[go: up one dir, main page]

WO2025233278A1 - Procédé de signalisation de pré-activation multi-modèle - Google Patents

Procédé de signalisation de pré-activation multi-modèle

Info

Publication number
WO2025233278A1
WO2025233278A1 PCT/EP2025/062215 EP2025062215W WO2025233278A1 WO 2025233278 A1 WO2025233278 A1 WO 2025233278A1 EP 2025062215 W EP2025062215 W EP 2025062215W WO 2025233278 A1 WO2025233278 A1 WO 2025233278A1
Authority
WO
WIPO (PCT)
Prior art keywords
model
activation
candidate
previous
models
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/EP2025/062215
Other languages
English (en)
Inventor
Hojin Kim
Rikin SHAH
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Aumovio Germany GmbH
Original Assignee
Aumovio Germany GmbH
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Aumovio Germany GmbH filed Critical Aumovio Germany GmbH
Publication of WO2025233278A1 publication Critical patent/WO2025233278A1/fr
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/08—Configuration management of networks or network elements
    • H04L41/0803—Configuration setting
    • H04L41/0813—Configuration setting characterised by the conditions triggering a change of settings
    • H04L41/0816—Configuration setting characterised by the conditions triggering a change of settings the condition being an adaptation, e.g. in response to network events
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
    • H04L41/16—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks using machine learning or artificial intelligence
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/02—Arrangements for optimising operational condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W24/00—Supervisory, monitoring or testing arrangements
    • H04W24/04—Arrangements for maintaining operational condition

Definitions

  • the present disclosure relates to AI/ML based candidate model pre-activation, where techniques for pre-configuring and signaling the specific information about candidate ML models applicable to radio access network are presented.
  • AI/ML artificial intelligence/machine learning
  • RP-213599 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.
  • 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.
  • AI/ML model terminology and description to identify common and specific characteristics for framework are included as one of key work scopes.
  • 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.
  • 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.
  • AI/ML UE-side
  • AI/ML network-side
  • UE-side (AI/ML) model is defined as an AI/ML model whose inference is performed entirely at the UE
  • AI/ML network-side
  • UE-ML user equipment
  • 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.
  • 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.
  • 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.
  • model performance for inferencing can be easily degraded if target ML condition is not well aligned with real ML condition measured for specific model operation.
  • signaling is crucial for communication between the UE and the network as this signaling occurs across different layers of the protocol stack, primarily L1 (Layer-1 ), L2 (Layer-2), and RRC (radio resource control).
  • L1 Layer-1
  • L2 Layer-2
  • RRC radio resource control
  • RRC radio resource control
  • it is a Layer-3 protocol used on the air interface between UE and the base station (e.g., gNB in 5G, eNB in LTE) where the main role is to establish, configure, maintain, and release radio resources and connections needed for communication.
  • US 2023069342 describes how to assist determination of the model update time in consideration of cost for the update of a model.
  • US 2023022737 explains supporting generation of machine learning model when a certain machine learning model is changed.
  • US 2019012876 provides projections, predictions, and recommendations for computing system.
  • US 2019332895 shows that the monitored states are to decide to change a trained ML model as currently used.
  • EP 4075348 describes control of machine learning model, which can be based on a federated learning method collectively performed by nodes of a decentralized distributed database.
  • US 2021019612 provides the self-healing system that can automatically provide a diagnostic, and it can also automatically provide an action if the performance of the model predictions has changed over time.
  • the present disclosure solves the cited problem by the proposed embodiments and describes a method of multi-model pre-activation signaling by configuring multiple pair of models based on a finite set of model pools on network side and/or UE side for pre-activation of candidate model(s) in a wireless communication system, comprising the steps resetting one or multiple candidate models or model IDs; activating backup model operation using candidate model(s) with the failure of main model based ML operation; configuring pre-activation modes and pre-activation levels with mapping relation information.
  • the method is characterized by, that candidate model(s) can be pre-activated with the configured timer setting and/or threshold-based triggering for quick activation of backup model operation.
  • the method is characterized by, that the list of candidate models can be pre-determined based on ML applications, ML applicable conditions and/or device model supportability. In some embodiments of the method according to the first aspect, the method is characterized by, that additional models along with main model can be co-activated to minimize the potential impact of main model failure.
  • the method is characterized by, that periodic message can be used for model status update about main model performance monitoring.
  • the method is characterized by, that non-periodic or on-demand message can be used for model status update about candidate model applicability or pre-activation.
  • model information e.g., model ID with the associated configuration
  • L1/L2 or RRC signaling can be sent via L1/L2 or RRC signaling.
  • the method is characterized by, that model information is the model ID with the associated configuration.
  • the method is characterized by, that the pre-activated model(s) can contribute to the improved model performance (e.g., model training/inferencing) along with main model in activation via ensemble model output.
  • the pre-activated model(s) can contribute to the improved model performance (e.g., model training/inferencing) along with main model in activation via ensemble model output.
  • the method is characterized by, that the pre-activated model(s) can be used as replacement of main model or supplementary model functionality with main model.
  • the method is characterized by, that a list of candidate models can be mapped onto pre-activation modes. In some embodiments of the method according to the first aspect, the method is characterized by, that pre-activation mode represents specific level of model functionality for support.
  • the method is characterized by, that different pre-activation modes can be set for each candidate models in (semi-)statical way or dynamically (after candidate models are determined and shared with UE).
  • the method is characterized by, that indication message about pre-activation mode change with the associated candidate model(s) can be sent via L1/L2 or RRC signaling.
  • the method is characterized by, that initial setting of mapping relation table of candidate models and pre-activation modes can be sent via system information or dedicated RRC signaling.
  • mapping relation table of pre-activation modes and the associated levels of model functionality can be sent via system information or dedicated RRC signaling if applicable.
  • the method is characterized by, that pre-activation levels can be pre-defined for the configured pre- activation modes.
  • the method is characterized by, that pre-activation level can represent the degree of model functionalities. In some embodiments of the method according to the first aspect, the method is characterized by, that model functionality can be features controlled with the associated parameters or attribute data.
  • the method is characterized by, that one or multiple candidate models or model IDs can be preconfigured by network side together with the associated mapping relation table(s) representing mapping between candidate models and pre-activation modes.
  • the method is characterized by, that model status update feedback is sent to network side via L1 or L2 signaling by indicating candidate model(s) with pre-activation level information.
  • the present disclosure relates to an apparatus for multi-model pre-activation signaling by configuring multiple pair of models based on a finite set of model pools on network side and/or UE side for pre-activation of candidate model(s) 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 carry out the steps according to the first aspect of this application.
  • the present disclosure relates to an user Equipment comprising an apparatus according to the second aspect.
  • the present disclosure relates to a gNB comprising an apparatus according to the second aspect.
  • the present disclosure relates to a wireless communication system for multi-model pre-activation signaling by configuring multiple pair of models based on a finite set of model pools on network side and/or UE side for pre-activation of candidate model(s), wherein the wireless communication systems comprises at least a user equipment according to the third aspect, at least a gNB according to the fourth aspect, whereby the user Equipment and the gNB each comprises a processor coupled with a memory in which computer program instructions are stored and can be executed.
  • the present disclosure relates to a computer program product comprising instructions which, when executed by at least one processor, configure said at least one processor to carry out a method according to the first aspect of the present disclosure.
  • the computer program product can use any programming language, and can be in the form of source code, object code, or in any intermediate form between source code and object code, such as in a partially compiled form, or in any other desirable form.
  • the present disclosure relates to a computer-readable storage medium comprising instructions which, when executed by at least one processor, configure said at least one processor to carry out a method according to any one of the embodiments of the present disclosure.
  • Figure 1 is an exemplary table of mapping relation table of candidate models and pre-activation modes.
  • Figure 2 is an exemplary table of mapping relation table of pre-activation modes and the associated levels of model functionality.
  • Figure 3 is an exemplary flow chart of configuring candidate models with the associated mapping relation table at network side.
  • Figure 4 is an exemplary flow chart of activating candidate model(s) with the associated mapping relation table at UE side.
  • 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.
  • 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.
  • MSC Mobile Switching Center
  • MME Mobility Management Entity
  • O&M Operations & Maintenance
  • OSS Operations Support System
  • SON Self Optimized Network
  • positioning node e.g. Evolved- Serving Mobile Location Centre (E-SMLC)
  • E-SMLC Evolved- Serving Mobile Location Centre
  • MDT Minimization of Drive Tests
  • test equipment physical node or software
  • 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.
  • 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.
  • 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.
  • gNB gNodeB
  • 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.
  • 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.
  • VLSI very-large-scale integration
  • 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.
  • 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.
  • 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
  • a storage device 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.
  • 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.
  • 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.
  • 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”)).
  • LAN local area network
  • WLAN wireless LAN
  • WAN wide area network
  • ISP Internet Service Provider
  • 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.
  • 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.
  • 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).
  • 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.
  • DL downlink
  • CN core network
  • uplink, UL uplink
  • the RAN comprises one base station, BS.
  • 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.
  • 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.
  • 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.
  • 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.
  • LoT Internet of Things
  • 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.
  • 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.
  • the MR unit corresponds to a 5G NR wireless communication unit.
  • AI/ML Model is a data driven algorithm that applies AI/ML techniques to generate set of outputs based on set of inputs.
  • 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.
  • An entity could mean network node/function (e.g., gNB, LMF, etc.), UE, proprietary server, etc.
  • AI/ML model Inference is a process of using trained AI/ML model to produce set of outputs based on set of inputs.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • 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.
  • Model activation means enable an AI/ML model for specific AI/ML-enabled feature.
  • Model deactivation means disable an AI/ML model for specific AI/ML-enabled feature.
  • Model download means Model transfer from the network to UE.
  • 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.
  • Model monitoring is A procedure that monitors the inference performance of the AI/ML model.
  • 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.
  • Model switching is deactivating currently active AI/ML model and activating different AI/ML model for specific AI/ML-enabled feature.
  • Model update is Process of updating the model parameters and/or model structure of model.
  • Model upload is Model transfer from UE to the network.
  • AI/ML Network-side
  • Offline field data is the data collected from field and used for offline training of the AI/ML model.
  • 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. Online field data is the data collected from field and used for online training of the AI/ML model.
  • 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.
  • Fine- tuning/re-training may be done via online or offline training. This note could be removed when we define the term fine-tuning.
  • Reinforcement Learning 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.
  • Semi-supervised learning is a process of training model with mix of labelled data and unlabelled data.
  • Supervised learning is a process of training model from input and its corresponding labels.
  • 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.
  • AI/ML UE-side
  • Unsupervised learning is a process of training model without labelled data.
  • 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.
  • 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.
  • 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).
  • 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.
  • 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.
  • 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.
  • AI/ML model enabled wireless communication network 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.
  • ML operation using model activation for LCM phases can be degraded due to ML device conditions, and ML performance can be sensitive depending on channel condition and/or ML capability status.
  • /V (pair of) models based on a finite set of model pools on network side and/or UE side are configured for pre-activation of candidate model(s).
  • one or multiple candidate models or model IDs are preset when main model is selected for activation.
  • backup model operation can be activated using candidate model(s).
  • candidate model(s) can be pre-activated with the configured timer setting and/or thresholdbased triggering that can be implemented and signaled by network side.
  • the list of candidate models can be pre-determined based on ML applications, ML applicable conditions and/or device model supportability. Depending on implementation scenarios, additional models along with main model can be coactivated to minimize the potential impact of main model failure.
  • periodic message can be used for model status update about main model performance monitoring.
  • non-periodic (aka on-demand) message can be used for model status update about candidate model applicability or preactivation.
  • Specific parameters related to periodic messaging and threshold of on- demand messaging can be implementation-specific and preset at network side.
  • Model information (e.g., model ID with the associated configuration) about the determined N (pair of) models can be sent via L1/L2 or RRC signaling.
  • the preactivated model(s) can contribute to the improved model performance (e.g., model training/inferencing) along with main model in activation via ensemble model output.
  • the pre-activated model(s) can be used as replacement of main model or supplementary model functionality with main model.
  • a list of candidate models can be mapped onto pre-activation modes where preactivation mode represents specific level of model functionality for support. After candidate models are determined and shared with UE, different pre-activation modes can be set for each candidate models in (semi-)statical way or dynamically.
  • indication message can be sent via L1/L2 or RRC signaling.
  • Initial setting of mapping relation table of candidate models and pre-activation modes can be sent via system information or dedicated RRC signaling.
  • Mapping relation table of pre-activation modes and the associated levels of model functionality can be sent via system information or dedicated RRC signaling if applicable.
  • Pre-activation levels can be pre-defined for the configured pre-activation modes.
  • Pre-activation level represents the degree of model functionalities, where model functionality can be features controlled with the associated parameters or attribute data.
  • One or multiple candidate models or model IDs can be pre-configured by network side together with the associated mapping relation table(s) representing mapping between candidate models and pre-activation modes.
  • indication message can be sent via L1/L2 or RRC signaling.
  • Initial setting of mapping relation table of candidate models and pre-activation modes can be sent via system information or dedicated RRC signaling.
  • different pre-activation modes can be set for each candidate models in (semi-)statical way or dynamically.
  • UE can activate the indicated candidate model(s) with or without main model.
  • candidate model activation decision it can be indicated by network side or UE can also decide activation autonomously if applicable. For example, UE activates candidate model(s) autonomously after measuring main model performance monitoring so as to maintain target model performance.
  • model status update feedback is sent to network side via L1 or L2 signaling by indicating candidate model(s) with pre-activation level information.
  • Figure 1 shows an exemplary table of mapping relation table of candidate models and pre-activation modes.
  • a list of candidate models can be mapped onto pre-activation modes where pre-activation mode represents specific level of model functionality for support.
  • different pre-activation modes can be set for each candidate models in (semi-)statical way or dynamically.
  • indication message can be sent via L1/L2 or RRC signaling.
  • Initial setting of mapping relation table of candidate models and pre- activation modes can be sent via system information or dedicated RRC signaling.
  • Figure 2 shows an exemplary table of mapping relation table of pre-activation modes and the associated levels of model functionality.
  • mapping relation table of pre-activation modes and the associated levels of model functionality can be sent via system information or dedicated RRC signaling if applicable.
  • Pre-activation levels can be pre-defined for the configured pre-activation modes.
  • Pre-activation level represents the degree of model functionalities, where model functionality can be features controlled with the associated parameters or attribute data. For example, PM #1 with full model functionality can enable all features supported by the indicated model. And other pre-activation mode except PM #1 can support various levels of different partial model functionalities or features so that model performance can be limited accordingly.
  • Figure 3 shows an exemplary flow chart of configuring candidate models with the associated mapping relation table at network side.
  • one or multiple candidate models or model IDs can be pre-configured by network side together with the associated mapping relation table(s) representing mapping between candidate models and pre-activation modes.
  • indication message can be sent via L1/L2 or RRC signaling.
  • Initial setting of mapping relation table of candidate models and pre- activation modes can be sent via system information or dedicated RRC signaling.
  • Figure 4 shows an exemplary flow chart of activating candidate model(s) with the associated mapping relation table at UE side.
  • different pre-activation modes can be set for each candidate models in (semi-)statical way or dynamically.
  • UE When triggered for any candidate model activation, UE can activate the indicated candidate model(s) with or without main model. For candidate model activation decision, it can be indicated by network side or UE can also decide activation autonomously if applicable. For example, UE activates candidate model(s) autonomously after measuring main model performance monitoring so as to maintain target model performance. After candidate model activation at UE side, model status update feedback is sent to network side via L1 or L2 signaling by indicating candidate model(s) with pre-activation level information. With this method, signaling overhead can be reduced by using the pre-configured mapping relation index or ID information and model performance can be also improved by activating candidate model(s).

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

La présente divulgation concerne des procédés d'utilisation d'une technologie IA/AA (intelligence artificielle/apprentissage automatique) préconfigurée sur la base d'une pré-activation de modèle candidat dans un système de communication mobile sans fil comprenant une station de base (par exemple, un gNB, un TN, un NTN) et une station mobile (par exemple, un UE). Si un modèle IA/AA est appliqué à un réseau d'accès radio, les performances du modèle peuvent être hautement vulnérables aux conditions d'AA. Par conséquent, une opération de modèle (par exemple, un entraînement/une inférence/une surveillance/une mise à jour de modèle) peut être établie entre un réseau et un UE par configuration d'un réglage de pré-activation de modèle.
PCT/EP2025/062215 2024-05-06 2025-05-05 Procédé de signalisation de pré-activation multi-modèle Pending WO2025233278A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
DE102024204224.2 2024-05-06
DE102024204224 2024-05-06

Publications (1)

Publication Number Publication Date
WO2025233278A1 true WO2025233278A1 (fr) 2025-11-13

Family

ID=95656290

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/EP2025/062215 Pending WO2025233278A1 (fr) 2024-05-06 2025-05-05 Procédé de signalisation de pré-activation multi-modèle

Country Status (1)

Country Link
WO (1) WO2025233278A1 (fr)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190012876A1 (en) 2017-07-08 2019-01-10 Gaming Analytics Inc Machine-learning platform for operational decision making
US20190332895A1 (en) 2018-04-30 2019-10-31 International Business Machines Corporation Optimizing machine learning-based, edge computing networks
US20210019612A1 (en) 2019-07-15 2021-01-21 Sony Interactive Entertainment LLC Self-healing machine learning system for transformed data
EP4075348A1 (fr) 2021-04-14 2022-10-19 Siemens Aktiengesellschaft Contrôle de qualité d'un modèle d'apprentissage machine
US20230022737A1 (en) 2021-07-21 2023-01-26 Hitachi, Ltd. Generation support apparatus, generation support method, and generation support program
US20230069342A1 (en) 2021-08-27 2023-03-02 Hitachi, Ltd. Computer system and method of determining model switch timing

