Method of model transfer configuration signaling

Abstract

The present disclosure describes methods of using the pre-configured AI / ML (artificial intelligence / machine learning) based model transfer type information in wireless mobile communication system including base station (e.g., gNB, TN, NTN) and mobile station (e.g., UE). In AI / ML model is applied to radio access network, signaling overhead can be significantly increased for model transfer / delivery. Therefore, model operation (e.g., model training / inferencing / monitoring / updating) can be set up between network and UE by using the pre-configured type of model transfer for ML operation.

Description

[0001] 202406417

[0002] - 1 -

[0003] TITLE

[0004] Method of model transfer configuration signaling

[0005] TECHNNICAL FIELD

[0006] The present disclosure relates to AI / ML based model operation with model transfer signaling, where techniques for pre-configuring model transfer type information with priority assignment applicable to radio access network are presented.

[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 an 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 202406417

[0009] - 2 -

[0010] 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 (Al) / Machine 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. 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, limiting flexibility. In RAN, signaling is crucial for communication between the UE and the network as this signaling occurs across different layers of the protocol stack, primarily 202406417

[0011] - 3 -

[0012] L1 (Layer 1 ), L2 (Layer 2), and RRC (radio resource control). Current approaches lack standardized identifiers and signaling procedures to support AI / ML-driven associations, leading to inefficiencies in model synchronization and adaptation. Future Al-native networks will integrate AI / ML models at both the UE level and network level to enable intelligent radio access, autonomous operation, and enhanced user experience. As 3GPP introduces AI / ML-based enhancements in mobile networks, UE-side AI / ML functionalities, such as channel state information (CSI) prediction, beam management, and CSI compression, demand optimized processing criteria and reporting timelines. Traditional approaches allocate CPU resources without considering AI / ML model complexity, processing unit constraints, or real-time inference demands, leading to inefficiencies in computational resource utilization. For example, WO2024110160A1 describes a request reception for a machine learning model, wherein the request comprises information on model adaptation constraint for training of the machine learning model or an inference of the machine learning model with response to the access node being able to adapt the machine learning model using model adaptation constraint. WO2023211572A1 describes a method of implementing AI / ML for air interface optimization determining a collaboration level for AI / ML collaboration between a network and a device from among a plurality of predetermined collaboration levels. W02023006205A1 describes a method of sending a request for a first machine learning model to a machine learning model provider and receiving a response on the request with an executable file or information to access a first part of the first machine learning model as a service, and metadata associated with the first part. US2024265306A1 describes a method of collaborating with a network device with selected collaboration levels for machine learning operations with life cycle management type and model transfer format. US2022400373A1 describes the method of determining neural network functions and configuring models for performing wireless communications management procedures. WO2022161624A1 describes the method of receiving a request for retrieving or executing a ML model or a combination of ML models. TR38.843 introduced different options for model delivery / transfer to UE, training location, and model delivery / transfer format combinations for UE-side models and UE-part of two-sided models. 202406417

[0013] - 4 -

[0014] BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is an exemplary mapping relation table for model transfer.

[0016] Figure 2 is an exemplary table of the supported model structures using a bitmap. Figure 3 is an exemplary flow chart of processing ML model transfer type at network side.

[0017] Figure 4 is an exemplary flow chart of processing ML model transfer at UE side.

[0018] DETAILED DESCRIPTION

[0019] 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.

[0020] 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.

[0021] 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 / the 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 202406417

[0022] - 5 - 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.

[0023] 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.

[0024] 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 mounted equipment (LME), USB dongles, UE category Ml, UE category M2, ProSe UE, V2V UE, V2X UE, etc.

[0025] Additionally, terminologies such as base station / gNodeB and UE should be considered non-limiting and do in particular not imply a certain hierarchical relation 202406417

[0026] - 6 - 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.

[0027] 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.

[0028] 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.

[0029] 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 code

[0030] 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, 202406417

[0031] - 7 - optical, electromagnetic, infrared, holographic, micromechanical, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.

[0032] 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.

[0033] 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”)).

[0034] Furthermore, the described features, structures, or characteristics of the embodiments may be combined in any suitable manner. In the following description, 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 202406417

[0035] - 8 - 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.

[0036] 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 fimctions / acts specified in the flowchart diagrams and / or block diagrams

[0037] 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. 202406417

[0038] - 9 -

[0039] 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.

