Method of multi-cell based concatenation signaling

Abstract

The present disclosure describes methods of using the pre-configured AI / ML (artificial intelligence / machine learning) based model density group in wireless mobile communication system including base station (e.g., gNB, TN, NTN) and mobile station (e.g., UE). In AI / ML model is applied to radio access network, single-cell based model can be well-trained and deployed for any specific cell environment (e.g., serving cell). However, single-cell based model cannot be directly applied to any other neighboring cells as ML conditions (e.g., dataset, site, configuration, etc.) can vary across different cells. Therefore, model operation (e.g., model training / inferencing / monitoring / updating) can be set up between network and UE by configuring multi-cell based model concatenation.

Description

[0001] TITLE

[0002] Method of multi-cell-based concatenation signaling

[0003] TECHNNICAL FIELD

[0004] The present disclosure relates to AI / ML based model density group, where techniques for pre-configuring and signaling the specific information about multi-cell- based model concatenation applicable to radio access network 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”. The goal of this study item is to identify a common AI / ML framework and areas of obtaining gains using AI / ML based techniques with use cases. According to 3GPP, the main objective of this study item is to study AI / ML framework for air-interface with target use cases by considering performance, complexity, and potential specification impact. In particular, AI / ML model, terminology and description to identify common and specific characteristics for framework are included as one of key work scopes. Regarding AI / ML framework, various aspects are under consideration for investigation and one of key items is about lifecycle management of AI / ML model where multiple stages are included as mandatory for model training, model deployment, model inference, model monitoring, model updating etc. Currently, AI / ML specification work is at the stage of work item discussion for Release 19. Earlier, in 3GPP TR 37.817 for Release 17, titled as Study on enhancement for Data Collection for NR and EN-DC, UE (user equipment) mobility was also considered as one of AI / ML use cases and one of scenarios for model training / inference is that both functions are located within RAN node. Followingly, in Release 18 the new work item of “Artificial Intelligence (AI)ZMachine Learning (ML) for NG-RAN” was initiated to specify data collection enhancements and signaling support within existing NG-RAN interfaces and architecture. For the above active standardization works, RAN-based AI / ML model is considered very significant for both network and UE to meet any desired model operations (e.g., model training, inference, selection, switching, update, monitoring, etc.).

[0007] Model information can be signaled to pair both network-side and UE-side models for various lifecycle management (LCM) operations. However, signaling overhead indicating model information can be very high especially when model based LCM is processed between base station (BS / gNB) and multiple UEs. In LCM, model training is one of the most important parts for model deployment and currently there is no specification defined for signaling methods and network-UE behaviors so as to identify the required dataset when model updating / re-training as any activated model can be also impacted due to model / data drift. When ML condition changes, the enabled AI / ML model(s) can be impacted for model performance due to data / model drift. In this case, model re-training / updating can be executed. For example, when the trained ML model is deployed in RAN, 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.

[0008] US2022353803A1 describes a machine-learning architecture for network slicing where the UE selects a machine-learning architecture that provides a quality-of- service level requested by an application the network-slice manager can determine an appropriate machine-learning architecture that satisfies a quality-of-service level associated with the application.

[0009] US20230048206A1 describes methods for controlling machine learning model structures where the machine learning model structure may be controlled based on an environmental condition.

[0010] W02022207102A1 describes a method for a feasibility check of a new RAN slice performed by a network node with computing the estimate of occupied resources using historical data of a measurement of utilization of each resource.

[0011] US2016379137A1 describes a method for processing on an acceleration component a machine learning classification model where the machine learning classification model includes a plurality of decision trees, the decision trees including a first amount of decision tree data by including slicing the model into a plurality of model slices.

[0012] The present disclosure solves the cited problem by the proposed embodiments and describes as a first aspect a method of multi-cell based concatenation by configuring a set of ML models that are applied to multiple cells in a wireless communication system, comprising configuring primary / supplementary model combinations; applying a set of ML models to multiple cells with serving cell / gNB and neighboring cells / gNBs; Sending the configured model pair ID information to UEs across multiple cells / gNBs.

[0013] In some embodiments of the method according to the first aspect the method is characterized by, that model concatenation set information with the associated primary / supplementary model combination can be sent via system information or dedicated RRC signaling.

[0014] In some embodiments of the method according to the first aspect the method is characterized by, that mapping relation information about a set of supplementary model pair IDs with list of candidate neighboring cells / gNBs can be sent via system information or dedicated RRC signaling.

[0015] In some embodiments of the method according to the first aspect the method is characterized by, that any change or update information about model concatenation set and / or primary and / or supplementary models can be sent via L1 / L2 or RRC message.

[0016] In some embodiments of the method according to the first aspect the method is characterized by, that the configured ML models for each cells can be aligned together via ensemble model or concatenated model operation.

[0017] In some embodiments of the method according to the first aspect the method is characterized by, that primary model pair is defined as two-sided model between source cell / gNB and UE(s). In some embodiments of the method according to the first aspect the method is characterized by, that supplementary model pair as two-sided model between neighboring cell / gNB and UE(s).

[0018] In some embodiments of the method according to the first aspect the method is characterized by, that one or more UE groups having their own on-device models can be assigned to support one- / two-sided model operation.

[0019] In some embodiments of the method according to the first aspect the method is characterized by, that there are a set of multiple model concatenations.

[0020] In some embodiments of the method according to the first aspect the method is characterized by, that primary model and the associated supplementary model(s) can be paired for combination for each model concatenation set.

[0021] In some embodiments of the method according to the first aspect the method is characterized by, that primary model and supplementary model can indicate either one-side model or two-side model depending on implementation scenarios.

[0022] In some embodiments of the method according to the first aspect the method is characterized by, that different number of pairs for primary and supplementary models can be configured between network side and UE side for two-sided model applied for primary and supplementary models.

[0023] In some embodiments of the method according to the first aspect the method is characterized by, that a set of supplementary model pair IDs can be configured across list of candidate neighboring cells / gNBs so that primary model pair ID can be concatenated with available supplementary model pair IDs for LCM use cases.

[0024] In some embodiments of the method according to the first aspect the method is characterized by, that each candidate neighboring cells / gNBs can have one or more number of supplementary model pair IDs that can be concatenated together for the end-to-end model operation. In some embodiments of the method according to the first aspect the method is characterized by, that primary model and the associated supplementary model(s) can be paired for combination across multiple cells with gNBs.

[0025] In some embodiments of the method according to the first aspect the method is characterized by, that the overall pairs of primary / supplementary models can be reconfigured when any associated supplementary model(s) gets out of the concatenated model.

[0026] In some embodiments of the method according to the first aspect the method is characterized by, that the number of supplementary models can be adaptively adjusted so that the overall concatenated model can achieve target performance threshold.

[0027] In some embodiments of the method according to the first aspect the method is characterized by, that UE sub-group moving to neighboring cell / gNB can send ML assistance information via uplink ML signaling so that ML assistance information of UE sub-group can be used as part of data for model aggregation of network-sided model in neighboring cell / gNB.

[0028] In some embodiments of the method according to the first aspect the method is characterized by, that ML assistance information of UE sub-group is UE trajectory and / or mobility and / or UE-side model information.

[0029] In some embodiments of the method according to the first aspect the method is characterized by, that the configuration of the defined ML models applied across serving cell / gNB and neighboring cells / gNBs across multiple cells can be dynamically updated by setting both ML models and the associated gNBs for different cells.

[0030] In some embodiments of the method according to the first aspect the method is characterized by, that model outputs can be shared each other so that each networkside models can be concatenated together for any application-specific LCM use cases for the configured end-to-end model across multiple gNBs with their own network-side models.

[0031] In some embodiments of the method according to the first aspect the method is characterized by, that application-specific LCM use cases can be obtained from training and / or inferencing, updating.

[0032] In some embodiments of the method according to the first aspect the method is characterized by, that the interface can be defined to support ML information exchange across different gNBs including source / neighboring cells / gNBs so as to exchange ML information from all network-side models.

[0033] In some embodiments of the method according to the first aspect the method is characterized by, that any existing interfaces can be also re-used to support ML information exchange such as Xn between RAN nodes, NG between RAN and CN or F1 / E1 within RAN.

[0034] In some embodiments of the method according to the first aspect the method is characterized by, that NW-side models of each gNBs have the paired UE-side models of UE group for ML operation.

[0035] In some embodiments of the method according to the first aspect the method is characterized by, that NW-side models can have the input data information from the concatenated NW-side model(s) from neighboring cells / gNBs so that output of NW- side model can then be sent to neighboring cell / gNB where the associated NW-side model can utilize it for model aggregation.

[0036] According to a second aspect the present disclosure solves the cited problem by the proposed embodiments and described by an apparatus for multi-cell based concatenation by configuring a set of ML models that are applied to multiple cells 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. According to a third aspect the present disclosure solves the cited problem by the proposed embodiments and described by a user equipment comprising an apparatus according to the second aspect of this application.

[0037] According to a third aspect the present disclosure solves the cited problem by the proposed embodiments and described by a gNB comprising an apparatus according to the second aspect of this application.

[0038] According to a fourth aspect, the present disclosure relates to a wireless communication system for multi-cell based concatenation by configuring a set of ML models that are applied to multiple cells, wherein the wireless communication systems comprises user equipment according to third aspect, 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, said instructions being configured to carry out the steps according to the first aspect.

[0039] According to a further 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 for multi-cell based concatenation by configuring a set of ML models that are applied to multiple cells in a wireless communication system 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.

[0040] According to a further 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.

[0041] BRIEF DESCRIPTION OF THE DRAWINGS

[0042] Figure 1 is an exemplary table of model concatenation set. Figure 2 is an exemplary table of mapping relation about candidate neighboring gNBs and supplementary model pair IDs.

[0043] Figure 3 is an exemplary new functions to be supported via network interface.

[0044] Figure 4 is an exemplary block diagram of the configured end-to-end model across multiple gNBs.

[0045] Figure 5 is an exemplary block diagram of primary model and the associated supplementary model(s) for pairing.

[0046] Figure 6 is an exemplary flow chart of configuring model concatenation set at network side.

[0047] Figure 7 is an exemplary flow chart of primary / supplementary model pairing at UE side.

[0048] Figure 8 is an exemplary signaling flow of the end-to-end model concatenation setup.

[0049] Figure 9 is an exemplary signaling flow of determining primary / supplementary model pairing.

[0050] DETAILED DESCRIPTION

[0051] 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. 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.

[0052] 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.

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

[0054] In some embodiments, the non-limiting term user equipment (UE) or wireless device may be used and may refer to any type of wireless device communicating with a network node and / or with another UE in a cellular or mobile communication system. Examples of UE are target device, device to device (D2D) UE, machine type UE or UE capable of machine to machine (M2M) communication, PDA, PAD, Tablet, mobile terminals, smart phone, laptop embedded equipped (LEE), laptop mounted equipment (LME), USB dongles, UE category Ml, UE category M2, ProSe UE, V2V UE, V2X UE, etc.

[0055] 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.

[0056] 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.

[0057] 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.

[0058] 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.

[0059] 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.

[0060] 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.

[0061] 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”)).

[0062] 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.

[0063] Aspects of the embodiments are described below with reference to schematic flowchart diagrams and / or schematic block diagrams of methods, apparatuses, systems, and program products according to embodiments. It will be understood that each block of the schematic flowchart diagrams and / or schematic block diagrams, and combinations of blocks in the schematic flowchart diagrams and / or schematic block diagrams, can be implemented by code. This code may be provided to a processor of a general-purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart diagrams and / or block diagrams.

[0064] 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.

[0065] 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.

[0066] 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).

[0067] 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.

[0068] 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.

[0069] 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.

[0070] 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.

[0071] 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.

[0072] 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.

[0073] 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.

[0074] 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.

[0075] 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.

[0076] 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.

[0077] AI / ML Model is a data driven algorithm that applies AI / ML techniques to generate set of outputs based on set of inputs.

[0078] AI / ML model delivery is a generic term referring to delivery of an AI / ML model from one entity to another entity in any manner. Note is An entity could mean network node / function (e.g., gNB, LMF, etc.), UE, proprietary server, etc.

[0079] AI / ML model Inference is a process of using trained AI / ML model to produce set of outputs based on set of inputs.

[0080] 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.

[0081] 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.

[0082] 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.

[0083] 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.

[0084] 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.

[0085] 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.

[0086] Model activation means enable an AI / ML model for specific AI / ML-enabled feature.

[0087] Model deactivation means disable an AI / ML model for specific AI / ML-enabled feature.

[0088] Model download means Model transfer from the network to UE.

[0089] 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.

[0090] 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.

[0091] Model switching is deactivating currently active AI / ML model and activating different AI / ML model for specific AI / ML-enabled feature.

[0092] Model update is Process of updating the model parameters and / or model structure of model.

[0093] Model upload is Model transfer from UE to the network.

[0094] Network-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the network.

[0095] Offline field data is the data collected from field and used for offline training of the AI / ML model.

[0096] 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.

[0097] Online field data is the data collected from field and used for online training of the AI / ML model.

[0098] 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. There may be cases that may not exactly conform to this definition but could still be categorized as online training by commonly accepted conventions. Note is Fine- tuning / re-training may be done via online or offline training. This note could be removed when we define the term fine-tuning.

[0099] Reinforcement Learning (RL) is a process of training an AI / ML model from input (a.k.a. state) and feedback signal (a.k.a. reward) resulting from the model’s output (a.k.a. action) in an environment the model is interacting with.

[0100] Semi-supervised learning is a process of training model with mix of labelled data and unlabelled data.

[0101] Supervised learning is a process of training model from input and its corresponding labels.

[0102] 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.

[0103] UE-side (AI / ML) model is an AI / ML Model whose inference is performed entirely at the UE.

[0104] Unsupervised learning is a process of training model without labelled data.

[0105] 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.

[0106] 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.

[0107] The following explanation will provide the detailed description of the mechanism about pre-configuring and signaling the specific information about model online training by configuring a set of UE behaviors. AI / ML based techniques are currently applied to many different applications and 3GPP also started to work on its technical investigation to apply to multiple use cases based on the observed potential gains. AI / ML lifecycle can be split into several stages such as data collection / pre- processing, model training, model testing / validation, model deployment / update, model monitoring etc., where each stage is equally important to achieve target performance with any specific model(s). In applying AI / ML model for any use case or application, one of the challenging issues is to manage the lifecycle of AI / ML model. It is mainly because the data / model drift occurs during model deployment / inference and it results in performance degradation of AI / ML model. Fundamentally, the dataset statistical changes occur after model is deployed and model inference capability is also impacted with unseen data as input. In a similar aspect, the statistical property of dataset and the relationship between input and output for the trained model can be changed with drift occurrence. In this context, model training or re-training is one of key issues for model performance maintenance as model performance such as inferencing and / or training is dependent on different model execution environment with varying configuration parameters. To handle this issue, collaboration between UE and gNB is highly important to track model performance and re-configure model corresponding to different environments.

[0108] AI / ML model needs model monitoring after deployment because model performance cannot be maintained continuously due to drift and update feedback is then provided to re-train / update the model or select alternative model. When AI / ML model enabled wireless communication network is deployed, it is then important to consider how to handle AI / ML model in activation with re-configuration for wireless devices under operations such as model training, inference, updating, etc. Single-cell based model can be well-trained and deployed for any specific cell environment (e.g., serving cell). However, this model cannot be directly applied to any other neighboring cells as ML conditions (e.g., dataset, site, configuration, etc.) can vary across different cells. In this method, a set of ML models that are applied to multiple cells with serving cell / gNB and neighboring cells / gNBs are configured so that the configured ML models for each cells can be aligned together via ensemble model or concatenated model operation. Conceptually, concatenation refers to a model operation where multiple ML models are combined sequentially or jointly for input processing, feature aggregation, or decision making. Specifically, primary model pair is defined as two- sided model between source cell / gNB and UE(s) and supplementary model pair as two-sided model between neighboring cell / gNB and UE(s). One or more UE groups having their own on-device models can be assigned to support one-Ztwo-sided model operation.

