Method for discovery and signaling processes for network-assisted clustering federated learning

Abstract

Signaling procedures are provided that allow UEs to be formed into clusters via network assistance and perform ML model training in a clustered (FL) environment. The UE provides a first message including the FL information to the network node. The UE also provides a second message indicating the network node. The UE obtains, based on the FL information, a third message indicating the network node or a different network node as an FL cluster leader and indicating an FL cluster of the UE. Accordingly, ML model training may be implemented in a distributed manner using clustered FLs while minimizing or avoiding bottlenecks, communication overhead, challenges brought to model training due to computing resources, training data, training tasks, or heterogeneity of associated ML models, security and privacy challenges, or other limitations associated with conventional FLs.

Description

Background Art Technical Field

[0001] The present disclosure generally relates to communication systems, and more particularly, to a wireless communication system between a user equipment (UE) and a network entity such as a base station (BS) or a road side unit (RSU) for cluster federated learning.

[0002] introduction

[0003] Wireless communication systems are widely deployed to provide a variety of telecommunication services, such as telephony, video, data, messaging, and broadcast. Typical wireless communication systems may employ multiple access technologies capable of supporting communication with multiple users by sharing available system resources. Examples of such multiple access technologies include code division multiple access (CDMA) systems, time division multiple access (TDMA) systems, frequency division multiple access (FDMA) systems, orthogonal frequency division multiple access (OFDMA) systems, single carrier frequency division multiple access (SC-FDMA) systems, and time division synchronous code division multiple access (TD-SCDMA) systems.

[0004] These multiple access technologies have been adopted in various telecommunication standards to provide a common protocol that enables different wireless devices to communicate at a city, country, region, or even global level. An example telecommunication standard is 5G New Radio (NR). 5G NR is part of the continued mobile broadband evolution promulgated by the Third Generation Partnership Project (3GPP) to meet new requirements associated with latency, reliability, security, scalability (e.g., with the Internet of Things (IoT)) and other requirements. 5G NR includes services associated with enhanced mobile broadband (eMBB), massive machine type communications (mMTC), and ultra-reliable low latency communications (URLLC). Certain aspects of 5G NR may be based on the 4G Long Term Evolution (LTE) standard. Further improvements to 5G NR technology are needed. In addition, these improvements may also be applicable to other multiple access technologies and telecommunication standards that employ these technologies.

[0005] For example, some aspects of wireless communication include direct communication between devices, such as device-to-device (D2D), vehicle-to-everything (V2X), etc. There is a need to further improve such direct communication between devices. Improvements related to direct communication between devices may also be applicable to other multiple access technologies and telecommunication standards that employ these technologies. Summary of the invention

[0006] The following presents a simplified summary of one or more aspects in order to provide a basic understanding of these aspects. This summary is not an extensive overview of all contemplated aspects, and is neither intended to identify key or important elements of all aspects, nor to describe the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to a more detailed description presented later.

[0007] Federated learning (FL) refers to a machine learning technique in which multiple distributed nodes that hold local data samples can train a global machine learning (ML) model (e.g., a classifier or other model applied by multiple network nodes) without exchanging the data samples themselves between the nodes to perform the training. However, conventional FL architectures rely on a centralized server to create, aggregate, and refine global ML models for participating nodes, thus requiring that locally trained ML models be sent from participating nodes to the server during FL iterations. This centralized approach to FL can have various disadvantages or limitations, including bottlenecks from single points of failure, significant communication overhead, challenges to model training due to heterogeneity in computing resources, training data, training tasks, or associated ML models, and security and privacy challenges.

[0008] To address these limitations associated with conventional FL architectures, a clustering or hierarchical approach may be applied to FL, where learning nodes that target common learning task work are grouped together into clusters served by a cluster leader. Cluster formation and leader selection are network-assisted (e.g., via messages that identify clusters and confirm cluster leaders that circulate within the network). The designated cluster leader of the cluster (rather than the FL parameter server) directly coordinates learning tasks (including local ML model training and updates within the cluster). After the cluster is formed, the FL parameter server may coordinate learning tasks (including global ML model training and updates between clusters). Thus, the cluster leader may act as an intermediary between the learning nodes and the FL parameter server for coordinating neural network training and optimization between different clusters. Thus, clustered FL may be used to implement neural network training in a distributed manner with minimal bottlenecks, minimal communication overhead, minimal challenges to model training due to heterogeneity of computing resources, training data, training tasks, or associated ML models, and minimal security and privacy challenges that may arise in conventional FL. Thus, aspects of the present disclosure provide various examples of signaling processes between network nodes for implementing clustered FL.

[0009] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may be a UE. The apparatus includes a processor and a memory coupled to the processor. The processor is configured to: provide a first message including federated learning (FL) information; provide a second message indicating a first network node; and obtain, in response to the FL information, a third message indicating one of the first network node or the second network node as a FL cluster leader and indicating a FL cluster of the apparatus.

[0010] In one aspect of the present disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may be a roadside unit (RSU) or a base station. The apparatus includes a processor and a memory coupled to the processor. The processor is configured to: obtain a first message including FL information of a first network node; and provide a second message indicating a FL cluster of the first network node in response to the FL information, wherein the second message indicates one of the apparatus or the second network node as a FL cluster leader of the FL cluster.

[0011] To achieve the foregoing and related ends, one or more aspects include the features fully described below and particularly pointed out in the claims. The following description and the accompanying drawings set forth in detail some illustrative features of one or more aspects. However, these features are merely indicative of some of the various ways in which the principles of the various aspects may be employed, and this specification is intended to include all such aspects and their equivalents. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 is a diagram illustrating an example of a wireless communication system and an access network.

[0013] Figure 2A is a diagram illustrating an example of a first frame according to various aspects of the present disclosure.

[0014] Figure 2B is a diagram illustrating an example of DL channels within a subframe according to various aspects of the present disclosure.

[0015] Figure 2C is a diagram illustrating an example of a second frame according to various aspects of the present disclosure.

[0016] Figure 2D is a diagram illustrating an example of UL channels within a subframe according to various aspects of the present disclosure.

[0017] Figure 3 Example aspects of a sidelink slot structure are illustrated.

[0018] Figure 4 is a diagram illustrating an example of a first device and a second device involved in wireless communication (eg, in an access network).

[0019] Figure 5 is a conceptual diagram of an example open radio access network architecture.

[0020] Figure 6 is a diagram illustrating an example of a neural network.

[0021] Figure 7 is a diagram illustrating an example of the FL architecture.

[0022] Fig. 8A and Figure 8B is a diagram illustrating examples of FL architecture in different applications.

[0023] Fig. 9 is a diagram illustrating an example of a clustered FL architecture.

[0024] Fig.10 is a diagram illustrating an example of a signaling process for network-assisted cluster formation and leader selection.

[0025] Fig.11 is a diagram illustrating another example of a signaling procedure for network-assisted cluster formation and leader selection.

[0026] Fig.12 is a diagram illustrating an example of a signaling procedure for FL within a cluster after a leader node is selected.

[0027] Fig.13 is a diagram illustrating an example of a signaling procedure for inter-cluster FL after one or more iterations of intra-cluster FL.

[0028] Fig.14 is a flow chart of a method of performing wireless communication at a UE.

[0029] FIG. 15A to FIG. 15B is a flow chart of a method of wireless communication at a network node (eg, a roadside unit or an edge server) or a FL parameter network entity (eg, a base station).

[0030] Fig.16 is a diagram illustrating an example of a hardware implementation of an example apparatus.

[0031] Fig.17 is a diagram illustrating another example of a hardware implementation for another example apparatus. DETAILED DESCRIPTION

[0032] The specific embodiments described below in conjunction with the accompanying drawings are intended as descriptions of various configurations and are not intended to represent the only configurations with which the concepts described herein can be practiced. In order to provide a thorough understanding of the various concepts, the specific embodiments include specific details. However, it is apparent to those skilled in the art that these concepts can be practiced without these specific details. In some instances, well-known structures and components are shown in block diagram form to avoid blurring these concepts.

[0033] Federated learning (FL) refers to a machine learning technique in which multiple distributed nodes that hold local data samples can train a global machine learning (ML) model (e.g., a classifier or other model applied by multiple network nodes) without exchanging the data samples themselves between the nodes to perform the training. The FL framework includes multiple network nodes or entities, namely a centralized aggregation server and participating FL devices (i.e., participants or nodes such as UEs). The FL framework enables FL devices to learn a global ML model by allowing messages to be passed between devices through a central aggregation server or coordinator, which can be configured to communicate with various FL devices and coordinate the learning framework. Nodes in the FL environment can process their own data sets and perform local updates to the global ML model, and the central server can aggregate the local updates and provide the updated global ML model to the nodes for further training or prediction.

[0034] However, conventional FL architectures rely on a centralized server to create, aggregate, and refine global ML models for participating nodes, and therefore require that locally trained ML models be sent from participating nodes to the server during FL iterations. This centralized approach to FL may have various disadvantages and limitations. In one example, since the centralized server is the only aggregator of participating nodes, the centralized server may act as a single point of failure for the FL system. Therefore, if the centralized server stops operating at any time, a bottleneck may occur in the entire FL process. In another example, since participants transmit their local model updates to the centralized server, significant communication overhead may occur in applications where the amount of ML model information exceeds the raw data itself. In other examples, statistical challenges may arise in model training due to the heterogeneity of computing resources that exist for different participants, the heterogeneity of training data available for participants, and the heterogeneity of training tasks and associated models configured for different participants. In another example, even if the raw data is not directly communicated between nodes in FL, security and privacy issues may still arise from the exchange of ML model parameters (e.g., due to the leakage of information about the underlying data samples).

[0035] To address these limitations associated with conventional FL architectures, a clustering or hierarchical approach may be applied to FL, where learning nodes that target common learning task work are grouped together into clusters. In one example, an FL parameter server (e.g., a base station) may group network nodes (e.g., UEs) together into clusters led by a designated cluster leader (e.g., a roadside unit, an edge server, or other network node). In another example, a network node (e.g., a roadside unit) may form and lead a cluster with other network nodes (e.g., UEs) by itself without the involvement of a base station. In either example, cluster formation and leader selection are network-assisted (e.g., via messages that identify clusters and confirm cluster leaders that circulate within the network). The designated cluster leader of the cluster (rather than the FL parameter server) directly coordinates learning tasks (including local ML model training and updates within the cluster). This coordination is referred to as intra-cluster FL. After the cluster is formed, the FL parameter server may coordinate learning tasks (including global ML model training and updates between clusters). This coordination is referred to as inter-cluster FL. Thus, the cluster leader may act as an intermediary between learning nodes and FL parameter servers for coordinating neural network training and optimization between different clusters. Therefore, clustered FL can be used to implement neural network training in a distributed manner with minimal bottlenecks, minimal communication overhead, minimal challenges in model training due to heterogeneity of computing resources, training data, training tasks, or associated ML models, and minimal security and privacy challenges that may arise in conventional FL.

[0036] Various examples of signaling procedures between network nodes (e.g., UEs, roadside units, and base stations) are provided to implement clustered FL. In one example, a signaling procedure for cluster formation and leader selection is provided, wherein nodes participating in an ML training task are grouped together into clusters, wherein other nodes are led by a selected cluster leader (ML model weight aggregator) of the corresponding cluster based on configured criteria (in the case of network participation). In another example, a signaling procedure for cluster formation and leader selection is provided, wherein nodes participating in an ML training task may join a cluster led by other nodes in response to corresponding requests from other nodes. In one example, after cluster formation and leader selection are completed, a signaling procedure for clustered FL training may be provided, wherein nodes may perform intra-FL training coordinated by a cluster leader within a corresponding cluster by learning messages passed between the nodes and the cluster leader. In another example, after cluster formation and leader selection are completed, a signaling procedure for clustered FL training may be provided, wherein nodes may perform inter-FL training coordinated by a FL parameter server across different clusters by exchanging messages between the corresponding cluster leader and the FL parameter server. The aforementioned examples of signaling procedures are applicable to downlink / uplink communications (through the Uu interface) between a UE and a network entity such as a base station or a roadside unit.

[0037] Several aspects of telecommunication systems will now be presented with reference to various apparatus and methods. These apparatus and methods will be described in the following detailed description and illustrated in the accompanying drawings by various blocks, components, circuits, processes, algorithms, etc. (collectively referred to as "elements"). These elements may be implemented using electronic hardware, computer software, or any combination thereof. Whether such elements are implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system.

[0038] As an example, an element, or any part of an element, or any combination of elements can be implemented as a "processing system", which includes one or more processors. The example of a processor includes a microprocessor, a microcontroller, a graphics processing unit (GPU), a central processing unit (CPU), an application processor, a digital signal processor (DSP), a reduced instruction set computing (RISC) processor, a system on a chip (SoC), a baseband processor, a field programmable gate array (FPGA), a programmable logic device (PLD), a state machine, a gate logic piece, a discrete hardware circuit and other suitable hardware configured to perform various functionalities described throughout the present disclosure. One or more processors in a processing system can execute software. Whether it is referred to as software, firmware, middleware, microcode, hardware description language or other names, software should be widely interpreted as meaning instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software components, applications, software applications, software packages, routines, subroutines, objects, executable files, threads of execution, processes, functions, etc.

[0039] Therefore, in one or more example embodiments, the described functions can be implemented with hardware, software or any combination thereof. If implemented with software, the functions can be stored or encoded on a computer-readable medium as one or more instructions or codes. Computer-readable media include computer storage media. Storage media can be any available medium that can be accessed by a computer. By way of example and not limitation, such computer-readable media can include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage device, magnetic disk storage device, other magnetic storage devices, a combination of computer-readable media of the above type, or any other medium that can be used to store computer executable code in the form of instructions or data structures that can be accessed by a computer.

[0040] Figure 11 is a diagram illustrating an example of a wireless communication system and an access network 100. The wireless communication system (also referred to as a wireless wide area network (WWAN)) includes a base station (BS) 102, a user equipment (UE) 104, an evolved packet core (EPC) 160, and another core network 190 (e.g., a 5G core (5GC)). The base station 102 may include a macro cell (a high-power cellular base station) and / or a small cell (a low-power cellular base station). A macro cell includes a base station. A small cell includes a femto cell, a pico cell, and a micro cell.

[0041] The base station 102 configured for 4G Long Term Evolution (LTE) (collectively referred to as Evolved Universal Mobile Telecommunications System (UMTS) Terrestrial Radio Access Network (E-UTRAN)) can interface with the EPC 160 via a first backhaul link 132 (e.g., an S1 interface). The base station 102 configured for 5G New Radio (NR) (collectively referred to as Next Generation RAN (NG-RAN)) can interface with the core network 190 via a second backhaul link 184. Among other functions, the base station 102 can also perform one or more of the following functions: delivery of user data, radio channel encryption and decryption, integrity protection, header compression, mobility control functions (e.g., handover, dual connectivity), inter-cell interference coordination, connection establishment and release, load balancing, distribution of non-access stratum (NAS) messages, NAS node selection, synchronization, radio access network (RAN) sharing, multimedia broadcast multicast service (MBMS), subscriber and equipment tracking, RAN information management (RIM), paging, positioning, and delivery of warning messages. The base stations 102 may communicate with each other directly or indirectly (eg, via the EPC 160 or the core network 190) via the third backhaul link 134 (eg, an X2 interface). The first backhaul link 132, the second backhaul link 184, and the third backhaul link 134 may be wired or wireless.

[0042] Base station 102 can communicate wirelessly with UE 104. Each of base stations 102 can provide communication coverage for a corresponding geographic coverage area 110. There may be overlapping geographic coverage areas 110. For example, a small cell 102' may have a coverage area 110' that overlaps with the coverage area 110 of one or more macro base stations 102. A network including both small cells and macro cells may be referred to as a heterogeneous network. A heterogeneous network may also include a home evolved Node B (eNB) (HeNB), which may provide services to a restricted group referred to as a closed subscriber group (CSG). A communication link 120 between base station 102 and UE 104 may include an uplink (UL) (also referred to as a reverse link) transmission from UE 104 to base station 102 and / or a downlink (DL) (also referred to as a forward link) transmission from base station 102 to UE 104. The communication link 120 may use multiple input multiple output (MIMO) antenna technology, including spatial multiplexing, beamforming and / or transmit diversity. The communication link may be through one or more carriers. For each carrier allocated in the carrier aggregation for up to a total of up to Yx MHz (x component carriers) for transmission in each direction, the base station 102 / UE 104 can use a spectrum with a bandwidth of up to Y megahertz (MHz) (e.g., 5 MHz, 10 MHz, 15 MHz, 20 MHz, 100 MHz, 400 MHz, etc.). The carriers may or may not be adjacent to each other. The allocation of carriers may be asymmetric with respect to DL and UL (e.g., more or fewer carriers may be allocated for DL ​​compared to UL). The component carrier may include a primary component carrier and one or more secondary component carriers. The primary component carrier may be referred to as a primary cell (PCell) and the secondary component carrier may be referred to as a secondary cell (SCell).

[0043] UE 104 can communicate with each other using device-to-device (D2D) communication link 158. D2D communication link 158 can use DL / UL WWAN spectrum. D2D communication link 158 can use one or more side link channels, such as physical side link broadcast channel (PSBCH), physical side link discovery channel (PSDCH), physical side link shared channel (PSSCH) and physical side link control channel (PSCCH). D2D communication can be through various wireless D2D communication systems, such as, for example, WiMedia, Bluetooth, ZigBee, Wi-Fi based on Institute of Electrical and Electronics Engineers (IEEE) 802.11 standard, LTE or NR.

[0044] The wireless communication system may also include a Wi-Fi access point (AP) 150 that communicates with a Wi-Fi station (STA) 152 via a communication link 154 in, for example, a 5 gigahertz (GHz) unlicensed spectrum. When communicating in the unlicensed spectrum, the STA 152 / AP 150 may perform a clear channel assessment (CCA) to determine whether a channel is available prior to communication.

[0045] The small cell 102' may operate in licensed and / or unlicensed spectrum. When operating in an unlicensed spectrum, the small cell 102' may employ NR and use the same unlicensed spectrum (e.g., 5 GHz, etc.) as used by the Wi-Fi AP 150. The small cell 102' employing NR in the unlicensed spectrum may improve the coverage of the access network and / or increase the capacity of the access network.

[0046] The electromagnetic spectrum is typically subdivided into various categories, bands, channels, etc. based on frequency / wavelength. In 5G NR, two initial operating bands have been identified as frequency range designations FR1 (410 MHz-7.125 GHz) and FR2 (24.25 GHz-52.6 GHz). Frequencies between FR1 and FR2 are typically referred to as mid-band frequencies. Although a portion of FR1 is greater than 6 GHz, FR1 is typically (interchangeably) referred to as the “sub-6 GHz” band in various documents and articles. A similar naming issue sometimes occurs with respect to FR2, which is typically (interchangeably) referred to as the “millimeter wave” band in documents and articles, despite being different from the extremely high frequency (EHF) band (30 GHz–300 GHz) identified as the “millimeter wave” band by the International Telecommunication Union (ITU).

[0047] In view of the above aspects, unless otherwise specifically stated, it should be understood that if the term "below 6 GHz" or the like is used in this document, it can be broadly referred to as a frequency that can be less than 6 GHz, can be within FR1, or can include mid-band frequencies. In addition, unless otherwise specifically stated, it should be understood that if the term "millimeter wave" or the like is used in this document, it can be broadly referred to as a frequency that can include mid-band frequencies, can be within FR2, or can be within the EHF band.