[0040] 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).

[0041] 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.

[0042] 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 the 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. 202406417

[0043] - 10 -

[0044] 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.

[0045] 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.

[0046] 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.

[0047] 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) implemented.

[0048] 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. 202406417

[0049] - 11 -

[0050] 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.

[0051] 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.

[0052] 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, the MR unit corresponds to a 5G NR wireless communication unit.

[0053] AI / ML Model is a data driven algorithm that applies AI / ML techniques to generate set of outputs based on set of inputs. 202406417

[0054] - 12 -

[0055] 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.

[0056] AI / ML model Inference is a process of using trained AI / ML model to produce set of outputs based on set of inputs.

[0057] 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.

[0058] 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.

[0059] AI / ML model transfer is a delivery of an AI / ML model over the air interface in manner that is not transparent to 3GPP signalling, either parameters of model structure known at the receiving end or new model with parameters. Delivery may contain full model or partial model.

[0060] 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.

[0061] 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.

[0062] 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. 202406417

[0063] - 13 -

[0064] 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.

[0065] Model activation means enable an AI / ML model for specific AI / ML-enabled feature.

[0066] Model deactivation means disable an AI / ML model for specific AI / ML-enabled feature.

[0067] Model download means Model transfer from the network to UE.

[0068] 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.

[0069] Model monitoring is A procedure that monitors the inference performance of the AI / ML model.

[0070] 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.

[0071] Model switching is deactivating currently active AI / ML model and activating different AI / ML model for specific AI / ML-enabled feature.

[0072] Model update is Process of updating the model parameters and / or model structure of model.

[0073] Model upload is Model transfer from UE to the network. 202406417

[0074] - 14 -

[0075] Network-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the network.

[0076] Offline field data is the data collected from field and used for offline training of the AI / ML model.

[0077] 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.

[0078] Online field data is the data collected from field and used for online training of the AI / ML model.

[0079] 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.

[0080] 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.

[0081] 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.

[0082] Semi-supervised learning is a process of training model with mix of labelled data and unlabelled data. 202406417

[0083] - 15 -

[0084] Supervised learning is a process of training model from input and its corresponding labels.

[0085] 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.

[0086] UE-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the UE.

[0087] Unsupervised learning is a process of training model without labelled data.

[0088] 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.

[0089] 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.

[0090] 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- 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. 202406417

[0091] - 16 -

[0092] It is mainly because the data / model drift occurs during model deployment / inference and it results in performance degradation of AI / ML model.

[0093] 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.

[0094] To handle this issue, collaboration between UE and gNB is highly important to track model performance and re-configure model corresponding to different environments. 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.

[0095] 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.

[0096] In this method, a list of multiple types for ML model transfer is configured and ML model transfer types are defined in the network’s RRC configuration, where each ML model transfer type might have a unique identifier (e.g., an index or ID). 202406417

[0097] - 17 -

[0098] Configuration information about ML model transfer type is signaled as part of RRC message or L1 / L2 signaling. A specific ML model transfer type is chosen for specific ML use case or application. LCM phases (e.g., training, inferencing, monitoring, etc.) and / or RRC states (e.g., active, inactive, idle) can be associated with specific model transfer type(s) if applicable. For example, prioritization of specific model transfer(s) is decided according to each model transfer's use related to LCM phase and / or device RRC state. Adaptation of ML model transfer type with / without the associated model ID is applied so that (semi-)statically ML model transfer type is applied to UE with RRC re-configuration, or dynamically ML model transfer type is applied to UE with L1 or L2 message (e.g., PDCCH or MAC CE).

[0099] Indication message of supported model transfer types (e.g., full / partial model) is in association with the configured specific model transfer type. Bitmap is used to indicate the supported model structure with any configured ML model transfer type (e.g., each bit represents a predefined model structure). In addition, priority index is indicated if the network prefers certain model transfer type under specific conditions (e.g., network conditions or UE reported resource constraints) where a priority index to each model transfers based on its suitability for different model transfer types is assigned. A mapping table associating each priority index with a list of model transfer types is configured if applicable and the mapping table reference or a subset of the mapping information is sent to UE via L1 / L2 or RRC signaling. UE can also provide any preferred model transfer type for prioritization based on device condition. Target models or candidate models for model transfer are prioritized for the associated priority level so that any prioritized model(s) can be transferred among others based on the configured prioritization criteria (e.g., the current network conditions, UE capability status, UE context, etc.). Another mapping relationship can be also set between priority index and model ID or model structure ID (via system information or dedicated RRC signaling). Indication message for any specific model with priority index is sent for model transfer (via L1 / L2 or RRC signaling). A list of multiple types for ML model transfer are configured at network side and a specific ML model transfer type for specific ML use case or application is determined. For capability reporting, UEs can report their supported model structures using a single bitmap field. 202406417

