Method for model signaling based on ntn

Abstract

This application describes methods for using pre-configured AI / ML (artificial intelligence / machine learning) based ML clustering in a wireless mobile communication system, including base stations (e.g., gNB, TN, NTN) and mobile stations (e.g., UE). When applying AI / ML models to a radio access network, the signaling of model information exchange can be severely congested. Therefore, it is possible to establish model operations (e.g., model training / inference / monitoring / update) between the network and the UE by configuring ML clustering.

Description

Technical Field

[0001] This disclosure relates to AI / ML-based clustering, in which techniques are proposed for pre-configuring and signaling specific information about ML clustering applicable to radio access networks. Background Technology

[0002] Non-terrestrial networks (NTNs) are a cutting-edge concept in the telecommunications field that utilizes airborne or spaceborne vehicles, such as satellites and drones, to provide wireless connectivity. Here is an overview based on search results: NTNs refer to networks or segments of networks that utilize airborne or spaceborne vehicles for data transmission. These networks play a crucial role in extending connectivity to remote and challenging terrains, revolutionizing industries such as agriculture and shipping by providing reliable, high-speed connectivity to previously inaccessible areas. 5G Integration: NTN technology is integrated into 5G telecommunications systems to ensure ubiquitous connectivity. By incorporating satellites, drones, and other airborne vehicles into 5G infrastructure, NTN systems enhance service coverage, continuity, and scalability, meeting diverse use cases ranging from rural internet access to remote monitoring and surveillance.

[0003] Satellites include low Earth orbit (LEO) satellites, medium Earth orbit (MEO) satellites, geostationary orbit (GEO) satellites, and highly elliptical orbit (HEO) satellites.

[0004] Airborne vehicles: High-altitude platforms (HAPs), such as unmanned aerial vehicle systems (UAS), lighter-than-air UAS (LTA), and heavier-than-air UAS (HTA), operate at altitudes typically between 8 and 50 km.

[0005] Compared to terrestrial networks, coverage and resilience are enhanced. It offers the potential to achieve global connectivity in remote areas and supports mission-critical communications.

[0006] After proper testing, a reliable, stable, and cost-effective deployment can be achieved.

[0007] Non-terrestrial networks represent a pioneering approach in telecommunications to extend wireless connectivity globally by utilizing airborne and spaceborne vehicles. With the integration of NTN technology into 5G systems, the potential for enhanced coverage, reliability, and innovative applications across various industries is immense.

[0008] One of the selected research projects in 3GPP (3rd Generation Partnership Project) as part of the approved Release 18 package is AI / ML (Artificial Intelligence / Machine Learning), as described in the relevant document (RP-213599) submitted at 3GPP TSG (Technical Specification Group) RAN (Radio Access Networks) meeting #94e. The formal title of the AI / ML research project is "Study on AI / ML for NR Air Interface." The goal of this research project is to establish a common AI / ML framework and areas where AI / ML-based technologies and use cases can be utilized to generate benefits. According to 3GPP, the main objective of this research project is to study an AI / ML framework for the air interface by considering performance, complexity, and potential specification impacts from the target use cases. Specifically, AI / ML models, terminology, and descriptions used to establish common and specific characteristics of the framework will be included as one of the key work scopes. Regarding the AI / ML framework, various aspects are being investigated, and one of the key projects is on the lifecycle management of AI / ML models, which mandatorily includes multiple phases for model training, model deployment, model inference, model monitoring, and model updates. Currently, AI / ML specification work is in the work project discussion phase for Release 19. Earlier, in 3GPP TR 37.817 (Release 17), titled "Study on enhancement for DataCollection for NR and EN-DC," UE (User Equipment) mobility was also considered as an AI / ML use case, and one scenario for model training / inference was that both functions resided within the RAN node. Subsequently, a new work project, "Artificial Intelligence (AI) / Machine Learning (ML) for NG-RAN," was initiated in Release 18 to specify data collection enhancements and signaling support within the existing NG-RAN interface and architecture. For these proactive standardization efforts, RAN-based AI / ML models are considered crucial for both the network and UE to meet any desired model operations (e.g., model training, inference, selection, handover, updates, monitoring, etc.). Signaling model information can be used to pair the network-side and UE-side models for various lifecycle management (LCM) operations. However, the signaling overhead for indicating model information can be very high, especially when the base station (BS / gNB) processes model-based LCM between multiple UEs.In LCM, model training is one of the most critical parts of model deployment. Currently, there are no defined specifications for signaling methods and network-UE behavior to establish the datasets required for model updates / retraining, as any activated model can be affected by model / data drift. When ML conditions change, the performance of the activated AI / ML model may be impacted by data / model drift. In such cases, model retraining / update may be necessary. For example, when a trained ML model is deployed in the RAN, model inference performance can easily degrade if the target ML conditions do not perfectly match the true ML conditions measured for a specific model operation.

[0009] WO2023179893A1 describes a method performed by a network node in a terrestrial network to determine whether a UE should connect to a non-terrestrial network (NTN), the NTN including obtaining the predicted capacity of the NTN for the UE to transmit on.

[0010] WO2023165818A1 describes a method executed by a network node for implementing a UE prediction process in a terrestrial network (TN) –NTN, which predicts handover metrics corresponding to the appropriate category of the aggregated UE for handover between source TN or NTN network nodes.

[0011] WO2023153962A1 describes a method for using a distributed machine learning model during condition switching.