[0048] The base station 102, whether a small cell 102' or a large cell (e.g., a macro base station), may include and / or be referred to as an eNB, a gNodeB (gNB), or another type of base station. Some base stations, such as gNB 180, may operate in the traditional sub-6 GHz spectrum, in millimeter wave frequencies, and / or near millimeter wave frequencies to communicate with the UE 104. When the gNB 180 operates in millimeter wave or near millimeter wave frequencies, the gNB 180 may be referred to as a millimeter wave base station. The millimeter wave base station 180 may utilize beamforming 182 with the UE 104 to compensate for path loss and short range. The base station 180 and the UE 104 may each include multiple antennas, such as antenna elements, antenna panels, and / or antenna arrays, to facilitate beamforming.

[0049] The base station 180 may transmit beamformed signals to the UE 104 in one or more transmit directions 182'. UE 104 may receive beamformed signals from base station 180 in one or more receive directions 182″. UE 104 may also send beamformed signals to base station 180 in one or more transmit directions. Base station 180 may receive beamformed signals from UE 104 in one or more receive directions. Base station 180 / UE 104 may perform beam training to determine the best receive direction and transmit direction for each of base station 180 / UE 104. The transmit direction and receive direction of base station 180 may or may not be the same. The transmit direction and receive direction of UE 104 may or may not be the same. Although the beamformed signals are shown as being between UE 104 and base station 102 / 180, UE 104 or RSU 107 may also similarly apply aspects of beamforming to communicate with another UE 104 or RSU 107 (such as based on V2X, V2V, or D2D communication).

[0050] The EPC 160 may include a mobility management entity (MME) 162, other MMEs 164, a serving gateway 166, an MBMS gateway 168, a broadcast multicast service center (BM-SC) 170, and a packet data network (PDN) gateway 172. The MME 162 may communicate with a home subscriber server (HSS) 174. The MME 162 is a control node that handles signaling between the UE 104 and the EPC 160. Typically, the MME 162 provides bearer and connection management. All user Internet Protocol (IP) packets are passed through the serving gateway 166, which itself is connected to the PDN gateway 172. The PDN gateway 172 provides UE IP address allocation and other functions. The PDN gateway 172 and the BM-SC 170 are connected to IP services 176. The IP services 176 may include the Internet, an intranet, an IP multimedia subsystem (IMS), a PS streaming service, and / or other IP services. The BM-SC 170 may provide functions for MBMS user service configuration and delivery. BM-SC 170 may serve as an entry point for content provider MBMS delivery, may be used to authorize and initiate MBMS bearer services in a public land mobile network (PLMN), and may be used to schedule MBMS delivery. MBMS gateway 168 may be used to distribute MBMS services to base stations 102 belonging to a multicast broadcast single frequency network (MBSFN) area of ​​a broadcast specific service, and may be responsible for session management (start / stop) and for collecting eMBMS related billing information.

[0051] The core network 190 may include an access and mobility management function (AMF) 192, other AMFs 193, a session management function (SMF) 194, and a user plane function (UPF) 195. The AMF 192 may communicate with a unified data management (UDM) 196. The AMF 192 is a control node that handles signaling between the UE 104 and the core network 190. Typically, the AMF 192 provides quality of service (QoS) flows and session management. All user IP packets are delivered through the UPF 195. The UPF 195 provides UE IP address allocation and other functions. The UPF 195 is connected to an IP service 197. The IP service 197 may include the Internet, an intranet, an IMS, a packet switching (PS) streaming media service, and / or other IP services.

[0052] Base stations may include and / or be referred to as gNBs, Node Bs, eNBs, access points, base transceivers, radio base stations, radio transceivers, transceiver functions, basic service sets (BSSs), extended service sets (ESSs), transmit receive points (TRPs), or some other suitable terminology. Base stations 102 provide access points to EPC 160 or core network 190 for UEs 104. Examples of UEs 104 include cellular phones, smart phones, session initiation protocol (SIP) phones, laptops, personal digital assistants (PDAs), satellite radios, global positioning systems, multimedia devices, video devices, digital audio players (e.g., MP3 players), cameras, game consoles, tablets, smart devices, wearable devices, vehicles, electric meters, gas pumps, large or small kitchen appliances, healthcare devices, implants, sensors / actuators, displays, or any other similarly functional devices. Some of the UEs 104 may be referred to as IoT devices (e.g., parking meters, gas pumps, toasters, vehicles, heart monitors, etc.). UE 104 may also be referred to as a station, a mobile station, a subscriber station, a mobile unit, a subscriber unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wireless communication device, a remote device, a mobile subscriber station, an access terminal, a mobile terminal, a wireless terminal, a remote terminal, a handset, a user agent, a mobile client, a client, or some other suitable terminology.

[0053] The deployment of a communication system (such as a 5G NR system) can be arranged in a variety of ways using various components or constituent parts. In a 5G NR system or network (NW), a network node, a network entity, a mobility element of a network, a RAN node, a core network node, a network element, or a network equipment (such as a BS, or one or more units (or one or more components) that perform base station functionality can be implemented in an aggregated or decomposed architecture. For example, a BS (such as a Node B (NB), an eNB, an NR BS, a 5G NB, an access point (AP), a TRP, or a cell, etc.) can be implemented as an aggregated base station (also called an independent BS or a monolithic BS) or a decomposed base station.

[0054] The aggregated base station may be configured to utilize a radio protocol stack physically or logically integrated within a single RAN node. The decomposed base station 181 may be configured to utilize a protocol stack physically or logically distributed between two or more units, such as one or more central units (CUs), one or more distributed units (DUs), or one or more radio units (RUs). In some aspects, the CU 183 may be implemented within a RAN node, and one or more DUs 185 may be co-located with the CU, or alternatively, may be geographically or virtually distributed in one or more other RAN nodes. The DU may be implemented to communicate with one or more RUs 187. Each of the CU, DU, and RU may also be implemented as a virtual unit, i.e., a virtual central unit (VCU), a virtual distributed unit (VDU), or a virtual radio unit (VRU).

[0055] Base station type operations or network designs may take into account the aggregated nature of base station functionality. For example, a disaggregated base station may be used in an integrated access backhaul (IAB) network, an open radio access network (O-RAN (network configurations such as those initiated by the O-RAN Alliance)), or a virtualized radio access network (vRAN, also known as a cloud radio access network (C-RAN)). Decomposition may include distributing functionality across two or more units at various physical locations, as well as virtually distributing functionality of at least one unit, which may enable flexibility in network design. Individual units of a disaggregated base station or disaggregated RAN architecture may be configured for wired or wireless communication with at least one other unit.

[0056] Some wireless communication networks may include vehicle-based communication devices that may communicate from vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I) (e.g., from a vehicle-based communication device to a road infrastructure node, such as a roadside unit (RSU)), vehicle-to-network (V2N) (e.g., from a vehicle-based communication device to one or more network nodes, such as a base station), and / or a combination thereof and / or communicate with other devices, which communications may be collectively referred to as vehicle-to-everything (V2X) communications. Again, referring to Figure 1 In some aspects, a UE 104 (e.g., a transmitting vehicle user equipment (VUE) or other UE) may be configured to send a message directly to another UE 104. The communication may be based on V2V / V2X / V2I or other D2D communications, such as proximity services (ProSe), etc. Communications based on V2V, V2X, V2I and / or D2D may also be sent and received by other transmitting and receiving devices (such as a roadside unit (RSU) 107, etc.). Aspects of the communication may be based on PC5 or sidelink communications, for example, as combined with Figure 3 as described in the examples.

[0057] Reference again Figure 1 In some aspects, the UE 104 may include a clustering FL UE component 198. The clustering FL UE component 198 is configured to provide a first message including FL information, provide a second message indicating a first network node, and obtain a third message indicating one of the first network node or the second network node as a FL cluster leader and indicating a FL cluster of the UE in response to the FL information. The UE 104 including the clustering FL UE component 198 may be a transmitting device in uplink or sidelink communication, such as a VUE, an IoT device, or other UE, or a receiving device in downlink or sidelink communication, such as another VUE, another IoT device, or other UE. The first network node and the second network node may be an RSU 107, an edge server, or other node in communication with the base station 102 / 180.

[0058] Still reference Figure 1 , a first network node (e.g., RSU 107 or base station 102 / 180) may include a clustering FL NW component 199. The clustering FL NW component 199 is configured to obtain a first message including FL information of a second network node, and to provide a second message indicating a FL cluster of the second network node in response to the FL information. The second message indicates one of the first network node or the third network node as a FL cluster leader of the FL cluster. The RSU 107 including the clustering FL NW component 199 may be a transmitting device in uplink or sidelink communication, or a receiving device in downlink or sidelink communication. The base station 102 / 180 including the clustering FL NW component 199 may be a transmitting device in downlink communication, or a receiving device in uplink communication. The second network node may be a UE (e.g., UE 104), and the third network node may be an RSU, an edge server, or other node communicating with the base station 102 / 180.

[0059] The concepts and various aspects described herein may be applicable to vehicle-to-everything (V2X) or other similar fields, such as D2D communication, IoT communication, industrial IoT (IIoT) communication, and / or other standards / protocols for communication in wireless / access networks. Additionally or alternatively, the concepts and various aspects described herein may be applicable to vehicle-to-pedestrian (V2P) communication, pedestrian-to-vehicle (P2V) communication, vehicle-to-infrastructure (V2I) communication, and / or other frameworks / models for communication in wireless / access networks. In addition, the concepts and various aspects described herein may be applicable to NR or other similar fields, such as LTE, Advanced LTE (LTE-A), Code Division Multiple Access (CDMA), Global System for Mobile Communications (GSM), or other wireless / radio access technologies. In addition, the concepts and various aspects described herein may be applicable to use in aggregated or decomposed base station architectures such as open radio access network (O-RAN) architectures.

[0060] Figure 2A FIG200 is a diagram illustrating an example of a first subframe within a 5G NR frame structure. Figure 2B FIG230 is a diagram illustrating an example of DL channels within a 5G NR subframe. Figure 2C FIG250 is a diagram illustrating an example of a second subframe within a 5G NR frame structure. Figure 2D FIG280 is a diagram illustrating an example of an UL channel within a 5G NR subframe. The 5G NR frame structure may be frequency division duplex (FDD) (wherein for a particular set of subcarriers (carrier system bandwidth), a subframe within the subcarrier set is dedicated to either DL or UL), or may be time division duplex (TDD) (wherein for a particular set of subcarriers (carrier system bandwidth), a subframe within the subcarrier set is dedicated to both DL and UL). Figure 2A , Figure 2C In the example provided, the 5G NR frame structure is assumed to be TDD, where subframe 4 is configured with slot format 28 (most of which are DL), where D is DL, U is UL, and F is flexible between DL / UL, and subframe 3 is configured with slot format 34 (most of which are UL). Although subframes 3 and 4 are shown as having slot formats 34 and 28, respectively, any particular subframe may be configured with any of the various available slot formats 0-61. Slot formats 0 and 1 are both DL and both UL, respectively. Other slot formats 2-61 include a mix of DL, UL, and flexible symbols. The slot format is configured for the UE via a received slot format indicator (SFI) (dynamically configured via DL control information (DCI) or semi-statically / statically configured via radio resource control (RRC) signaling). Note that the following description also applies to the 5G NR frame structure as TDD.

[0061] Other wireless communication technologies may have different frame structures and / or different channels. For example, a 10 millisecond (ms) frame may be divided into 10 equally sized subframes (1 ms). Each subframe may include one or more time slots. A subframe may also include a microslot, which may include 7, 4, or 2 symbols. Each time slot may include 7 or 14 symbols, depending on the time slot configuration. For time slot configuration 0, each time slot may include 14 symbols, and for time slot configuration 1, each time slot may include 7 symbols. The symbol on the DL may be a cyclic prefix (CP) orthogonal frequency division multiplexing (OFDM) (CP-OFDM) symbol. The symbol on the UL may be a CP-OFDM symbol (for high throughput scenarios) or a discrete Fourier transform (DFT) spread OFDM (DFT-s-OFDM) symbol (also known as a single carrier frequency division multiple access (SC-FDMA) symbol) (for power-limited scenarios; limited to single-stream transmission). The number of time slots in a subframe is based on the time slot configuration and parameter set (numerology). For slot configuration 0, different parameter sets μ0 to 4 allow 1, 2, 4, 8, and 16 slots per subframe, respectively. For slot configuration 1, different parameter sets 0 to 2 allow 2, 4, and 8 slots per subframe, respectively. Accordingly, for slot configuration 0 and parameter set μ, there are 14 symbols per slot and 2 per subframe. μ time slots. The subcarrier spacing and symbol length / duration are functions of the parameter set. The subcarrier spacing can be equal to 2 μ *15 kilohertz (kHz), where μ is parameter set 0 to 4. Therefore, the subcarrier spacing for parameter set μ=0 is 15 kHz, and the subcarrier spacing for parameter set μ=4 is 240 kHz. The symbol length / duration is inversely related to the subcarrier spacing. FIG. 2A to FIG. 2D An example is provided for slot configuration 0 with 14 symbols per slot and parameter set μ=2 with 4 slots per subframe. The slot duration is 0.25 ms, the subcarrier spacing is 60 kHz, and the symbol duration is approximately 16.67 μs. Within a frame set, there may be one or more different bandwidth parts (BWPs) that are frequency-division multiplexed (see Figure 2B ). Each BWP can have a specific set of parameters.

[0062] A resource grid may be used to represent the frame structure. Each slot includes a resource block (RB) (also referred to as a physical RB (PRB)) extending over 12 consecutive subcarriers. The resource grid is divided into a plurality of resource elements (REs). The number of bits carried by each RE depends on the modulation scheme.

[0063] like Figure 2AAs illustrated, some of the REs carry reference (pilot) signals (RS) for the UE. The RS may include a demodulation RS (DM-RS) for channel estimation at the UE (indicated as R for a particular configuration). x , where 100x is the port number, but other DM-RS configurations are possible) and a channel state information reference signal (CSI-RS). RS may also include a beam measurement RS (BRS), a beam refinement RS (BRRS), and a phase tracking RS (PT-RS).

[0064] Figure 2B Examples of various DL channels within a subframe of a frame are illustrated. The physical downlink control channel (PDCCH) carries DCI within one or more control channel elements (CCEs), each CCE including nine RE groups (REGs), each REG including four consecutive REs in an OFDM symbol. The PDCCH within a BWP may be referred to as a control resource set (CORESET). Additional BWPs may be located at higher and / or lower frequencies on the channel bandwidth. The primary synchronization signal (PSS) may be within symbol 2 of a specific subframe of a frame. The PSS is used by UE 104 to determine subframe / symbol timing and physical layer identification. The secondary synchronization signal (SSS) may be within symbol 4 of a specific subframe of a frame. The SSS is used by the UE to determine the physical layer cell identification group number and radio frame timing. Based on the physical layer identification and the physical layer cell identification group number, the UE may determine the physical cell identifier (PCI). Based on the PCI, the UE may determine the position of the aforementioned DM-RS. The physical broadcast channel (PBCH) carrying the master information block (MIB) can be logically grouped with the PSS and SSS to form a synchronization signal (SS) / PBCH block (also referred to as an SS block (SSB)). The MIB provides the system frame number (SFN) and the number of RBs in the system bandwidth. The physical downlink shared channel (PDSCH) carries user data, broadcast system information not sent over the PBCH such as the system information block (SIB), and paging messages.

[0065] like Figure 2CAs illustrated, some of the REs carry DM-RS (indicated as R for a particular configuration, but other DM-RS configurations are possible) for channel estimation at the base station. The UE may send a DM-RS for a physical uplink control channel (PUCCH) and a DM-RS for a physical uplink shared channel (PUSCH). The PUSCH DM-RS may be sent in the first or first two symbols of the PUSCH. Depending on whether a short PUCCH or a long PUCCH is sent and depending on the specific PUCCH format used, the PUCCH DM-RS may be sent in different configurations. The UE may send a sounding reference signal (SRS). The SRS may be sent in the last symbol of a subframe. The SRS may have a comb structure, and the UE may send the SRS on one of the teeth of the comb. The SRS may be used by the base station for channel quality estimation to achieve frequency-dependent scheduling of the UL.

[0066] Figure 2D Examples of various UL channels within a subframe of a frame are illustrated. The PUCCH may be located at a position as indicated in one configuration. The PUCCH carries uplink control information (UCI), such as scheduling requests, channel quality indicator (CQI), precoding matrix indicator (PMI), rank indicator (RI), and hybrid automatic repeat request (HARQ) acknowledgement (ACK) / negative acknowledgement (NACK) feedback. The PUSCH carries data and may additionally be used to carry a buffer status report (BSR), a power headroom report (PHR), and / or UCI.

[0067] Figure 3Example diagrams 300 and 310 are illustrated, which illustrate example time slot structures that can be used for wireless communication (e.g., for sidelink communication) between UE 104 and UE 104'. The time slot structure can be within a 5G / NR frame structure. Although the following description may focus on 5G NR, the concepts described herein may be applicable to other similar fields, such as LTE, LTE-A, CDMA, GSM, and other wireless technologies. This is just an example, and other wireless communication technologies may have different frame structures and / or different channels. A frame (10ms) can be divided into 10 subframes of the same size (1ms). Each subframe may include one or more time slots. A subframe may also include a microslot, which may include, for example, 7, 4, or 2 symbols. Each time slot may include 7 or 14 symbols, depending on the time slot configuration. For time slot configuration 0, each time slot may include 14 symbols, and for time slot configuration 1, each time slot may include 7 symbols. Diagram 300 illustrates a single time slot transmission, which may correspond to a 0.5 ms transmission time interval (TTI), for example. Diagram 310 illustrates an example double time slot aggregation, for example, an aggregation of two 0.5 ms TTIs. Diagram 300 illustrates a single RB, while diagram 310 illustrates N RBs. In diagram 310, the 10 RBs used for control are only an example. The number of RBs may be different.

[0068] A resource grid may be used to represent the frame structure. Each time slot may include a resource block (RB) (also called a physical RB (PRB)) extending over 12 consecutive subcarriers. The resource grid is divided into a number of resource elements (REs). The number of bits carried by each RE depends on the modulation scheme. Figure 3 As illustrated, some of the REs may include control information, eg, along with a demodulation RS (DMRS). Figure 3 It is also illustrated that the symbol may include CSI-RS. Figure 3The symbol indicated for DMRS or CSI-RS in indicates that the symbol includes DMRS or CSI-RS RE. Such symbols may also include REs containing data. For example, if the number of ports of DMRS or CSI-RS is 1 and the comb-2 pattern is used for DMRS / CSI-RS, half of the REs may include the RS, and the other half of the REs may include data. CSI-RS resources may start at any symbol in the time slot and may occupy 1, 2, or 4 symbols, depending on the number of configured ports. CSI-RS may be periodic, semi-persistent, or aperiodic (e.g., based on DCI triggering). For time / frequency tracking, CSI-RS may be periodic or aperiodic. CSI-RS may be sent in bursts of two or four symbols spread across one or two time slots. Control information may include sidelink control information (SCI). As described herein, at least one symbol may be used for feedback. Symbols before and / or after feedback may be used for transitions between receiving data and sending feedback. Although symbol 12 is illustrated for data, the symbol may be a gap symbol to enable a transition to feedback in symbol 13. Another symbol (e.g., at the end of a time slot) may be used as a gap. The gap enables the device to switch from operating as a transmitting device to preparing to operate as a receiving device, e.g., in a subsequent time slot. As illustrated, data may be sent in the remaining REs. The data may include data messages as described herein. The location of any of the SCI, feedback, and LBT symbols may be different from Figure 3 The examples shown are different. Multiple time slots can be aggregated together. Figure 3 An example aggregation of two time slots is also illustrated. The aggregated number of time slots may also be greater than two. When time slots are aggregated, the symbols and / or slot symbols used for feedback may be different from the symbols and / or slot symbols used for feedback of a single time slot. Although feedback is not illustrated for this aggregation example, symbols in a multi-slot aggregation may also be allocated for feedback, as illustrated in the one time slot example.

[0069] Figure 4 4 is a block diagram of a first wireless communication device 410 communicating with a second wireless communication device 450, for example, via V2V / V2X / D2D communication or in an access network. The device 410 may include a transmitting device that communicates with a receiving device (e.g., device 450) via a side link (e.g., V2V / V2X / D2D) communication or an uplink / downlink communication. The transmitting device 410 may include a UE, a base station, an RSU, etc. The receiving device may include a UE, a base station, an RSU, etc.

[0070] The IP packets from EPC 160 may be provided to controller / processor 475. Controller / processor 475 implements layer 3 and layer 2 functionality. Layer 3 includes a radio resource control (RRC) layer, and layer 2 includes a service data adaptation protocol (SDAP) layer, a packet data convergence protocol (PDCP) layer, a radio link control (RLC) layer, and a medium access control (MAC) layer. The controller / processor 475 provides RRC layer functionality associated with broadcasting of system information (e.g., MIB, SIB), RRC connection control (e.g., RRC connection paging, RRC connection establishment, RRC connection modification, and RRC connection release), inter-radio access technology (RAT) mobility, and measurement configuration for UE measurement reporting; PDCP layer functionality associated with header compression / decompression, security (encryption, decryption, integrity protection, integrity verification), and handover support functions; RLC layer functionality associated with delivery of upper layer packet data units (PDUs), error correction through ARQ, concatenation, segmentation and reassembly of RLC service data units (SDUs), re-segmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto transport blocks (TBs), demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.

[0071] The transmit (TX) processor 416 and the receive (RX) processor 470 implement layer 1 functionality associated with various signal processing functions. Layer 1 (which includes the physical (PHY) layer) may include error detection on the transmission channel, forward error correction (FEC) decoding / decoding of the transmission channel, interleaving, rate matching, mapping to the physical channel, modulation / demodulation of the physical channel, and MIMO antenna processing. The TX processor 416 processes the mapping to the signal constellation based on various modulation schemes (e.g., binary phase shift keying (BPSK), quadrature phase shift keying (QPSK), M-order phase shift keying (M-PSK), M-order quadrature amplitude modulation (M-QAM)). The decoded and modulated symbols can then be divided into parallel streams. Subsequently, each stream can be mapped to an OFDM subcarrier, multiplexed with a reference signal (e.g., a pilot) in the time domain and / or frequency domain, and then combined using an inverse fast Fourier transform (IFFT) to produce a physical channel carrying a time domain OFDM symbol stream. The OFDM stream is spatially pre-decoded to generate multiple spatial streams. Channel estimates from channel estimator 474 can be used to determine the coding and modulation schemes, as well as for spatial processing. Channel estimates can be derived from reference signals and / or channel condition feedback sent by device 450. Each spatial stream can then be provided to a different antenna 420 via a separate transmitter 418TX. Each transmitter 418TX can modulate an RF carrier with a corresponding spatial stream for transmission.

[0072] At the device 450, each receiver 454RX receives a signal through its corresponding antenna 452. Each receiver 454RX recovers the information modulated onto the RF carrier and provides the information to a receive (RX) processor 456. The TX processor 468 and the RX processor 456 implement layer 1 functionality associated with various signal processing functions. The RX processor 456 can perform spatial processing on the information to recover any spatial stream destined for the device 450. If multiple spatial streams are destined for the device 450, the RX processor 456 can combine them into a single OFDM symbol stream. The RX processor 456 then converts the OFDM symbol stream from the time domain to the frequency domain using a fast Fourier transform (FFT). The frequency domain signal includes a separate OFDM symbol stream for each subcarrier of the OFDM signal. By determining the most likely signal constellation point sent by the device 410, the symbols on each subcarrier and the reference signal are recovered and demodulated. These soft decisions can be based on channel estimates calculated by the channel estimator 458. The soft decisions are then decoded and deinterleaved to recover the data and control signals originally sent on the physical channel by device 410. The data and control signals are then provided to controller / processor 459, which implements layer 3 and layer 2 functionality.

[0073] The controller / processor 459 may be associated with a memory 460 that stores program codes and data. The memory 460 may be referred to as a computer readable medium. The controller / processor 459 provides demultiplexing between transport channels and logical channels, packet reassembly, decryption, header decompression, and control signal processing to recover IP packets from the EPC 160. The controller / processor 459 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operations.

[0074] Similar to the functionality described in conjunction with DL transmissions performed by device 410, the controller / processor 459 provides RRC layer functionality associated with system information (e.g., MIB, SIB) acquisition, RRC connection, and measurement reporting; PDCP layer functionality associated with header compression / decompression and security (encryption, decryption, integrity protection, integrity verification); RLC layer functionality associated with delivery of upper layer PDUs, error correction through ARQ, concatenation, segmentation and reassembly of RLC SDUs, resegmentation of RLC data PDUs, and reordering of RLC data PDUs; and MAC layer functionality associated with mapping between logical channels and transport channels, multiplexing of MAC SDUs onto TBs, demultiplexing of MAC SDUs from TBs, scheduling information reporting, error correction through HARQ, priority handling, and logical channel prioritization.

[0075] Channel estimates derived by the channel estimator 458 from a reference signal or feedback transmitted by the device 410 may be used by the TX processor 468 to select appropriate coding and modulation schemes, and to facilitate spatial processing. The spatial streams generated by the TX processor 468 may be provided to different antennas 452 via corresponding transmitters 454TX. Each transmitter 454TX may modulate an RF carrier with a corresponding spatial stream for transmission.

[0076] Transmissions are processed at device 410 in a manner similar to that described in conjunction with the receiver functionality at device 450. Each receiver 418RX receives a signal through its respective antenna 420. Each receiver 418RX recovers information modulated onto an RF carrier and provides the information to a RX processor 470.

[0077] The controller / processor 475 may be associated with a memory 476 that stores program codes and data. The memory 476 may be referred to as a computer readable medium. The controller / processor 475 provides demultiplexing between transport channels and logical channels, packet reassembly, decryption, header decompression, control signal processing to recover IP packets from the device 450. The IP packets from the controller / processor 475 may be provided to the EPC 160. The controller / processor 475 is also responsible for error detection using ACK and / or NACK protocols to support HARQ operations.

[0078] At least one of the TX processors 416, 468, the RX processors 456, 470, and the controller / processors 459, 475 may be configured to combine Figure 1 For example, the controller / processor 459, 475 may include a clustered FL UE component 498 configured to provide a first message including FL information, provide a second message indicating a first network node, and obtain a third message indicating one of the first network node or the second network node as a FL cluster leader and indicating a FL cluster of the UE in response to the FL information.

[0079] In one example, the clustered FL UE component 498 of the controller / processor 475 in the device 410 may provide a first message to the device 450 via the TX processor 416, which may transmit the first message to the device 450 via the antenna 420. The clustered FL UE component 498 of the controller / processor 475 in the device 410 may provide a second message to the device 450 via the TX processor 416, which may transmit the second message to the device 450 via the antenna 420. The clustered FL UE component 498 of the controller / processor 475 in the device 410 may obtain a third message from the device 450 via the RX processor 470, which may receive the third message from the device 450 via the antenna 420.

[0080] In another example, the clustered FL UE component 498 of the controller / processor 459 in the device 450 may provide a first message to the device 410 via the TX processor 468, which may transmit the first message to the device 410 via the antenna 452. The clustered FL component 498 of the controller / processor 459 in the device 450 may provide a second message to the device 410 via the TX processor 468, which may transmit the second message to the device 410 via the antenna 452. The clustered FL component 498 of the controller / processor 459 in the device 450 may obtain a third message from the device 410 via the RX processor 456, which may receive the third message from the device 410 via the antenna 452.

[0081] In addition, at least one of the TX processors 416, 468, the RX processors 456, 470, and the controller / processors 459, 475 may be configured to combine Figure 1For example, the controller / processor 459, 475 may include a clustered FL NW component 499 configured to obtain a first message including FL information of a second network node, and provide a second message indicating a FL cluster of the second network node in response to the FL information, wherein the second message indicates one of the first network node or the third network node as a FL cluster leader of the FL cluster.

[0082] In one example, the clustered FL NW component 499 of the controller / processor 475 in the device 410 may obtain the first message from the device 450 via the RX processor 470, which may obtain the first message from the device 450 via the antenna 420. The clustered FL UE component 498 of the controller / processor 475 in the device 410 may provide the second message to the device 450 via the TX processor 416, which may send the second message to the device 450 via the antenna 420.

[0083] In another example, the clustered FL NW component 499 of the controller / processor 459 in the device 450 may obtain a first message from the device 410 via the RX processor 456, which may receive the first message from the device 410 via the antenna 452. The clustered FL NW component 499 of the controller / processor 459 in the device 450 may provide a second message to the device 410 via the TX processor 468, which may send the second message to the device 410 via the antenna 452.

[0084] Figure 5 1 shows a diagram illustrating an example decomposed base station 500 architecture. The decomposed base station 500 architecture may include one or more CUs 510 (e.g., Figure 1 CU 183), the one or more CUs can communicate directly with the core network 520 via a backhaul link, or indirectly with the core network 520 through one or more decomposed base station units (such as a near real-time RIC 525 via an E2 link, or a non-real-time RIC 515 associated with a service management and orchestration (SMO) framework 505, or both). CU 510 can communicate with one or more DU 530 (e.g., Figure 1 DU 530 can communicate with one or more RU 540 (e.g., Figure 1 RU 187) for communication. RU 540 can communicate with UE 104 via one or more radio frequency (RF) access links. In some specific implementations, UE 104 can be served by multiple RU 540 simultaneously.

[0085] Each of the units (i.e., CU 510, DU 530, RU 540, and near-RT RIC 525, non-RT RIC 515, and SMO framework 505) may include or be coupled to one or more interfaces configured to receive or send signals, data, or information (collectively referred to as signals) via a wired or wireless transmission medium. Each of the units or an associated processor or controller that provides instructions to the communication interface of these units may be configured to communicate with one or more of the other units via a transmission medium. For example, the unit may include a wired interface configured to receive or send signals to one or more of the other units on a wired transmission medium. Additionally, these units may include a wireless interface that may include a receiver, a transmitter, or a transceiver (such as a radio frequency (RF) transceiver) that is configured to receive or send signals, or both, to one or more of the other units on a wireless transmission medium.

[0086] In some aspects, the CU 510 may host higher-layer control functions. Such control functions may include radio resource control (RRC), packet data convergence protocol (PDCP), service data adaptation protocol (SDAP), etc. Each control function may be implemented using an interface that is configured to communicate signals with other control functions hosted by the CU 510. The CU 510 may be configured to handle user plane functionality (i.e., central unit-user plane (CU-UP)), control plane functionality (i.e., central unit-control plane (CU-CP)), or a combination thereof. In some specific implementations, the CU 510 may be logically split into one or more CU-UP units and one or more CU-CP units. When implemented in an O-RAN configuration, the CU-UP unit may communicate bidirectionally with the CU-CP unit via an interface (such as an E1 interface). As needed, the CU 510 may be implemented to communicate with the DU 530 for network control and signaling.

[0087] DU 530 may correspond to a logical unit that includes one or more base station functions for controlling the operation of one or more RU 540. In some aspects, DU 530 may host one or more of a radio link control (RLC) layer, a medium access control (MAC) layer, and one or more high physical (PHY) layers (such as modules for forward error correction (FEC) encoding and decoding, scrambling, modulation and demodulation, etc.) depending at least in part on functional divisions such as those defined by the 3rd Generation Partnership Project (3GPP). In some aspects, DU 530 may also host one or more low PHY layers. Each layer (or module) may be implemented using an interface that is configured to communicate signals with other layers (and modules) hosted by DU 530 or with control functions hosted by CU 510.

[0088] The lower layer functionality may be implemented by one or more RUs 540. In some deployments, a RU 540 controlled by a DU 530 may correspond to a logical node that hosts RF processing functions or low PHY layer functions (such as performing Fast Fourier Transform (FFT), Inverse FFT (iFFT), digital beamforming, physical random access channel (PRACH) extraction and filtering, etc.), or both, based at least in part on a functional split (such as a lower layer functional split). In such an architecture, the RU 540 may be implemented to handle over-the-air (OTA) communications with one or more UEs 120. In some implementations, real-time and non-real-time aspects of control plane and user plane communications with the RU 540 may be controlled by the corresponding DU 530. In some scenarios, this configuration may enable the implementation of the DU 530 and the CU 510 in a cloud-based RAN architecture (such as a vRAN architecture).

[0089] The SMO framework 505 may be configured to support RAN deployment and provisioning of non-virtualized network elements and virtualized network elements. For non-virtualized network elements, the SMO framework 505 may be configured to support the deployment of dedicated physical resources for RAN coverage requirements, which may be managed via an operation and maintenance interface (such as an O1 interface). For virtualized network elements, the SMO framework 505 may be configured to interact with a cloud computing platform (such as an open cloud (O-Cloud) 590) to perform network element lifecycle management (such as to instantiate virtualized network elements) via a cloud computing platform interface (such as an O2 interface). Such virtualized network elements may include, but are not limited to, CU 510, DU 530, RU 540, and near-RT RIC 525. In some specific implementations, the SMO framework 505 may communicate with hardware aspects of the 4G RAN (such as an open eNB (O-eNB) 511) via the O1 interface. Additionally, in some specific implementations, the SMO framework 505 may communicate directly with one or more RUs 540 via the O1 interface. The SMO framework 505 may also include a non-RT RIC 515 configured to support the functionality of the SMO framework 505 .

[0090] The non-RT RIC 515 may be configured to include logic functions that enable non-real-time control and optimization of RAN elements and resources, artificial intelligence / machine learning (AI / ML) workflows including model training and updating, or policy-based guidance of applications / features in the near-RT RIC 525. The non-RT RIC 515 may be coupled to or communicate with the near-RT RIC 525 (such as via an A1 interface). The near-RT RIC 525 may be configured to include logic functions that enable near-real-time control and optimization of RAN elements and resources via data collection and actions through an interface (such as via an E2 interface) that connects one or more CUs 510, one or more DUs 530, or both, and the O-eNB with the near-RT RIC 525.

[0091] In some implementations, in order to generate an AI / ML model to be deployed in the near-RT RIC 525, the non-RT RIC 515 may receive parameters or external enrichment information from an external server. Such information may be utilized by the near-RT RIC 525 and may be received from a non-network data source or from a network function at the SMO framework 505 or the non-RT RIC 515. In some examples, the non-RT RIC 515 or the near-RT RIC 525 may be configured to tune RAN behavior or performance. For example, the non-RT RIC 515 may monitor long-term trends and patterns of performance and employ AI / ML models to perform corrective actions through the SMO framework 505 (such as via reconfiguration of O1) or via creation of RAN management policies (such as A1 policies).

[0092] UE 104, RSU 107, base station 102 / 180 including aggregated and decomposed base station 181, or other network nodes including at least controller / processor 459, 475 of device 410, 450 may be configured to perform AI / ML tasks using artificial neural network (ANN). ANN (or simply neural network) is a computational learning system that uses a functional network to understand and convert data input in one form into a desired output, usually in another form. Examples of ANN include multilayer perceptron (MLP), convolutional neural network (CNN), deep neural network (DNN), deep convolutional network (DCN) and recurrent neural network (RNN), among others. Generally speaking, ANN includes a layered architecture in which the output of one layer of neurons is input to a second layer of neurons (via connections or synapses), the output of the second layer of neurons becomes the input of the third layer of neurons, and so on. These neural networks can be trained to recognize hierarchical structures of features, and are therefore increasingly used in object recognition applications. For example, a neural network can be used for supervised learning tasks such as classification (which combines ML models such as logistic regression, support vector machines, boosting or other classifiers) to perform object detection and provide bounding boxes for categories or classes in an image. In addition, backpropagation or gradient descent can be used to fine-tune these multi-layer architectures to produce more accurate predictions.

[0093] Figure 6An example of a neural network 600 (specifically, a CNN) is illustrated. The CNN may be designed to detect objects sensed from a camera 602 (e.g., an onboard camera) or other sensor. The neural network 600 may initially receive an input 604, such as an image, such as a speed limit sign (or other object or size) of size 32×32 pixels. During a forward pass, the input image is initially passed through a convolutional layer 606 including a plurality of convolutional kernels (e.g., six kernels of size 5×5 pixels or some other amount or size) that slide over the image to detect basic patterns or features, such as straight edges and corners. The images output from the convolutional layer 606 (e.g., six images of size 28×28 pixels or some other amount or size) are passed through an activation function (e.g., a rectified linear unit (ReLU)) and then passed as input into a subsampling layer 608, which scales down the size of the image, for example, by a factor of two (e.g., producing six images of size 14×14 pixels or some other amount or size). These scaled-down images output from the subsampling layer 608 may similarly be passed through an activation function (e.g., ReLU or other function) and similarly passed as input through subsequent convolutional layers, subsampling layers, and activation functions (not shown) to detect more complex features and further scale down the image or kernel size. These outputs are ultimately passed as input to a fully connected layer 610, where each node output from the previous layer is connected to all neurons in the current layer. The output from this layer may similarly be passed through an activation function and potentially as input through one or more other fully connected layers (not shown). Thereafter, the output is passed as input to an output layer 612, which converts the input into an output 614 such as a probability distribution (e.g., using a softmax function). The probability distribution may include a vector of confidence levels or probability estimates that the input image depicts a predicted feature (such as a sign or speed limit value (or other object)).

[0094] During training, ML models (e.g., classifiers) with weights 616 and biases 618 are initially created for different layers of the neural network 600, respectively. For example, when the input from a training image (or other source) enters a given layer of an MLP or CNN, the dot product of the input and weights summed with the biases may be transformed using an activation function before being passed to the next layer. The probability estimates generated from the final output layer may then be applied to a loss function that measures the accuracy of the ANN, such as a cross entropy loss function. Initially, the output of the loss function may be quite large, indicating that the predicted value is far from the true or actual value. In order to reduce the value of the loss function and produce more accurate predictions, gradient descent may be applied.

[0095] In gradient descent, the gradient of the loss function may be calculated with respect to each weight of the ANN using back propagation, where the gradient is calculated for the last layer back to the first layer of the neural network 600. The gradient may then be used to update each weight to reduce the loss function with respect to that weight until a global minimization of the loss function is obtained, for example using stochastic gradient descent. For example, after each weight adjustment, subsequent iterations of the above training process may be performed using the same or new training images, and if the loss function is still large (even if it has been reduced), back propagation may be applied again to identify the gradient of the loss function with respect to each weight. The weights may be updated again, and the process may continue to be repeated until the difference between the predicted and actual values ​​is minimized.

[0096] A network node such as a UE or a base station may use federated learning (FL) to train a neural network (e.g., neural network 600). FL refers to a machine learning technique in which multiple distributed nodes storing local data samples may train a global ML model (e.g., a classifier or other model applied by multiple network nodes) without exchanging the data samples themselves between the nodes to perform the training. Therefore, compared to centralized machine learning techniques that typically upload all local data sets to one server, this approach allows the generation of high-quality ML models without aggregating distributed data. Therefore, FL facilitates parallel processing, significantly reduces the costs associated with message exchange, and protects data privacy.

[0097] The FL framework includes multiple network nodes or entities, namely a centralized aggregation server and participating FL devices (i.e., participants or nodes such as UEs). The FL framework enables FL devices to learn a global ML model by allowing messages to be passed between devices through a central aggregation server or coordinator, which can be configured to communicate with various FL devices and coordinate the learning framework. For example, nodes can provide weights, biases, gradients, or other ML information to each other (other nodes) through messages exchanged between nodes via a central coordinator (e.g., base station, RSU, edge server, etc.).

[0098] Each node in the FL environment uses a dataset to locally train and update a coordinated global ML model. The dataset can be a local dataset that a node or device can obtain for a certain ML task (e.g., object detection, etc.). The data in a given dataset can be preloaded or accumulated over the life of the device. For example, an accumulated dataset may include recorded data that a node observes from an onboard sensor such as a camera and stores locally at the device. The global ML model can be defined by its model architecture and model weights. An example of a model architecture is a neural network, such as Figure 6The CNN described herein may include multiple hidden layers, multiple neurons per layer, and synapses connecting these neurons together. Model weights are applied to data passed through the various layers of the ML model for processing by the various neurons. Each node in the FL environment may process its own data set and perform local updates to the global ML model, and the central server may aggregate the local updates and provide the updated global ML model to the nodes for further training or prediction.

[0099] Figure 7 An example 700 of a FL architecture is illustrated. Initially, the FL parameter server 702 determines the task requirements and target application (e.g., detecting vehicles, pedestrians, or other objects for self-driving applications). After this determination, the FL parameter server initializes a global ML model 704 (W0 G ) (e.g., with random or default ML weights such as Figure 6 t) and broadcasts the global ML model 704 to participating devices or learning nodes 706 (e.g., UEs). After receiving the global ML model at the learning node, the iterative process of FL can begin. For example, after receiving the global ML model 704 (W at a given iteration t), the global ML model 704 is broadcasted to participating devices or learning nodes 706 (e.g., UEs). t G ), the learning node 706 (k nodes) locally trains its corresponding model 708 using its internal local data set, which can be a preconfigured data set such as a training set and / or sensory data from the environment. After training, the learning node updates its corresponding k-th model W t k (e.g., local weights) until the kth loss function or cost function F for the model is achieved k (W t k ) is minimized or optimized. At this time, due to different update weights, the learning nodes may have different local models W t k .

[0100] Afterwards, the learning node 706 updates its locally updated model W t k The FL parameter server 702 aggregates the corresponding weights of the corresponding models 708 upon receipt (e.g., by averaging the weights or performing some other calculation on the weights). The FL parameter server 702 may thus generate an updated global model W including the aggregated weights. t+1 G , after which the aforementioned process may be repeated for subsequent iteration t+1. For example, the FL parameter server 702 may update the global model W t+1 GThe training and local update are broadcasted to the learning nodes 706 to perform training and local update again based on the same data set or a different local data set, after which the nodes can again share their corresponding updated models to the FL parameter server for subsequent aggregation and global model update. This process can continue to repeat in further iterations and result in an update of the global model W. t G Further update of the global model loss function F G (W t G ) is minimized, or until a predetermined number of iterations has been reached.

[0101] Fig. 8A and Figure 8B Examples 800, 850 of different applications associated with wirelessly connected devices that may benefit from FL are illustrated, including connected vehicles for autonomous driving ( Fig. 8A ) and mobile robots for manufacturing ( Figure 8B ). For example, in Fig. 8A In example 800, a network node 802 (e.g., such as a sensor such as a camera, light detection and ranging (LIDAR), or radio detection and ranging (RADAR) is provided. Figure 7 The VUE of the learning node 706 in the example may communicate with the FL parameter server 804 (e.g., a base station or RSU) to collaboratively train and enhance the accuracy of the neural network 806 for detecting objects and object bounding boxes (OBBs) in conjunction with autonomous driving. Figure 8B In example 850, a network node 852 (e.g., such as a Figure 7 The mobile robot UE of the learning node 706 in the can communicate with the FL parameter server 854 (e.g., a base station) at mmW frequency to collaboratively train the neural network 856 (e.g., a base station) associated with the manufacturing-related tasks.

[0102] However, conventional FL architectures rely on centralized servers (e.g., FL parameter servers 702, 804, 854) to create, aggregate, and refine global ML models for participating nodes, and therefore require that locally trained ML model information be sent from participating nodes to the server during FL iterations. This centralized approach to FL may have various disadvantages and limitations. In one example, since the centralized server is the only aggregator of participating nodes, the centralized server may act as a single point of failure for the FL system. Therefore, if the centralized server stops operating at any time, a bottleneck may occur in the entire FL process. In another example, since participants transmit their local model updates to the centralized server, significant communication overhead may occur in applications where the amount of ML model information exceeds the raw data itself. In other examples, statistical challenges may arise in model training due to the heterogeneity of computing resources that exist for different participants, the heterogeneity of training data available to participants, and the heterogeneity of training tasks and associated models configured for different participants. In another example, even if the raw data is not directly communicated between nodes in FL, security and privacy issues may still arise from the exchange of ML model parameters (e.g., due to the leakage of information about the underlying data samples).

[0103] To address these limitations associated with conventional FL architectures, a clustering or hierarchical approach may be applied to FL, where learning nodes that target working on a common learning task are grouped together into clusters. In clustered FL, multiple clusters may be formed by respective groups of learning nodes (e.g., UEs) that have local datasets and share a common ML task, such as object detection or classification (e.g., detecting OBBs, vehicles on the road, or pedestrians, etc.). In one example, a FL parameter server (e.g., a base station) may group network nodes (e.g., UEs) together into clusters led by a designated cluster leader (e.g., a roadside unit, edge server, or other network node). In another example, a network node (e.g., a roadside unit) may form and lead a cluster with other network nodes (e.g., UEs) by itself without the involvement of the base station. In either example, cluster formation and leader selection are network-assisted (e.g., via messages that circulate within the network to identify clusters and confirm cluster leaders).

[0104] In addition, compared to conventional FL, in hierarchical FL, the designated cluster leader of each cluster (rather than the FL parameter server) directly coordinates learning tasks (including local ML model training and updating within the cluster). This coordination is referred to as intra-cluster FL. For example, each node within a cluster may pass a message including local updates to ML model weights to a cluster leader (e.g., an RSU, edge server, or other network node designated as the leader of the cluster by an identifier) ​​to aggregate the updated local model and transmit it back to each node within the cluster. After the cluster is formed, a centralized FL parameter server (e.g., a base station) may coordinate learning tasks (including global ML model training and updating between clusters). This coordination is referred to as inter-cluster FL. For example, each cluster leader of the corresponding cluster may pass a message including aggregated local updates to ML model weights to the FL parameter server to aggregate the updated global ML model and transmit it back to each cluster leader, which in turn transmits the updated global model to its corresponding cluster members for further training and updating. Therefore, the cluster leader can act as an intermediary between the learning nodes and the FL parameter server for coordinating neural network training and optimization between different clusters.

[0105] Fig. 9 An example 900 of a clustered FL architecture including a cluster 902 of UEs 904 (e.g., vehicle UEs, pedestrian UEs, etc.) communicating with a FL parameter server 906 (e.g., a base station, an RSU, an edge server, or other network entity) is illustrated. UEs 904 that share a common learning task, model, dataset, or computing resource may be grouped into one or more clusters, and multiple clusters 902 of such UEs may be formed. Cluster leaders 908 may be designated for clusters with network assistance. For example, a FL parameter server 906 (e.g., a base station) may designate an RSU, an edge server, or other network entity as a cluster leader 908 for a given cluster (if the network entity is in communication with the UEs 904 of the corresponding cluster), as well as designating the UEs 904 that participate in the corresponding cluster.

[0106] UEs 904 in a given cluster may communicate with Figure 7The training process is similar to the conventional FL process described, except that the cluster leader 908 acts as an aggregator for its corresponding cluster rather than a FL parameter server, and model training is performed at multiple levels (intra-cluster and inter-cluster). For example, the cluster leader 908 of a given cluster may multicast the initialized ML model to the UEs 904 within the cluster 902 to perform local training, and these UEs then transmit their individually updated ML models 910 back to the cluster leader 908 to be aggregated into an updated local model 912 for the cluster. The cluster leader 908 may then multicast the updated local model 912 to the UEs 904 to perform local training again in the next iteration, and the intra-cluster process may be repeated in further iterations. In addition, at certain times or in response to certain events, the cluster leader 908 may communicate its corresponding updated local model to the FL parameter server 906 to be aggregated into an updated global model 914 for the cluster. The FL parameter server 906 may then transmit these aggregated global models back to the cluster leader 908 to circulate within its corresponding cluster 902. Therefore, unlike conventional FL where learning nodes communicate directly with the FL parameter server for model optimization, here the cluster leader communicates directly with the FL parameter server, and the learning nodes within the cluster communicate directly with the cluster leader instead. Therefore, clustered FL can be used to implement neural network training in a distributed manner with minimal bottlenecks, minimal communication overhead, minimal challenges to model training due to heterogeneity of computing resources, training data, training tasks, or associated ML models, and minimal security and privacy challenges that may arise in conventional FL.

[0107] Various examples of signaling procedures between network nodes (e.g., UEs, roadside units, and base stations) are provided to implement clustered FL. In one example, a signaling procedure for cluster formation and leader selection is provided, wherein nodes participating in an ML training task are grouped together into clusters, wherein other nodes are led by a selected cluster leader (ML model weight aggregator) of the corresponding cluster based on configured criteria (in the case of network participation). In another example, a signaling procedure for cluster formation and leader selection is provided, wherein nodes participating in an ML training task may join a cluster led by other nodes in response to corresponding requests from other nodes. In one example, after cluster formation and leader selection are completed, a signaling procedure for clustered FL training may be provided, wherein nodes may perform intra-FL training coordinated by a cluster leader within a corresponding cluster by learning messages passed between the nodes and the cluster leader. In another example, after cluster formation and leader selection are completed, a signaling procedure for clustered FL training may be provided, wherein nodes may perform inter-FL training coordinated by a FL parameter server across different clusters by exchanging messages between the corresponding cluster leader and the FL parameter server. The aforementioned examples of signaling procedures are applicable to downlink / uplink communications (through the Uu interface) between a UE and a network entity such as a base station or a roadside unit.

[0108] Fig.10 An example 1000 of a signaling process is illustrated that allows UEs 1002 to form a cluster (eg, Fig. 9 902 in the cluster), and allow the base station 1004 to select an RSU 1006 as a cluster leader or a model weight aggregator for the UE 1002 and other FL participants within the cluster. In the process, the base station 1004 may form a cluster of UEs 1002 based on the FL information (e.g., ML model-related information) of these respective UEs, and the base station may designate an RSU that is capable of communicating with these UEs as the respective cluster leader. For example, the base station 1004 may select one of a plurality of RSUs to act as a model weight aggregator for a group of UEs that communicate with the RSU and are indicated by the RSU as being interested in performing the same ML task in the FL, having the same or similar sensors and input formats for training data in the FL, having the same or similar amount of available computing resources or other parameters for the FL. Thus, the base station may cluster UEs with similar FL parameters for maximum efficiency in model training and optimization (e.g., by not grouping UEs with different ML tasks, different computing capabilities, etc. together), and select an RSU for cluster leadership that is capable of communicating with these UEs for coordinated model training and optimization. Although Fig.10The illustrated example specifically refers to RSU 1006 as a cluster leader or model weight aggregator, but in other examples, an edge server or other network node may replace the RSU as a cluster leader or model weight aggregator. For example, the RSU may be applied to systems such as Fig. 8A In the transportation-related applications of FL shown in the example, the edge server can be applied to Figure 8B In the manufacturing-related applications of FL shown in the example.

[0109] Initially, the UEs 1002 may each send a FL message 1008. The FL message 1008 is intended to be received by the RSU 1006, which is the intended cluster leader in this example. When the FL message 1008 is sent, the RSU is not aware of the UEs 1002 with which the RSU may communicate respectively (e.g., which UEs are neighbors or proximate to the respective RSU), nor the ML tasks that these UEs are interested in performing. Therefore, the FL message 1008 may serve as a discovery message in response to which the UE and RSU may become aware of the existence of the other.

[0110] The FL message 1008 may be provided periodically (e.g., with a preconfigured periodicity) or in response to an event. In one example of an event, the UE may be triggered to transmit the FL message 1008 upon entering the service coverage area of ​​the RSU or base station. In another example of an event, the UE may be triggered to transmit the FL message 1008 in response to the UE's decision to join a FL cluster to improve the accuracy of its ML model. For example, if the UE's classification accuracy or other evaluation metric drops below a threshold, the UE may provide the FL message 1008.

[0111] The FL message 1008 also indicates FL or model training related information of the corresponding UE. This information may include, for example: the ML tasks in which the UE is participating or interested in participating; the available sensors at the UE and their associated data input formats; the available ML models in training, including model status, model architecture, model training parameters, and current performance (e.g., accuracy and loss); and available computing resources (e.g., whether the UE includes a CPU or GPU, information about its clock speed, available memory, etc.). For example, the FL message 1008 may indicate that the UE is configured to perform object detection (e.g., to identify OBBs), image classification, reinforcement learning, or other ML tasks. The FL message 1008 may indicate that the UE includes a camera, LIDAR, RADAR, IMU, or other sensor, and a data format that can be read by the indicated sensor. The FL message 1008 may indicate that the UE is configured with a neural network (e.g., Figure 6The FL message 1008 may indicate the UE's CPU or GPU (e.g., controller / processor 459 or some other processor of device 450) to apply the indicated neural network and model to the indicated ML task, the clock speed of the CPU or GPU, and an amount of available memory (e.g., memory 460 or some other memory of device 450) for storing information associated with the ML task, neural network, data, etc. The FL message 1008 may include any combination of the foregoing as well as other information.

[0112] The FL message 1008 may be broadcast to solicit a response from any RSU that is capable of decoding the FL message. Fig.10 In the illustrated example, RSU 1 may be adjacent to (e.g., be a neighbor of) both UE 1 and UE 2 and thus successfully decode the FL messages of both UE 1 and UE 2, while RSU 2 may be adjacent to UE 2 and thus successfully decode the FL message of UE 2. Therefore, one UE may provide FL messages to multiple RSUs, and one RSU may obtain FL messages from multiple UEs, respectively.

[0113] In response to receiving and decoding the FL message 1008 from the respective UE, the RSU (e.g., RSU 1 or RSU 2) may store an identifier of the UE in a memory, store the FL information of the UE 1002 (at least temporarily) in a memory, and provide a FL message confirmation 1010 to the UE 1002 confirming receipt of its FL message. The RSU 1006 may provide the FL message confirmation 1010 to the respective UE via unicast. The FL message confirmation 1010 may also indicate the identifier of the RSU 1006 so that the UE 1002 receiving the confirmation may determine the source RSU. For example, if the UE 1002 provides the FL message 1008 to multiple RSUs 1006, the UE will obtain multiple such FL message confirmations 1010 including the respective identifiers from the respective RSUs. For example, in Fig.10In the illustrated example of , UE 2 may provide its FL message to both RSU 1 and RSU 2, and thus UE 2 may obtain a FL message confirmation from RSU 1 indicating the identifier of RSU 1 and a FL message confirmation from RSU 2 indicating the identifier of RSU 2. Similarly, UE 1 also provides its FL message to RSU 1, and thus UE 1 may similarly obtain a FL message confirmation from RSU 1 indicating the identifier of RSU 1 (but not a confirmation from RSU 2 because RSU 2 has not obtained or successfully decoded the FL message).

[0114] After obtaining the FL message confirmation from the corresponding RSU 1006, the UE can determine the RSUs in the network that have decoded its FL message. The UE can then select one of these confirming RSUs to act as its representative for passing its FL information to the base station 1004 for cluster formation and leader selection. Similarly, other UEs can select corresponding confirming RSUs to act as their respective representatives for passing corresponding FL information. For example, in Fig.10 In the illustrated example of , UE 1 may select only RSU 1 (given its sole acknowledgment of the FL message 1008 from the UE), while UE 2 may select either RSU 1 or RSU 2 (given the acknowledgments of the FL message 1008 from the UE by both RSUs). However, if UE 2 also happens to select RSU 1 in this example, RSU 1 will end up inefficiently transmitting the FL information of both UEs to the base station, thereby generating additional communication overhead at RSU 1 compared to the case where RSU 2 happens to be selected. Therefore, in order to minimize the communication overhead between RSU 1006 and base station 1004, UE 1002 may be configured to select a different RSU for FL message delivery. For example, in the aforementioned example, UE 2 may be configured to select RSU 2 (rather than RSU 1) in this case. Therefore, the inefficient situation where the RSU delivers FL information from multiple UEs to the base station, or the inefficient situation where multiple RSUs deliver FL information of a single UE to the base station, may be avoided.

[0115] After selecting an RSU from the confirmed RSUs, the UE 1002 may provide an RSU indication message 1012 including an identifier of the selected RSU to the confirmed RSU. Fig.10For RSU 1 and RSU 2 of UE 2 in the example of ), the UE may provide an RSU indication message 1012 to multiple confirming RSUs via multicast. The message is provided via multicast to allow the confirming RSUs to respectively determine whether the RSU is indicated as a representative for FL message delivery by the UE. After receiving the RSU indication message 1012 from the corresponding UE, an RSU having an identifier matching the identifier included in the RSU indication message 1012 may determine that it is a representative for delivering the FL information of the UE, and thus maintain its storage of the FL information in the FL message 1008 from the UE in a memory. In contrast, an RSU having an identifier that does not match the identifier included in the RSU indication message 1012 may determine that it is not a representative of the UE, and thus may discard or discard the FL information of the UE from the memory, while still maintaining its storage of the identifier of the UE in the memory. Regardless of the indicated RSU in the RSU indication message 1012, the RSU may continue to store identifiers of UEs that the RSU previously acknowledged in order to track its ability to communicate with these UEs and inform the base station 1004 of the list of UEs during cluster formation and leader selection.

[0116] In response to obtaining the RSU indication message 1012 from the UE 1002, the RSU 1006 may respectively provide a message 1014 to the base station 1004, the message including the UE's FL information indicating the identifier of the RSU and a list (or other data structure) of identifiers of the UEs 1002 that the RSU has previously confirmed (and therefore has communication capability with). Fig.10 In the illustrated example, RSU 1 may provide FL information of UE 1 to base station 1004, RSU 2 may provide FL information of UE 2 to base station 1004, and both RSU 1 and RSU 2 may provide identifiers of UE 1 and UE 2 to base station 1004. Therefore, base station 1004 may be informed of ML tasks, sensors, model information, and computing capabilities of UE 1002 and RSU 1006 that may communicate with the corresponding UE.

[0117] In one example, one or more of the RSUs 1006 may be a learning node, rather than just a UE FL information aggregator. For example, these RSUs may have obtained their own local data set and intend to use the data set in the FL to train their own ML models. In this case, those RSUs 1006 may also provide their own FL information to the base station 1004 in a message 1014, similar to the UE's FL information. This information may include, for example: ML tasks that the RSU is participating in or interested in participating in; available ML models in training, including model status, model architecture, model training parameters, and current performance (e.g., accuracy and loss); and available computing resources (e.g., whether the RSU includes a CPU or GPU, information about its clock speed, available memory, etc.). Although in one example, the message 1014 from the RSU may include UE FL information, a UE list, and RSU FL information (if present), in other examples, any combination of the foregoing may be included in one or more such messages 1014 from the RSU.

[0118] In response to receiving the message 1014 from the respective RSUs 1006, the base station 1004 may aggregate the UE FL information (e.g., store the FL information of the respective UEs 1002 in a memory), select an RSU to act as a cluster leader based on the aggregated information, and select the UE 1002 as a member or participant of the cluster led by the respective selected RSU based on the aggregated information. For example, the base station may assign the UE 1002 to a cluster of RSUs that indicate the ability to communicate with those UEs in the message 1014 (e.g., via identifiers that include those UEs). The base station may not necessarily assign the UE to a cluster of the same RSU that identifies the UE indicated in the RSU indication message 1012. For example, in Fig.10 In the illustrated example, even if the base station 1004 obtains message 1014 indicating FL information of UE 1 and UE 2 respectively from both RSU 1 and RSU 2 (in response to UE 1 and UE 2 respectively indicating RSU 1 and RSU 2 as their representatives in the corresponding RSU indication messages 1012), the base station can also assign both UE 1 and UE 2 as cluster members of the cluster led by RSU 1.