[0100] - 18 -

[0101] For efficient model transfer, the bitmap is applied to determine which model structures are supported by the UE and transfer the corresponding parameters efficiently. The mapping relation between model / functionality ID and full / partial model transfer type is configured, where model ID serves as a unique identifier for a specific AI / ML model and encapsulates all relevant information about the model, including its architecture, version, and associated parameters. The model ID is essential for tracking model versions and identifying model capabilities. Functionality ID represents the specific functions or tasks that the AI / ML model is designed to execute and helps in understanding the operational context of the model and its relevance to the UE's current needs.

[0102] The Functionality ID is important for mapping use cases of associating the model with specific applications or scenarios (e.g., predictive analytics, anomaly detection) and assessing whether the model's functionality aligns with the UE's current operational requirements. The network side initiates the model transfer process by sending a request to the UE, which includes the relevant configuration information for the AI / ML model. Prior to executing the model transfer, the UE assesses its current state and capabilities, generating a report on the applicability and availability of the requested AI / ML model. The UE evaluates various factors such as on-device resources (e.g., availability of computational power and memory), model applicability (e.g., relevance of the model to the current operational context and tasks), network conditions (e.g., current network performance metrics that may affect model transfer). Based on this evaluation, the UE generates a report indicating whether the model is applicable and available for use. Upon receiving the UE report, the network determines the appropriate model transfer type such as full model transfer (e.g., if the UE indicates that the model is fully applicable and available, the network proceeds with a complete transfer of the model) and partial model transfer (e.g., if the UE indicates limitations (e.g., insufficient resources or partial applicability), the network may opt for a partial model transfer, sending only the necessary components or parameters required for the UE to function effectively). 202406417

[0103] - 19 -

[0104] Target model for transfer is used as either common part of multiple models across different models or a specific model's dedicated part. Regarding data for transfer, there are a list of elements as follows. Model ID ensures that the correct model is associated with the dataset and configuration used on both the UE and network sides. Model structure information describes the architecture or structure of the AI / ML model and allows the UE or network to understand how the model operates, ensuring compatibility between the two sides. Model parameters are the learned weights and biases (or other relevant parameters) of the AI / ML model, trained by the network or other entities. Dataset ID refers to the identifier for the dataset used in model training that helps ensure that the same dataset has been used during the training of the model. Input feature set contains the relevant features used by the AI / ML model to make predictions or decisions that informs the UE or network what kind of data the model expects as input (e.g., CSI, channel measurements, or user mobility patterns). If the model undergoes periodic updates, the version or iteration number of the model might be transferred as this allows the UE to keep track of the model’s updates and ensures that an outdated version of the model is not used. The AI / ML model delivery may include specific performance metrics or thresholds that must be met, such as accuracy, latency, or reliability.

[0105] In a real deployment scenario, a network node configures, via RRC signaling, a plurality of AI / ML model transfer types, each identified by a identifier. The configuration further includes a bitmap (e.g., indicating UE-supported model structures per transfer type), a priority index and an index-to-type mapping. A transfer type responsive to LCM phase (e.g., training, inference, monitoring) is selected at network with UE RRC state (e.g., Connected / lnactive / ldle). Semi-static updates are conveyed via RRCReconfiguration, while dynamic selection is signaled via L1 / L2, e.g., PDCCH / DCI or MAC control elements. The UE report capabilities using a single bitmap field, signal preferred transfer types and resource constraints, and receive target / candidate model identifiers with priority indices.