[0012] US2023180286A1 describes a method for transmitting data from a second node to a first node, wherein the method predicts the possible content of the data and sends the prediction of the possible content of the data to the second node. Summary of the Invention

[0013] This application describes a method for using pre-configured AI / ML (Artificial Intelligence / Machine Learning) based ML clustering in a wireless mobile communication system, which includes base stations (e.g., gNB, TN, NTN) and mobile stations (e.g., UE). When applying AI / ML models to a radio access network, signaling for model information exchange can become severely congested. Therefore, model operations (e.g., model training / inference / monitoring / updating) can be established between the network and the UE by configuring ML clustering.

[0014] This disclosure addresses the identified problems through the proposed embodiments and describes a method for configuring ML cluster mapping information based on NTN model signaling in a wireless communication system. The method includes: identifying a TN cell as an ML cluster; offloading some or all of the ML signaling overhead; transmitting the ML cluster mapping information via system information or a dedicated RRC; configuring three ML signaling modes, such as ML cluster mode, hybrid ML mode, and direct ML mode; configuring a limited set of ML cluster identifiers associated with the TN cell; and dynamically switching ML clusters (indexes or IDs) via L1 / L2 signaling.

[0015] In some embodiments of the method according to the first aspect, the method is characterized in that, for the mapping configuration of the ML cluster, the UE is able to provide auxiliary information (e.g., such as ML conditions, ML capabilities and / or supported model IDs) for ML signaling modes for single-sided or double-sided models.

[0016] In some embodiments of the method according to the first aspect, the method is characterized in that the UE can also be virtually assigned to different ML clusters, regardless of the TN cells they are connected to.

[0017] In some embodiments of the method according to the first aspect, the method is characterized in that the ML cluster mapping relationship information can be (non)periodically updated by reflecting any changes related to the TN cell set and the associated ML signaling patterns.

[0018] In some embodiments of the method according to the first aspect, the method is characterized in that the ML signaling exchange between the source entity and the target entity is performed directly in direct ML mode.

[0019] In some embodiments of the method according to the first aspect, the method is characterized in that the ML signaling exchange between the source entity and the target entity is performed indirectly via an intermediate entity in ML cluster mode.

[0020] In some embodiments of the method according to the first aspect, the method is characterized in that, in a hybrid ML mode, it is capable of establishing both direct ML and ML cluster connections, enabling any duplicate or separate ML signaling exchange between the source entity and the target entity with or without an intermediary entity.

[0021] In some embodiments of the method according to the first aspect, the method is characterized in that, for a UE in an ML cluster or hybrid ML operation mode, the configured ML operation can continue to be performed across TN cells within the ML cluster area during UE mobility.

[0022] In some embodiments of the method according to the first aspect, the method is characterized in that, for ML signaling mode switching, a 1-bit or 2-bit message for ML signaling mode switching can be configured.

[0023] In some embodiments of the method according to the first aspect, the method is characterized in that the trigger mode switching can be based on ML condition measurements and device ML capability updates (e.g., using a preset threshold) and a list of supported models for each entity, wherein the preset threshold can be associated with measurements of ML applicability conditions (e.g., ML application, LCM status, ML capability, model characteristics, site, etc.) by taking into account wireless communication conditions (e.g., data service congestion, energy-saving plans, link quality status, etc.).

[0024] In some embodiments of the method according to the first aspect, the method is characterized in that the ML signaling mode can be switched based on semi-static mode switching (e.g., via RRC signaling) or dynamic mode switching (e.g., L1 / L2 signaling).

[0025] According to a second aspect, this disclosure relates to an apparatus for configuring ML cluster mapping relationship information based on NTN model signaling in a wireless communication system, the apparatus comprising a wireless transceiver, a processor coupled to a memory, wherein computer program instructions are stored in the memory, the instructions being configured to implement the steps of any embodiment of the embodiments according to the first aspect.

[0026] According to the third aspect, this disclosure relates to user equipment, which includes the equipment according to the second aspect.

[0027] According to the fourth aspect, this disclosure relates to a base station, which includes the equipment according to the second aspect.

[0028] According to a fifth aspect, this disclosure relates to a wireless communication system, wherein a gNB includes a processor coupled to a memory storing computer program instructions configured to implement the steps according to the first aspect, wherein a user equipment (UE) includes a processor coupled to a memory storing computer program instructions configured to implement the steps according to the first aspect.

[0029] According to the sixth aspect, this disclosure relates to non-terrestrial networks (NTNs), which include wireless communication systems according to the fifth aspect.

[0030] According to a seventh aspect, this disclosure relates to a computer program product comprising instructions that, when executed by at least one processor, configure the at least one processor to perform a method according to a first aspect, the at least one processor being configured to perform a method for exchanging data according to any embodiment of the embodiments of this disclosure. The computer program product may use any programming language and may be in the form of source code, object code, or any intermediate form between source code and object code, such as a partially compiled form, or any other desired form.

[0031] According to an eighth aspect, this disclosure relates to a computer-readable storage medium including instructions that, when executed by at least one processor, configure the at least one processor to perform a method according to any embodiment of the present disclosure. Attached Figure Description

[0032] Figure 1 This is an example table of ML cluster mapping relationships.

[0033] Figure 2 This is an exemplary block diagram of the ML signaling mode.

[0034] Figure 3 This is an exemplary flowchart for configuring ML cluster mapping relationships on the network side.

[0035] Figure 4 This is an exemplary flowchart of activating ML operations using an ML cluster on the UE side.

[0036] Figure 5 This is an example signaling flow for ML signaling mode configuration between NTN and TN.

[0037] