Model parameter adjustment signaling in ran

Abstract

The present disclosure describes methods of using the pre-configured AI / ML (artificial intelligence / machine learning) based a set of AI / ML adaptive modes 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, model performance can be significantly impacted with ML processing capability degradation. Therefore, model operation (e.g., model training / inferencing / monitoring / updating) can be set up between network and UE by using multiple sub-categorized mode adjustments for ML operation.

Description

[0001] 202406422

[0002] - 1 -

[0003] TITLE

[0004] Method of model parameter adjustment signaling in RAN

[0005] TECHNNICAL FIELD

[0006] The present disclosure relates to AI / ML based model operation with a set of AI / ML adaptive mode signaling, where techniques for pre-configuring and signaling the specific information about multiple sub-categorized mode adjustments 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.

[0009] 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 onesided (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 202406422

[0010] - 2 - 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 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.

[0011] 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 network-side 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.

[0012] W02024010340A1 describes a method for reporting UE AI / ML capability to a network with an indication of the UE AI / ML capability and an indication of the network AI / ML capability.

[0013] US2022116764A1 describes a method of UE reporting with UE grouping.

[0014] US2022360973A1 describes a method of UE capability with indication of one or more ML capability and associated ML procedure. 202406422

[0015] - 3 -

[0016] US2023075276A1 describes a method of sending request message including indication of ML model or function with parameter configuration transmission.

[0017] US2024276357A1 describes a method of transmitting meta information associated with ML model among network functions.

[0018] WO2024061568A1 describes a method for capability reporting for multi-model AI / ML UE features including identifying ML model available at the device side for a predetermined scenario.

[0019] BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 is an exemplary table of AI / ML adaptive modes.

[0021] Figure 2 is an exemplary mapping relation table of applying adaptive mode.

[0022] Figure 3 is an exemplary flow chart of processing adaptive mode at network side. Figure 4 is an exemplary flow chart of processing adaptive mode at UE side.

[0023] Figure 5 is an exemplary flow chart of switching adaptive modes at UE side.

[0024] DETAILED DESCRIPTION

[0025] 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.

[0026] 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 202406422

[0027] - 4 - 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.

[0028] 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 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.

[0029] 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. 202406422

[0030] - 5 -

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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. 202406422

[0035] - 6 -

[0036] 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

[0037] 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.

[0038] 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.

[0039] 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 202406422

[0040] - 7 - 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”)).

[0041] 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 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.

[0042] 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 202406422

[0043] - 8 - 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

[0044] 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.

[0045] 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.

[0046] 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).

[0047] 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. 202406422

[0048] - 9 -

[0049] 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.

[0050] 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.

[0051] 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.

[0052] 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. 202406422

[0053] - 10 -

[0054] 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.

[0055] 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.

[0056] 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.

[0057] 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. 202406422

[0058] - 11 -

[0059] 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.

[0060] AI / ML Model is a data driven algorithm that applies AI / ML techniques to generate set of outputs based on set of inputs.

[0061] 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.

[0062] AI / ML model Inference is a process of using trained AI / ML model to produce set of outputs based on set of inputs.

[0063] 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.

[0064] 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.

[0065] 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. 202406422

[0066] - 12 -

[0067] 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.

[0068] 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.

[0069] 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.

[0070] Functionality identification is a process / method of identifying an AI / ML functionality for the common understanding between the network 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.

[0071] Model activation means enable an AI / ML model for specific AI / ML-enabled feature.

[0072] Model deactivation means disable an AI / ML model for specific AI / ML-enabled feature.

[0073] Model download means Model transfer from the network to UE.

[0074] Model identification is A process / method of identifying an AI / ML model for the common understanding between the network 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.

[0075] Model monitoring is A procedure that monitors the inference performance of the AI / ML model. 202406422

[0076] - 13 -

[0077] 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.

[0078] Model switching is deactivating currently active AI / ML model and activating different AI / ML model for specific AI / ML-enabled feature.

[0079] Model update is Process of updating the model parameters and / or model structure of model.

[0080] Model upload is Model transfer from UE to the network.

[0081] Network-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the network.

[0082] Offline field data is the data collected from field and used for offline training of the AI / ML model.

[0083] 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.

[0084] Online field data is the data collected from field and used for online training of the AI / ML model.

[0085] 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. 202406422

[0086] - 14 -

[0087] 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.

[0088] 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.

[0089] Semi-supervised learning is a process of training model with mix of labelled data and unlabelled data.

[0090] Supervised learning is a process of training model from input and its corresponding labels.

[0091] 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.

[0092] UE-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the UE.

[0093] Unsupervised learning is a process of training model without labelled data.

[0094] 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.