[0119] The base station 1004 may also select an RSU to serve as a cluster leader and select UEs to serve as cluster members of such an RSU based on other factors other than the communication capabilities indicated in the message 1014. For example, the base station may select any one RSU that is capable of communicating with the largest number of UEs (e.g., an RSU whose list includes the largest number of UE identifiers) as the cluster leader and group these UEs together in a cluster under that RSU. Fig.10In the illustrated example of , the base station may select RSU 1 as the cluster leader for both UE 1 and UE 2 in response to determining from the obtained UE list in message 1014 that RSU 1 can communicate with a larger number of UEs (e.g., both UE 1 and UE 2) than RSU 2 (which in this example can communicate only with UE 1), instead of selecting RSU 1 as the cluster leader for UE 1 and RSU 2 as the cluster leader for UE 2. Additionally or alternatively, the base station may select UEs 1002 with the same or similar computing capabilities to be in the same cluster, while selecting UEs with different computing capabilities to be in different clusters. For example, in Fig.10 In the illustrated example of , the base station 1004 may group UE 1 and UE 2 in the same cluster led by RSU 1 in response to determining that both UE 1 and UE 2 have high computing capabilities or both have low computing capabilities based on the FL information in the message 1014. On the contrary, if UE 1 has high computing capabilities and UE 2 has low computing capabilities, or vice versa, the base station 1004 may determine to group UE 1 and UE 2 in different clusters led by different RSUs (e.g., to avoid low-capability UEs acting as bottlenecks in model training via FL for high-capability UEs). Additionally or alternatively, in other examples, the base station may apply other criteria in its selection of cluster leaders and cluster members based on the FL information in the message 1014.

[0120] After the aggregation and selection, the base station 1004 may provide the selected RSUs with messages 1016 indicating their respective cluster information via unicast. The cluster information provided to the respective RSUs may include, for example, identifiers of UEs to be grouped into a cluster for the FL led by the RSU. Fig.10 In the illustrated example of , base station 1004 may notify RSU 1 of its status as a cluster leader or model update aggregator of a cluster including UE 1 and UE 2. For example, base station 1004 may provide RSU 1 with identifiers of UE 1 and UE 2. If the base station does not select a particular RSU as a cluster leader or aggregator, the base station may not provide such a message or cluster information to the RSU. For example, in Fig.10 In the illustrated example, the base station may not select RSU 2 as the cluster leader, and therefore the base station may not provide message 1016 to RSU 2.

[0121] After obtaining the corresponding cluster information in the message 1016 from the base station 1004, the RSU 1006 receiving such information may respectively provide the message 1018 to the UEs 1002 indicated in its corresponding cluster information. The RSU may provide its corresponding message 1018 to those UEs 1002 having the identifier assigned or indicated in the cluster information of the message 1016 via multicast. The message 1018 may inform these UEs 1002 of their status as participants or follower nodes of the FL in the cluster led by the RSU, and may instruct these UEs to provide ML model weight updates to the RSU for training and optimization during clustering FL. For example, in Fig.10 In the illustrated example of , RSU 1 may provide message 1018 to UE 1 and UE 2 via multicast, indicating that those UEs are cluster members of the cluster led by RSU 1.

[0122] Fig.11 An example 1100 of a signaling process is illustrated, for example, in sidelink communications, to allow a first node 1102 (e.g., an RSU) to form a cluster with a second node 1104 (e.g., a UE) (as a cluster leader in a clustered FL architecture). In the process, a network node (e.g., an RSU) may designate itself as a cluster leader, rather than being selected as a cluster leader by other network nodes (e.g., a base station). In addition, a network node that intends to act as a leader may form a cluster with other network nodes by transmitting a message to recruit these other nodes to its cluster. The recruitment message may indicate that the network node intends to operate as a cluster leader and FL coordinator, as well as indicate ML training related information of the network node.

[0123] Nodes that receive the recruitment message and potentially other recruitment messages from other self-designated leaders may determine whether to subscribe to any indicated cluster led by the corresponding transmitter based on the indicated ML training-related information in the corresponding message. If the network node determines to subscribe to the cluster of one of these transmitting nodes, the network node may transmit back a message requesting subscription to the cluster and further indicating the ML-related training information of the node; otherwise, the network node may ignore the recruitment message. Upon receiving the subscription message, the recruitment node may similarly determine whether to allow the subscribing node to join its cluster based on the indicated ML-related training information of the subscribing node. If a permission decision is made, the recruitment node may transmit a confirmation of cluster permission to the subscribing node. Otherwise, the recruitment node may ignore the subscription message, and the subscribing node may search to join a different cluster after a specified time period.

[0124] Initially, the first node 1102 sends a message 1106 indicating that the first node 1102 is interested in recruiting other nodes to form or join a cluster led by the first node. For example, if the first node is not currently participating in an active cluster FL session, the message 1106 may be provided periodically (e.g., according to a preconfigured periodicity). Alternatively, the message 1106 may be event-triggered, for example, in response to the first node 1102 determining to train or update the ML model of the UE to improve the performance of a specific ML task by the UE. The first node 1102 may broadcast the message 1106 to any network node capable of decoding the message. Alternatively, the message 1106 may be multicast, for example, to network nodes known to the first node 1102. The message 1106 may also be transmitted using multicast option 1 to enhance the reliability of the recruitment message (e.g., the first node 1102 may indicate in the second stage SCI the distance at which the first node expects to receive NACKs from other nodes that failed to decode the message).

[0125] In addition, message 1106 may indicate model training related information of first node 1102. This information may include, for example: ML tasks that first node 1102 is participating in or interested in participating in; available ML models in training, including model status, model architecture, model training parameters, and current performance (e.g., accuracy and loss); and available computing resources (e.g., whether first node 1102 includes a CPU or GPU, information about its clock speed, available memory, etc.). Therefore, message 1106 may include information related to Fig.10 Similar types of information as those provided in message 1014.

[0126] exist Fig.11In the example of , if the nodes are near each other, the second node 1104 may receive a message 1106 from the first node 1102. The second node 1104 may potentially receive other such messages from other network nodes requesting that the second node be recruited to a cluster led by the respective node. Thus, the second node 1104 may receive a recruitment message from a plurality of candidates for cluster leadership. In response to receiving the recruitment message, the second node may determine whether to subscribe to a cluster of one of the candidates based at least in part on the model training related information indicated in the respective message. The determination may be based on the model training related information in the message 1106, including factors such as whether the candidate node and the second node have similar ML models, computing resources, and the like. For example, if the information indicates that the first node has a different ML model than the second node or has lower computing power than the second node (e.g., if the RSU is configured with a Markov model or a small amount of available memory for ML, while the UE is configured with a classification model or a large amount of available memory for ML), the second node 1104 may decide not to subscribe to the cluster of the first node 1102. Alternatively, the second node 1104 may decide to subscribe to the cluster of the first node 1102 if the information indicates, for example, that the first node has the same or similar ML model (e.g., classification model) or the same or similar computing capabilities (e.g., memory) as the second node.

[0127] In this example, the second node 1104 determines to form or join a cluster led by the first node 1102, and therefore the second node may provide a message 1108 (e.g., via unicast) to the first node 1102 requesting to subscribe to or join its cluster. The message 1108 may also indicate model training related information of the second node 1104. The information may include, for example: the ML tasks that the second node 1104 is participating in or interested in participating in; the available sensors at the second node and their associated data input formats; the available ML models in training, including model state, model architecture, model training parameters, and current performance (e.g., accuracy and loss); and available computing resources (e.g., whether the second node includes a CPU or GPU, information about its clock speed, available memory, etc.). Therefore, the message 1108 may include the same type of information as the message 1106, but for the second node 1104 instead of the first node 1102.

[0128] In response to receiving the message 1108, the first node 1102 may similarly determine whether to allow the second node 1104 to join its cluster based at least in part on the model training related information indicated in the message 1108. For example, if the information indicates that the second node has a different ML model than the first node or has lower computing power than it, the first node 1102 may decide not to add the second node 1104 to its cluster. In this case, the first node 1102 may disregard or ignore (and therefore not respond to) the message 1108. Alternatively, if the information indicates, for example, that the nodes have the same or similar ML models or the same or similar computing power, the first node 1102 may decide to add the second node 1104 to its cluster. In this case, the first node 1102 may provide (e.g., via unicast) a message 1110 confirming that the second node 1104 is allowed to join the cluster led by the first node 1102.

[0129] On the other hand, if the first node 1102 decides not to allow the second node 1104 to join its cluster, the second node may not receive the message 1110 within the timeout window 1112 from the time the message 1108 was provided (because the first node disregarded or ignored the message 1108). In this case, the second node 1104 may subscribe to the cluster of another network node from which the second node previously received a recruitment request. Fig.11 In the illustrated example of , the second node 1104 may have previously received a message 1114 (similar to message 1106) from a third node 1116 (e.g., another RSU) requesting to recruit other nodes to its cluster, and based at least in part on the model training related information of the third node 1116 indicated in the message 1114, the second node 1104 may send a message 1118 requesting to subscribe to or join the cluster led by the third node 1116 after the timeout window 1112 expires. In response to receiving the message 1118, the third node 1116 may similarly determine whether to allow the second node 1104 to join its cluster based at least in part on the model training related information indicated in the message 1118, in which case the third node 1116 may provide (e.g., via unicast) a message 1120 confirming that the second node 1104 is allowed to join the cluster led by the third node 1116.

[0130] Fig.12 An example 1200 of a signaling process is illustrated, in which a participant node 1202 may be in a communication such as regarding Fig.10 or Fig.11The described selection or designation of a leader node 1204 (e.g., a cluster leader) and clustering of participant nodes 1202 are followed by performing intra-cluster FL. Participant nodes 1202 (e.g., UEs) may be, for example, cluster members in cluster Ci. Leader node 1204 (e.g., an RSU, an edge server, a local FL server, or other network node) may be, for example, a selected or self-designated leader of cluster Ci.

[0131] Initially, at step 1206, the leader node 1204 may initialize an ML model (eg, a cluster model W for clustering FL Ci ). The initialization may include, for example, configuring the ML task (e.g., object detection), the neural network (e.g., CNN), the number of neurons and synapses, random weights and biases, the model algorithm (e.g., logistic regression), and other model parameters. After initialization, at step 1208, the leader node 1204 may broadcast or multicast these ML model parameters to the network nodes 1202 for download.

[0132] After receiving the ML model parameters from the leader node 1204 and configuring its local ML model accordingly, at step 1210, the participant nodes 1202 (e.g., k cluster members) and potentially the leader node 1204 may perform local ML model training based on their respective data sets. For example, during a given FL iteration t, the respective node k (corresponding to the cluster model WtCik or the global model) may train the local ML model 1211 to identify the optimal model parameters for minimizing the loss function F(WtCik), such as with respect to Figure 6 As described. For example, a node may utilize back-propagation and stochastic gradient descent to identify the optimal model weights to be applied to its corresponding neural network, which results in a minimized cross-entropy loss after multiple training sessions. Thereafter, the participant node 1202 may upload its corresponding updated ML model parameters (updated ML model 1212) to the leader node 1204. For example, the participant node 1202 may send the optimized ML model weights and other information to the leader node 1204. After receiving these ML model information updates from the participant nodes 1202, at step 1214, the leader node 1204 may aggregate the updates to generate an updated ML model 1215 for the node (e.g., an updated cluster model Wt+1Ci to be applied to the next FL iteration t+1). For example, the leader node 1204 may average the corresponding model weights indicated by the participant nodes 1202 or perform some other calculation, potentially including the corresponding model weights of the leader node 1204.

[0133] After generating the aggregated ML model information, the leader node 1204 may determine that the loss function associated with the updated ML model is no longer minimized. For example, the aggregated ML model weights may potentially result in an increased loss compared to the previous ML model weights of the individual nodes. Therefore, the leader node may transmit the aggregated ML model information to the participant nodes 1202, which may be the same nodes as before or may include additional or fewer nodes, for further local ML model training. For example, after configuring their local ML models with the updated weights, during the next FL iteration t+1, the participant nodes 1202 (and potentially the leader node 1204) may again perform local ML model training to achieve a set of optimal ML model weights for their respective models, and the participant nodes 1202 may similarly transmit their updated ML models to the leader node 1204 for further aggregation. This process may be repeated until minimization of the loss function associated with the aggregated ML model (e.g., the cluster loss function F(WtCi) for cluster Ci) is achieved. Alternatively, the process may be repeated until a predetermined number of FL iterations in the cluster occur (e.g., based on the computational power of the participant nodes 1202 or the number of other ML model information).

[0134] Fig.13 An example 1300 of a signaling process is illustrated, in which a leader node 1302 can communicate with a FL parameter server 1304 to communicate with the FL parameter server 1304 as described above. Fig.12 Inter-cluster FL is performed after one or more FL iterations of intra-cluster model training with participant nodes 1305 are described. Leader node 1302 (e.g., RSU or edge server) may be, for example, a selected or self-designated leader of a corresponding cluster 1306. FL parameter server 1304 may be, for example, a base station or other network entity that coordinates FL between corresponding clusters 1306.

[0135] At a given moment after intra-cluster FL training, the leader node 1302 may communicate the locally updated ML model information (intra-cluster) to the FL parameter server 1304 for inter-cluster FL training. For example, the FL parameter server 1304 may periodically or aperiodically transmit a request to the cluster leader to communicate its model updates for inter-cluster FL training. Alternatively, the leader node 1302 itself may communicate its model updates for inter-cluster FL training in response to an event trigger, such as the minimization of a local loss function in the corresponding cluster, or the occurrence of a certain number of intra-cluster FL iterations. The FL parameter server 1304 may aggregate this information received from the corresponding cluster leaders to generate a global (multi-cluster) ML model update, after which the FL parameter server may provide this globally updated ML model information to the corresponding leader nodes. These leader nodes may then provide the globally updated ML model information to their corresponding participant nodes to further refine the local ML model through additional intra-cluster FL training. Intra-cluster and inter-cluster FL training may or may not be synchronized; for example, different clusters may perform intra-cluster FL training or inter-cluster FL training for the same number or different number of iterations before stopping to perform FL training. For example, the leader node 1302 of the corresponding cluster may stop communicating local model updates (in intra-cluster training) or global model updates (in inter-cluster training) to the participant nodes or FL parameter servers at the same time or at different times.

[0136] Initially, at step 1308, the leader node 1302 of the corresponding cluster may transmit its updated ML model WtCi of its cluster Ci to the FL parameter server 1304, the updated ML model including one or more previous aggregations 1307 of local ML model updates 1309 from follower nodes. For example, the leader node 1302 may transmit its most recently generated aggregated ML model weights after a given number of intra-cluster FL iterations to be further aggregated with other aggregated ML model weights generated by other leader nodes in other clusters. For example, in response to receiving a request from the FL parameter server 1304, achieving minimization of a loss function associated with the updated ML model (e.g., a cluster loss function F(WtCi) of the cluster), and the occurrence of a predetermined number of FL iterations in the cluster, the leader node 1302 may be triggered to transmit the updated ML model for the inter-cluster FL training. Similarly, in response to similar events, the leader nodes 1302 of other corresponding clusters may respectively transmit their own clusters' updated ML models (e.g., aggregated ML model weights) to the FL parameter server 1304 for inter-cluster FL training.

[0137] After receiving the updated ML model from the cluster leader, at step 1310, the FL parameter server 1304 may aggregate the updates to generate an updated global ML model 1311 for the leader node (e.g., updated global model Wt+1G). For example, the FL parameter server 1304 may average the corresponding aggregated model weights indicated by the leader node 1302 or perform some other calculation. After generating the aggregated ML model information, the FL parameter server 1304 may determine that the global loss function associated with the updated ML model is no longer minimized. For example, the aggregated ML model weights across clusters may potentially result in an increased loss compared to the previously updated ML model weights of the individual cluster leaders. Therefore, at step 1312, the FL parameter server may transmit the aggregated ML model information to the leader node 1302 for further training of the corresponding in-cluster ML model 1313 (starting from the updated model Wt+1G), such as with respect to Fig.12 After this intra-cluster FL training, the leader node 1302 may again transmit its updated or aggregated ML model information to the FL parameter server 1304 for further inter-cluster FL training, and the process may be repeated until a global loss function associated with the aggregated ML model across clusters (e.g., global loss function F G Alternatively, the process may be repeated until a predetermined amount of inter-cluster FL iterations occur.

[0138] Fig.14 1400 is a flow chart of a method of wireless communication. The method may be performed by a UE (e.g., UE 104, 904, 1002; device 410, 450; learning node 706; network node 802, 852, 1104, 1202, 1305; apparatus 1602). For example, the method may be performed by a controller / processor 459, 475 coupled to a memory 460, 476 of the apparatus 410, 450. Optional aspects are illustrated by dashed lines. The method allows a UE to be grouped with other UEs in a cluster led by another network node (e.g., an RSU or an edge server), so that the UE can perform ML model training in a clustered FL environment through various signaling procedures.

[0139] At 1402, the UE may provide a first message including FL information. For example, 1402 may be performed by cluster forming component 1640. For example, referring to Figure 4 , the controller / processor 475 in the device 450 (e.g., UE) may provide the first message to the device 410 (e.g., another node such as an RSU or an edge server) via the TX processor 416, which may send the first message to the device 450 via the antenna 420. In one example, referring to Fig.10, UE 1002 may provide FL message 1008 to RSU 1006 as the intended cluster leader. FL message 1008 may indicate FL or model training related information of UE 1002. In another example, referring to Fig.11 , the second node 1104 (UE in this example) may provide a message 1108 to the first node 1102 (eg, RSU or edge server) requesting to subscribe to or join its cluster. The message 1108 may indicate model training related information of the second node 1104.

[0140] In one example, the FL information may include at least one of the following: a machine learning task of the UE, an available sensor coupled to the UE for the machine learning task, an available ML model associated with the machine learning task, or an available computing resource of the UE for the machine learning task. Fig.10 and Fig.11 , the FL or model training related information provided by the UE 1002 or the second node 1104 in the FL message 1008 or message 1108 may include, for example: the ML task in which the UE is participating or interested in participating; the available sensors at the UE and their associated data input formats; the available ML models in training, including model state, model architecture, model training parameters, and current performance (e.g., accuracy and loss); and available computing resources (e.g., whether the UE includes a CPU or GPU, information about its clock speed, available memory, etc.). For example, the FL message 1008 or message 1108 may indicate that the UE is configured to perform object detection (e.g., to identify OBBs), image classification, reinforcement learning, or other ML tasks. The FL message 1008 or message 1108 may indicate that the UE includes a camera, LIDAR, RADAR, IMU, or other sensor, and a data format that can be read by the indicated sensor. The FL message 1008 or message 1108 may indicate that the UE is configured with a neural network (e.g., Figure 6 1008 or 1108 may indicate the UE's CPU or GPU (e.g., controller / processor 459 or some other processor of device 450) to apply the indicated neural network and model to the indicated ML task, the clock speed of the CPU or GPU, and an amount of available memory (e.g., memory 460 or some other memory of device 450) for storing information associated with the ML task, neural network, data, etc. FL message 1008 or message 1108 may include any combination of the foregoing as well as other information.

