Method of multi-model signaling for ran

Abstract

The present disclosure describes methods of using the pre-configured AI / ML (artificial intelligence / machine learning) based model information sharing in wireless mobile communication system including base station (e.g., gNB) and mobile station (e.g., UE). In AI / ML model is applied to radio access network, signaling of model transfer / delivery can be heavily congested based on multiple models execution with varying applications. Therefore, model operation e.g., model transfer / retraining / updating can be set up between network and UE by reducing the amount of multi-model signaling overhead.

Description

[0001] TITLE

[0002] Method of multi-model signaling for RAN

[0003] TECHNNICAL FIELD

[0004] The present disclosure relates to AI / ML based model information sharing, where techniques for pre-configuring and signaling the specific information about model structure / properties are presented.

[0005] BACKGROUND

[0006] 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”, and currently RAN WG1 (Working Group 1 ) and WG2 are actively working on specification. 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 will be one of key work scope. 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. Earlier, in 3GPP TR 37.817 for Release 17, titled as Study on enhancement for Data Collection for NR and EN-DC, UE (user equipment) mobility was also considered as one of AI / ML use cases and one of scenarios for model training / inference is that both functions are located within RAN node. Followingly, in Release 18 the new work item of “Artificial Intelligence (AI)ZMachine Learning (ML) for NG-RAN” was initiated to specify data collection enhancements and signaling support within existing NG-RAN interfaces and architecture. For the above active standardization works, model identification (e.g., model ID) to support 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 ID information can be signaled to pair both network-side and UE-side models for various lifecycle management (LCM) operations.

[0007] US2020374711 A1 describes a representation of a local model of the first data endpoint of the radio access network with multiple common models for endpoints of the radio access network, selecting one of multiple common models for the first data endpoint and transmitting the selected common model to the first data endpoint, any other data endpoint or any other external system which utilizes the selected common model.

[0008] US2021097428A1 describes a method for adapting a deep learning model to a local environment with collecting training data and training a common deep learning model, customizing the deep learning model based on characteristics specific to one of a plurality of local devices utilizing transfer learning.

[0009] W02022003949A1 describes machine learning models trained using training data with a classifier configured to classify an input data and to output an output data.

[0010] WO2022073167A1 describes a method of wireless communication receiving, via radio resource control (RRC) signaling, configuration messages as the configuration messages include parameters of an artificial neural network and the configuration messages also including a common configuration for basic set signaling.

[0011] However, when there are multiple models in parallel to be activated at UE, the multimodel signaling overhead can be very high especially when multiple UEs have their own on-device multiple models for activation between base station (BS / gNB) and multiple UEs. Currently, there is no specification known for signaling methods and network-UE behaviors so as to manage multi-model based model transfer and / or other related model signaling overhead for LCM operations.

[0012] According to a first aspect, the present disclosure relates to a A method of multimodel signaling for RAN with configuring model block structure having model- common block and model-dedicated block for ML model with in a wireless communication system comprising, configuring ML model to split into two blocks as model-common block and model-dedicated block; determining model-common block for multiple models to be shared and / or paired across different models; determining model-dedicated block to be uniquely configured for the associated ML model only; setting the criteria configured in advance where the specific threshold can be used to assess applicability of model-common block across multiple ML models.

[0013] In some embodiments, the method according to the first aspect can further comprise one or more of the following optional features, considered either alone or in any technically possible combination.

[0014] In some embodiments of the method according to the first aspect, the method is characterized by, that model block is further segmented into smaller blocks such as sub-blocks under model-common and model-dedicated blocks.

[0015] In some embodiments of the method according to the first aspect, the method is characterized by, that a finite number of sub-blocks contained in model- common / dedicated blocks are configured depending on varying properties used for block-based split of ML model as criteria.

[0016] In some embodiments of the method according to the first aspect, the method is characterized by, that the indication information about model-common block is sent with the associated model IDs so that model-common block is be applied to the indicated multiple models when transmitting ML configuration to UEs.

[0017] In some embodiments of the method according to the first aspect, the method is characterized by, that index-based indication information can be sent to apply modelcommon block to multiple ML models.