[0095] Open-format models is ML models of specified format that are mutually recognizable across vendors and allow interoperability, from 3GPP perspective. They are mutually 202406422

[0096] - 15 - recognizable between vendors and do not hide model design information from other vendors when shared.

[0097] 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. It is mainly because the data / model drift occurs during model deployment / 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.

[0098] 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. 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. For determining information about model identification (e.g., model ID), frequent model ID 202406422

[0099] - 16 - 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. When AI / ML models are processed on a UE device, the associated processing capability of AI / ML model may degrade due to limited computational resources, thermal constraints, or other factors (e.g., site, mobility, etc.). With UE ML capability degradation, the overall end-to-end model performance between network side and UE side can be impacted. The potential impact on model operation is the mismatch between the pre-trained model size and dataset / feature set size based on the applicability of UE processing capability. In this method, a set of AI / ML adaptive modes are configured by network side for applying one of the sub-categorized mode adjustments such as Mode-1 (adaptation of ML model size only), Mode-2 (adaptation of dataset size only), Mode-3 (adaptation of feature set only), Mode-4 (any combinations of Mode-11-21-3), where those set of AI / ML adaptive modes are defined in the network’s RRC configuration and signaled as part of RRC message or L1 / L2 signaling.

[0100] The configured adaptive modes can be also mapped to execution types (e.g., real- network, digital-twin network, hybrid with real network and digital-twin network). Adaptive modes support seamless operation across digital twin-assisted LCM phases including data collection, model training, model monitoring, inference, etc.

[0101] The number of modes can vary for different use cases with more combinations of modes. The network configures the adaptive modes based on predefined criteria, including the current resource availability of the UE, network conditions, and the specific tasks the AI / ML model is intended to perform.

[0102] Each mode is associated with specific identifiers that facilitate tracking and management of the models, datasets, and feature sets. Specifically, Mode-1 represents model granularity changes to reduce the model size dynamically based on the available processing capability (e.g., pruning, quantization). In this mode, the network can increase or decrease the size of the ML model based on the processing 202406422

[0103] - 17 - capabilities of the UE. The model size can be adjusted by modifying the number of parameters or layers in the model architecture. Mode-2 represents dataset size adjustment by selecting a subset of data that provides a balance between performance and processing capability used for model inference or other LCM operations. This mode allows the network to modify the dataset size used for training or inference. The network can select a subset of the dataset that is most relevant to the current task, ensuring efficient use of resources while maintaining model performance. Mode-3 represents feature set modification for the input feature set by selecting a subset of features or reducing the dimensionality to lower the computational load on the UE. The network can adjust the feature set utilized by the model, selecting or deselecting features based on their importance and relevance to the task at hand. This adaptation helps simplify the model and reduce computational overhead. Mode-4 provides the flexibility to combine adaptations from Modes 1 , 2, and 3 as the network can simultaneously adjust the model size, dataset size, and feature set based on the UE's capabilities and the specific requirements of the task. Regarding model configuration information, model size parameters include initial size (e.g., the original size of the model such as number of parameters), minimum size (e.g., the smallest allowable size for the model when adapting), maximum size (e.g., the largest allowable size for the model). Regarding dataset configuration information, dataset size parameters include initial size (e.g., the original size of the dataset such as number of samples), minimum size (e.g., the smallest allowable size for the dataset when adapting), maximum size (e.g., the largest allowable size for the dataset).

[0104] Regarding feature set configuration information, initial features include a list of all features initially included in the model and feature importance scores indicate the importance of each feature for model performance. Along with the pre-configured adaptive mode selection, the associated assistance information is configured to be sent. For indication message (via L1 / L2 signaling), it is used for triggering the preconfigured adaptive modes via uplink or downlink. Based on the triggered indication message, model reconfiguration or transmission of new AI / ML model parameters is enabled (e.g., via downlink). Any specific adaptive mode(s) can be directly included in indication message for activation via downlink or uplink. Model-specific information 202406422

[0105] - 18 - is conveyed such as request for processing capacity or resource availability at the UE (e.g., sending a request for the UE to report its available processing resources that can be sent via UE capability signaling). For RRC reconfiguration messages, it is used in informing the UE about new AI / ML model configurations or updates to the existing model structure. These messages can include details such as model size (e.g., information on the size of the model, allowing the UE to determine if it can handle the model based on its processing capabilities), input feature set (e.g., details on which input features are required for the model, potentially allowing the UE to simplify the model if needed). If necessary, one or more look-up tables representing mapping relation between model granularity, subset of data and / or subset of features is preset. Depending on selection of AI / ML adaptive mode, the associated parameter set is configured to mapped together such as quantized dataset size, feature subset, or model granularity level where they can be also indicated as identifiers.