[0141] In one example, the UE may provide the first message periodically or in response to an event trigger. Fig.10 , the FL message 1008 may be provided periodically (e.g., with a preconfigured periodicity) or in response to an event. In one example of an event, the UE may be triggered to transmit the FL message 1008 after entering the service coverage area of ​​the RSU or base station. In another example of an event, the UE may be triggered to transmit the FL message 1008 in response to the UE's decision to join a FL cluster to improve the accuracy of its ML model. For example, if the UE's classification accuracy or other evaluation metric drops below a threshold, the UE may provide the FL message 1008.

[0142] In one example, the UE may provide the first message in a broadcast. Fig.10 , the FL message 1008 may be broadcast to solicit a response from any RSU that is capable of decoding the FL message. Fig.10 In the illustrated example, RSU 1 may be adjacent to (e.g., be a neighbor of) both UE 1 and UE 2 and thus successfully decode the FL messages of both UE 1 and UE 2, while RSU 2 may be adjacent to UE 2 and thus successfully decode the FL message of UE 2. Therefore, one UE may provide FL messages to multiple RSUs, and one RSU may obtain FL messages from multiple UEs, respectively.

[0143] In one example, the UE may provide (at 1402) a first message to the second network node. In this example, the first message may also include a request to join a second FL cluster of the second network node. For example, referring to Fig.11 , the UE (second node 1104) may provide a message 1108 to the second network node (first node 1102) requesting to subscribe to or join its cluster.

[0144] At 1404, the UE may obtain a message indicating that the second network node is a candidate to become a second FL cluster leader of the second FL cluster, wherein the first message is provided to the second network node in response to the message (at 1402). For example, 1404 may be performed by cluster formation component 1640. For example, referring to Figure 4 , the controller / processor 475 in the device 410 (UE) may obtain the message from the device 450 (e.g., another network node such as an RSU or an edge server) via the RX processor 470, which may receive the message from the device 450 via the antenna 420. For example, referring to Fig.11, the UE (second node 1104) may receive a message 1106 from the second network node (first node 1102) indicating that the first node 1102 is interested in recruiting other nodes to form or join a cluster led by the first node. The recruitment message may indicate that the network node intends to operate as a cluster leader (e.g., become a candidate for it) and FL coordinator, as well as ML training-related information indicating the network node. In response to receiving the message 1106, the UE (second node 1104) may provide a message 1108 (first message) to the second network node (first node 1102) requesting to subscribe to or join its cluster.

[0145] At 1406, the UE may provide a second message indicating the first network node. For example, 1406 may be performed by cluster forming component 1640. For example, referring to Figure 4 , the controller / processor 475 in the device 450 (e.g., UE) may provide the second message to the device 410 (e.g., another node such as an RSU or an edge server) via the TX processor 416, which may send the second message to the device 450 via the antenna 420. In one example, referring to Fig.10 , UE 1002 may provide RSU 1006 with an RSU indication message 1012 including an identifier of a selected RSU (first network node) for acting as a representative of the UE to pass its FL information to base station 1004 for cluster formation and leader selection. In another example, referring to Fig.11 , the UE (second node 1104 ) may send a message 1118 requesting to subscribe to or join the cluster led by the third node 1116 (first network node).

[0146] At 1408, the UE may obtain confirmation of the FL information from the first network node, wherein a second message is provided in response to the confirmation (at 1406). For example, 1408 may be performed by cluster forming component 1640. For example, referring to Fig.10 , UE 1002 may obtain a FL message confirmation 1010 from the corresponding RSU confirming receipt of FL message 1008 (including FL information). Figure 4 , the controller / processor 475 in the device 410 (UE) may obtain an acknowledgement from the device 450 (e.g., another network node such as an RSU or an edge server) via the RX processor 470, which may receive the acknowledgement from the device 450 via the antenna 420. In response to obtaining the FL message acknowledgement 1010, the UE may provide an RSU indication message 1012 (a second message) including an identifier of the RSU selected from the acknowledged RSUs.

[0147] At 1410, the UE may provide a second message to the first network node in response to a lack of an acknowledgement (at 1406) of the first message (provided at 1402) from the second network node within a message timeout window. For example, 1410 may be performed by cluster formation component 1640. For example, referring to Fig.11 , if the UE fails to receive a message 1110 confirming that it is permitted to join the cluster of another node (the first node 1102) within the timeout window 1112, the UE (the second node 1104) may provide a message 1118 (a second message in this example) to the third node 1116 (the first network node in this example). In one example, the second message may also include FL information. For example, message 1118 may request to subscribe to or join the cluster led by the third node 1116, and may also indicate model training related information of the UE (the second node 1104). This information may include, for example: the ML tasks that the second node 1104 is participating in or interested in participating in; the available sensors at the second node and their associated data input formats; the available ML models in training, including model status, model architecture, model training parameters, and current performance (e.g., accuracy and loss); and available computing resources (e.g., whether the second node includes a CPU or GPU, information about its clock speed, available memory, etc.).

[0148] At 1412, the UE may obtain a third message indicating one of the first network node or the second network node as the FL cluster leader and indicating the FL cluster of the UE based on the FL information. For example, 1412 may be performed by the cluster formation component 1640. The first network node and the second network node may be, for example, an RSU or an edge server. For example, referring to Figure 4 , the controller / processor 475 in the device 410 (UE) may obtain a third message from the device 450 (e.g., another network node such as an RSU or an edge server) via the RX processor 470, which may receive the third message from the device 450 via the antenna 420. In one example, referring to Fig.10 , UE 1002 may receive a message 1018 (third message) from RSU 1006 (first network node) identified by the UE in its RSU indication message 1012 or from a different RSU (second network node), which notifies the UE that it is a member of a cluster led by the corresponding RSU (first network node or second network node) (e.g., Fig. 9 The RSU selected as the cluster leader and the UEs selected as members or participants of the cluster led by the RSU may be based on the aggregated FL information from UE 1002 and other UEs. In another example, referring to Fig.11 In response to transmitting a message 1108 or a message 1118 including its FL or model training related information to the corresponding node, the UE (the second node 1104) may receive a message 1110 (an example of a third message) confirming that the UE is allowed to join the cluster led by the first node 1102, or a message 1120 (another example of a third message) confirming that the UE is allowed to join the cluster led by the third node 1116 (e.g., the first network node or the second network node).

[0149] In one example, the UE may obtain a third message indicating the FL cluster leader and the FL cluster of the UE in a multicast from the first network node. Fig.10 , UE 1002 may receive a message 1018 from RSU 1006 (first network node) via multicast indicating that the UE is a cluster member of a cluster led by the RSU.

[0150] In one example, after step 1410, the third message may indicate the first network node as the FL cluster leader. Fig.11 After the UE (second node 1104) provides message 1118 to the third node 1116 (the first network node in this example), the UE may obtain a message 1120 (third message) confirming that the UE (second node 1104) is allowed to join the cluster led by the third node 1116.

[0151] At 1414, the UE may obtain the ML model configuration including initial weights from the FL cluster leader. For example, 1414 may be performed by the FL training component 1642. For example, referring to Figure 4 , the controller / processor 475 in the device 410 (UE) may obtain the ML model configuration from the device 450 (e.g., another network node such as an RSU or an edge server) via the RX processor 470, which may receive the ML model configuration from the device 450 via the antenna 420. For example, referring to Fig.12 , the participant node 1202 (UE) may receive the ML model parameters at step 1208, which are initialized by the leader node 1204 at step 1206. The initialization of the leader node may include, for example, configuring the ML task (e.g., object detection), the neural network (e.g., CNN), the number of neurons and synapses, random weights and biases, the model algorithm (e.g., logistic regression), and other model parameters. Thus, the initial weights (e.g., Figure 6 The initial value of the weight 616 may be a random weight.

[0152] At 1416, the UE may provide the FL cluster leader with an ML model information update including an update to the initial weights. For example, 1416 may be performed by the FL training component 1642. For example, referring to Figure 4 , the controller / processor 475 in the device 410 (e.g., UE) may provide the ML model information update to the device 450 (e.g., another node such as an RSU or an edge server) via the TX processor 416, which may send the ML model information update to the device 450 via the antenna 420. For example, referring to Fig.12 , after receiving the ML model parameters from the leader node 1204 and configuring its local ML model accordingly, at step 1210, the participant node 1202 (UE) may perform local ML model training based on its corresponding data set. For example, during a given FL iteration t, the corresponding node k (corresponding to the cluster model WtCik) may train the local ML model 1211 to identify the optimal model parameters for minimizing the loss function F(WtCik), such as Figure 6 As described. For example, the nodes may utilize back-propagation and stochastic gradient descent to identify the optimal model weights to be applied to their respective neural networks, which results in a minimized cross-entropy loss after multiple training sessions. Thereafter, the participant node 1202 may upload its corresponding updated ML model parameters (updated ML model 1212) to the leader node 1204. For example, the participant node 1202 may send the optimized ML model weights and other information to the leader node 1204.

[0153] At 1418, the UE may obtain an aggregated ML model information update from the FL cluster leader, the aggregated ML model information update comprising an aggregation of the ML model information update and a second ML model information update of a third network node in the FL cluster. For example, 1418 may be performed by the FL training component 1642. For example, referring to Figure 4 , the controller / processor 475 in the device 410 (UE) may obtain the aggregated ML model information update from the device 450 (e.g., another network node such as an RSU or an edge server) via the RX processor 470, which may receive the aggregated ML model information update from the device 450 via the antenna 420. For example, referring to Fig.12 , after receiving ML model information updates from participant nodes 1202 (including an update from a UE and another update from a different UE in the same cluster (e.g., a third network node)), at step 1214, the leader node 1204 may aggregate these updates to generate an updated ML model 1212 for these nodes (e.g., an updated cluster model Wt+1Ci to be applied to the next FL iteration t+1). For example, the leader node 1204 may average the corresponding model weights indicated by the participant nodes 1202 or perform some other calculation. After the leader node 1204 generates the aggregated ML model information, the participant nodes 1202 may receive the aggregated ML model information from the leader node 1204.

[0154] In one example, the aggregated ML model information update may further include a second aggregation of the ML model information update and a third ML model information update from a fourth network node in the second FL cluster. Fig.13 At step 1308, the leader node 1302 of the corresponding cluster may transmit an updated ML model WtCi (in this example, an ML model information update) of its cluster Ci to the FL parameter server 1304, the updated ML model including the updated ML model information from the follower nodes (e.g., Fig.12 1G ). For example, the leader node 1302 may transmit the aggregated ML model weights it has most recently generated after a given number of intra-cluster FL iterations for the FL parameter server to further aggregate (in a second aggregation) with other aggregated ML model weights (the third ML model information update in this example) generated by other leader nodes (including the fourth network node in this example) in other clusters (including the second FL cluster). After receiving the updated ML model from the cluster leader, at operation 1310, the FL parameter server 1304 may aggregate these updates to generate an updated global ML model 1311 (e.g., an updated global model Wt+1G) for the leader node. For example, the FL parameter server 1304 may average or perform some other calculation on the corresponding aggregated model weights indicated by the leader node 1302. Therefore, at step 1312, the FL parameter server may transmit the aggregated ML model information to the leader node 1302 for further training of the corresponding intra-cluster ML model 1313 (from the updated model Wt+1G). t+1 G start), such as Fig.12 UE (e.g., Fig.12 The participant node 1202) may then obtain the further aggregated updates (e.g., updated ML model 1212) from the leader node.

[0155] FIG. 15A to FIG. 15B1500 is a flow chart of a method of wireless communication. The method may be performed by a network node such as an RSU, an edge server, a base station, a FL parameter server, or other network node (e.g., base station 102 / 180; decomposed base station 181; devices 410, 450; FL parameter servers 702, 804, 854, 906, 1304; cluster leader 908; base station 1004; RSU 1006; node 1102, 1116; leader node 1204, 1302; device 1702). For example, the method may be performed by a controller / processor 459, 475 coupled to a memory 460, 476 of the device 410, 450. Optional aspects are illustrated by dashed lines. The method allows a network node such as a base station, RSU, or edge server to designate a cluster leader and form a cluster of UEs led by those cluster leaders so that the UEs can perform ML model training in a clustered FL environment through various signaling procedures.

[0156] refer to Fig.15A At 1502, the leader node can obtain a first message including FL information of a first network node. For example, 1502 can be performed by the cluster formation component 1740. For example, referring to Figure 4 , the controller / processor 475 in the device 410 (network node such as an RSU) may obtain a first message from the device 450 (e.g., another network node such as a UE) via the RX processor 470, which may receive the first message from the device 450 via the antenna 420. In one example, referring to Fig.10 , RSU 1006 (network node) may receive a FL message 1008 (first message) including FL or model training related information (FL information) of UE 1002 (first network node). Fig.11 , the first node 1102 (network node) may receive a message 1108 (first message) including model training related information (FL information) of the second node 1104 (first network node). In another example, referring to Fig.10 , the base station 1004 (network node) may obtain a message 1014 (first message) including FL or model training related information (FL information) of the UE 1002 (first network node).

[0157] At 1504, the network node may provide a third message to the first network node indicating that the device is a candidate to become a FL cluster leader of the FL cluster, wherein the first message is responsive to the third message and indicates a request from the first network node to join the FL cluster. For example, 1504 may be performed by cluster formation component 1740. For example, referring to Figure 4, the controller / processor 475 in the device 410 (e.g., a network node such as an RSU) may provide the first message to the device 450 (e.g., another network node such as a UE) via the TX processor 416, which may send the third message to the device 450 via the antenna 420. For example, referring to Fig.11 , the first node 1102 (network node) may provide a second node 1104 (first network node) with an indication that the first node 1102 is a member of the FL cluster (eg, Fig. 9 In response to providing message 1106 (third message), first node 1102 (network node) may obtain message 1108 (first message) requesting subscription to the first node's cluster from second node 1104 (first network node).

[0158] In one example, the network node may provide the third message periodically or in response to an event trigger. Fig.11 For example, if the first node is not currently participating in an active clustered FL session, the first node 1102 (network node) may periodically (e.g., according to a preconfigured periodicity) provide message 1106 (third message). Alternatively, message 1106 may be, for example, in response to the first node 1102 determining that training or updating the UE's ML model to improve the performance of a specific ML task by the UE is event-triggered.

[0159] In one example, the network node may provide the third message to a plurality of network nodes including the first network node in a broadcast or in a multicast. Fig.11 , the first node 1102 (network node) may broadcast the message 1106 to any network node that can decode the message, including the second node 1104 (first network node). Alternatively, the message 1106 may be multicast, for example, to network nodes known to the first node 1102 (including the second node 1104). The message 1106 may also be transmitted using multicast option 1 to enhance the reliability of the solicitation message (e.g., the first node 1102 may indicate in the second stage SCI the distance at which the first node expects to receive NACKs from other nodes that fail to decode the message).

[0160] In one example, the third message may include the second FL information of the device. Fig.11, message 1106 (third message) may indicate model training related information (second FL information) of the first node 1102 (network node or device). This information may include, for example: ML tasks that the first node 1102 is participating in or interested in participating in; available ML models in training, including model status, model architecture, model training parameters, and current performance (e.g., accuracy and loss); and available computing resources (e.g., whether the first node 1102 includes a CPU or GPU, information about its clock speed, available memory, etc.). Therefore, message 1106 may include information related to Fig.10 Similar types of information as those provided in message 1014.

[0161] At 1506, the network node can provide an acknowledgment to the first network node in response to the first message. For example, 1506 can be performed by cluster formation component 1740. For example, referring to Figure 4 , the controller / processor 475 in the device 410 (e.g., a network node such as an RSU) may provide an acknowledgment to the device 450 (e.g., another network node such as a UE) via the TX processor 416, which may send the acknowledgment to the device 450 via the antenna 420. For example, referring to Fig.10 , RSU 1006 may provide FL message confirmation 1010 to UE 1002 (first network node) confirming receipt of FL message 1008 (first message).

[0162] At 1508, the network node can obtain a third message indicating an identifier of the device or the second network node from the first network node in response to the confirmation. For example, 1508 can be performed by cluster formation component 1740. For example, referring to Figure 4 , the controller / processor 475 in the device 410 (network node such as an RSU) may obtain a third message from the device 450 (e.g., another network node such as a UE) via the RX processor 470, which may receive the third message from the device 450 via the antenna 420. For example, referring to Fig.10 In response to providing the FL message confirmation 1010 (confirmation), the RSU 1006 (network node) may obtain an RSU indication message 1012 (third message) from the UE 1002 (first network node), the RSU indication message indicating an identifier of the RSU 1006 (device, such as RSU 1) or a different RSU (second network node, such as RSU 2), depending on which RSU the UE selects as an agent for delivering the FL message to the base station 1004.

[0163] At 1510, the network node may provide a fourth message including FL information and a second identifier of the first network node to the FL parameter network entity in response to the identifier of the third message indicating the device. For example, 1510 may be performed by the cluster formation component 1740. The fourth message may also include the second FL information of the device. For example, referring to Figure 4 , the controller / processor 475 in the device 410 (e.g., a network node such as an RSU) may provide a fourth message to the device 450 (e.g., a base station, a FL parameter server, or other FL parameter network entity) via the TX processor 416, which may send the fourth message to the device 450 via the antenna 420. For example, referring to Fig.10 In response to receiving an RSU indication message 1012 (third message) indicating an identifier of an RSU 1006 (a device or a network node, such as RSU 1) from a UE 1002, the RSU 1006 (e.g., RSU 1) may provide a message 1014 (fourth message) to a base station 1004 (a FL parameter network entity in this example), the fourth message including FL information of the UE 1002 indicating the identifier of the RSU and a list (or other data structure) of identifiers (including the second identifier) ​​of the UE 1002 (including the first network node) that the RSU has previously confirmed.

[0164] At 1512, the network node may provide a fourth message including a second identifier of the first network node to the FL parameter network entity in response to the third message indicating an identifier of the second network node. For example, 1512 may be performed by cluster formation component 1740. For example, referring to Figure 4 , the controller / processor 475 in the device 410 (e.g., a network node such as an RSU) may provide a fourth message to the device 450 (e.g., a base station, a FL parameter server, or other FL parameter network entity) via the TX processor 416, which may send the fourth message to the device 450 via the antenna 420. For example, referring to Fig.10 In response to receiving an RSU indication message 1012 (third message) indicating an identifier of a different RSU (a second network node, such as RSU 2) from UE 1002, RSU 1006 (a network node, such as RSU 1) may provide a message 1014 (a fourth message) to base station 1004 (the FL parameter network entity in this example), the fourth message including a list (or other data structure) of identifiers (including the second identifier) ​​of UE 1002 (including the first network node) that the RSU has previously confirmed.

[0165] At 1514, the network node may provide a second message indicating a FL cluster of the first network node based on the FL information, wherein the second message indicates one of the device or the second network node as a FL cluster leader of the FL cluster. For example, 1514 may be performed by cluster formation component 1740. For example, referring to Figure 4 , the controller / processor 475 in the device 410 (e.g., a network node such as an RSU, an edge server, a base station, a FL parameter server, or other node) may provide a second message to the device 450 (e.g., another network node such as an RSU, an edge server, a base station, a FL parameter server, or other node) via the TX processor 416, which may send the second message to the device 450 via the antenna 420. In one example, referring to Fig.10 , the RSU 1006 (network node) may provide a message 1018 (a second message) indicating a FL cluster (e.g., clusters 902, 1306) of the UE 1002 in response to receiving FL information from the UE 1002 (a first network node) in the FL message 1008, wherein the message 1018 indicates that the RSU 1006 (device or network node) is a FL cluster leader (e.g., leader node 1204, 1302) of the cluster including the UE 1002. In another example, referring to Fig.11 , the first node 1102 (network node) may provide a message 1110 (second message) indicating the FL cluster of the second node 1104 in response to receiving the FL information from the second node 1104 (first network node) in the message 1108, wherein the message 1110 indicates that the first node 1102 (device or network node) is the FL cluster leader of the cluster including the second node 1104. In another example, referring to Fig.10 , base station 1004 (network node) may provide message 1016 (second message) indicating the FL cluster of UE 1002 (first network node) in response to receiving FL information from RSU 1006 in message 1014, wherein message 1014 indicates that RSU 1006 (second network node) is the FL cluster leader of the cluster including UE 1002.

