Method and system for virtual cluster identification with ai / ML model-based radio access networks

Abstract

The present invention disclosure relates to a method and system for clustering identification of radio access network nodes with AI / ML model operation. The invention establishes a mapping relationship between the virtual clustering ID and AI / ML model identification to facilitate two-sided AI / ML interactions between a UE and its dynamically assigned virtual cluster of radio access network nodes. This approach enables efficient adaptation, resource allocation, and predictive beamforming while reducing overhead. The proposed method enhances network flexibility, reduces signaling overhead, and ensures an optimized user experience through AI / ML-based dynamic cluster assignment and adaptation.

Description

[0001] 202501718

[0002] - 1 -

[0003] TITLE

[0004] Method and system for virtual cluster identification with AI / ML model-based radio access networks

[0005] TECHNNICAL FIELD

[0006] The present invention disclosure relates to wireless communications, particularly to Al-native radio access networks in a cell-free environment, where AI / ML-driven resource allocation, beamforming, and connectivity management are enhanced through virtual clustering of radio access network nodes. It addresses the need for Al-based dynamic reconfiguration of network elements to maximize efficiency and adaptability in next-generation networks.

[0007] BACKGROUND

[0008] In 3GPP (Third Generation Partnership Project), one of the selected study items as the approved Release 18 package is AI / ML (artificial intelligence / machine learning) as described in the related document (RP-213599) addressed in 3GPP TSG (Technical Specification Group) RAN (Radio Access Network) meeting #94e. The official title of AI / ML study item is “Study on AI / ML for NR Air Interface”. The goal of this study item is to identify a common AI / ML framework and areas of obtaining gains using AI / ML based techniques with use cases. According to 3GPP, the main objective of this study item is to study AI / ML framework for air-interface with target use cases by considering performance, complexity, and potential specification impact. In particular, AI / ML model, terminology and description to identify common and specific characteristics for framework are included as one of key work scopes. Regarding AI / ML framework, various aspects are under consideration for investigation and one of key items is about lifecycle management of AI / ML model where multiple stages are included as mandatory for model training, model deployment, model inference, model monitoring, model updating etc. Also in 3GPP, two-sided (AI / ML) model is defined as a paired AI / ML model(s) over which joint inference is performed, where joint inference comprises AI / ML Inference whose inference is performed jointly across the UE and the network. Also for one-sided (AI / ML) model, UE-side (AI / ML) model is defined as an AI / ML model whose inference is performed entirely at the UE and network-side (AI / ML) model is defined as an202501718

[0009] -2 -

[0010] AI / ML model whose inference is performed entirely at the network. Currently, AI / ML specification work is at the stage of work item discussion for Release 19. Earlier, in 3GPP TR 37.817 for Release 17, titled as Study on enhancement for Data Collection for NR and EN-DC, UE (user equipment) mobility was also considered as one of AI / ML use cases and one of scenarios for model training / inference is that both functions are located within RAN node. Followingly, in Release 18 the new work item of “Artificial Intelligence (AI)ZMachine Learning (ML) for NG-RAN” was initiated to specify data collection enhancements and signaling support within existing NG-RAN interfaces and architecture. For the above active standardization works, RAN-based AI / ML model is considered very significant for both network and UE to meet any desired model operations (e.g., model training, inference, selection, switching, update, monitoring, etc.). Model information can be signaled to pair both networkside and UE-side models for various lifecycle management (LCM) operations.

[0011] However, signaling overhead indicating model information can be very high especially when model based LCM is processed between base station (BS / gNB) and multiple UEs. In LCM, model training is one of the most important parts for model deployment and currently there is no specification defined for signaling methods and network-UE behaviors so as to identify the required dataset when model updating / re-training as any activated model can be also impacted due to model / data drift. When ML condition changes, the enabled AI / ML model(s) can be impacted for model performance due to data / model drift. In this case, model re-training / updating can be executed. The existing 3GPP framework does not support a conditional, preconfigured AI / ML model switching mechanism, which can dynamically adapt to radio conditions, computational resources, and inference quality. With the increasing adoption of AI / ML models for RAN optimization and decision-making, network sharing scenarios face challenges in model selection, compatibility, and lifecycle management. Traditional AI / ML model deployment often lacks standardized compatibility across RAN, core networks (CN), and inter-operator environments, leading to inefficiencies in model execution, synchronization, and adaptation. There are several functional units defined in RAN such as RU (radio unit), DU (distributed unit), CU (central unit) as well as TRP (transmission reception point) as a network node. In conventional cellular networks, the association between a user equipment (UE) and a base station (BS) is based on geographic cell boundaries, limiting202501718

[0012] - 3 -

[0013] flexibility. In cell-free architectures, multiple distributed network nodes (e.g., TRP, DU, RU, etc.) cooperatively serve UEs without predefined cell boundaries, improving spectral efficiency and connectivity robustness. However, as AI / ML is increasingly integrated into network operations, there remains a need for efficient mapping and identification mechanisms that link UEs with dynamically changing distributed network node clusters. Current approaches lack standardized identifiers and signaling procedures to support AI / ML-driven associations, leading to inefficiencies in model synchronization and adaptation. Without a mechanism to dynamically map UEs to Al-driven distributed network node clusters, network coordination becomes complex, leading to performance bottlenecks, redundant signaling, and suboptimal resource utilization. This invention aims to overcome these challenges by introducing a cluster identification framework that enhances AI / ML-based connectivity.

