularly advantageous for use in future (e.g. 6G) networks, moving from centralized functionality to a more distributed procedure.
[0047] Aspects of the present disclosure are described in the context of a wireless communications system.
[0048] Figure 1 illustrates an example of a wireless communications system 100 in accordance with aspects of the present disclosure. The wireless communications system 100 may include one or more NE 102, one or more UE 104, and a core network (CN) 106. The wireless communications system 100 may support various radio access technologies. In some implementations, the wireless communications system 100 may be a 4G network, such as an LTE network or an LTE -Advanced (LTE-A) network. In some other implementations, the wireless communications system 100 may be a NR network, such as a 5G network, a 5G- Advanced (5G-A) network, or a 5G ultrawideband (5G-UWB) network. In other implementations, the wireless communications system 100 may be a combination of a 4Gnetwork and a 5G network, or other suitable radio access technology including Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20. The wireless communications system 100 may support radio access technologies beyond 5G, for example, 6G. Additionally, the wireless communications system 100 may support technologies, such as time division multiple access (TDMA), frequency division multiple access (FDMA), or code division multiple access (CDMA), etc.
[0049] The one or more NE 102 may be dispersed throughout a geographic region to form the wireless communications system 100. One or more of the NE 102 described herein may be or include or may be referred to as a network node, a base station, a network element, a network function, a network entity, a radio access network (RAN), a NodeB, an eNodeB (eNB), a next-generation NodeB (gNB), or other suitable terminology. An NE 102 and a UE 104 may communicate via a communication link, which may be a wireless or wired connection. For example, an NE 102 and a UE 104 may perform wireless communication (e.g., receive signaling, transmit signaling) over a Uu interface.
[0050] An NE 102 may provide a geographic coverage area for which the NE 102 may support services for one or more UEs 104 within the geographic coverage area. For example, an NE 102 and a UE 104 may support wireless communication of signals related to services (e.g., voice, video, packet data, messaging, broadcast, etc.) according to one or multiple radio access technologies. In some implementations, an NE 102 may be moveable, for example, a satellite associated with a non-terrestrial network (NTN). In some implementations, different geographic coverage areas 112 associated with the same or different radio access technologies may overlap, but the different geographic coverage areas may be associated with different NE 102.
[0051] The one or more UE 104 may be dispersed throughout a geographic region of the wireless communications system 100. A UE 104 may include or may be referred to as a remote unit, a mobile device, a wireless device, a remote device, a subscriber device, a transmitter device, a receiver device, or some other suitable terminology. In some implementations, the UE 104 may be referred to as a unit, a station, a terminal, or a client, among other examples. Additionally, or alternatively, the UE 104 may be referred to as anInternet-of- Things (loT) device, an Internet-of-Everything (loE) device, or machine-type communication (MTC) device, among other examples.
[0052] A UE 104 may be able to support wireless communication directly with other UEs104 over a communication link. For example, a UE 104 may support wireless communication directly with another UE 104 over a device-to-device (D2D) communication link. In some implementations, such as vehicle-to-vehicle (V2V) deployments, vehicle-to-everything (V2X) deployments, or cellular-V2X deployments, the communication link 114 may be referred to as a sidelink. For example, a UE 104 may support wireless communication directly with another UE 104 over a PC5 interface.
[0053] An NE 102 may support communications with the CN 106, or with another NE 102, or both. For example, an NE 102 may interface with other NE 102 or the CN 106 through one or more backhaul links (e.g., S1, N2, N2, or network interface). In some implementations, the NE 102 may communicate with each other directly. In some other implementations, the NE 102 may communicate with each other or indirectly (e.g., via the CN 106. In some implementations, one or more NE 102 may include subcomponents, such as an access network entity, which may be an example of an access node controller (ANC). An ANC may communicate with the one or more UEs 104 through one or more other access network transmission entities, which may be referred to as a radio heads, smart radio heads, or transmission-reception points (TRPs).
[0054] The CN 106 may support user authentication, access authorization, tracking, connectivity, and other access, routing, or mobility functions. The CN 106 may be an evolved packet core (EPC), or a 5G core (5GC), which may include a control plane entity that manages access and mobility (e.g., a mobility management entity (MME), an access and mobility management functions (AMF)) and a user plane entity that routes packets or interconnects to external networks (e.g., a serving gateway (S-GW), a Packet Data Network (PDN) gateway (P-GW), or a user plane function (UPF)). In some implementations, the control plane entity may manage non-access stratum (NAS) functions, such as mobility, authentication, and bearer management (e.g., data bearers, signal bearers, etc.) for the one or more UEs 104 served by the one or more NE 102 associated with the CN 106.
[0055] The CN 106 may communicate with a packet data network over one or more backhaul links (e.g., via an SI, N2, N2, or another network interface). The packet data network may include an application server. In some implementations, one or more UEs 104 may communicate with the application server. A UE 104 may establish a session (e.g., a protocol data unit (PDU) session, or the like) with the CN 106 via an NE 102. The CN 106 may route traffic (e.g., control information, data, and the like) between the UE 104 and the application server using the established session (e.g., the established PDU session). The PDU session may be an example of a logical connection between the UE 104 and the CN 106 (e.g., one or more network functions of the CN 106).