[0109] There are a set of multiple model concatenations depending on implementation scenarios. For each model concatenation set, primary model and the associated supplementary model(s) can be paired for combination. Primary model and supplementary model can indicate either one-side model or two-side model depending on implementation scenarios. When two-sided model is applied for primary and supplementary models, different number of pairs for primary and supplementary models can be configured between network side and UE side. A set of supplementary model pair IDs can be configured across list of candidate neighboring cells / gNBs so that primary model pair ID can be concatenated with available supplementary model pair IDs for LCM use cases. Each candidate neighboring cells / gNBs can have one or more number of supplementary model pair IDs that can be concatenated together for the end-to-end model operation. Primary model and the associated supplementary model(s) can be paired for combination across multiple cells with gNBs.

[0110] For example, both primary model pair ID and supplementary model pair ID can be exchanged so that UE can also stay in the paired model operation with or without UE mobility. When any associated supplementary model(s) gets out of the concatenated model, the overall pairs of primary / supplementary models can be re-configured accordingly. The number of supplementary models can be adaptively adjusted so that the overall concatenated model can achieve target performance threshold. UE sub-group moving to neighboring cell / gNB can send ML assistance information via uplink ML signaling so that ML assistance information of UE sub-group (e.g., UE trajectory, mobility, UE-side model information etc.) can be used as part of data for model aggregation of network-sided model in neighboring cell / gNB. The configuration of the defined ML models applied across serving cell / gNB and neighboring cell / gNBs across multiple cells can be dynamically updated by setting both ML models and the associated gNBs for different cells (e.g., triggered by mobility, performance degradation, change of neighboring cells, or explicit reconfiguration command). For the configured end-to-end model across multiple gNBs with their own network-side models, model outputs can be shared each other so that each network-side models can be concatenated together for any application-specific LCM use cases (training, inferencing, updating, etc.). To exchange ML information from all network-side models, specific interface can be defined to support ML information exchange across different gNBs including source / neighboring gNBs. Any existing interfaces can be also re-used to support ML information exchange such as Xn between RAN nodes, NG between RAN and CN or F1 / E1 within RAN. A set of ML models are applied to multiple cells with serving gNB and neighboring gNBs. NW(network)-side models of each gNBs have the paired UE-side models of UE group for ML operation. NW-side models can have the input data information from the concatenated NW-side model(s) from neighboring gNBs so that output of NW-side model can then be sent to neighboring gNB where the associated NW-side model can utilize it for model aggregation. When UEs from UE group move to other neighboring gNB with UE mobility, those UEs can still be aligned with NW-side model. This invention provides reduced handover latency, improved model robustness across mobility, and scalable multi-cell Al processing, compared to conventional per-cell isolated models.

[0111] Figure 1 shows an exemplary table of model concatenation set. In this example, there are a set of multiple model concatenations. For each model concatenation set, Primary model and the associated supplementary model(s) can be paired for combination. Primary model and supplementary model can indicate either one-side model or two-side model depending on implementation scenarios. When two-sided model is applied for primary and supplementary models, different number of pairs for primary and supplementary models can be configured between network side and UE side. Model concatenation set information with the associated primary / supplementary model combination can be sent via system information or dedicated RRC signaling.

[0112] Figure 2 shows an exemplary table of mapping relation about candidate neighboring gNBs and supplementary model pair IDs. In this example, a set of supplementary model pair IDs can be configured across list of candidate neighboring gNBs so that primary model pair ID can be concatenated with available supplementary model pair IDs for LCM use cases. Each candidate neighboring gNBs can have one or more number of supplementary model pair IDs that can be concatenated together for the end-to-end model operation. Mapping relation information about a set of supplementary model pair IDs with list of candidate neighboring gNBs can be sent via system information or dedicated RRC signaling.

[0113] Figure 3 shows an exemplary new function to be supported via network interface. In this example, new functions are defined to support model concatenation operation across nodes via network interface between RAN nodes or between RAN and core network. Specifically, model concatenation management is a function supporting setup of candidate models to be used for model concatenation across source node and neighboring nodes based on ML configuration information obtained from network side. Model status report indicates model operation status of each nodes is reported to network side so that any re-configuration can be also made when any of concatenated models degrades after activating models concatenated across nodes. Model data transfer is a function that concatenated models can exchange input and / or output data of each models so that the overall model performance can be up- to-date with model updating or continuous training as well as inferencing.