[0018] In some embodiments of the method according to the first aspect, the method is characterized by, that model-common and model-dedicated blocks can be part of model structure, architecture, layout, functionality, etc. depending on varying implementation use cases. For example, model-common block can be pre-defined to indicate specific part of model structural / parameter set information that are applicable commonly across models of different UEs while model-dedicated block can be predefined to indicate specific part of model structural / parameter set information that are applicable only for the associated model of a UE. In other words, information contained in model-common and model-dedicated blocks can be pre-defined at network side based on different combinations of model-related configuration information in association with model applications for deployment.

[0019] In some embodiments of the method according to the first aspect, the method is characterized by, wherein model-common block can be many different forms of applicable models depending on applications such as group of functionalities, group of sub-models, or group of parameters / layers, etc. based on model structure / characteristics.

[0020] In some embodiments of the method according to the first aspect, the method is characterized by, wherein specific configuration of selecting properties of modelcommon block can be set by network side in advance for different model applications or deployment scenarios.

[0021] In some embodiments of the method according to the first aspect, the method is characterized by, that model-common block can be independently configured and applied to all applicable ML models where the pre-configured model-common block can be sent to UEs or known to UEs in advance.

[0022] In some embodiments of the method according to the first aspect, the method is characterized by, that a finite number of candidate model-common blocks applicable to any ML models can be set with pre-configuration and indication information is sent about specific candidate model-common block(s) for use.

[0023] In some embodiments of the method according to the first aspect, the method is characterized by, that the specific model can be determined to be reference model having model-common block, comprising that other multiple models are transferred together with the determined reference model; the indicated reference model is applied to other multiple models transferred for activation.

[0024] According to a second aspect, the present disclosure relates to a wireless device comprising at least one memory and at least one processor configured to carry out a method according to any one of the embodiments of the first aspect.

[0025] According to a third aspect, the present disclosure relates to a user equipment, UE, comprising a wireless device according to any one of the embodiments of the present disclosure.

[0026] According to a fourth aspect, the present disclosure relates to a base station, BS, comprising at least one memory and at least one processor configured to carry out a method according to any one of the embodiments of the first aspect.

[0027] According to a fifth aspect, the present disclosure relates to a wireless communication system comprising at least one base station according to any one of the embodiments of the present disclosure and at least one user equipment according to any one of the embodiments of the present disclosure.

[0028] According to a sixth aspect, the present disclosure relates to a computer program product comprising instructions which, when executed by at least one processor, configure said at least one processor to carry out a method according to the first aspect said at least one processor to carry out a method for exchanging data according to any one of the embodiments of the present disclosure. The computer program product can use any programming language, and can be in the form of source code, object code, or in any intermediate form between source code and object code, such as in a partially compiled form, or in any other desirable form.

[0029] According to a sixth aspect, the present disclosure relates to a computer-readable storage medium comprising instructions which, when executed by at least one processor, configure said at least one processor to carry out a method according to any one of the embodiments of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 is an exemplary block diagram of ML model block structure.

[0031] Figure 2 is an exemplary block diagram of types of ML model block.

[0032] Figure 3 is an exemplary block diagram of multiple ML models with model block structure.

[0033] Figure 4 is an exemplary block diagram of allocating model-common block to multiple ML models.

[0034] Figure 5 is an exemplary block diagram of transferring multiple ML models with model block structure.

[0035] Figure 6 is an exemplary flow chart of network side behavior for applying ML model block.

[0036] Figure 7 is an exemplary flow chart of UE side behavior for applying ML model block. Figure 8 is an exemplary signaling flow of applying ML model block with activation decision at UE side.

[0037] Figure 9 is an exemplary signaling flow of applying ML model block with activation decision at network side.

[0038] DETAILED DESCRIPTION

[0039] 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.

[0040] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Other embodiments, however, are contained within the scope of the subject matter disclosed herein, the disclosed subject matter should not be construed as limited to only the embodiments set forth herein; rather, these embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

[0041] 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.

[0042] 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. 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.

[0043] 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.

[0044] 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.