[0056] In the wireless communications system 100, the NEs 102 and the UEs 104 may use resources of the wireless communications system 100 (e.g., time resources (e.g., symbols, slots, subframes, frames, or the like) or frequency resources (e.g., subcarriers, carriers)) to perform various operations (e.g., wireless communications). In some implementations, the NEs 102 and the UEs 104 may support different resource structures. For example, the NEs 102 and the UEs 104 may support different frame structures. In some implementations, such as in 4G, the NEs 102 and the UEs 104 may support a single frame structure. In some other implementations, such as in 5G and among other suitable radio access technologies, the NEs 102 and the UEs 104 may support various frame structures (i.e., multiple frame structures). The NEs 102 and the UEs 104 may support various frame structures based on one or more numerologies.
[0057] One or more numerologies may be supported in the wireless communications system 100, and a numerology may include a subcarrier spacing and a cyclic prefix. A first numerology (e.g., / r=0) may be associated with a first subcarrier spacing (e.g., 15 kHz) and a normal cyclic prefix. In some implementations, the first numerology (e.g., / r=0) associated with the first subcarrier spacing (e.g., 15 kHz) may utilize one slot per subframe. A second numerology (e.g., / r=l) may be associated with a second subcarrier spacing (e.g., 30 kHz) and a normal cyclic prefix. A third numerology (e.g., / r=2) may be associated with a third subcarrier spacing (e.g., 60 kHz) and a normal cyclic prefix or an extended cyclic prefix. A fourth numerology (e.g., / r=3) may be associated with a fourth subcarrier spacing (e.g., 120kHz) and a normal cyclic prefix. A fifth numerology (e.g., / r=4) may be associated with a fifth subcarrier spacing (e.g., 240 kHz) and a normal cyclic prefix.
[0058] A time interval of a resource (e.g., a communication resource) may be organized according to frames (also referred to as radio frames). Each frame may have a duration, for example, a 10 millisecond (ms) duration. In some implementations, each frame may include multiple subframes. For example, each frame may include 10 subframes, and each subframe may have a duration, for example, a 1 ms duration. In some implementations, each frame may have the same duration. In some implementations, each subframe of a frame may have the same duration.
[0059] Additionally or alternatively, a time interval of a resource (e.g., a communication resource) may be organized according to slots. For example, a subframe may include a number (e.g., quantity) of slots. The number of slots in each subframe may also depend on the one or more numerologies supported in the wireless communications system 100. For instance, the first, second, third, fourth, and fifth numerologies (i.e., / r=0, / r=l, / r=2, / r=3, / r=4) associated with respective subcarrier spacings of 15 kHz, 30 kHz, 60 kHz, 120 kHz, and 240 kHz may utilize a single slot per subframe, two slots per subframe, four slots per subframe, eight slots per subframe, and 16 slots per subframe, respectively. Each slot may include a number (e.g., quantity) of symbols (e.g., OFDM symbols). In some implementations, the number (e.g., quantity) of slots for a subframe may depend on a numerology. For a normal cyclic prefix, a slot may include 14 symbols. For an extended cyclic prefix (e.g., applicable for 60 kHz subcarrier spacing), a slot may include 12 symbols. The relationship between the number of symbols per slot, the number of slots per subframe, and the number of slots per frame for a normal cyclic prefix and an extended cyclic prefix may depend on a numerology. It should be understood that reference to a first numerology (e.g., / i =0) associated with a first subcarrier spacing (e.g., 15 kHz) may be used interchangeably between subframes and slots.
[0060] In the wireless communications system 100, an electromagnetic (EM) spectrum may be split, based on frequency or wavelength, into various classes, frequency bands, frequency channels, etc. By way of example, the wireless communications system 100 may support one or multiple operating frequency bands, such as frequency range designationsFR1 (410 MHz - 7.125 GHz), FR2 (24.25 GHz - 52.6 GHz), FR3 (7.125 GHz - 24.25 GHz), FR4 (52.6 GHz - 114.25 GHz), FR4a or FR4-1 (52.6 GHz - 71 GHz), and FR5 (114.25 GHz - 300 GHz). In some implementations, the NEs 102 and the UEs 104 may perform wireless communications over one or more of the operating frequency bands. In some implementations, FR1 may be used by the NEs 102 and the UEs 104, among other equipment or devices for cellular communications traffic (e.g., control information, data). In some implementations, FR2 may be used by the NEs 102 and the UEs 104, among other equipment or devices for short-range, high data rate capabilities.
[0061] FR1 may be associated with one or multiple numerologies (e.g., at least three numerologies). For example, FR1 may be associated with a first numerology (e.g., / r=0), which includes 15 kHz subcarrier spacing; a second numerology (e.g., / r=l), which includes 30 kHz subcarrier spacing; and a third numerology (e.g., / r=2), which includes 60 kHz subcarrier spacing. FR2 may be associated with one or multiple numerologies (e.g., at least 2 numerologies). For example, FR2 may be associated with a third numerology (e.g., / r=2), which includes 60 kHz subcarrier spacing; and a fourth numerology (e.g., / r=3), which include s 120 kHz subcarrier spacing.
[0062] Figure 2 illustrates an example of a network architecture 200 for registering and selecting UEs for use in federated machine learning in accordance with aspects of the present disclosure.
[0063] The network architecture 200 includes: a plurality of User Equipment Federated Learning (UE FL) Clients 202 (referred to herein as “UE Clients” or “UEs”); a Permissioned Distributed Ledger (PDL) Network 204, comprising a plurality of PDL Nodes 206 and a PDL Application Function (AF) 208; and an Analytics Function Federated Learning Server ( or “FL Server”) 210.