[0014] US2025056252A1 proposes a clustering method in cell-free networks by focusing on optimizing the assignment of transmission reception points (TRPs) to user clusters and improves the coordination among multiple TRPs for enhanced communication quality where the approach leverages advanced signal processing and network resource management for more efficient and seamless connectivity.

[0015] US2025056321A1 addresses the assignment of radio bearer identifiers in cell-free network environments with a mechanism for dynamically managing identifiers in a distributed architecture, thereby enhancing the efficiency of data routing and reducing network latency.

[0016] WO2024248438A1 focuses on the formation of a user centric cluster for 6G cell-free femtocell deployments by utilizing multiple TRPs and integrating centralized and localized processing, it enhances indoor coverage and supports high data rates and low latency.

[0017] W02022207102A1 describes a method for a feasibility check of a new RAN slice performed by a network node with computing the estimate of occupied resources using historical data of a measurement of utilization of each resource.202501718

[0018] -4 -

[0019] US2022400373A1 describes the method of determining neural network functions and configuring models for performing wireless communications management procedures.

[0020] The present disclosure solves the cited problem by the proposed embodiments and describes as first aspect a method for dynamically managing AI / ML model operation at network entity in a cell-free radio access network, comprising: establishing a dynamic mapping between a virtual cluster identifier assigned to a virtual cluster of radio access network nodes and an AI / ML model identifier; assigning the virtual cluster identifier to a UE connection; updating the virtual cluster identifier dynamically based on UE mobility or network conditions; and synchronizing AI / ML models between the UE and the virtual cluster based on the updated virtual cluster identifier.

[0021] In some embodiments of the method according to the first aspect the method is characterized by, that UE-sided model is aligned with virtual cluster identifier-based models in the network.

[0022] In some embodiments of the method according to the first aspect the method is characterized by, that virtual cluster identifier is allowed to map multiple AI / ML models on the network side to corresponding AI / ML models running on the UE side.

[0023] In some embodiments of the method according to the first aspect the method is characterized by, that the virtual cluster identifier and associated AI / ML model identifier are conveyed to the UE through a RRC message.

[0024] In some embodiments of the method according to the first aspect the method is characterized by, that the UE performs a model compatibility check upon receiving the virtual cluster identifier and AI / ML model identifier.

[0025] In some embodiments of the method according to the first aspect the method is characterized by, that mapping table of virtual cluster identification and AI / ML model identification is maintained in the AI / ML model repository.202501718

[0026] - 5 -

[0027] In some embodiments of the method according to the first aspect the method is characterized by, that UE is allowed to identify on-device AI / ML models based on the mapping information after obtaining virtual cluster ID so that AI / ML model pair is matched for two-sided model use case.

[0028] In some embodiments of the method according to the first aspect the method is characterized by, that the virtual cluster identifier and associated AI / ML model identifier is updated via RRC Reconfiguration such as VirtualClusterlD_UPDATE message when network conditions change.

[0029] In some embodiments of the method according to the first aspect the method is characterized by, that fast adaptation to dynamic conditions with dynamic mapping information is executed through Layer-2 or Layer-1 signaling.

[0030] In some embodiments of the method according to the first aspect the method is characterized by, that the virtual cluster identifier is uniquely generated based on the UE's location, traffic demand, and network node availability.

[0031] In some embodiments of the method according to the first aspect the method is characterized by, that the virtual cluster dynamically adapts based on UE mobility, traffic load balancing, interference management, and AI / ML model operation.

[0032] The present disclosure solves the cited problem by the proposed embodiments and describes as a second aspect a system for dynamically managing AI / ML model operation in a cell-free radio access network, comprising: a virtual cluster identifier generator configured to assign a unique virtual cluster identifier based on UE mobility and network conditions; a communication module for transmitting virtual cluster identifier information and AI / ML model identifier to the UE through an RRC message; an AI / ML model repository for storing and managing AI / ML models; and a synchronization module for updating AI / ML models between the UE and the virtual cluster based on dynamic virtual cluster identifier changes.202501718

[0033] -6 -

[0034] The present disclosure solves the cited problem by the proposed embodiments and describes as a third aspect an apparatus for dynamically managing AI / ML model operation in a cell-free radio access network within a wireless communication system the apparatus comprising a wireless transceiver, a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to carry out the steps according to the first aspect.

[0035] The present disclosure solves the cited problem by the proposed embodiments and describes as a third aspect a user equipment comprising an apparatus according third aspect.

[0036] The present disclosure solves the cited problem by the proposed embodiments and describes as a fourth aspect a gNB comprising an apparatus according to the third aspect.