[0045] 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. 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

[0046] 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.

[0047] 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.

[0048] Code for carrying out operations for embodiments may be any number of lines and may be written in any combination of one or more programming languages including an object- oriented programming language such as Python, Ruby, Java, Smalltalk, C++, or the like, and conventional procedural programming languages, such as the “C” programming language, or the like, and / or machine languages such as assembly languages. The code may execute entirely on the user’s computer, partly on the user’s computer, as a stand-alone software package, partly on the user’s computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user’s computer through any type of network, including a local area network (“LAN”), wireless LAN (“WLAN”), or a wide area network (“WAN”), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider (“ISP”)).

[0049] 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.

[0050] Aspects of the embodiments are described below with reference to schematic flowchart diagrams and / or schematic block diagrams of methods, apparatuses, systems, and program products according to embodiments. It will be understood that each block of the schematic flowchart diagrams and / or schematic block diagrams, and combinations of blocks in the schematic flowchart diagrams and / or schematic block diagrams, can be implemented by code. This code may be provided to a processor of a general-purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the fimctions / acts specified in the flowchart diagrams and / or block diagrams

[0051] 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.

[0052] 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.

[0053] 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).

[0054] 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. 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.

[0055] 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.

[0056] 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.

[0057] 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. Also, the order of steps of any methods disclosed herein, in particular in the figures, is provided only for illustration purposes and is not meant to limit the present disclosure which may be applied with the same steps executed in a different order and / or with all or part of the steps executed in parallel or jointly, 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. Also, in a figure, steps represented surrounded by a dashed line are to be considered as optional for the embodiment represented in this figure. 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.

[0058] 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.

[0059] 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.

[0060] 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.

[0061] 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.

[0062] 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 program-code 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.

[0063] 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.

[0064] The following explanation will provide the detailed description of the mechanism about pre-configuring AI / ML-based model before handover occurrence in wireless mobile communication system including base station (e.g., gNB) and mobile station (e.g., UE).

[0065] 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, model switching / selection 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. 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. Then model adaptation is required to support operations such as model switching, retraining, fallback, etc. When AI / ML model enabled wireless communication network is deployed, it is then important to consider how to handle adaptation of AI / ML model under operations such as model training, inference, monitoring, updating, etc. Based on specific network-UE ML collaboration in deployment scenarios (e.g., UE mobility case), ML applicable conditions for LCM (lifecycle management) operations can be significantly changed with different use cases and environmental properties. 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.

[0066] 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 performance such as inferencing and / or training is dependent on different model execution environment with varying configuration parameters.

[0067] To handle this issue, collaboration between UE and gNB is highly important to track model performance and re-configure model corresponding to different environments between UE and different gNBs. 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. In other words, by re-configuring any model in operation with different gNBs such as master node (MN) and secondary node (SN) in advance, the performance impact can be minimized compared with when any single connection link is used for model operation.

[0068] In this method, UE connections to multiple gNBs such as MN and SN based on master cell group (MCG) and secondary cell group (SCG), respectively, are enabled to support distributed multi-model operation that is activated across MN and / or SN(s) so that ML model signaling exchange due to LCM-based model operation can be distributed to one or multiple SNs. Firstly, ML configuration and LCM-based model information is informed to candidate SN(s) by MN. To trigger distributed multi-model operation, there can be multiple conditions (e.g., pre-configured metrics or threshold values) such as when actual traffic load gets high in current cell condition and / or additional model operation is needed through separate links (e.g., SN-UE) in parallel with the activated link (e.g., MN-UE). The configured model requested by MN (e.g., LCM operation in MN-UE link) can be duplicated for activation in SN-UE link after SN connection setup. Or separately configured model operation can be also activated in SN-UE link as requested by MN.

[0069] The following explanation will provide the detailed description of the mechanism about pre-configuring and signaling the specific information about model selection using association between models and index values.

[0070] 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).