[0106] The new LCID is specifically configured to carry information related to AI / ML adaptive modes, where request for selection of adaptive modes (for example, the UE can signal the need for adjustments in the model, such as reducing model size or changing the input feature set or dataset size) is included. New LCID is defined to be used specifically for AI / ML model-related MAC CE containing LCID header (for the newly defined value for AI / ML adaptive mode signaling) and the requested adaptive mode(s) based on target model ID and UE processing capability updates. In downlink, this LCID to send MAC CE is used to configure the UE with the appropriate AI / ML adaptive mode. In uplink, the UE can use this LCID to report its processing capabilities, request adjustments, or acknowledge receipt of new model configurations.

[0107] Network side uses the newly defined LCID in a MAC PDU to send AI / ML adaptive mode configuration data to the UE and UE processes the information to adjust the intended adaptive mode. A set of AI / ML adaptive modes are configured by network side for applying one of the sub-categorized mode adjustments. AI / ML adaptive modes are defined in the network’s RRC configuration and signaled as part of RRC message or L1 / L2 signaling. For each sub-modes, it indicates the specific quantized selection of each mode. For example, if Mode 1 is about model granularity changes, 202406422

[0108] - 19 - each sub-modes have different granularity levels of model size. As another example, if Mode 2 is about dataset size adjustment, each sub-modes have different dataset sizes or subset of data for selection. Associated data identifier in the table is about representing any valid ID information related to specific mode and sub-mode such as model ID and / or dataset ID, feature set ID, etc.

[0109] Each adaptive mode, or sub-mode, is mapped to different identifiers so that the network and UE maintain a common reference when applying mode-specific reconfiguration. Such mapping information can be semi-statically provided in system information blocks (SIB) or dynamically updated through dedicated RRC messages. Furthermore, the adaptive mode selection may be triggered either by the network via downlink signaling or autonomously by the UE when local resource constraints or latency conditions require immediate adaptation, with subsequent reporting to the network using MAC CE carried by a reserved LCID. This dual triggering framework ensures robust applicability across different deployment scenarios, including AI / ML execution in real network-based inference, digital twin-based inference, or hybrid operation.

[0110] Figure 1 shows an exemplary table of AI / ML adaptive modes. In this example, a set of AI / ML adaptive modes are configured by network side for applying one of the subcategorized mode adjustments. AI / ML adaptive modes are defined in the network’s RRC configuration and signaled as part of RRC message or L1 / L2 signaling. For each sub-modes, it indicates the specific quantized selection of each mode. For example, if Mode 1 is about model granularity changes, each sub-modes have different granularity levels of model size. As another example, if Mode 2 is about dataset size adjustment, each sub-modes have different dataset sizes or subset of data for selection. Associated data identifier in the table is about representing any valid ID information related to specific mode and sub-mode such as model ID and / or dataset ID, feature set ID, etc. Mapping relation information for adaptive modes is configured by network side. AI / ML adaptive modes are defined in the network’s RRC configuration. Any available updates about mapping relation information are provided to UE via system information or dedicated RRC signaling. For dynamic adaptation of different modes, L1 / L2 signaling is used to indicate any specific mode for adaptation. 202406422

[0111] - 20 -

[0112] In the mapping relation information, the associated ID represents one of more identifiers related to mode configuration information along with model ID, dataset ID, feature set ID, etc. for specific size indication.

[0113] Figure 2 shows an exemplary mapping relation table of applying adaptive mode. In this example, if mode-4 is selected, this table shows possible combinations of mode- 1 / -2 / -3, mode-11-2, mode-2 / -3, mode-1 / -3. Based on the selected mode such as mode-4, mode specific parameters as mode configuration information are provided so as to adapt sizes of target associated IDs.

[0114] Depending on different deployment scenarios or applications, two or more modes can be simultaneously applied jointly.

[0115] Figure 3 shows an exemplary flow chart of processing adaptive mode at network side. In this example, the network assesses the capabilities of the UE to determine if it can handle the current model / dataset / featureset size. The network selects the appropriate adaptive mode.

[0116] The network performs the selected mode configuration based on the selected mode and prepares it for transfer. The network sends the selected mode configuration and the associated assistance information to the UE (including the adapted model / dataset / featureset size data if applicable). Based on the feedback from UE, the network either continues with the current configuration or reassesses the adapted mode and size for further adjustments.

[0117] Figure 4 shows an exemplary flow chart of processing adaptive mode at UE side. In this example, the UE receives the adaptive mode information sent by the network. The UE loads the model, dataset, and / or featureset for use based on the received configuration. The UE executes the adaptive mode. The UE sends feedback regarding the model's performance back to the network. The UE continuously monitors its resource usage to ensure optimal performance.