[0064] Figure 3 illustrates a procedure 300 (e.g. to be implemented by the network architecture 200) for registering and selecting UE Clients for use in federated machine learning in accordance with aspects of the present disclosure.
[0065] Registration Phase
[0066] In a first phase of the procedure (the “Registration Phase”), as shown in Steps la.- le., profile information of a plurality of UEs is registered, for later use in the selection of UEs for training a ML model.
[0067] In Step la., each UE sends a respective UE Information Registration Request to an Application Function (AF) associated with a Permissioned Distributed Ledger (PDL). Each UE Information Registration Request includes profile information of the respective UE, indicating at least (i) an identifier (ID) of the UE and (ii) one or more capabilities of, and / or an availability of, the UE for training a ML model. In addition to the UE ID, the UE Information Registration Request may also include an address of the UE (e.g. a network access identifier (NAI) or an IP address). The one or more capabilities of the UE for training a ML model may include various factors indicative of the suitability of the UE for training a ML model, or for training a particular ML model or model type. Such factors include properties of the UE device, such as power constraints, factors relating to the usage of the device, such as a movement or location history of the device, or a loT / Machine Type Communication such as a low priority indicator. The availability of the UE for training a ML model may include a true / false indication of the availability of the UE for training a ML model (e.g. in the short-term), or a long-term availability (e.g. an indication of specific times when the UE is available or unavailable for training).
[0068] The UE Information Registration Request is received by the PDL AF, and the PDL AF then authenticates and authorizes the UE based on the UE profile information (Step lb.). In one example, the PDL AF authenticates and authorizes the UE based on the UE ID, and / or other UE credentials present in the UE profile information such as a username / password, or another suitable challenge-response protocol.
[0069] In Step 1c., following successful authentication and authorization of the UE, the PDL AF then sends a UE Information Registration Request, including the UE profde information, to one of a plurality of nodes of the PDL network. The PDL node then adds the UE profile information to a blockchain block (e.g. following a transaction validation and consensus protocol), and distributes the block to the plurality of nodes of PDL network.
[0070] In Step le., the PDL node confirms the storage of the profile information in the PDL, and sends a UE Information Registration Response to the UEs, optionally via the PDL AF.
[0071] The PDL AF may store the one or more block addresses of the profile information, for later use in the selection of UE(s) for use in ML model training. For example, the PDL AF may store each of the one or more block addresses in association with profile information (or “UE profiles”) of the corresponding UE(s) (i.e. UEs the profile information of which is stored at said block addresses in the PDL. In some examples, the profile information stored in association with the one or block addresses includes at least one or more capabilities of, and / or an availability of, the corresponding UE(s) for training a ML model. In some examples, the profile information stored in association with the one or more block addresses does not include UE identifiers and / or addresses of the corresponding UEs. For example, the PDL AF may only temporarily store the UE identifiers received in the registration requests, and optionally may delete said UE identifiers (e.g. after sending the UE profile information to the PDL node or after receiving the confirmation response from the PDL node).
[0072] In some examples, the PDL AF may group the profile information received in a plurality of UE Information Registration Requests, for example according to the capabilities of, and / or the availabilities of, the respective UE for training a ML model. In this case, in Step 1c., the PDL AF sends each group of profile information in a respective request to the PDL node. The PDL node may then store each group of profile information together in the PDL (e.g. in the same block), and may return in Step Id. a confirmation response comprising one or more block addresses of each group of profile information as stored in the PDL. In this way, each block of the PDL may store a plurality of UE IDs having the same capabilities and availabilities, thus simplifying the UE selection process as described below. The PDL node may then send a UE Information Registration Response to all UEs individually. Alternatively, the PDL node may send a list of UE IDs of the block to the PDL AF for the PDL AF to send the UE Information Registration Response to each UE associated with the block.
[0073] Selection Phase
[0074] In a second phase of the procedure (the “Selection Phase”), as shown in Steps 2a.- 2e., one or more UEs registered during the Registration Phase are selected for use in ML model training.
[0075] In Step 2a., an Analytics Function FL Server (or “FL Server”) sends a ML Client Selection Request to the PDL AF. The ML Client Selection Request includes any one ormore of: an ML Model Identifier; a ML Model type; and one or more desired UE capabilities. The ML Model type may, for example, indicate an application to which the ML Model relates, such as a camera app or a keyboard app. The desired UE capabilities may correspond to any of the UE capabilities indicated in the UE profile information included in the UE Information Registration Requests.
[0076] In Step 2., the PDL AF then authenticates and authorizes the FL Server, for example based on an identifier of the FL Server or one or more additional credentials included in the ML Client Selection Request. Following successful authentication and authorization, the PDL AF selects one or more of the UE profiles from the database, based on the ML Client Selection Request. For example, the PDL AD may compare the one or more desired UE capabilities indicated in the ML Client Selection Request with the one or more capabilities of the UEs included in the UE profiles. If the UE profiles in the database include an indication of UE availability, the PDL AF may select only those UE profiles indicating that the UE is available for training a ML model (e.g. Availability = True). The one or more block addresses associated with the selected UE profiles are then obtained.
[0077] In Step 2c., the PDL AF sends a ML Model Client Selection Request, including the obtained block address(es) to a PDL node.
[0078] The PDL Node then fetches the one or more UE IDs associated with the obtained block address(es) (Step 2d.), and sends a ML Model Client Selection Response including the fetched UE IDs to the FL Server (optionally via the PDL AF).