[0114] Figure 4 shows an exemplary block diagram of the configured end-to-end model across multiple gNBs. In this example, for the configured end-to-end model across multiple gNBs with their own network-side models, model outputs can be shared each other so that each network-side models can be concatenated together for any application-specific LCM use cases (training, inferencing, updating, etc.). To exchange ML information from all network-side models, specific interface can be defined to support ML information exchange across different gNBs including source / neighboring gNBs. Any existing interfaces can be also re-used to support ML information exchange such as Xn between RAN nodes, NG between RAN and CN or F1 / E1 within RAN.

[0115] Figure 5 shows an exemplary block diagram of primary model and the associated supplementary model(s) for pairing. In this example, primary model and the associated supplementary model(s) can be paired for combination across multiple cells with gNBs. For example, both primary model pair ID and supplementary model pair ID can be exchanged so that UE can also stay in the paired model operation with or without UE mobility. When any associated supplementary model(s) gets out of the concatenated model, the overall pairs of primary / supplementary models can be reconfigured accordingly. The number of supplementary models can be adaptively adjusted so that the overall concatenated model can achieve target performance threshold. Any change or update information about model concatenation set and / or primary / supplementary models can be sent via L1 / L2 or RRC message.

[0116] Figure 6 shows an exemplary flow chart of configuring model concatenation set at network side. In this example, on network side, model concatenation sets can be configured for varying combinations of primary and supplementary model sets. Primary model is assigned to source cell and the associated supplementary models are assigned to neighboring cells. If there is any updates about configuration of model concatenation sets, the updated configuration information can be maintained in periodic or aperiodic way. In addition, a set of supplementary model pair IDs can be configured across list of candidate neighboring cells if applicable.

[0117] Figure 7 shows an exemplary flow chart of primary / supplementary model pairing at UE side. In this example, for UEs located in source gNB, primary model pairing is performed between network side and UE side. For UEs located in neighboring gNBs, supplementary model pairing is performed between network side and UE side. When models are paired, network side can determine UE-side model with indication directly. Or UE can autonomously decide UE-side model based on pairable model combination information. Figure 8 shows an exemplary signaling flow of the end-to-end model concatenation setup. In this example, after receiving ML configuration related information with model concatenation setup from network side, source gNB initiates sending model concatenation setup to neighboring gNBs and primary model pairing to UEs. When UEs paired with source gNB for primary model activation move to any neighboring gNB with mobility, those UEs can then be paired with their connected gNBs for supplementary model activation. During handover procedure, UEs in handover operation can be pre-paired with candidate neighboring gNB by receiving supplementary model information. Or after handover completion, UEs can receive ML re-configuration with supplementary model information for pairing and activation as well depending on implementation use cases.

[0118] Figure 9 shows an exemplary signaling flow of determining primary / supplementary model pairing. In this example, using any existing network interface or new interface, model concatenation setup is executed across multiple gNBs or multiple cells including source gNB and neighboring gNBs. Primary model pair and supplementary model pairs are activated in source gNB and neighboring gNBs, respectively. When candidate UEs having UE mobility or trajectory are identified, their ML condition / capability information can be provided to neighboring gNBs so that those UEs can be pre-paired with candidate supplementary model.

Claims

CLAIMS1 . A method of multi-cell based concatenation by configuring a set of ML models at network entity that are applied to multiple cells in a wireless communication system, comprising:• Configuring primary / supplementary model combinations;• Applying a set of ML models to multiple cells with serving cell / gNB and neighboring cells / gNBs;• Sending the configured model pair ID information to UEs across multiple cells / gNBs.

2. The method according to previous claim 1 , wherein model concatenation set information with the associated primary / supplementary model combination can be sent via system information or dedicated RRC signaling.

3. The method according to one of the previous claims, wherein mapping relation information about a set of supplementary model pair IDs with list of candidate neighboring cells / gNBs can be sent via system information or dedicated RRC signaling.

4. The method according to one of the previous claims, wherein any change or update information about model concatenation set and / or primary and / or supplementary models can be sent via L1 / L2 or RRC message.