[0166] At 1516, the network node may obtain a third message from the FL parameter network entity, the third message indicating the FL cluster and indicating that the device is a FL cluster leader of the FL cluster, wherein the second message is provided to the first network node in response to the third message. For example, 1516 may be performed by cluster formation component 1740. For example, referring to Figure 4, the controller / processor 475 in the device 410 (network node such as an RSU) may obtain a third message from the device 450 (e.g., a base station, a FL parameter server, or other FL parameter network entity) via the RX processor 470, which may receive the third message from the device 450 via the antenna 420. For example, referring to Fig.10 , RSU 1006 (device or network node) may obtain message 1016 (third message) from base station 1004 (FL parameter network entity), the third message indicating the FL cluster of UE 1002 (e.g., cluster 902, 1306) and RSU 1006 is the FL cluster leader of the cluster (e.g., leader node 1204, 1302). In response to obtaining message 1016 (third message), RSU 1006 may provide message 1018 (second message) to UE 1002 (first network node).

[0167] In one example, the second message may be multicast to a plurality of network nodes including the first network node in the FL cluster. Fig.10 , RSU 1006 may provide message 1018 via multicast to those UEs 1002 having an identifier assigned or indicated in the cluster information of message 1016 (including a first network node in the cluster such as the network node of UE 1).

[0168] In one example, the second message may confirm that the first network node is allowed to join the FL cluster. Fig.11 , the first node 1102 may provide (eg, via unicast) a message 1110 (second message) confirming permission for the second node 1104 (first network node) to join the FL cluster (eg, clusters 902, 1306) led by the first node 1102 (eg, leader node 1204, 1302).

[0169] refer to Fig. 15B At 1518, depending on whether the network node is a FL parameter network entity (e.g., a base station or a FL server that can otherwise perform inter-cluster FL), the process can branch in different directions. If the network node is not a FL parameter network entity (e.g., if the network node is a cluster leader, such as an RSU, an edge server, or a FL server that can otherwise perform intra-cluster FL), the process continues at 1520, 1522, and 1524. Otherwise, if the network node is a FL parameter network entity, the process continues at 1526 and 1528.

[0170] At 1520, the network node may provide the ML model configuration including the initial weights to the first network node. For example, 1520 may be performed by the FL training component 1742. For example, referring to Figure 4, the controller / processor 475 in the device 410 (e.g., a network node such as an RSU) may provide the ML model configuration to the device 450 (e.g., a UE) via the TX processor 416, which may send the ML model configuration to the device 450 via the antenna 420. For example, referring to Fig.12 , the leader node 1204 (network node) may provide the ML model parameters (ML model configuration) to the participant node 1202 (first network node) at step 1208, which are initialized by the leader node 1204 at step 1206. The initialization of the leader node may include, for example, configuring the ML task (e.g., object detection), the neural network (e.g., CNN), the number of neurons and synapses, random weights and biases, the model algorithm (e.g., logistic regression), and other model parameters. Thus, the initial weights (e.g., Figure 6 The initial value of the weight 616 may be a random weight.

[0171] At 1522, the network node may obtain an ML model information update including an update to the initial weights from the first network node. For example, 1522 may be performed by the FL training component 1742. For example, referring to Figure 4 , the controller / processor 475 in the device 410 (network node such as an RSU) may obtain ML model information updates from the device 450 (e.g., UE) via the RX processor 470, which may receive the ML model information updates from the device 450 via the antenna 420. For example, referring to Fig.12 , after receiving the ML model parameters from the leader node 1204 and configuring its local ML model accordingly, at step 1210, the participant node 1202 (first network node) may perform local ML model training based on its corresponding data set. For example, during a given FL iteration t, the corresponding node k (corresponding to the cluster model WtCik) may train the local ML model 1211 to identify the optimal model parameters for minimizing the loss function F(WtCik), such as Figure 6 As described. For example, a node may utilize back-propagation and stochastic gradient descent to identify the optimal model weights to be applied to its corresponding neural network, which results in a minimized cross entropy loss after multiple training sessions. Thereafter, the participant node 1202 may upload its corresponding updated ML model parameters (updated ML model 1212) to the leader node 1204. For example, the participant node 1202 may send the optimized ML model weights and other information to the leader node 1204. Thus, the leader node 1204 (network node) may obtain updated ML model parameters (ML model information update) including the optimal model weights (updates to the initial weights) for its neural network from the participant node 1202 (first network node).

[0172] At 1524, the network node may provide the first network node with an aggregated ML model information update, the aggregated ML model information update comprising an aggregation of the ML model information update and a second ML model information update of a third network node in the FL cluster. For example, 1524 may be performed by the FL training component 1742. For example, referring to Figure 4 , the controller / processor 475 in the device 410 (e.g., a network node such as an RSU) may provide aggregated ML model information updates to the device 450 (e.g., a UE) via the TX processor 416, which may send the aggregated ML model information updates to the device 450 via the antenna 420. For example, referring to Fig.12 , after receiving ML model information updates from participant nodes 1202 (including an update from a UE and another update from a different UE in the same cluster (e.g., a third network node), at step 1214, the leader node 1204 may aggregate these updates to generate an updated ML model 1212 for these nodes (e.g., an updated cluster model Wt+1Ci to be applied to the next FL iteration t+1). For example, the leader node 1204 may average the corresponding model weights indicated by the participant nodes 1202 or perform some other calculation. After the leader node 1204 generates the aggregated ML model information, the participant node 1202 may receive the aggregated ML model information from the leader node 1204. Therefore, the leader node 1204 (network node) may provide the aggregated ML model information (aggregated ML model information updates) to the participant node 1202 (first network node).

[0173] In one example, the aggregated ML model information update may further include a second aggregation of the ML model information update and a third ML model information update from a fourth network node in the second FL cluster. Fig.13 At step 1308, the leader node 1302 of the corresponding cluster may transmit an updated ML model WtCi (in this example, an ML model information update) of its cluster Ci to the FL parameter server 1304, the updated ML model including the updated ML model information from the follower nodes (e.g., Fig.121G ). For example, the leader node 1302 may transmit the aggregated ML model weights it most recently generated after a given number of intra-cluster FL iterations for the FL parameter server to further aggregate (in a second aggregation) with other aggregated ML model weights (the third ML model information update in this example) generated by other leader nodes (including the fourth network node in this example) in other clusters (including the second FL cluster). After receiving the updated ML model from the cluster leader, at operation 1310, the FL parameter server 1304 may aggregate these updates to generate an updated global ML model 1311 (e.g., an updated global model Wt+1G) for the leader node. For example, the FL parameter server 1304 may average the corresponding aggregated model weights indicated by the leader node 1302 or perform some other calculation. Therefore, at step 1312, the FL parameter server may transmit the aggregated ML model information to the leader node 1302 for further training of the corresponding intra-cluster ML model 1313 (starting from the updated model Wt+1G), such as about Fig.12 UE (e.g., Fig.12 The participant node 1202) may then obtain the further aggregated updates (e.g., updated ML model 1212) from the leader node.

[0174] In one example, the second message may indicate that the second network node is the FL cluster leader. In this example, the network node may obtain the first message from the second network node, and the first message may also include an identifier of the first network node. For example, referring to Fig.10 , after the base station 1004 (network node) obtains a message 1014 (first message) including an identifier of the UE 1002 (first network node) from the RSU 1006 (second network node), the base station 1004 may provide a message 1016 (second message) indicating that the RSU 1006 (second network node) is the FL cluster leader (e.g., leader node 1204, 1302) of the cluster including the identified UE.

[0175] At 1526, the network node may obtain an ML model information update from the second network node. For example, 1526 may be performed by the FL training component 1742. For example, referring to Figure 4 , the controller / processor 475 in the device 410 (base station, FL parameter server or other FL parameter network entity) can obtain ML model information updates from the device 450 (e.g., RSU, edge server or other node) via the RX processor 470, which can receive the ML model information updates from the device 450 via the antenna 420. For example, referring to Fig.13, after the in-cluster training at step 1308 , the FL parameter server 1304 (network node) may obtain the aggregated ML model weights (ML model information update) from the leader node 1302 (second network node).

[0176] At 1528, the network node may provide an aggregated ML model information update to the second network node, the aggregated ML model information update comprising an aggregation of the ML model information update and a second ML model information update from a third network node in the second FL cluster. For example, 1528 may be performed by the FL training component 1742. For example, referring to Figure 4 , the controller / processor 475 in the device 410 (e.g., a base station, a FL parameter server, or other FL parameter network entity) may provide aggregated ML model information updates to the device 450 (e.g., an RSU, an edge server, or other node) via the TX processor 416, which may send the aggregated ML model information updates to the device 450 via the antenna 420. For example, referring to Fig.13 , after inter-cluster training of corresponding aggregate model weights (including second ML model information updates) indicated by leader node 1302 (including third network node) of different clusters (e.g., cluster 1306), the FL parameter server 1304 (network node) may provide aggregate ML model information (aggregate ML model information update) to leader node 1302 (second network node) at step 1312.

[0177] Fig.161600 is an example of a hardware implementation of an exemplary device 1602. The device 1602 is a UE and includes a cellular baseband processor 1604 (also referred to as a modem) coupled to a cellular RF transceiver 1622 and one or more subscriber identity modules (SIM) cards 1620, an application processor 1606 coupled to a secure digital (SD) card 1608 and a screen 1610, a Bluetooth module 1612, a wireless local area network (WLAN) module 1614, a global positioning system (GPS) module 1616, and a power source 1618. The cellular baseband processor 1604 communicates with the UE 104, the RSU 107, the BS 102 / 180, and / or other network nodes through the cellular RF transceiver 1622. The cellular baseband processor 1604 may include a computer-readable medium / memory. The computer-readable medium / memory may be non-transitory. The cellular baseband processor 1604 is responsible for general processing, including executing software stored on the computer-readable medium / memory. The software, when executed by the cellular baseband processor 1604, causes the cellular baseband processor 1604 to perform the various functions described above. The computer-readable medium / memory may also be used to store data manipulated by the cellular baseband processor 1604 when executing the software. The cellular baseband processor 1604 also includes a receiving component 1630, a communication manager 1632, and a sending component 1634. The communication manager 1632 includes one or more of the illustrated components. The components within the communication manager 1632 may be stored in a computer-readable medium / memory and / or configured as hardware within the cellular baseband processor 1604. The cellular baseband processor 1604 may be a component of the device 410, 450, and may include a memory 460, 476 and / or at least one of the following: a TX processor 416, 468, an RX processor 456, 470, and a controller / processor 459, 475. In one configuration, the apparatus 1602 may be a modem chip and include only the baseband processor 1604, and in another configuration, the device 1602 may be an entire UE (e.g., see Figure 4 Devices 410, 450) and include the aforementioned additional modules of device 1602.

[0178] The communication manager 1632 includes a cluster forming component 1640 configured to provide a first message including FL information, e.g., as described in conjunction with 1402. The cluster forming component 1640 is further configured to obtain a message indicating that the second network node is a candidate to become a second FL cluster leader of a second FL cluster, wherein the second network node is provided in response to the message to the first message, e.g., as described in conjunction with 1404. The cluster forming component 1640 is further configured to provide a second message indicating the first network node, e.g., as described in conjunction with 1406. The cluster forming component 1640 is further configured to obtain an acknowledgment of the FL information from the first network node, wherein the second message is provided in response to the acknowledgment, e.g., as described in conjunction with 1408. The cluster forming component 1640 is further configured to provide a second message to the first network node in response to the absence of an acknowledgment of the first message from the second network node within a message timeout window, e.g., as described in conjunction with 1410. The cluster forming component 1640 is further configured to obtain a third message in response to the FL information, the third message indicating one of the first network node or the second network node as the FL cluster leader and indicating a FL cluster of the device, for example, as described in conjunction with 1412 .

[0179] The communication manager 1632 also includes a FL training component 1642 configured to obtain an ML model configuration including initial weights from the FL cluster leader, e.g., as described in conjunction with 1414. The FL training component 1642 is further configured to provide an ML model information update including an update to the initial weights to the FL cluster leader, e.g., as described in conjunction with 1416. The FL training component 1642 is further configured to obtain an aggregated ML model information update from the FL cluster leader, the aggregated ML model information update including an aggregation of the ML model information update and a second ML model information update of a third network node in the FL cluster, e.g., as described in conjunction with 1418.

[0180] The apparatus may include executing Fig.14 Each of the boxes in the algorithm in the preceding flowchart is an additional component. Therefore, Fig.14 Each block in the aforementioned flow chart of can be performed by a component, and the apparatus may include one or more of those components. These components may be one or more hardware components that are specifically configured to perform the process / algorithm, implemented by a processor configured to perform the process / algorithm, stored in a computer-readable medium for implementation by a processor, or some combination thereof.

[0181] In one configuration, the device 1602 (and specifically, the cellular baseband processor 1604) includes a component for providing a first message including FL information, the component for providing being further configured to provide a second message indicating a first network node; and a component for obtaining a third message in response to the FL information, the third message indicating one of the first network node or the second network node as a FL cluster leader and indicating a FL cluster of the device.

[0182] In one configuration, the FL information includes at least one of: a machine learning task of the UE, an available sensor coupled to the UE for the machine learning task, an available ML model associated with the machine learning task, or available computing resources of the UE for the machine learning task.

[0183] In one configuration, the means for providing is configured to provide the first message periodically or in response to an event trigger.

[0184] In one configuration, the means for providing is configured to provide the first message in a broadcast.

[0185] In one configuration, the means for providing is configured to provide the first message to a second network node, wherein the first message may further include a request to join a second FL cluster of the second network node.

[0186] In one configuration, the means for obtaining is further configured to obtain a message indicating that the second network node is a candidate to become a second FL cluster leader of a second FL cluster, wherein the first message is provided to the second network node in response to the message.

[0187] In one configuration, the means for obtaining is further configured to obtain an acknowledgement of the FL information from the first network node, wherein the second message is provided in response to the acknowledgement.

[0188] In one configuration, the means for providing is configured to provide the second message to the first network node in response to a lack of an acknowledgement of the first message from the second network node within a message timeout window.In one configuration, the second message may further include FL information.

[0189] In one configuration, the first network node and the second network node may be, for example, RSUs or edge servers.

[0190] In one configuration, the means for obtaining is configured to obtain a third message indicating the FL cluster leader and the FL cluster of the UE in a multicast from the first network node.

[0191] In one configuration, the third message may indicate the first network node as the FL cluster leader.

[0192] In one configuration, the component for obtaining is further configured to obtain the ML model configuration including initial weights from the FL cluster leader.

[0193] In one configuration, the means for providing is further configured to provide the FL cluster leader with ML model information updates including updates to the initial weights.

[0194] In one configuration, the means for obtaining is further configured to obtain, from the FL parameter network entity, an aggregated ML model information update comprising an aggregation of the ML model information update and a second ML model information update of a third network node in the FL cluster.

[0195] In one configuration, aggregating the ML model information update may also include a second aggregation of the ML model information update with a third ML model information update from a fourth network node in the second FL cluster.

[0196] The aforementioned means may be one or more of the aforementioned components of the apparatus 1602 configured to perform the functions recited by the aforementioned means. As described above, the apparatus 1602 may include the TX processors 416, 468, the RX processors 456, 470, and the controller / processors 459, 475. Therefore, in one configuration, the aforementioned means may be the TX processors 416, 468, the RX processors 456, 470, and the controller / processors 459, 475 configured to perform the functions recited by the aforementioned means.

[0197] Fig.171700 is an example of a hardware implementation of an exemplary device 1702. The device 1702 is a network node such as an RSU or BS and includes a baseband unit 1704. The baseband unit 1704 can communicate with the UE 104, RSU 107, BS 102 / 180 or other network nodes through a cellular RF transceiver. The baseband unit 1704 may include a computer-readable medium / memory. The baseband unit 1704 is responsible for general processing, including executing software stored on the computer-readable medium / memory. The software, when executed by the baseband unit 1704, causes the baseband unit 1704 to perform the various functions described above. The computer-readable medium / memory can also be used to store data manipulated by the baseband unit 1704 when executing the software. The baseband unit 1704 also includes a receiving component 1730, a communication manager 1732, and a sending component 1734. The communication manager 1732 includes one or more of the illustrated components. The components within the communication manager 1732 may be stored in a computer-readable medium / memory and / or configured as hardware within the baseband unit 1704. The baseband unit 1704 may be a component of the device 410, 450 and may include the memory 460, 476 and / or at least one of the following: the TX processor 416, 468, the RX processor 456, 470, and the controller / processor 459, 475.

[0198] The communication manager 1732 includes a cluster forming component 1740 configured to obtain a first message including FL information of a first network node, e.g., as described in conjunction with 1502. The cluster forming component 1740 is further configured to provide a third message to the first network node, the third message indicating that the device is a candidate to become a FL cluster leader of the FL cluster, wherein the first message is responsive to the third message and indicates a request from the first network node to join the FL cluster, e.g., as described in conjunction with 1504. The cluster forming component 1740 is further configured to provide a confirmation to the first network node in response to the first message, e.g., as described in conjunction with 1506. The cluster forming component 1740 is further configured to obtain a third message indicating an identifier of the device or the second network node from the first network node in response to the confirmation, e.g., as described in conjunction with 1508. The cluster forming component 1740 is further configured to provide a fourth message including the FL information and a second identifier of the first network node to the FL parameter network entity in response to the third message indicating the identifier of the device, e.g., as described in conjunction with 1510. The cluster forming component 1740 is further configured to provide, to the FL parameters network entity, a fourth message including a second identifier of the first network node in response to the third message indicating an identifier of the second network node, e.g., as described in conjunction with 1512. The cluster forming component 1740 is further configured to provide, to the FL parameters network entity, a second message indicating a FL cluster of the first network node in response to the FL information, wherein the second message indicates one of the device or the second network node as a FL cluster leader of the FL cluster, e.g., as described in conjunction with 1514. The cluster forming component 1740 is further configured to obtain, from the FL parameters network entity, a third message indicating the FL cluster and indicating that the device is a FL cluster leader of the FL cluster, wherein the second message is provided to the first network node in response to the third message, e.g., as described in conjunction with 1516.

[0199] The communication manager 1732 includes a FL training component 1742 configured to provide the ML model configuration including the initial weights to the first network node, e.g., as described in conjunction with 1520. The FL training component 1742 is further configured to obtain, from the first network node, an ML model information update including an update to the initial weights, e.g., as described in conjunction with 1522. The FL training component 1742 is further configured to provide, to the first network node, an aggregated ML model information update including an aggregation of the ML model information update with a second ML model information update of a third network node in the FL cluster, e.g., as described in conjunction with 1524. The FL training component 1742 is further configured to obtain, from the second network node, an ML model information update, e.g., as described in conjunction with 1526. The FL training component 1742 is further configured to provide, to the second network node, an aggregated ML model information update including an aggregation of the ML model information update with a second ML model information update of a third network node in a second FL cluster, e.g., as described in conjunction with 1528.

[0200] The device may include executing FIG. 15A to FIG. 15B Each of the boxes in the algorithm in the preceding flowchart is an additional component. Therefore, FIG. 15A to FIG. 15B Each block in the aforementioned flow chart of can be performed by a component, and the apparatus may include one or more of these components. These components may be one or more hardware components, which are specifically configured to perform the process / algorithm, implemented by a processor configured to perform the process / algorithm, stored in a computer-readable medium so as to be implemented by a processor, or some combination thereof.