[0079] The desired UE capabilities may also be included in the ML Model Client Selection Request sent to the PDL node. This allows for the PDL node to fetch only the IDs of UEs having the desired capabilities even if one or more blocks of the PDL contain information of UEs having different capabilities for training a ML model.
[0080] Training Request Phase
[0081] In a third phase of the procedure (the “Training Request Phase”), as shown in Steps 3a.-3c., requests to train a ML model are sent to selected UE Clients.
[0082] In Step 3a., the FL Server selects one or more UE Clients to be used to train a ML model, based on the list of UE IDs received in step 2e.
[0083] The FL Server then sends a ML Model Training Request to each of the selected UE IDs. The ML Model Training Request includes at least an identifier of the ML model tobe trained. In some examples, registered UE Clients may already store the ML model locally. In which case, the ML Model Training Request may also include identifiers of the current (initial) model parameters. Alternatively, the ML Model Training Request may include ML model information including at least one of: (i) the ML model, (ii) a download address from which the ML model may be downloaded, and (iii) model parameters (e.g. weights) of the ML model. In another example, the ML Model Training Request may include one or more block addresses of the ML model identifier or the ML model information as stored in a PDL. In some examples, the ML Model Training Request may be sent to the selected UE IDs via a Network Exposure Lunction (NEP).
[0084] Upon receiving a ML Model Training Request, each UE Client may perform local training of the ML model, including the generation of updated model parameters for the model. The UE Client may then return the updated model / parameters to the FL Server, either directly or via the PDL AF. Alternatively, if a UE FL Client is not available, it will reject the request with a ML Model Training Rejection (e.g. indicating: Availability = False).
[0085] Alternatively, as shown in Steps 4a. -4d., the FL Server may send the ML Model Training Request to the PDL AF. The PDL AF may then authenticate and authorize the FL Server, before sending a ML Training Request to each of the UEs IDs in the list. In this example, the PDL AF may store the UE IDs fetched in the Selection Phase (e.g. for use in selecting UE Clients based on a ML Model Training Request received from the FL Server (Step 4b.) and sending a ML Model Training Request to the selected UE IDs (Step 4c.).
[0086] Following ML Model training, the trained version of the ML model or the updated ML model parameters may be provided to the FL Server, for the FL Server to update a global ML model (e.g. based on the trained model parameters from a plurality of UEs).
[0087] The use of a PDL as described herein allows for the UE profile information to be stored in a secure and integrity-protected manner, and since access to the ledger is permissioned, entities such as the FL Server and the UE Clients need to be authenticated and authorized by the PDL AF in order to access the network.. The distribution of the profde information within the PDL network also allows for optimized access by participating entities. For example, the nodes of the PDL network could be widely distributed geographically.
[0088] Application to 5G
[0089] As described above, the architectures and methods as described herein may be particularly advantageous for use in future (e.g. 6G) networks. However, the present solution can also be used to support PDL-based FL in the context of 5G Advanced functions.
[0090] For example, the Analytics Function FL Server can be an Application Data Analytics Enabler Server (ADAES) or an AIML Enablement Server. AD AES is a SEAL service, defined in TS 23.436, TS 23.434 in Rell8. The AIML Enablement Server is discussed in TR 23.700-82 in the Rell9 study on AIMLAPP in SA6.
[0091] The PDL AF can be mapped to the ML model repository function as discussed in SA6 (in TR 23.700-82) and this can be in certain deployments the A-ADRF as specified in TS 23.436 in the ADAE layer internal architecture. Application layer - Analytical Data Repository Function (A-ADRF) role is to store data / analytics in application layer as the ADRF is doing in SA2 NWDAF architecture.
[0092] The A-ADRF may need to be enhanced to support smart contracts, in other words to be PDL-enabled (part of the blockchain). In such deployment, smart contracts may be assumed to be pre-configured at the A-ADRF with certain rules. Smart contracts may be considered as a series of instructions written in code which works based on the IFTTT logic, aka the IF-THIS-THEN-THAT logic.)
[0093] The other PDL nodes of the PDL network may be 3rd party nodes (e.g. servers, platforms at edge / cloud), and can be VAL servers in certain implementations (e.g. at the vertical / enterprise premises). VAL servers are defined in TS 23.434.
[0094] Figure 400 illustrates an example of a UE 400 in accordance with aspects of the present disclosure. The UE 400 may include a processor 402, a memory 404, a controller 406, and a transceiver 408. The processor 402, the memory 404, the controller 406, or the transceiver 408, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.
[0095] The processor 402, the memory 404, the controller 406, or the transceiver 408, or various combinations or components thereof may be implemented in hardware (e.g., circuitry). The hardware may include a processor, a digital signal processor (DSP), anapplication-specific integrated circuit (ASIC), or other programmable logic device, or any combination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.
[0096] The processor 402 may include an intelligent hardware device (e.g., a general- purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof). In some implementations, the processor 402 may be configured to operate the memory 404. In some other implementations, the memory 404 may be integrated into the processor 402. The processor 402 may be configured to execute computer-readable instructions stored in the memory 404 to cause the UE 400 to perform various functions of the present disclosure.
[0097] The memory 404 may include volatile or non-volatile memory. The memory 404 may store computer-readable, computer-executable code including instructions when executed by the processor 402 cause the UE 400 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 404 or another type of memory. Computer-readable media includes both non- transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or specialpurpose computer.
[0098] In some implementations, the processor 402 and the memory 404 coupled with the processor 402 may be configured to cause the UE 400 to perform one or more of the functions described herein (e.g., executing, by the processor 402, instructions stored in the memory 404). For example, the processor 402 may support wireless communication at the UE 400 in accordance with examples as disclosed herein. The UE 400 may be configured to support a means for: sending, to a first network function, a registration request comprising profile information of the UE, said profile information indicating at least (i) an identifier and / or an address of the UE and (ii) one or more capabilities of, and / or an availability of, the UE for training a machine learning (ML) model; and receiving, from the first network function, a confirmation response comprising one or more block addresses of profile information associated with the UE as stored in a permissioned distributed ledger (PDL).
[0099] The controller 406 may manage input and output signals for the UE 400. The controller 406 may also manage peripherals not integrated into the UE 400. In some implementations, the controller 406 may utilize an operating system such as iOS®, ANDROID®, WINDOWS®, or other operating systems. In some implementations, the controller 406 may be implemented as part of the processor 402.
[0100] In some implementations, the UE 400 may include at least one transceiver 408. In some other implementations, the UE 400 may have more than one transceiver 408. The transceiver 408 may represent a wireless transceiver. The transceiver 408 may include one or more receiver chains 410, one or more transmitter chains 412, or a combination thereof.
[0101] A receiver chain 410 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 410 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 410 may include at least one amplifier (e.g., a low-noise amplifier (LNA)) configured to amplify the received signal. The receiver chain 410 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 410 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.
[0102] A transmitter chain 412 may be configured to generate and transmit signals (e.g., control information, data, packets). The transmitter chain 412 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmission over a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM). The transmitter chain 412 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 412 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.
[0103] Figure 5 illustrates an example of a processor 500 in accordance with aspects of the present disclosure. The processor 500 may be an example of a processor configured toperform various operations in accordance with examples as described herein. The processor 500 may include a controller 502 configured to perform various operations in accordance with examples as described herein. The processor 500 may optionally include at least one memory 504, which may be, for example, an L1 / L2 / L3 cache. Additionally, or alternatively, the processor 500 may optionally include one or more arithmetic-logic units (ALUs) 506. One or more of these components may be in electronic communication or otherwise coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces (e.g., buses).
[0104] The processor 500 may be a processor chipset and include a protocol stack (e.g., a software stack) executed by the processor chipset to perform various operations (e.g., receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) in accordance with examples as described herein. The processor chipset may include one or more cores, one or more caches (e.g., memory local to or included in the processor chipset (e.g., the processor 500) or other memory (e.g., random access memory (RAM), read-only memory (ROM), dynamic RAM (DRAM), synchronous dynamic RAM (SDRAM), static RAM (SRAM), ferroelectric RAM (FeRAM), magnetic RAM (MRAM), resistive RAM (RRAM), flash memory, phase change memory (PCM), and others).
[0105] The controller 502 may be configured to manage and coordinate various operations (e.g., signaling, receiving, obtaining, retrieving, transmitting, outputting, forwarding, storing, determining, identifying, accessing, writing, reading) of the processor 500 to cause the processor 500 to support various operations in accordance with examples as described herein. For example, the controller 502 may operate as a control unit of the processor 500, generating control signals that manage the operation of various components of the processor 500. These control signals include enabling or disabling functional units, selecting data paths, initiating memory access, and coordinating timing of operations.
[0106] The controller 502 may be configured to fetch (e.g., obtain, retrieve, receive) instructions from the memory 504 and determine subsequent instruct! on(s) to be executed to cause the processor 500 to support various operations in accordance with examples as described herein. The controller 502 may be configured to track memory address ofinstructions associated with the memory 504. The controller 502 may be configured to decode instructions to determine the operation to be performed and the operands involved. For example, the controller 502 may be configured to interpret the instruction and determine control signals to be output to other components of the processor 500 to cause the processor 500 to support various operations in accordance with examples as described herein. Additionally, or alternatively, the controller 502 may be configured to manage flow of data within the processor 500. The controller 502 may be configured to control transfer of data between registers, arithmetic logic units (ALUs), and other functional units of the processor 500.
[0107] The memory 504 may include one or more caches (e.g., memory local to or included in the processor 500 or other memory, such RAM, ROM, DRAM, SDRAM, SRAM, MRAM, flash memory, etc. In some implementations, the memory 504 may reside within or on a processor chipset (e.g., local to the processor 500). In some other implementations, the memory 504 may reside external to the processor chipset (e.g., remote to the processor 500).
[0108] The memory 504 may store computer-readable, computer-executable code including instructions that, when executed by the processor 500, cause the processor 500 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such as system memory or another type of memory. The controller 502 and / or the processor 500 may be configured to execute computer-readable instructions stored in the memory 504 to cause the processor 500 to perform various functions. For example, the processor 500 and / or the controller 502 may be coupled with or to the memory 504, the processor 500, the controller 502, and the memory 504 may be configured to perform various functions described herein. In some examples, the processor 500 may include multiple processors and the memory 504 may include multiple memories. One or more of the multiple processors may be coupled with one or more of the multiple memories, which may, individually or collectively, be configured to perform various functions herein.