[0037] According to a fifth aspect, the present disclosure relates to a computer program product comprising instructions which, when executed by at least one processor, configure said at least one processor to carry out a method according to the first aspect said at least one processor to carry out a method for exchanging data according to any one of the embodiments of the present disclosure. The computer program product can use any programming language, and can be in the form of source code, object code, or in any intermediate form between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0038] According to an sixth aspect, the present disclosure relates to a computer-readable storage medium comprising instructions which, when executed by at least one processor, configure said at least one processor to carry out a method according to any one of the embodiments of the present disclosure.

[0039] SUMMARY OF THE INVENTION

[0040] The present application disclosure introduces a cluster identification mechanism that establishes a dynamic mapping between a virtual cluster of radio access network nodes and AI / ML model identifier so that two-sided AI / ML framework allows both the202501718

[0041] - 7 -

[0042] UE and the network node cluster to optimize their operations collaboratively. By implementing this approach, the invention ensures adaptive network clustering, optimized radio resource allocation, and seamless transitions between dynamically assigned virtual clusters, enhancing overall network performance.

[0043] BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is an exemplary flow chart of virtual cluster and AI / ML model mapping. Figure 2 is an exemplary signaling flow of virtual cluster identifier assignment.

[0045] Figure 3 is an exemplary flow chart of AI / ML model synchronization procedure.

[0046] Figure 4 is an exemplary flow chart of handover with virtual cluster identifier.

[0047] DETAILED DESCRIPTION

[0048] The detailed description set forth below, with reference to annexed drawings, is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that these concepts may be practiced without these specific details. In particular, although terminology from 3GPP 5G NR may be used in this disclosure to exemplify embodiments herein, this should not be seen as limiting the scope of the invention.

[0049] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Other embodiments, however, are contained within the scope of the subject matter disclosed herein, the disclosed subject matter should not be construed as limited to only the embodiments set forth herein; rather, these embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

[0050] Generally, all terms used herein are to be interpreted according to their ordinary meaning in the relevant technical field, unless a different meaning is clearly given and / or is implied from the context in which it is used. All references to a / an / the202501718

[0051] - 8 -

[0052] element, apparatus, component, means, step, etc. are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any methods disclosed herein do not have to be performed in the exact order disclosed, unless a step is explicitly described as following or preceding another step and / or where it is implicit that a step must follow or precede another step. Any feature of any of the embodiments disclosed herein may be applied to any other embodiment, wherever appropriate. Likewise, any advantage of any of the embodiments may apply to any other embodiments, and vice versa. Other objectives, features and advantages of the enclosed embodiments will be apparent from the following description.

[0053] In some embodiments, a more general term “network node” may be used and may correspond to any type of radio network node or any network node, which communicates with a UE (directly or via another node) and / or with another network node. Examples of network nodes are NodeB, MeNB, ENB, a network node belonging to MCG or SCG, base station (BS), multi-standard radio (MSR) radio node such as MSR BS, eNodeB, gNodeB, network controller, radio network controller (RNC), base station controller (BSC), relay, donor node controlling relay, base transceiver station (BTS), access point (AP), transmission points, transmission nodes, RRU, RRH, nodes in distributed antenna system (DAS), core network node (e.g. Mobile Switching Center (MSC), Mobility Management Entity (MME), etc), Operations & Maintenance (O&M), Operations Support System (OSS), Self Optimized Network (SON), positioning node (e.g. Evolved- Serving Mobile Location Centre (E-SMLC)), Minimization of Drive Tests (MDT), test equipment (physical node or software), etc.

[0054] In some embodiments, the non-limiting term user equipment (UE) or wireless device may be used and may refer to any type of wireless device communicating with a network node and / or with another UE in a cellular or mobile communication system. Examples of UE are target device, device to device (D2D) UE, machine type UE or UE capable of machine to machine (M2M) communication, PDA, PAD, Tablet, mobile terminals, smart phone, laptop embedded equipped (LEE), laptop mounted202501718

[0055] - 9 -

[0056] equipment (LME), USB dongles, UE category Ml, UE category M2, ProSe UE, V2V UE, V2X UE, etc.

[0057] Additionally, terminologies such as base station / gNodeB and UE should be considered non-limiting and do in particular not imply a certain hierarchical relation between the two; in general, “gNodeB” could be considered as device 1 and “UE” could be considered as device 2 and these two devices communicate with each other over some radio channel. And in the following the transmitter or receiver could be either gNodeB (gNB), or UE.

[0058] As will be appreciated by one skilled in the art, aspects of the embodiments may be embodied as a system, apparatus, method, or program product. Accordingly, embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects.

[0059] For example, the disclosed embodiments may be implemented as a hardware circuit comprising custom very-large-scale integration (“VLSI”) circuits or gate arrays, off-the-shelf semiconductors such as logic chips, transistors, or other discrete components. The disclosed embodiments may also be implemented in programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices, or the like. As another example, the disclosed embodiments may include one or more physical or logical blocks of executable code which may, for instance, be organized as an object, procedure, or function.