[0106] For model structure, it denotes the formal specification of an AI / ML model’s architecture and its logical components that together determine the model operation. A model structure includes, for example, the layer topology (e.g., number and types of layers), parameter categories (e.g., weights, biases), supported data formats 202406417

[0107] - 20 -

[0108] (input / output), quantization or compression schemes, and associated metadata. A partial model denotes any subset or fragment of a full model that provides a particular functionality or to perform an incremental update without transmitting the entire model. For example, partial model can be a subset of layer parameters (e.g., the last N layers), quantized or compressed parameter sets, and delta updates (residuals) relative to a reference model version, as described by metadata to support segmented transfer and retransmission or resume operations. A model transfer type (also referred to as transfer type) is a semantically and operationally defined category that specifies how a model or model fragment is transferred between network entities and / or a UE. Each model transfer type is identified by a unique identifier (e.g., TransferTypelD) and defines transmission semantics and parameters such as full model transfer, partial model transfer, delta transfer, quantized transfer, shared / common transfer. The TransferTypelD is carried via, for example, RRC IE or MAC CE to indicate the procedure to be used for a given transfer. A model ID is a unique identifier that designates a specific AI / ML model in a particular version or revision, as it directly or indirectly indicates the model’s structural reference (e.g., ModelStructurelD). The Model ID is also used for version tracking, mapping to transfer types, selection of target / candidate models for transfer during lifecycle operations. Prioritization criteria consists of the set of metrics, conditions and policy rules used to determine an ordering or priority index for model transfer operations by including network conditions (e.g., available throughput, latency, packet loss), UE-reported capability parameters (e.g., available memory, compute capacity, supported model structures), energy state (e.g., battery level), current RRC state (e.g., Connected, Inactive, Idle), LCM phase of the model (e.g., training, inference, monitoring), application QoS requirements, and security / privacy constraints. Prioritization criteria may be evaluated to assign a priority index or to select in a mapping table that associates priority levels with lists of TransferTypelDs, ModellDs or ModelStructurelDs.

[0109] Figure 1 shows an exemplary mapping relation table for model transfer. In this example, a list of multiple types for ML model transfer are configured at network side and a specific ML model transfer type for specific ML use case or application is determined. A set of ML model transfer types are defined in the network’s RRC 202406417

[0110] - 21 - configuration, and each ML model transfer type might have an identifier (e.g., an index or ID). ML model transfer type information is signaled as part of RRC message or L1 / L2 signaling. The mapping relation between model / functionality ID and full / partial model transfer type is configured for adaptive model transfer configuration. Based on the UE report about the applicability and availability of the AI / ML model, it can utilize the mapping relation to make informed decisions. For full model transfer, if the model ID (identified as MID_1 ) is fully applicable and the corresponding functionality ID aligns with the UE's needs, the network initiates a full model transfer. For partial model transfer, if the model ID is only partially applicable or if the UE has limited resources, the network can transfer only the components associated with the relevant functionality ID, optimizing resource usage. For partial model transfer, subset of model (identified as MID_1_x) is sent to UE with support of applicable functionality (identified as FID_1 _y) where x and y represents part of identifier in association with the number of model subsets and functionality subsets under partial model transfer type, respectively. In addition, there can be multiple model IDs and the associated functionality IDs that belong to either full model transfer type or partial model transfer type such as MID_2 / FID_2, MID_3 / FID_3, etc.

[0111] Figure 2 shows an exemplary table of the supported model structures using a bitmap. In this example, bitmap for UE #1 indicates supporting model structures A, C, and D. Bitmap for UE #2 indicates supporting model structures B and D. Bitmap for UE #3 indicates supporting model structures A, B, and D. For capability reporting, UEs can report their supported model structures using a single bitmap field. For efficient model transfer, the bitmap is applied to determine which model structures are supported by the UE and transfer the corresponding parameters efficiently.

[0112] Figure 3 shows an exemplary flow chart of processing ML model transfer type at network side. In this example, based on the pre-configured ML model transfer types and the associated parameter set information, a specific ML model transfer type is configured and sent to a UE so that one or more ML model(s) can be processed for model transfer. If priority index information is indicated as well, different model transfer types are prioritized and / or different model (structure) IDs are prioritized. Depending on deployment scenarios, UE can indicate the preferred ML model 202406417

[0113] - 22 - transfer type information via uplink so that network side can consider UE indication message for ML model transfer configuration. The process begins with the network initiating a model transfer request to the UE, including relevant configuration information. The network then waits for a report from the UE regarding the applicability and availability of the AI / ML model. Upon receiving the report, the network analyzes it to determine whether to proceed with a full or partial model transfer. The appropriate transfer is initiated, and the process concludes.