[0071] 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. 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 selection 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 reconfiguration for wireless devices under operations such as model training, inference, updating, etc. With multiple AI / ML models in parallel for varying LCM operations on UE device or across multiple UEs, both signaling overhead and compute power increase can be quite significant for model transfer / delivery and / or model re- training / updating. In this method, each ML model is determined to split into two blocks such as model-common block and model-dedicated block where modelcommon block can be shared and / or paired with other ML model(s) and model- dedicated block is uniquely configured for the associated ML model only. For modelcommon block, it is part of ML model that can be used for other ML models based on the criteria configured in advance where the specific threshold can be used to assess applicability of model-common block across multiple ML models as threshold value is configured from similarity measure, as an example. Or model-common block can be independently configured and applied to all applicable ML models where the preconfigured model-common block can be sent to UEs or known to them in advance. In this case, there can be a finite number of candidate model-common blocks applicable to any ML models to be set with pre-configuration if necessary when indication information is sent about specific candidate model-common block(s) for use. In implementation aspect, model-common and model-dedicated blocks can be part of model structure, architecture, layout, functionality, etc. depending on varying implementation use cases. When model-common block is used across different ML models for multiple UEs and / or multiple applications on a device, index-based indication information can be sent to apply model-common block to multiple ML models where index can be configured in advance by network side. For example, if model-common block is valid for application with any specific ML model, index value is configured for the indicated model-common block of ML model so that other ML models refer to the configured index that indicates specific model-common block and the indexed model-common block is then applied for multiple ML models. The major benefit for doing this is that model-common block is sent once and applied to multiple ML models across multiple applications and / or multiple UEs. Otherwise, each ML models need to be sent individually including common part of model that can be used for multiple models. In other aspect, common part of ML model for multiple models can be saved for signaling overhead when it can be pre-configured with index-based indication for UEs. When sending indication information of model-common block of ML model, all associated model ID list need to be sent together so that the identified models can be indicated to apply the indexed model-common block across different models if applicable. Alternatively, network side performs model transfer of multiple models such as three models of M1 , M2 and M3. If these models share some common part of each model (e.g., sub-model), UE applies the indexed sub-model (configured by network side) to those three models when indication of index information is received.

[0072] Figure 1 shows an exemplary block diagram of ML model block structure. In this example, ML model can be structured to split into model-common block and model- dedicated block where block-wise segmentation can be based on varying properties such as group of layers, group of sub-models, group of model functionalities / parameters, etc. Depending on ML model characteristics, either model-common block or model-dedicated block can be unavailable. For example, some model can have model-dedicated block only.

[0073] Figure 2 shows an exemplary block diagram of types of ML model block. In this example, model block can be further segmented into smaller blocks such as subblocks under model-common and model-dedicated blocks. Depending on varying properties used for block-based split of ML model as criteria, a finite number of subblocks contained in model-common / dedicated blocks can be configured.

[0074] Figure 3 shows an exemplary block diagram of multiple ML models with model block structure. In this example, with finite number of ML models model-common block is configured for all models. Different models can have different model size and / or complexity while model-common block is commonly included across K different models. Therefore, for model transfer / delivery of those K different models, modelcommon block does not need to be sent for each model separately since it can be reused for all models by sharing. As an example, specific model can be determined to be reference model having model-common block so that it is sent together with other multi-model transfer information and the indicated reference model is applied to other multiple models transferred for activation.

[0075] Figure 4 shows an exemplary block diagram of allocating model-common block to multiple ML models. In this example, model-common block can be many different forms of applicable models depending on applications such as group of functionalities, group of sub-models, group of parameters / layers, etc. based on model structure / characteristics. Specific configuration of selecting properties of model-common block can be set by network side in advance for different model applications or deployment scenarios.

[0076] Figure 5 shows an exemplary block diagram of transferring multiple ML models with model block structure. In this example, there are two independent ML models and model-common block is identified applicable to both models. When both models are transferred over the air, the determined model-common block is sent together with model-dedicated block of each model where model-common block does not need to be sent separately on each model transfer since it can be duplicated after reception. When the number of ML models having model-common block increase, the gain of signaling overhead reduction can be quite high.