[0060] Furthermore, embodiments may take the form of a program product embodied in one or more computer readable storage devices storing machine readable code, computer readable code, and / or program code, referred hereafter as code. The storage devices may be tangible, non- transitory, and / or non-transmission. The storage devices may not embody signals. In a certain embodiment, the storage devices only employ signals for accessing code202501718

[0061] - 10 -

[0062] Any combination of one or more computer readable medium may be utilized. The computer readable medium may be a computer readable storage medium. The computer readable storage medium may be a storage device storing the code. The storage device may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, holographic, micromechanical, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.

[0063] More specific examples (a non-exhaustive list) of the storage device would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random-access memory (“RAM”), a read-only memory (“ROM”), an erasable programmable read-only memory (“EPROM” or Flash memory), a portable compact disc readonly memory (“CD-ROM”), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0064] Code for carrying out operations for embodiments may be any number of lines and may be written in any combination of one or more programming languages including an object- oriented programming language such as Python, Ruby, Java, Smalltalk, C++, or the like, and conventional procedural programming languages, such as the “C” programming language, or the like, and / or machine languages such as assembly languages. The code may execute entirely on the user’s computer, partly on the user’s computer, as a stand-alone software package, partly on the user’s computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user’s computer through any type of network, including a local area network (“LAN”), wireless LAN (“WLAN”), or a wide area network (“WAN”), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider (“ISP”)).

[0065] Furthermore, the described features, structures, or characteristics of the embodiments may be combined in any suitable manner. In the following description,202501718

[0066] - 11 -

[0067] numerous specific details are provided, such as examples of programming, software modules, user selections, network transactions, database queries, database structures, hardware modules, hardware circuits, hardware chips, etc., to provide a thorough understanding of embodiments. One skilled in the relevant art will recognize, however, that embodiments may be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects of an embodiment. Reference throughout this specification to “one embodiment,” “an embodiment,” or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases “in one embodiment,” “in an embodiment,” and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment, but mean “one or more but not all embodiments” unless expressly specified otherwise. The terms “including,” “comprising,” “having,” and variations thereof mean “including but not limited to,” unless expressly specified otherwise. An enumerated listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise. The terms “a,” “an,” and “the” also refer to “one or more” unless expressly specified otherwise.

[0068] Aspects of the embodiments are described below with reference to schematic flowchart diagrams and / or schematic block diagrams of methods, apparatuses, systems, and program products according to embodiments. It will be understood that each block of the schematic flowchart diagrams and / or schematic block diagrams, and combinations of blocks in the schematic flowchart diagrams and / or schematic block diagrams, can be implemented by code. This code may be provided to a processor of a general-purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart diagrams and / or block diagrams202501718

[0069] - 12 -

[0070] The code may also be stored in a storage device that can direct a computer, other programmable data processing apparatus, or other devices to function in a particular manner, such that the instructions stored in the storage device produce an article of manufacture including instructions which implement the function / act specified in the flowchart diagrams and / or block diagrams.

[0071] The code may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other devices to produce a computer implemented process such that the code which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart diagrams and / or block diagrams.

[0072] The flowchart diagrams and / or block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of apparatuses, systems, methods, and program products according to various embodiments. In this regard, each block in the flowchart diagrams and / or block diagrams may represent a module, segment, or portion of code, which includes one or more executable instructions of the code for implementing the specified logical function(s).

[0073] It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the Figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. Other steps and methods may be conceived that are equivalent in function, logic, or effect to one or more blocks, or portions thereof, of the illustrated Figures.

[0074] Although various arrow types and line types may be employed in the flowchart and / or block diagrams, they are understood not to limit the scope of the corresponding embodiments. Indeed, some arrows or other connectors may be used to indicate only the logical flow of the depicted embodiment. For instance, an arrow may indicate a waiting or monitoring period of unspecified duration between enumerated steps of the202501718

[0075] - 13 -

[0076] depicted embodiment. It will also be noted that each block of the block diagrams and / or flowchart diagrams, and combinations of blocks in the block diagrams and / or flowchart diagrams, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and code.

[0077] The description of elements in each figure may refer to elements of proceeding figures. Like numbers refer to like elements in all figures, including alternate embodiments of like elements.

[0078] The detailed description set forth below, with reference to the figures, is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that these concepts may be practiced without these specific details. For instance, although 3GPP terminology, from e.g., 5G NR, may be used in this disclosure to exemplify embodiments herein, this should not be seen as limiting the scope of the present disclosure.

[0079] The disclosure is related to wireless communication system, which may be for example a 5G NR wireless communication system. More specifically, it represents a RAN of the wireless communication system, which is used exchange data with UEs via radio signals. For example, the RAN may send data to the UEs (downlink, DL), for instance data received from a core network (CN). The RAN may also receive data from the UEs (uplink, UL), which data may be forwarded to the CN.