5. The method according to one of the previous claims, wherein the configured ML models for each cells can be aligned together via ensemble model or concatenated model operation.

6. The method according to one of the previous claims, wherein primary model pair is defined as two-sided model between source cell / gNB and UE(s).

7. The method according to one of the previous claims, wherein supplementary model pair as two-sided model between neighboring cell / gNB and UE(s).

8. The method according to one of the previous claims, wherein one or more UE groups having their own on-device models can be assigned to support one- / two- sided model operation.

9. The method according to one of the previous claims, wherein there are a set of multiple model concatenations.

10. The method according to one of the previous claims, wherein primary model and the associated supplementary model(s) can be paired for combination for each model concatenation set.11 . The method according to one of the previous claims, wherein primary model and supplementary model can indicate either one-side model or two-side model depending on implementation scenarios.

12. The method according to one of the previous claims, wherein different number of pairs for primary and supplementary models can be configured between network side and UE side for two-sided model applied for primary and supplementary models.

13. The method according to one of the previous claims, wherein a set of supplementary model pair IDs can be configured across list of candidate neighboring cells / gNBs so that primary model pair ID can be concatenated with available supplementary model pair IDs for LCM use cases.

14. The method according to one of the previous claims, wherein each candidate neighboring cells / gNBs can have one or more number of supplementary model pair IDs that can be concatenated together for the end-to-end model operation.

15. The method according to one of the previous claims, wherein primary model and the associated supplementary model(s) can be paired for combination across multiple cells with gNBs.

16. The method according to one of the previous claims, wherein the overall pairs of primary / supplementary models can be re-configured when any associated supplementary model(s) gets out of the concatenated model.

17. The method according to one of the previous claims, wherein the number of supplementary models can be adaptively adjusted so that the overall concatenated model can achieve target performance threshold.

18. The method according to one of the previous claims, wherein UE sub-group moving to neighboring cell / gNB can send ML assistance information via uplink ML signaling so that ML assistance information of UE sub-group can be used as part of data for model aggregation of network-sided model in neighboring cell / gNB.

19. The method according to one of the previous claims, wherein ML assistance information of UE sub-group is UE trajectory and / or mobility and / or UE-side model information.

20. The method according to one of the previous claims, wherein the configuration of the defined ML models applied across serving cell / gNB and neighboring cells / gNBs across multiple cells can be dynamically updated by setting both ML models and the associated gNBs for different cells.21 .The method according to one of the previous claims, wherein model outputs can be shared each other so that each network-side models can be concatenated together for any application-specific LCM use cases for the configured end-to-end model across multiple gNBs with their own network-side models.

22. The method according to one of the previous claims, wherein application-specificLCM use cases can be obtained from training and / or inferencing, updating.

23. The method according to one of the previous claims wherein specific interface can be defined to support ML information exchange across different gNBs including source / neighboring cells / gNBs so as to exchange ML information from all network-side models.

24. The method according to one of the previous claims, wherein any existing interfaces can be also re-used to support ML information exchange such as Xn between RAN nodes, NG between RAN and CN or F1 / E1 within RAN.

25. The method according to one of the previous claims, wherein NW-side models of each gNBs have the paired UE-side models of UE group for ML operation.

26. The method according to one of the previous claims, wherein NW-side models can have the input data information from the concatenated NW-side model(s) from neighboring cells / gNBs so that output of NW-side model can then be sent to neighboring cell / gNB where the associated NW-side model can utilize it for model aggregation.

27. Apparatus for multi-cell based concatenation by configuring a set of ML models that are applied to multiple cells the apparatus comprising a wireless transceiver, a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to implement steps of the claims 1 to 2628. User Equipment comprising an apparatus according to claim 27.

29. gNB comprising an apparatus according to claim 27.

30. Wireless communication system multi-cell based concatenation by configuring a set of ML models that are applied to multiple cells, wherein the wireless communication systems comprises user equipment according to claim 28, gNB according to claim 29, whereby the user equipment and the gNB each comprises a processor coupled with a memory in which computer program instructions arestored, said instructions being configured to implement steps of the claims 1 to26.

Images