[0109] The one or more ALUs 506 may be configured to support various operations in accordance with examples as described herein. In some implementations, the one or more ALUs 506 may reside within or on a processor chipset (e.g., the processor 500). In someother implementations, the one or more ALUs 506 may reside external to the processor chipset (e.g., the processor 500). One or more ALUs 506 may perform one or more computations such as addition, subtraction, multiplication, and division on data. For example, one or more ALUs 506 may receive input operands and an operation code, which determines an operation to be executed. One or more ALUs 506 be configured with a variety of logical and arithmetic circuits, including adders, subtractors, shifters, and logic gates, to process and manipulate the data according to the operation. Additionally, or alternatively, the one or more ALUs 506 may support logical operations such as AND, OR, exclusive-OR (XOR), not-OR (NOR), and not-AND (NAND), enabling the one or more ALUs 506 to handle conditional operations, comparisons, and bitwise operations.
[0110] The processor 500 may support wireless communication in accordance with examples as disclosed herein. The processor 500 may be configured to or operable to support a means for sending, to a first network function, a registration request comprising profile information of the UE, said profile information indicating at least (i) an identifier and / or an address of the UE and (ii) one or more capabilities of, and / or an availability of, the UE for training a machine learning (ML) model; and receiving, from the first network function, a confirmation response comprising one or more block addresses of profile information associated with the UE as stored in a permissioned distributed ledger (PDL).
[0111] Figure 6 illustrates an example of a NE 600 in accordance with aspects of the present disclosure. The NE 600 may include a processor 602, a memory 604, a controller 606, and a transceiver 608. The processor 602, the memory 604, the controller 606, or the transceiver 608, or various combinations thereof or various components thereof may be examples of means for performing various aspects of the present disclosure as described herein. These components may be coupled (e.g., operatively, communicatively, functionally, electronically, electrically) via one or more interfaces.
[0112] The processor 602, the memory 604, the controller 606, or the transceiver 608, or various combinations or components thereof may be implemented in hardware (e.g., circuitry). The hardware may include a processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), or other programmable logic device, or anycombination thereof configured as or otherwise supporting a means for performing the functions described in the present disclosure.
[0113] The processor 602 may include an intelligent hardware device (e.g., a general- purpose processor, a DSP, a CPU, an ASIC, an FPGA, or any combination thereof). In some implementations, the processor 602 may be configured to operate the memory 604. In some other implementations, the memory 604 may be integrated into the processor 602. The processor 602 may be configured to execute computer-readable instructions stored in the memory 604 to cause the NE 600 to perform various functions of the present disclosure.
[0114] The memory 604 may include volatile or non-volatile memory. The memory 604 may store computer-readable, computer-executable code including instructions when executed by the processor 602 cause the NE 600 to perform various functions described herein. The code may be stored in a non-transitory computer-readable medium such the memory 604 or another type of memory. Computer-readable media includes both non- transitory computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A non-transitory storage medium may be any available medium that may be accessed by a general-purpose or specialpurpose computer.
[0115] In some implementations, the processor 602 and the memory 604 coupled with the processor 602 may be configured to cause the NE 600 to perform one or more of the functions described herein (e.g., executing, by the processor 602, instructions stored in the memory 604). For example, the processor 602 may support wireless communication at the NE 600 in accordance with examples as disclosed herein. The NE 600 may be configured to support a means for: receiving from each of a plurality of first network functions associated with respective User Equipments (UEs), a registration request comprising UE profile information of the UE, said UE profile information indicating at least (i) a UE identifier and (ii) one or more capabilities of, and / or an availability of, the UE for training a machine learning (ML) model; authenticating and authorizing each of the first network functions; sending the UE profile information to a second network function; receiving, from the second network function, one or more confirmation responses comprising one or more block addresses of the UE profile information as stored in a permissioned distributed ledger (PDL);storing each of the one or more block addresses in a database in association with a respective profile of one or more corresponding UE(s); receiving from a third network function a ML client selection request, the ML client selection request including a ML Model Identifier and / or type and / or one or more desired UE capabilities; authenticating and authorizing the third network function; selecting one or more UE profiles from the database based on the ML client selection request, and obtaining the associated block address or addresses; fetching one or more UE identifiers from the second network function using the obtained block address or addresses; and sending to the third network function a ML client selection including the fetched UE identifiers.
[0116] The controller 606 may manage input and output signals for the NE 600. The controller 606 may also manage peripherals not integrated into the NE 600. In some implementations, the controller 606 may utilize an operating system such as iOS®, ANDROID®, WINDOWS®, or other operating systems. In some implementations, the controller 606 may be implemented as part of the processor 602.
[0117] In some implementations, the NE 600 may include at least one transceiver 608. In some other implementations, the NE 600 may have more than one transceiver 608. The transceiver 608 may represent a wireless transceiver. The transceiver 608 may include one or more receiver chains 610, one or more transmitter chains 612, or a combination thereof.
[0118] A receiver chain 610 may be configured to receive signals (e.g., control information, data, packets) over a wireless medium. For example, the receiver chain 610 may include one or more antennas for receive the signal over the air or wireless medium. The receiver chain 610 may include at least one amplifier (e.g., a low-noise amplifier (LNA)) configured to amplify the received signal. The receiver chain 610 may include at least one demodulator configured to demodulate the receive signal and obtain the transmitted data by reversing the modulation technique applied during transmission of the signal. The receiver chain 610 may include at least one decoder for decoding the processing the demodulated signal to receive the transmitted data.