[0080] In the examples illustrated, the RAN comprises one base station, BS. Of course, the RAN may comprise more than one BS to increase the coverage of the wireless communication system. Each of these BSs may be referred to as NB, eNodeB (or eNB), gNodeB (or gNB, in the case of a 5G NR wireless communication system), an access point or the like, depending on the wireless communication standard(s)202501718

[0081] - 14 -

[0082] implemented.

[0083] The UEs are located in a coverage of the BS. The coverage of the BS corresponds for example to the area in which UEs can decode a PDCCH transmitted by the BS.

[0084] An example of a wireless device suitable for implementing any method, discussed in the present disclosure, performed at a UE corresponds to an apparatus that provides wireless connectivity with the RAN of the wireless communication system, and that can be used to exchange data with said RAN. Such a wireless device may be included in a UE. The UE may for instance be a cellular phone, a wireless modem, a wireless communication device, a handheld device, a laptop computer, or the like. The UE may also be an Internet of Things (loT) equipment, like a wireless camera, a smart sensor, a smart meter, smart glasses, a vehicle (manned or unmanned), a global positioning system device, etc., or any other equipment that may run applications that need to exchange data with remote recipients, via the wireless device.

[0085] The wireless device comprises one or more processors and one or more memories. The one or more processors may include for instance a central processing unit (CPU), a digital signal processor (DSP), a field-programmable gate array (FPGA), an application specific integrated circuit (ASIC), etc. The one or more memories may include any type of computer readable volatile and non-volatile memories (magnetic hard disk, solid-state disk, optical disk, electronic memory, etc.). The one or more memories may store a computer program product, in the form of a set of programcode instructions to be executed by the one or more processors to implement all or part of the steps of a method for exchanging data, performed at a UE’s side, according to any one of the embodiments disclosed herein.

[0086] The wireless device can comprise also a main radio, MR, unit. The MR unit corresponds to a main wireless communication unit of the wireless device, used for exchanging data with BSs of the RAN using radio signals. The MR unit may implement one or more wireless communication protocols, and may for instance be a 3G, 4G, 5G, NR, WiFi, WiMax, etc. transceiver or the like. In preferred embodiments,202501718

[0087] - 15 -

[0088] the MR unit corresponds to a 5G NR wireless communication unit.

[0089] AI / ML Model is a data driven algorithm that applies AI / ML techniques to generate set of outputs based on set of inputs.

[0090] AI / ML model delivery is a generic term referring to delivery of an AI / ML model from one entity to another entity in any manner. Note is An entity could mean network node / function (e.g., gNB, LMF, etc.), UE, proprietary server, etc.

[0091] AI / ML model Inference is a process of using trained AI / ML model to produce set of outputs based on set of inputs.

[0092] AI / ML model testing is a subprocess of training, to evaluate the performance of final AI / ML model using dataset different from one used for model training and validation. Differently from AI / ML model validation, testing does not assume subsequent tuning of the model.

[0093] AI / ML model training is a process to train an AI / ML Model [by learning the input / output relationship] in data driven manner and obtain the trained AI / ML Model for inference.

[0094] AI / ML model transfer is a delivery of an AI / ML model over the air interface in manner that is not transparent to 3GPP signaling, either parameters of model structure known at the receiving end or new model with parameters. Delivery may contain full model or partial model.

[0095] AI / ML model validation is a subprocess of training, to evaluate the quality of an AI / ML model using dataset different from one used for model training, that helps selecting model parameters that generalize beyond the dataset used for model training.

[0096] Data collection is a process of collecting data by the network nodes, management entity, or UE for the purpose of AI / ML model training, data analytics and inference.202501718

[0097] - 16 -

[0098] Federated learning I federated training is a machine learning technique that trains an AI / ML model across multiple decentralized edge nodes e.g., UEs, gNBs each performing local model training using local data samples. The technique requires multiple interactions of the model, but no exchange of local data samples.

[0099] Functionality identification is a process / method of identifying an AI / ML functionality for the common understanding between the NW and the UE. Note is Information regarding the AI / ML functionality may be shared during functionality identification. Where AI / ML functionality resides depends on the specific use cases and sub use cases.

[0100] Model activation means enable an AI / ML model for specific AI / ML-enabled feature.

[0101] Model deactivation means disable an AI / ML model for specific AI / ML-enabled feature.

[0102] Model download means Model transfer from the network to UE.

[0103] Model identification is A process / method of identifying an AI / ML model for the common understanding between the NW and the UE. The process / method of model identification may or may not be applicable and regarding the AI / ML model may be shared during model identification.

[0104] Model monitoring is A procedure that monitors the inference performance of the AI / ML model.

[0105] Model parameter update is Process of updating the model parameters of model. Model selection is the process of selecting an AI / ML model for activation among multiple models for the same AI / ML enabled feature. Model selection may or may not be carried out simultaneously with model activation.

[0106] Model switching is deactivating currently active AI / ML model and activating different AI / ML model for specific AI / ML-enabled feature.202501718

[0107] - 17 -

[0108] Model update is Process of updating the model parameters and / or model structure of model.

[0109] Model upload is Model transfer from UE to the network.

[0110] Network-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the network.