[0201] In one configuration, the device 1702 (and specifically, the baseband unit 1704) includes components for obtaining a first message including FL information of a first network node, and components for providing a second message indicating a FL cluster of the first network node in response to the FL information, wherein the second message indicates one of the device or the second network node as a FL cluster leader of the FL cluster.

[0202] In one configuration, the means for providing may be further configured to provide a third message to the first network node indicating that the apparatus is a candidate to become a FL cluster leader of the FL cluster, wherein the first message is responsive to the third message and indicates a request from the first network node to join the FL cluster.

[0203] In one configuration, the means for providing may be further configured to provide the third message periodically or in response to an event trigger.

[0204] In one configuration, the means for providing may be further configured to provide the third message in a broadcast or in a multicast to a plurality of network nodes including the first network node.

[0205] In one configuration, the third message may include second FL information of the device.

[0206] In one configuration, the means for providing may be further configured to provide an acknowledgement to the first network node in response to the first message.

[0207] In one configuration, the means for obtaining may be further configured to obtain, from the first network node in response to the confirmation, a third message indicating an identifier of the apparatus or the second network node.

[0208] In one configuration, the means for providing may be further configured to provide a fourth message including FL information and a second identifier of the first network node to the FL parameter network entity in response to the third message indicating the identifier of the device. In one configuration, the fourth message may also include the second FL information of the device.

[0209] In one configuration, the means for providing may be further configured to provide, to the FL parameters network entity, a fourth message including a second identifier of the first network node in response to the third message indicating an identifier of the second network node.

[0210] In one configuration, the means for obtaining may be further configured to obtain a third message from the FL parameter network entity, the third message indicating the FL cluster and indicating that the device is a FL cluster leader of the FL cluster, wherein the second message is provided to the first network node in response to the third message.

[0211] In one configuration, the second message may be multicast to a plurality of network nodes including the first network node in the FL cluster.

[0212] In one configuration, the second message may confirm that the first network node is allowed to join the FL cluster.

[0213] In one configuration, the means for providing may be further configured to provide the ML model configuration including the initial weights to the first network node.

[0214] In one configuration, the means for obtaining may be further configured to obtain, from the first network node, an ML model information update including an update to the initial weights.

[0215] In one configuration, the means for providing may be further configured to provide, to the first network node, an aggregated ML model information update comprising an aggregation of the ML model information update and a second ML model information update of a third network node in the FL cluster.

[0216] In one configuration, aggregating the ML model information update may also include a second aggregation of the ML model information update with a third ML model information update from a fourth network node in the second FL cluster.

[0217] In one configuration, the second message may indicate that the second network node is the FL cluster leader.In one configuration, the network node may obtain the first message from the second network node, and the first message may also include an identifier of the first network node.

[0218] In one configuration, the means for obtaining may be further configured to obtain the ML model information update from the second network node.

[0219] In one configuration, the means for providing may be further configured to provide an aggregated ML model information update to the second network node, the aggregated ML model information update comprising an aggregation of the ML model information update and a second ML model information update of a third network node in the second FL cluster.

[0220] The aforementioned means may be one or more of the aforementioned components of the apparatus 1702 configured to perform the functions recited by the aforementioned means. As described above, the apparatus 1702 may include the TX processors 416, 468, the RX processors 456, 470, and the controller / processors 459, 475. Therefore, in one configuration, the aforementioned means may be the TX processors 416, 468, the RX processors 456, 470, and the controller / processors 459, 475 configured to perform the functions recited by the aforementioned means.

[0221] It should be understood that the specific order or hierarchy of the blocks in the disclosed process / flowchart is merely an illustration of the exemplary method. It should be understood that the specific order or hierarchy of the blocks in the process / flowchart can be rearranged based on design preferences. Further, some blocks can be combined or omitted. The attached method claims provide the elements of each block in a sample order, but are not meant to be limited to the specific order or hierarchy provided.

[0222] The foregoing description is provided to enable any person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects. Therefore, the claims are not intended to be limited to the aspects shown herein, but to conform to the full scope consistent with the language claims, wherein the elements mentioned in the singular are not intended to mean "one and only one", unless specifically so stated, but "one or more". Terms such as "if", "when ..." and "while ..." should be interpreted as "under the conditions of ...", rather than meaning an instantaneous time relationship or reaction. That is, these phrases, such as "when ...", do not mean an instantaneous action in response to the occurrence of an action or during the occurrence of an action, but simply imply that if the conditions are met, then the action will occur, but no specific or instantaneous time limit is required for the occurrence of the action. The word "exemplary" is used herein to mean "used as an example, instance, or illustration". Any aspect described as "exemplary" herein is not necessarily interpreted as being preferred or having advantages over other aspects. Unless otherwise specifically stated, the term "some" refers to one or more. Combinations such as “at least one of A, B, or C,” “one or more of A, B, or C,” “at least one of A, B and C,” “one or more of A, B, and C,” and “A, B, C, or any combination thereof” include any combination of A, B, and / or C, and may include multiple A, multiple B, or multiple C. Specifically, combinations such as “at least one of A, B, or C,” “one or more of A, B, or C,” “at least one of A, B, and C,” “one or more of A, B, and C,” and “A, B, C, or any combination thereof” may be only A, only B, only C, A and B, A and C, B and C, or A and B and C, where any such combination may include one or more members of A, B, or C.

[0223] The term "receive" and its variations (e.g., "received" and / or "received", etc.) may alternatively be referred to as "obtain" or its respective variations (e.g., "obtained" and / or "obtained", etc.). Similarly, the term "send" and its word forms (e.g., "send" and / or "sent", etc.) may alternatively be referred to as "provide" or its corresponding word forms (e.g., "provide" and / or "provided", etc.), "generate" or its corresponding word forms (e.g., "generate" and / or "generated", etc.) and / or "output" or its corresponding word forms (e.g., "output" and / or "outputted", etc.).

[0224] All structural and functional equivalents of the elements of the various aspects described throughout the present disclosure that are known or will later be known to those of ordinary skill in the art are expressly incorporated herein by reference and are intended to be covered by the claims. In addition, nothing disclosed herein is intended to be dedicated to the public, regardless of whether such disclosure is explicitly stated in the claims. Words such as "module," "mechanism," "element," "device," etc. cannot replace the word "component." Therefore, no claim element will be understood as a component plus function unless the element is explicitly stated using the phrase "component for..."

[0225] The following examples are merely illustrative and may be combined with aspects of other embodiments or teachings described herein, but are not limited thereto.

[0226] Embodiment 1 is a device for wireless communication, the device comprising: a processor; a memory coupled to the processor, the processor being configured to: provide a first message comprising federated learning (FL) information; provide a second message indicating a first network node; and obtain a third message based on the FL information, the third message indicating one of the first network node or the second network node as a FL cluster leader and indicating a FL cluster of the device.

[0227] Embodiment 2 is a device according to embodiment 1, wherein the FL information includes at least one of the following: a machine learning task of the device; an available sensor coupled to the device for the machine learning task; an available ML model associated with the machine learning task; or available computing resources of the device for the machine learning task; and wherein each of the first network node and the second network node is an RSU or an edge server; and wherein the device is a UE.

[0228] Embodiment 3 is an apparatus according to embodiment 1 or 2, wherein the processor is configured to provide the first message periodically or in response to an event trigger.

[0229] Embodiment 4 is the apparatus of any one of embodiments 1 to 3, wherein the processor is configured to provide the first message in a broadcast.

[0230] Embodiment 5 is the apparatus of any one of embodiments 1 to 4, wherein the processor is configured to obtain confirmation of the FL information from the first network node, wherein the processor is configured to provide the second message in response to the confirmation.

[0231] Embodiment 6 is the apparatus according to any one of embodiments 1 to 5, wherein the processor is configured to obtain the third message indicating the FL cluster leader and the FL cluster of the apparatus in a multicast from the first network node.

[0232] Embodiment 7 is an apparatus according to embodiment 1 or 2, wherein the processor is configured to provide the first message to the second network node, the first message also including a request to join a second FL cluster of the second network node.

[0233] Embodiment 8 is an apparatus according to embodiment 7, wherein the processor is further configured to: obtain a message indicating that the second network node is a candidate for becoming a second FL cluster leader of the second FL cluster; wherein the processor is configured to provide the first message to the second network node in response to the message.

[0234] Embodiment 9 is an apparatus according to embodiment 8, wherein the second message also includes the FL information; and wherein the processor is configured to provide the second message to the first network node in response to a lack of confirmation of the first message from the second network node within a message timeout window; wherein the third message indicates the first network node as the FL cluster leader.

[0235] Embodiment 10 is an apparatus according to any one of embodiments 1 to 9, wherein the processor is further configured to: obtain a machine learning (ML) model configuration including initial weights from the FL cluster leader; provide an ML model information update including an update to the initial weights to the FL cluster leader; and obtain an aggregated ML model information update from the FL cluster leader, the aggregated ML model information update including an aggregation of the ML model information update and a second ML model information update of a third network node in the FL cluster.

[0236] Embodiment 11 is the apparatus of embodiment 10, wherein the aggregated ML model information update further comprises a second aggregation of the ML model information update with a third ML model information update of a fourth network node in a second FL cluster.

[0237] Embodiment 12 is a device for wireless communication, the device comprising: a processor; a memory coupled to the processor, the processor being configured to: obtain a first message comprising FL information of a first network node; and provide a second message indicating a FL cluster of the first network node based on the FL information, wherein the second message indicates one of the device or the second network node as the FL cluster leader of the FL cluster.

[0238] Embodiment 13 is an apparatus according to embodiment 12, wherein the processor is further configured to: provide a confirmation to the first network node in response to the first message; and obtain a third message indicating an identifier of the apparatus or the second network node from the first network node in response to the confirmation.

[0239] Embodiment 14 is an apparatus according to embodiment 13, wherein the processor is further configured to: provide a fourth message including the FL information and a second identifier of the first network node to a FL parameter network entity in response to the third message indicating the identifier of the apparatus.

[0240] Embodiment 15 is the apparatus of embodiment 14, wherein the fourth message further includes second FL information of the apparatus.

[0241] Embodiment 16 is an apparatus according to embodiment 13, wherein the processor is further configured to: provide a fourth message including a second identifier of the first network node to a FL parameter network entity in response to the third message indicating the identifier of the second network node.

[0242] Embodiment 17 is an apparatus according to any one of embodiments 12 to 16, wherein the processor is further configured to: obtain a third message from a FL parameter network entity, the third message indicating the FL cluster and indicating that the apparatus is the FL cluster leader of the FL cluster; wherein the second message is provided to the first network node in response to the third message.

[0243] Embodiment 18 is the apparatus of any one of embodiments 12 to 17, wherein the processor is configured to multicast the second message to a plurality of network nodes including the first network node in the FL cluster.

[0244] Embodiment 19 is an apparatus according to embodiment 12, wherein the processor is further configured to: provide a third message to the first network node indicating that the apparatus is a candidate for becoming the FL cluster leader of the FL cluster; wherein the first message is responsive to the third message and indicates a request from the first network node to join the FL cluster.

[0245] Embodiment 20 is an apparatus according to embodiment 19, wherein the processor is configured to provide the third message periodically or in response to an event trigger.

[0246] Embodiment 21 is an apparatus according to embodiment 19 or 20, wherein the processor is configured to provide the third message to a plurality of network nodes including the first network node in a broadcast or in a multicast.

[0247] Embodiment 22 is the apparatus according to any one of embodiments 19 to 21, wherein the third information comprises second FL information of the apparatus.

[0248] Embodiment 23 is the apparatus of any one of embodiments 19 to 22, wherein the second message confirms that the first network node is allowed to join the FL cluster.

[0249] Embodiment 24 is an apparatus according to any one of embodiments 12 to 23, wherein in response to the second message indicating that the apparatus is the FL cluster leader of the FL cluster, the processor is further configured to: provide a machine learning (ML) model configuration including initial weights to the first network node; obtain an ML model information update including an update to the initial weights from the first network node; and provide an aggregated ML model information update to the first network node, the aggregated ML model information update including an aggregation of the ML model information update and a second ML model information update of a third network node in the FL cluster.

[0250] Embodiment 25 is the apparatus of embodiment 24, wherein the aggregated ML model information update further comprises a second aggregation of the ML model information update with a third ML model information update of a fourth network node in a second FL cluster.

[0251] Embodiment 26 is the apparatus of any one of embodiments 12 to 23, wherein the second message indicates that the second network node is the FL cluster leader.

[0252] Embodiment 27 is the apparatus of embodiment 26, wherein the processor is further configured to obtain the first message from the second network node; and wherein the first message further includes an identifier of the first network node.

[0253] Embodiment 28 is an apparatus according to any one of embodiments 12 to 23, wherein the processor is further configured to: obtain a machine learning (ML) model information update from the second network node; and provide an aggregated ML model information update to the second network node, wherein the aggregated ML model information update includes an aggregation of the ML model information update and a second ML model information update from a third network node in the second FL cluster.

[0254] Embodiment 29 is a method for performing wireless communication at a user equipment (UE), the method comprising: providing a first message including federated learning (FL) information; providing a second message indicating a first network node; and obtaining a third message based on the FL information, the third message indicating one of the first network node or the second network node as a FL cluster leader and indicating the FL cluster of the UE.

[0255] Embodiment 30 is a method for performing wireless communication at a first network node, the method comprising: obtaining a first message including federated learning (FL) information of a second network node; and providing a second message indicating an FL cluster of the second network node based on the FL information, wherein the second message indicates one of the first network node or a third network node as the FL cluster leader of the FL cluster.

Claims

1. A device for wireless communication, the device comprising: processor; as well as a memory coupled to the processor, the processor being configured to: providing a first message including federated learning (FL) information; providing a second message indicative of the first network node; as well as A third message is obtained based on the FL information, the third message indicating one of the first network node or the second network node as a FL cluster leader and indicating a FL cluster of the device.

2. The device according to claim 1, The FL information includes information related to at least one of the following: a machine learning task for the device; an available sensor coupled to said device for said machine learning task; An available ML model associated with the machine learning task; or the available computing resources of the device for the machine learning task; and wherein each of the first network node and the second network node is a road side unit (RSU) or an edge server; and The device is a UE. 3 . The apparatus of claim 1 , wherein the processor is configured to provide the first message periodically or in response to an event trigger. The apparatus of claim 1 , wherein the processor is configured to provide the first message in a broadcast.

5. The apparatus of claim 1 , wherein the processor is configured to: Obtaining an acknowledgement of the FL information from the first network node, wherein the processor is configured to provide the second message in response to the acknowledgement. 6 . The apparatus of claim 1 , wherein the processor is configured to obtain the third message indicating the FL cluster leader and the FL cluster of the apparatus in a multicast from the first network node. 7 . The apparatus of claim 1 , wherein the processor is configured to provide the first message to the second network node, the first message further comprising a request to join a second FL cluster of the second network node.

8. The apparatus of claim 7, wherein the processor is further configured to: obtaining a message indicating that the second network node is a candidate to become a second FL cluster leader of the second FL cluster; Wherein the processor is configured to provide the first message to the second network node in response to the message.

9. The device according to claim 8, wherein the second message also includes the FL information; and wherein the processor is configured to provide the second message to the first network node in response to a lack of an acknowledgement of the first message from the second network node within a message timeout window; The third message indicates that the first network node serves as the FL cluster leader.

10. The apparatus of claim 1, wherein the processor is further configured to: Obtaining a machine learning (ML) model configuration including initial weights from the FL cluster leader; providing an ML model information update including an update to the initial weights to the FL cluster leader; and An aggregated ML model information update is obtained from the FL cluster leader, the aggregated ML model information update comprising an aggregation of the ML model information update and a second ML model information update of a third network node in the FL cluster. 11 . The apparatus of claim 10 , wherein the aggregated ML model information update further comprises a second aggregation of the ML model information update with a third ML model information update of a fourth network node in a second FL cluster.

12. An apparatus for wireless communication, the apparatus comprising: processor; as well as a memory coupled to the processor, the processor being configured to: Obtaining a first message including federated learning (FL) information of a first network node; as well as A second message indicating a FL cluster of the first network node is provided based on the FL information, wherein the second message indicates one of the device or a second network node as a FL cluster leader of the FL cluster.

13. The apparatus of claim 12, wherein the processor is further configured to: providing an acknowledgement to the first network node in response to the first message; and A third message indicating an identifier of the apparatus or the second network node is obtained from the first network node in response to the confirmation.

14. The apparatus of claim 13, wherein the processor is further configured to: In response to the third message indicating the identifier of the apparatus, a fourth message including the FL information and a second identifier of the first network node is provided to a FL parameters network entity. The apparatus according to claim 14 , wherein the fourth message further includes second FL information of the apparatus.

16. The apparatus of claim 13, wherein the processor is further configured to: A fourth message including a second identifier of the first network node is provided to the FL parameters network entity in response to the third message indicating the identifier of the second network node.

17. The apparatus of claim 12, wherein the processor is further configured to: obtaining a third message from a FL parameter network entity, the third message indicating the FL cluster and indicating that the apparatus is the FL cluster leader of the FL cluster; The second message is provided to the first network node in response to the third message.

18. The apparatus of claim 12, wherein the processor is configured to multicast the second message to a plurality of network nodes including the first network node in the FL cluster.

19. The apparatus of claim 12, wherein the processor is further configured to: providing a third message to the first network node indicating that the apparatus is a candidate to become the FL cluster leader of the FL cluster; The first message is in response to the third message and indicates a request from the first network node to join the FL cluster.

20. The apparatus of claim 19, wherein the processor is configured to provide the third message periodically or in response to an event trigger.

21. The apparatus of claim 19, wherein the processor is configured to provide the third message to a plurality of network nodes including the first network node in a broadcast or in a multicast.

22. The apparatus of claim 19, wherein the third message comprises second FL information of the apparatus.

23. The apparatus of claim 19, wherein the second message confirms that the first network node is permitted to join the FL cluster.

24. The apparatus of claim 12, wherein in response to the second message indicating that the apparatus is the FL cluster leader of the FL cluster, the processor is further configured to: providing a machine learning (ML) model configuration including initial weights to the first network node; obtaining, from the first network node, an ML model information update including an update to the initial weights; and An aggregated ML model information update is provided to the first network node, the aggregated ML model information update comprising an aggregation of the ML model information update and a second ML model information update of a third network node in the FL cluster. 25 . The apparatus of claim 24 , wherein the aggregated ML model information update further comprises a second aggregation of the ML model information update with a third ML model information update of a fourth network node in a second FL cluster.

26. The apparatus of claim 12, wherein the second message indicates that the second network node is the FL cluster leader.

27. The device according to claim 26, wherein the processor is configured to obtain the first message from the second network node; and The first message further includes an identifier of the first network node.

28. The apparatus of claim 12, wherein the processor is further configured to: Obtaining a machine learning (ML) model information update from the second network node; and An aggregated ML model information update is provided to the second network node, the aggregated ML model information update comprising an aggregation of the ML model information update and a second ML model information update from a third network node in a second FL cluster.

29. A method of wireless communication at a user equipment (UE), the method comprising: providing a first message including federated learning (FL) information; providing a second message indicative of the first network node; as well as A third message is obtained based on the FL information, the third message indicating one of the first network node or the second network node as a FL cluster leader and indicating a FL cluster of the UE.

30. A method of wireless communication at a first network node, the method comprising: obtaining a first message including federated learning (FL) information of a second network node; as well as A second message indicating a FL cluster of the second network node is provided based on the FL information, wherein the second message indicates one of the first network node or a third network node as a FL cluster leader of the FL cluster.

Images