[0114] Figure 4 shows an exemplary flow chart of processing ML model transfer at UE side. In this example, UE can provide the supported model structures and / or model transfer types based on RRC configuration information. When indication message about specific model transfer type is received at UE, one or more ML model(s) can then be processed for model transfer. Decision of specific ML model transfer type is given by network side or by UE autonomously with confirmation from network side. The UE starts by receiving the model transfer request from the network. It evaluates the model's applicability and availability based on its resources and operational context. The UE generates a report and sends it back to the network. After sending the report, the UE waits for the model transfer, which it then receives and loads for execution.

Claims

202406417- 23 -CLAIMS1. A method of model transfer configuration signaling by configuring a list of multiple types for ML model transfer in a wireless communication system, comprising:• Defining ML model transfer types in the network’s RRC configuration;• Assigning each ML model transfer type with a unique identifier;• Configuring mapping relation information;• Deciding prioritization of specific model transfer type;• Sending indication message of supported model transfer types.

2. The method according to previous claim 1 , wherein configuration information about ML model transfer type is signaled as part of RRC message or L1 / L2 signaling.

3. The method according to one of the previous claims, wherein the network determines the appropriate model transfer type such as full model transfer and partial model transfer.

4. The method according to one of the previous claims, wherein a specific ML model transfer type is chosen for specific ML use case or application.

5. The method according to one of the previous claims, wherein the mapping relation between model / functionality ID and full / partial model transfer type is configured.

6. The method according to one of the previous claims, wherein LCM phases (e.g., training, inferencing, monitoring, etc.) and / or RRC states (e.g., active, inactive, idle) is associated with specific model transfer type(s) if applicable.

7. The method according to one of the previous claims, wherein prioritization of specific model transfer(s) is decided according to each model transfer's use related to LCM phase and / or device RRC state.202406417- 24 -8. The method according to one of the previous claims, wherein adaptation of ML model transfer type with / without the associated model ID is applied so that (semi- )statically ML model transfer type is applied to UE with RRC re-configuration, or dynamically ML model transfer type is applied to UE with L1 or L2 message (e.g., PDCCH or MAC CE).

9. The method according to one of the previous claims, wherein indication message of supported model transfer types (e.g., full / partial model, common / dedicated model) is in association with the configured specific model transfer type.

10. The method according to one of the previous claims, wherein bitmap is used to indicate the supported model structure with any configured ML model transfer type (e.g., each bit represents a predefined model structure).11 . The method according to one of the previous claims, wherein priority index is indicated if the network prefers certain model transfer type under specific conditions (e.g., network conditions or UE reported resource constraints).

12. The method according to one of the previous claims, wherein a priority index to each model transfers based on its suitability for different model transfer types is assigned.

13. The method according to one of the previous claims, wherein a mapping table associating each priority index with a list of model transfer types is configured if applicable (e.g., sent via L1 / L2 or RRC signaling).

14. The method according to one of the previous claims, wherein UE can provide any preferred model transfer type for prioritization based on device condition.

15. The method according to one of the previous claims, wherein target models or candidate models for model transfer are prioritized for the associated priority level so that any prioritized model(s) is transferred among others based on the202406417- 25 - configured prioritization criteria (e.g., the current network conditions, UE capability status, UE context, etc.).

16. The method according to one of the previous claims, wherein separate mapping relationship is set between priority index and model ID or model structure ID (via system information or dedicated RRC signaling).

17. The method according to one of the previous claims, wherein indication message for any specific model with priority index is sent for model transfer (via L1 / L2 or RRC signaling).

18. The method according to one of the previous claims, wherein for capability reporting UEs report their supported model structures using a single bitmap field.

19. The method according to one of the previous claims, wherein the bitmap for efficient model transfer is applied to determine which model structures are supported by the UE and transfer the corresponding parameters efficiently.

20. Apparatus for model transfer configuration signaling by configuring a list of multiple types for ML model transfer in 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 implement steps of the claims 1 to 19.21 . User Equipment comprising an apparatus according to claim 20.

22. gNB comprising an apparatus according to claim 20.

23. Wireless communication system for model transfer configuration signaling by configuring a list of multiple types for ML model transfer comprises user equipment according to claim 21 , gNB according to claim 22, whereby the user Equipment and the gNB each comprises a processor coupled with a memory in202406417- 26 - which computer program instructions are stored, said instructions being configured to implement steps of the claims 1 to 19.

Images