[0111] Offline field data is the data collected from field and used for offline training of the AI / ML model.

[0112] Offline training is an AI / ML training process where the model is trained based on collected dataset, and where the trained model is later used or delivered for inference. Note is This definition only serves as guidance. There may be cases that may not exactly conform to this definition but could still be categorized as offline training by commonly accepted conventions.

[0113] Online field data is the data collected from field and used for online training of the AI / ML model.

[0114] Online training is an AI / ML training process where the model being used for inference) is (typically continuously) trained in (near) real-time with the arrival of new training samples. Note is the notion of (near) real-time vs. non real-time is context-dependent and is relative to the inference time-scale. This definition only serves as guidance.

[0115] There may be cases that may not exactly conform to this definition but could still be categorized as online training by commonly accepted conventions. Note is Fine-tuning / re-training may be done via online or offline training. This note could be removed when we define the term fine-tuning.

[0116] Reinforcement Learning (RL) is a process of training an AI / ML model from input (a.k.a. state) and feedback signal (a.k.a. reward) resulting from the model’s output (a.k.a. action) in an environment the model is interacting with.202501718

[0117] - 18 -

[0118] Semi-supervised learning is a process of training model with mix of labelled data and unlabelled data.

[0119] Supervised learning is a process of training model from input and its corresponding labels.

[0120] Two-sided (AI / ML) model is a paired AI / ML Model(s) over which joint inference is performed, where joint inference comprises AI / ML Inference whose inference is performed jointly across the UE and the network, i.e, the first part of inference is firstly performed by UE and then the remaining part is performed by gNB, or vice versa.

[0121] UE-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the UE.

[0122] Unsupervised learning is a process of training model without labelled data.

[0123] Proprietary-format models is ML models of vendor-Zdevice-specific proprietary format, from 3GPP perspective. They are not mutually recognizable across vendors and hide model design information from other vendors when shared.

[0124] Open-format models is ML models of specified format that are mutually recognizable across vendors and allow interoperability, from 3GPP perspective. They are mutually recognizable between vendors and do not hide model design information from other vendors when shared.

[0125] The following explanation will provide the detailed description of the mechanism about pre-configuring and signaling the specific information about model online training by configuring a set of UE behaviors. AI / ML based techniques are currently applied to many different applications and 3GPP also started to work on its technical investigation to apply to multiple use cases based on the observed potential gains. AI / ML lifecycle can be split into several stages such as data collection / pre-202501718

[0126] - 19 -

[0127] processing, model training, model testing / validation, model deployment / update, model monitoring etc., where each stage is equally important to achieve target performance with any specific model(s). In applying AI / ML model for any use case or application, one of the challenging issues is to manage the lifecycle of AI / ML model. It is mainly because the data / model drift occurs during model deployment and inference and it results in performance degradation of AI / ML model. Fundamentally, the dataset statistical changes occur after model is deployed and model inference capability is also impacted with unseen data as input. In a similar aspect, the statistical property of dataset and the relationship between input and output for the trained model can be changed with drift occurrence. In this context, model training or re-training is one of key issues for model performance maintenance as model performance such as inferencing and / or training is dependent on different model execution environment with varying configuration parameters. To handle this issue, collaboration between UE and gNB is highly important to track model performance and re-configure model corresponding to different environments.

[0128] AI / ML model needs model monitoring after deployment because model performance cannot be maintained continuously due to drift and update feedback is then provided to re-train / update the model or select alternative model. When AI / ML model enabled wireless communication network is deployed, it is then important to consider how to handle AI / ML model in activation with re-configuration for wireless devices under operations such as model training, inference, updating, etc.

[0129] For determining information about model identification (e.g., model ID), frequent model ID assignment / re-assignment processes might occur due to model drift related to model performance variation and / or model applicable condition change. In addition, if all identified models at UE side are to be assessed and monitored, the associated signaling overhead and computing power demand can increase significantly. And signaling overhead can highly increase for model ID decision and assignment. When there are multiple models for model transfer / delivery, significant increase of signaling overhead and the limited UE capability supporting models to be transferred can be critical for the deployment of target models at UE side.202501718

[0130] - 20 -

[0131] By introducing a cluster identification mechanism that establishes a dynamic mapping between a virtual cluster of radio access network nodes and AI / ML model identifier, two-sided AI / ML framework allows both the UE and the network node cluster to optimize their operations collaboratively so that overall network performance can be enhanced along with adaptive network clustering, optimized radio resource allocation, and seamless transitions between dynamically assigned virtual clusters.