[0119] A transmitter chain 612 may be configured to generate and transmit signals (e.g., control information, data, packets). The transmitter chain 612 may include at least one modulator for modulating data onto a carrier signal, preparing the signal for transmissionover a wireless medium. The at least one modulator may be configured to support one or more techniques such as amplitude modulation (AM), frequency modulation (FM), or digital modulation schemes like phase-shift keying (PSK) or quadrature amplitude modulation (QAM). The transmitter chain 612 may also include at least one power amplifier configured to amplify the modulated signal to an appropriate power level suitable for transmission over the wireless medium. The transmitter chain 612 may also include one or more antennas for transmitting the amplified signal into the air or wireless medium.
[0120] Figure 7 illustrates a flowchart of a method in accordance with aspects of the present disclosure. The operations of the method may be implemented by a NE as described herein. In some implementations, the NE may execute a set of instructions to control the function elements of the NE to perform the described functions.
[0121] At 702, the method may include receiving, from each of a plurality of first network functions associated with respective User Equipments (UEs), a plurality of registration requests comprising UE profile information. The operations of 702 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 702 may be performed by a NE as described with reference to Figure 6.
[0122] At 704, the method may include authenticating and authorizing each of the first network functions. The operations of 704 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 704 may be performed by a NE as described with reference to Figure 6.
[0123] At 706, the method may include sending the UE profile information to a second network function. The operations of 706 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 706 may be performed a NE as described with reference to Figure 6.
[0124] At 708, the method may include sending the UE profile information to a second network function. The operations of 708 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 708 may be performed a NE as described with reference to Figure 6.
[0125] At 710, the method may include sending the UE profile information to a second network function. The operations of 710 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 710 may be performed a NE as described with reference to Figure 6.
[0126] At 712, the method may include sending the UE profile information to a second network function. The operations of 712 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 712 may be performed a NE as described with reference to Figure 6.
[0127] At 714, the method may include sending the UE profile information to a second network function. The operations of 714 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 714 may be performed a NE as described with reference to Figure 6.
[0128] At 716, the method may include sending the UE profile information to a second network function. The operations of 716 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 716 may be performed a NE as described with reference to Figure 6.
[0129] At 718, the method may include sending the UE profile information to a second network function. The operations of 718 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 718 may be performed a NE as described with reference to Figure 6.
[0130] At 720, the method may include sending the UE profile information to a second network function. The operations of 720 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 720 may be performed a NE as described with reference to Figure 6.
[0131] Figure 8 illustrates a flowchart of a method in accordance with aspects of the present disclosure. The operations of the method may be implemented by a UE as described herein. In some implementations, the UE may execute a set of instructions to control the function elements of the UE to perform the described functions.
[0132] At 802, the method may include sending, to a first network function, a registration request comprising profile information of a User Equipment (UE), said profile information indicating at least (i) an identifier of the UE and (ii) one or more capabilities of, and / or an availability of, the UE for training a machine learning (ML) model. The operations of 802 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 802 may be performed by a UE as described with reference to Figure 4.
[0133] At 804, the method may include receiving, from the first network function, a confirmation response comprising one or more block addresses of profile information associated with the UE as stored in a permissioned distributed ledger (PDL). The operations of 804 may be performed in accordance with examples as described herein. In some implementations, aspects of the operations of 804 may be performed by a UE as described with reference to Figure 4.
[0134] It should be noted that the method described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.
[0135] It should be noted that the method described herein describes a possible implementation, and that the operations and the steps may be rearranged or otherwise modified and that other implementations are possible.
[0136] The description herein is provided to enable a person having ordinary skill in the art to make or use the disclosure. Various modifications to the disclosure will be apparent to a person having ordinary skill in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the disclosure is not limited to the examples and designs described herein but is to be accorded the broadest scope consistent with the principles and novel features disclosed herein.
Claims
CLAIMS1. A network entity comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the network entity to: receive from each of a plurality of first network functions associated with respective User Equipments (UEs), a registration request comprising UE profile information of the UE, said UE profile information indicating at least (i) a UE identifier and (ii) one or more capabilities of, and / or an availability of, the UE for training a machine learning (ML) model; authenticate and authorize each of the first network functions; send the UE profile information to a second network function; receive, from the second network function, one or more confirmation responses comprising one or more block addresses of the UE profile information as stored in a permissioned distributed ledger (PDL); store each of the one or more block addresses in a database in association with a respective profile of one or more corresponding UE(s); receive from a third network function a ML client selection request, the ML client selection request including a ML Model Identifier and / or type and / or one or more desired UE capabilities; authenticate and authorize the third network function; select one or more UE profiles from the database based on the ML client selection request, and obtain the associated block address or addresses; fetch one or more UE identifiers from the second network function using the obtained block address or addresses; and send to the third network function a ML client selection including the fetched UE identifiers.
2. The network entity of claim 1, wherein each UE profile in the database indicates at least one or more capabilities of, and / or an availability of, the corresponding UE(s) for training a ML model.
3. The network entity of claim 1 or claim 2, wherein the at least one processor is further configured to cause the network entity to: temporarily store the UE identifiers received in the registration requests from the first network functions, and optionally to delete said UE identifiers after sending the UE profile information to the second network function or after receiving the confirmation response from the second network function.
4. The network entity of any one preceding claim, wherein the at least one processor is configured to cause the network entity to: group the profile information received from the first network functions according to the capabilities of, and / or the availabilities of, the respective UEs for training a ML model; send each group of profile information in a respective request to the second network function; and receive, for each group, a respective confirmation response from the second network function comprising one or more block addresses of the group of profile information in the PDL.
5. The network entity of claim 5, wherein the selection request comprising the selected one or more block addresses further comprises the capabilities of, and / or the availabilities of, the corresponding UE(s) for training a ML model.