[0118] Figure 5 shows an exemplary flow chart of switching adaptive modes at UE side. In this example, after activating initial adaptive mode operation, the UE monitors performance status. If the current mode is triggered for switching due to performance 202406422

[0119] - 21 - degradation or other condition failure, adaptive mode is switched to other mode based on UE decision autonomously or indication sent by network side.

[0120] Mode switching is configurable in dynamic or semi-static way based on implementation scenarios or use cases.

Claims

202406422- 22 -CLAIMS1. A method of model parameter adjustment signaling in RAN by configuring a set of AI / ML adaptive modes in a wireless communication system, comprising:• Setting configuration parameters of each adaptive mode;• Configuring mapping relation information to support adaptive modes;• Defining a new LCID to support mode adaptation;• Generating combinations of different modes.

2. The method according to previous claim 1 , wherein the sub-categorized mode adjustment using AI / ML adaptive modes is applied such as Mode-1 (adaptation of ML model size only), Mode-2 (adaptation of dataset size only), Mode-3 (adaptation of feature set only), Mode-4 (any combinations of Mode-1 Z-2 / -3).

3. The method according to one of the previous claims, wherein set of AI / ML adaptive modes are defined in the network’s RRC configuration and signaled as part of RRC message or L1 / L2 signaling.

4. The method according to one of the previous claims, wherein the number of AI / ML adaptive modes can vary for different use cases with more combinations of modes.

5. The method according to one of the previous claims, wherein Mode-1 represents model granularity changes to reduce the model size dynamically based on the available processing capability (e.g., pruning, quantization).

6. The method according to one of the previous claims, wherein Mode-2 represents dataset size adjustment by selecting a subset of data that provides a balance between performance and processing capability used for model inference or other LCM operations.202406422- 23 -7. The method according to one of the previous claims, wherein Mode-3 represents feature set modification for the input feature set by selecting a subset of features or reducing the dimensionality to lower the computational load on the UE.

8. The method according to one of the previous claims, wherein indication message (e.g., L1 / L2 signaling) is used for triggering the pre-configured adaptive modes via uplink or downlink.

9. The method according to one of the previous claims, wherein based on the triggered indication message, model reconfiguration or transmission of new AI / ML model parameters is enabled (e.g., via downlink).

10. The method according to one of the previous claims, wherein any specific adaptive mode(s) can be directly included in indication message for activation via downlink or uplink.11 . The method according to one of the previous claims, wherein model-specific information is conveyed such as request for processing capacity or resource availability at the UE (e.g., sending a request for the UE to report its available processing resources).

12. The method according to one of the previous claims, wherein RRC reconfiguration messages is used in informing the UE about new AI / ML model configurations or updates to the existing model structure by including information such as model size (e.g., information on the size of the model, allowing the UE to determine if it can handle the model based on its processing capabilities), input feature set (e.g., details on which input features are required for the model, potentially allowing the UE to simplify the model if needed).

13. The method according to one of the previous claims, wherein one or more look-up tables representing mapping relation between model granularity, subset of data and / or subset of features is preset.202406422- 24 -14. The method according to one of the previous claims, wherein depending on selection of AI / ML adaptive mode, the associated parameter set is configured to mapped together such as quantized dataset size, feature subset, or model granularity level indicated as identifiers.

15. The method according to one of the previous claims, wherein the new LCID is specifically configured to carry information related to AI / ML adaptive modes with request for selection of adaptive modes (e.g., the UE can signal the need for adjustments in the model, such as reducing model size or changing the input feature set or dataset size).

16. The method according to one of the previous claims, wherein new LCID is defined to be used specifically for AI / ML model-related MAC CE containing LCID header (for the newly defined value for AI / ML adaptive mode signaling) and the requested adaptive mode(s) based on target model ID and UE processing capability updates.

17. The method according to one of the previous claims, wherein a new LCID to send MAC CE is used to configure the UE with the appropriate AI / ML adaptive mode.

18. The method according to one of the previous claims, wherein the UE uses a new LCID to report its processing capabilities, request adjustments, or acknowledge receipt of new model configurations.

19. The method according to one of the previous claims, wherein network side uses the newly defined LCID in a MAC PDU to send AI / ML adaptive mode configuration data to the UE and UE processes the information to adjust the intended adaptive mode.

20. The method according to one of the previous claims, wherein each sub-modes of AI / ML adaptive mode indicates the specific quantized selection of each mode.202406422- 25 -21 .Apparatus for model parameter adjustment signaling in RAN by configuring a set of AI / ML adaptive modes 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 10.

22. User Equipment comprising an apparatus according to claim 21 .

23. gNB comprising an apparatus according to claim 21 .

24. Wireless communication system model parameter adjustment signaling in RAN by configuring a set of AI / ML adaptive modes comprising user equipment according to claim 22, gNB according to claim 23, whereby the user Equipment and the gNB each comprises 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 20.

Images