[0077] Figure 6 shows an exemplary flow chart of network side behavior for applying ML model block. On network side, ML configuration with model block structure for all applicable models is set to determine model-common and model-dedicated blocks of each model. The specific threshold can be used to identify model-common block across different models based on the pre-configured criteria such as similarity measure. When transmitting ML configuration to UEs, the indication information about model-common block is sent with the associated model IDs so that modelcommon block can be applied to the indicated multiple models.

[0078] Figure 7 shows an exemplary flow chart of UE side behavior for applying ML model block. On UE side, there can be multiple ML models for activation in parallel and the identified model-common block indicated by network side can be used to apply to models for activation if valid.

[0079] Figure 8 shows an exemplary signaling flow of applying ML model block with activation decision at UE side. In this example, model-common block is determined to apply to multiple models based on the received assistance information about ML configuration from network side. The criteria of determining model-common block such as threshold can be provided by network side in advance. After applying modelcommon block, the indication message about activation of applying model-common block is sent to network side so that both sides can be aligned for ML reconfiguration. General ML configuration information can be sent via system information or RRC signaling. Model block related information can be sent via L1 / L2 or L3 signaling.

[0080] Figure 9 shows an exemplary signaling flow of applying ML model block with activation decision at network side. In this example, on network side model-common block is determined to apply to multiple models based on the received assistance information about ML configuration from UE side. The indication information about model-common block is sent with the associated model IDs so that model-common block can be applied to the indicated multiple models when transmitting ML configuration to UEs.

Claims

CLAIMS1 . A method of multi-model signaling for RAN with configuring model block structure having model-common block and model-dedicated block for ML model with in a wireless communication system comprising:• Configuring ML model to split into two blocks as model-common block and model-dedicated block;• Determining model-common block for multiple models to be shared and / or paired across different models;• Determining model-dedicated block to be uniquely configured for the associated ML model only;• Setting the criteria configured in advance where the specific threshold can be used to assess applicability of model-common block across multiple ML models.

2. The method according to claim 1 , wherein model block is further segmented into smaller blocks such as sub-blocks under model-common and model-dedicated blocks.

3. The method according to any one of the preceding claims, wherein a finite number of sub-blocks contained in model-common and / or dedicated blocks are configured depending on varying properties used for block-based split of ML model as criteria.

4. The method according to any one of the preceding claims, wherein the indication information about model-common block is sent with the associated model IDs so that model-common block is be applied to the indicated multiple models when transmitting ML configuration to UEs.

5. The method according to previous claim 4, wherein index-based indication information can be sent to apply model-common block to multiple ML models.

6. The method according to any one of the preceding claims, wherein modelcommon and model-dedicated blocks can be part of model structure and / or architecture and / or layout, functionality depending on varying implementation use cases.

7. The method according to any one of the preceding claims, wherein modelcommon block has different forms of applicable models depending on applications as group of functionalities and / or group of sub-models and / or or group of parameters / layers, based on model structure and / or model characteristics.

8. The method according to any one of the preceding claims, wherein specific configuration of selecting properties of model-common block is set by network side in advance for different model applications or deployment scenarios.

9. The method according to any one of the preceding claims, wherein modelcommon block can be independently configured and applied to all applicable ML models where the pre-configured model-common block can be sent to UEs or known to UEs in advance.

10. The method according to any one of the preceding claims, wherein a finite number of candidate model-common blocks applicable to any ML models can be set with pre-configuration and indication information is sent about specific candidate model-common block(s) for use.11 . The method according to any one of the preceding claims, wherein specific model can be determined to be reference model having model-common block, comprising:• Other multiple models are transferred together with the determined reference model;• The indicated reference model is applied to other multiple models transferred for activation.

12. A wireless device comprising at least one memory and at least one processor configured to carry out a method according to any one of the preceding claims.

13. A user equipment, UE, comprising a wireless device according to claim 12.

14. A base station, BS, comprising at least one memory and at least one processor configured to carry out a method according to any one of claims 1 to 11 .

15. A wireless communication system comprising at least one base station according to claim 14 and at least one user equipment according to claim 12.

16. 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 any one of claims 1 to 11 .

17. 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 (40) according to any one of claims 1 to 11 .

Images