6. The network entity of any one preceding claim, wherein the second network function is associated with one of a plurality of nodes of a PDL network, and is configured to add the UE profile information to a blockchain block and distribute said block to the plurality of nodes of the PDL network.
7. The network entity of any one preceding claim, wherein the at least one processor is further configured to cause the network entity to: after receiving a confirmation response from the second network function comprising one or more block addresses of UE profde information in the PDL, send a confirmation response to one or more corresponding first network functions, optionally comprising said one or more block addresses.
8. The network entity of any one preceding claim, wherein the at least one processor is further configured to cause the network entity to: receive, from the third network function, a request to train a ML model, the request comprising (i) one or more UE identifiers and (ii) a ML model identifier and ML model parameters, or one or more block addresses of the ML model identifier and parameters as stored in a PDL; and send, to the first network functions associated with said one or more UE identifiers, a training request comprising the ML model identifier and parameters or the one or more block addresses of the ML model identifier and parameters in the PDL.
9. A method performed by a network entity, the method comprising: receiving from each of a plurality of first network functions associated with respective User Equipments (UEs), a registration request comprising UE profile information of the UE, said UE profile information indicating at least (i) a UE identifier and (ii) one or more capabilities of, and / or an availability of, the UE for training a machine learning (ML) model; authenticating and authorizing each of the first network functions; sending the UE profile information to a second network function; receiving, from the second network function, one or more confirmation responses comprising one or more block addresses of the UE profile information as stored in a permissioned distributed ledger (PDL); storing each of the one or more block addresses in a database in association with a respective profile of one or more corresponding UE(s);receiving from a third network function a ML client selection request, the ML client selection request including a ML Model Identifier and / or type and / or one or more desired UE capabilities; authenticating and authorizing the third network function; selecting one or more UE profiles from the database based on the ML client selection request, and obtaining the associated block address or addresses; fetching one or more UE identifiers from the second network function using the obtained block address or addresses; and sending to the third network function a ML client selection including the fetched UE identifiers.
10. The method of claim 9, wherein each UE profile in the database indicates at least one or more capabilities of, and / or an availability of, the corresponding UE(s) for training a ML model.
11. The method of claim 9 or claim 10, comprising: temporarily storing the UE identifiers received in the registration requests from the first network functions, and optionally deleting said UE identifiers after sending the UE profile information to the second network function or after receiving the confirmation response from the second network function.
12. The method of any one of claims 9 to 11, comprising: grouping the profile information received from the first network functions according to the capabilities of, and / or the availabilities of, the respective UEs for training a ML model; sending each group of profile information in a respective request to the second network function; and receiving, for each group, a respective confirmation response from the second network function comprising one or more block addresses of the group of profile information in the PDL.
13. The method of claim 12, wherein the selection request comprising the selected one or more block addresses further comprises the capabilities of, and / or the availabilities of, the corresponding UE(s) for training a ML model.
14. The method of any one of claims 9 to 13, wherein the second network function is associated with one of a plurality of nodes of a PDL network, and is configured to add the UE profile information to a blockchain block and distribute said block to the plurality of nodes of the PDL network.
15. The method of any one of claims 9 to 14, further comprising: after receiving a confirmation response from the second network function comprising one or more block addresses of UE profile information in the PDL, sending a confirmation response to one or more corresponding first network functions, optionally comprising said one or more block addresses.
16. The method of any one of claims 9 to 15, further comprising: receiving, from the third network function, a request to train a ML model, the request comprising (i) one or more UE identifiers and (ii) a ML model identifier and ML model parameters, or one or more block addresses of the ML model identifier and parameters as stored in a PDL; and sending, to the first network functions associated with said one or more UE identifiers, a training request comprising the ML model identifier and parameters or the one or more block addresses of the ML model identifier and parameters in the PDL.
17. A User Equipment (UE), comprising: at least one memory; and at least one processor coupled with the at least one memory and configured to cause the UE to: send, to a first network function, a registration request comprising profile information of the UE, said profile information indicating at least (i) an identifier of the UE and(ii) one or more capabilities of, and / or an availability of, the UE for training a machine learning (ML) model; and receive, from the first network function, a confirmation response comprising one or more block addresses of profde information associated with the UE as stored in a permissioned distributed ledger (PDL).
18. The UE of claim 17, wherein processor is further configured to cause the UE to: receive, from a second network function, a request to train a ML model; and perform training of the ML model using local data so as to produce a trained version of the ML model.
19. A processor, comprising: at least one memory; and at least one controller coupled with the at least one memory and configured to cause the processor to: send, to a first network function, a registration request comprising profile information of User Equipment (UE), said profile information indicating at least (i) an identifier of the UE and (ii) one or more capabilities of, and / or an availability of, the UE for training a machine learning (ML) model; and receive, from the first network function, a confirmation response comprising one or more block addresses of profile information associated with the UE as stored in a permissioned distributed ledger (PDL).
20. The processor of claim 19, wherein processor is further configured to cause the UE to: receive, from a second network function, a request to train a ML model; and perform training of the ML model using local data so as to produce a trained version of the ML model.
Citation Information
Patent Citations
Methods, architectures, apparatuses and systems for decentralized data control and access management
WO2023212051A1
Authorization and authentication of machine learning model transfer
WO2023215720A1
Methods, architectures, apparatuses and systems enabling artificial intelligence applications in networks
WO2024006178A1