[0132] In this method, a dynamic mapping between a virtual cluster of radio access network nodes (a group of coordinated network nodes serving a UE in a cell-free manner) and AI / ML model identifier (indicating the AI / ML model used between UE side and network side) is established so that AI / ML framework allows both the UE and the virtual cluster to optimize their operations collaboratively. Specifically, a virtual cluster identifier is assigned for UE connection to cell-free networks as the assigned virtual cluster identifier is updated dynamically as UE mobility or network conditions change. Based on dynamic updates of virtual cluster identifier, the two-sided AI / ML model synchronization and adaptation is executed, ensuring seamless AI / ML model operation between the UE and network entities. Regarding the virtual cluster identifier, it is a unique identifier assigned to a virtual cluster of radio access network nodes with AI / ML model operation, which consists of multiple distributed network nodes dynamically grouped to serve a UE in a cell-free environment. The virtual cluster identifier represents a flexible and Al-driven grouping of radio access network nodes that dynamically adapts based on UE mobility, traffic conditions, and network performance metrics. The network dynamically generates a virtual cluster identifier based on the UE’s location, traffic demand, and network node availability. And the virtual cluster identifier is mapped to AI / ML model identifier(s) that is used for AI / ML use cases such as beamforming management, CSI prediction / compression, scheduling, and handover, etc.

[0133] This mapping ensures that both the UE and the network use the most optimal AI / ML model for communication. AI / ML model repository is maintained for two-sided model operation between UE and network so that UE-sided model(s) is aligned with virtual cluster identifier-based model(s) in the network. Also it is ensured that the UE and202501718

[0134] - 21 -

[0135] virtual cluster operate on compatible AI / ML models through matching model configuration. Virtual cluster identifier is allowed to map multiple AI / ML models on the network side (gNB or Near-RT RIC) to corresponding AI / ML models running on the UE side. In RAN architecture, different AI / ML models need to be synchronized between the UE side and the network side for real-time inference and traffic optimization. This mapping relation information is configured at network side and the configured mapping relation table of virtual cluster identification and AI / ML model identification is maintained in the AI / ML model repository. In addition, UE is allowed to identify on-device AI / ML models based on the mapping relation information after obtaining virtual cluster ID so that AI / ML model pair is matched for two-sided model use case. For procedural aspects, the UE requests access and receives an initial virtual cluster information mapped to AI / ML model IDs for immediate AI / ML model operation. As the UE moves, the serving cluster updates the virtual cluster identifier information and the associated AI / ML model ID(s), ensuring AI / ML model operation continuity. For model synchronization, the UE’s AI / ML model remains updated through periodic or event-triggered synchronization procedures, preventing model drift and performance degradation. For signaling aspects, a new RRC message (e.g., VirtualClusterlD_ASSIGN) is introduced to convey virtual cluster identifier information to the UE, enabling efficient assignment and updates. Fast adaptation to dynamic conditions is achieved through L2 (layer-2) and L1 (layer-1) signaling, allowing dynamic adjustments based on network state. The dedicated messages of dynamic mapping between a virtual cluster and AI / ML model identifier enable model updates for use, ensuring alignment between network-side and UE-side models. For example, the network-side model is responsible for predicting UE movement and dynamically adjusting the virtual cluster, optimizing resource allocation within the cluster. And UE-side AI / ML model supports training and predicting optimal beamforming parameters based on historical and real-time data, enhancing channel estimation and signal quality predictions with adjusting transmission and reception strategies based on the assigned virtual cluster identifier and its associated AI / ML model. During initial access, the UE receives a virtual cluster identifier information along with an AI / ML model identifier. The network and UE perform a model compatibility check to ensure both entities operate with synchronized AI / ML models. Model updates are exchanged to maintain optimal alignment. If network conditions change, a202501718

[0136] - 22 -

[0137] VirtualClusterlDJJPDATE message is sent to the UE, indicating a new cluster and AI / ML model adaptation. In a traditional network node cluster, a set of network nodes may be predefined and serve UEs based on static network configurations. In a virtual cluster, the network node grouping is dynamically formed based on any combination of factors such as UE mobility, traffic load balancing, interference management, and AI / ML model operation. A virtual cluster is not tied to any physical cell or geographic boundary and instead, it is formed logically based on the best available network nodes to serve a UE at any given time. A virtual cluster is continuously optimized using AI / ML model operation. Since a virtual cluster is dynamically formed based on AI / ML model operation, it must be assigned a virtual cluster identifier that helps map the current set of serving cluster to the AI / ML model being used.

[0138] This mapping ensures that the UE and the network operate under the matched AI / ML model pair, optimizing the transmission parameters and radio resource allocation. The introduction of virtual cluster identification and AI / ML model mapping offers several key benefits such as standardized identification for virtual clusters (that provides a unique and structured way to identify dynamically formed network node clusters by allowing efficient management, coordination, and tracking of APs serving a given UE), low-latency transitions between different network node clusters with dynamic switching between serving clusters (by minimizing packet loss and improving user experience), and AI / ML model synchronization between network and UE with the mapping between virtual cluster identifier and AI / ML model identifiers (by reducing AI / ML model mismatches with improving training efficiency and adaptability to changing network conditions).