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190012876A1 (en) 2017-07-08 2019-01-10 Gaming Analytics Inc Machine-learning platform for operational decision making
US20190332895A1 (en) 2018-04-30 2019-10-31 International Business Machines Corporation Optimizing machine learning-based, edge computing networks
US20210019612A1 (en) 2019-07-15 2021-01-21 Sony Interactive Entertainment LLC Self-healing machine learning system for transformed data
EP4075348A1 (fr) 2021-04-14 2022-10-19 Siemens Aktiengesellschaft Contrôle de qualité d'un modèle d'apprentissage machine
US20230022737A1 (en) 2021-07-21 2023-01-26 Hitachi, Ltd. Generation support apparatus, generation support method, and generation support program
US20230069342A1 (en) 2021-08-27 2023-03-02 Hitachi, Ltd. Computer system and method of determining model switch timing

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
HOJIN KIM ET AL: "Discussion on general aspects of AI-ML framework", vol. RAN WG1, no. Toulouse, FR; 20230821 - 20230825, 11 August 2023 (2023-08-11), XP052435925, Retrieved from the Internet <URL:https://www.3gpp.org/ftp/TSG_RAN/WG1_RL1/TSGR1_114/Docs/R1-2306694.zip R1-2306694.docx> [retrieved on 20230811] *
PATRICK MERIAS ET AL: "Summary #2 for other aspects of AI/ML model and data", vol. RAN WG1, no. Athens, GR; 20240226 - 20240301, 27 February 2024 (2024-02-27), XP052577459, Retrieved from the Internet <URL:https://www.3gpp.org/ftp/TSG_RAN/WG1_RL1/TSGR1_116/Docs/R1-2401570.zip R1-2401570.docx> [retrieved on 20240227] *

Similar Documents

Publication Publication Date Title
WO2025008304A1 (fr) Procédé de signalisation avancée de rapport ml
WO2024208702A1 (fr) Procédé de signalisation d&#39;ensemble de données de modèle pour réseau d&#39;accès radioélectrique
WO2025026970A1 (fr) Procédé d&#39;activation d&#39;un modèle candidat
WO2025233278A1 (fr) Procédé de signalisation de pré-activation multi-modèle
WO2025233225A1 (fr) Procédé de signalisation d&#39;adaptation d&#39;identification de modèle
WO2025195960A1 (fr) Procédé de signalisation d&#39;ajustement de modèle à l&#39;aide d&#39;un modèle représentatif
WO2025195957A1 (fr) Procédé de signalisation d&#39;activation de modèle avancée
WO2025233226A1 (fr) Procédé de signalisation de commutation de modèle multimode
WO2025195815A1 (fr) Procédé de signalisation d&#39;attribution de modèle ia/aa avancée
WO2025168462A1 (fr) Procédé de signalisation d&#39;entraînement en ligne avancée pour ran
WO2025210138A1 (fr) Procédé de signalisation d&#39;opération de modèle multi-entraînement
WO2025233227A1 (fr) Signalisation de modèle adaptatif avec l&#39;ensemble de données associé pour ran
WO2025195792A1 (fr) Procédé de configuration d&#39;un ensemble de modes de fonctionnement pris en charge pour une fonctionnalité aa dans un système de communication sans fil
WO2025168471A1 (fr) Procédé de signalisation d&#39;entraînement en ligne basée sur un état rrc
WO2025233201A1 (fr) Procédé de configuration de hiérarchisation de modèles
WO2025168463A1 (fr) Procédé de signalisation de mise à jour de modèle avancée pour un ran
WO2025233207A1 (fr) Signalisation de rétroaction de mesure de modèle
WO2025196092A1 (fr) Procédé de configuration de l&#39;appariement de modèles multi-côtés avec l&#39;opération de modèle ml de bout en bout à travers différentes entités
WO2025210139A1 (fr) Procédé de signalisation d&#39;adaptation de mode d&#39;entraînement
WO2025233228A1 (fr) Procédé de signalisation de concaténation basée sur des cellules multiples
WO2025168468A1 (fr) Procédé de signalisation aa avancée pour ran
WO2025168467A1 (fr) Procédé d&#39;appariement de conditions ml
WO2025195952A1 (fr) Procédé de fonctionnement de modèle adaptatif à perception d&#39;état de dispositif
WO2025168469A1 (fr) Procédé de signalisation d&#39;alignement de modèle
WO2025172265A1 (fr) Procédé de signalisation de modèle basée sur des conditions avancées