[0139] Figure 1 illustrates an exemplary flow chart of virtual cluster and AI / ML model mapping. This flowchart shows the overall mapping process between the virtual cluster identifier and the AI / ML model used for network optimization. It indicates the steps involved in dynamically assigning a virtual cluster identifier to a UE and associating it with an appropriate AI / ML model. For UE initial access, the UE initiates a connection to the network and network determines the best virtual cluster, where202501718

[0140] - 23 -

[0141] the network evaluates various network nodes based on UE location, network conditions, and traffic load. The network assigns a unique virtual cluster identifier corresponding to the selected virtual cluster. The network maps the virtual cluster identifier to an AI / ML model and sends the virtual cluster identifier and corresponding AI / ML model identifier to the UE via RRC signaling. The UE updates its local AI / ML model repository for optimized communication. The network and UE communicate based on the mapped AI / ML model for enhanced efficiency.

[0142] Figure 2 illustrates an exemplary signaling flow of virtual cluster identifier assignment. This figure depicts the sequence of messages exchanged between the UE and the network to establish a virtual cluster identifier during initial access. RRC connection request (e.g., UE requests network access) is sent by UE and RRC connection setup (e.g., network establishes the connection) is signaled to UE. After then, network sends assigned virtual cluster ID and mapped AI / ML model ID to UE. UE then acknowledges receipt of the assigned virtual cluster ID so that UE and network begin AI / ML-driven communication based on the assigned virtual cluster ID and mapped AI / ML model ID.

[0143] Figure 3 illustrates an exemplary flow chart of AI / ML model synchronization procedure. This figure details how the network and UE ensure alignment of their AI / ML models for optimized communication. Specifically, the network periodically verifies if the AI / ML models between the UE and network are synchronized. If a mismatch or outdated model is detected, a model update is initiated. Network sends an updated AI / ML model request to the UE and the UE downloads and updates its AI / ML model. UE then confirms successful model synchronization.

[0144] Figure 4 illustrates an exemplary flow chart of handover with virtual cluster identifier. This flowchart explains how the network dynamically reassigns a UE to a new virtual cluster and updates the corresponding virtual cluster ID. For example, the network detects that the UE is moving outside the coverage of the current virtual cluster. The network assesses nearby network nodes to form a new virtual cluster. The network generates a new virtual cluster ID for the new virtual cluster. The network sends the new virtual cluster ID and updated AI / ML model ID. UE then confirms the updated202501718

[0145] -24 -

[0146] assignment so that the UE continues communication with the new virtual cluster for service continuity.

Claims

202501718- 25 -CLAIMS1. A method for dynamically managing AI / ML model operation at network entity in a cell-free radio access network, comprising:• establishing a dynamic mapping between a virtual cluster identifier assigned to a virtual cluster of radio access network nodes and an AI / ML model identifier;• assigning the virtual cluster identifier to a UE connection;• updating the virtual cluster identifier dynamically based on UE mobility or network conditions; and• synchronizing AI / ML models between the UE and the virtual cluster based on the updated virtual cluster identifier.

2. The method according to claim 1 , wherein UE-sided model is aligned with virtual cluster identifier-based models in the network.

3. The method according to one of the previous claims, wherein virtual cluster identifier is allowed to map multiple AI / ML models on the network side to corresponding AI / ML models running on the UE side.

4. The method according to one of the previous claims, wherein the virtual cluster identifier and associated AI / ML model identifier are conveyed to the UE through a RRC message.

5. The method according to one of the previous claims, wherein the UE performs a model compatibility check upon receiving the virtual cluster identifier and AI / ML model identifier.

6. The method according to one of the previous claims, wherein mapping table of virtual cluster identification and AI / ML model identification is maintained in the AI / ML model repository.

7. The method according to one of the previous claims, wherein UE is allowed to identify on-device AI / ML models based on the mapping information after obtaining202501718- 26 -virtual cluster ID so that AI / ML model pair is matched for two-sided model use case.

8. The method according to one of the previous claims, wherein the virtual cluster identifier and associated AI / ML model identifier is updated via RRC Reconfiguration such as VirtualClusterlD_UPDATE message when network conditions change.

9. The method according to one of the previous claims, wherein fast adaptation to dynamic conditions with dynamic mapping information is executed through Layer- 2 or Layer-1 signaling.

10. The method according to one of the previous claims, wherein the virtual cluster identifier is uniquely generated based on the UE's location, traffic demand, and network node availability.

11. The method according to one of the previous claims, wherein the virtual cluster dynamically adapts based on UE mobility, traffic load balancing, interference management, and AI / ML model operation.

12. A system for dynamically managing AI / ML model operation in a cell-free radio access network, comprising:• a virtual cluster identifier generator configured to assign a unique virtual cluster identifier based on UE mobility and network conditions;• a communication module for transmitting virtual cluster identifier information and AI / ML model identifier to the UE through an RRC message;• an AI / ML model repository for storing and managing AI / ML models; and • a synchronization module for updating AI / ML models between the UE and the virtual cluster based on dynamic virtual cluster identifier changes.

13. Apparatus for dynamically managing AI / ML model operation in a cell-free radio access network within a wireless communication system the apparatus202501718- 27 -comprising a wireless transceiver, a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to implement steps of the claims 1 to 11.

14. User Equipment comprising an apparatus according to claim 13.

15. gNB comprising an apparatus according to claim 13.

Images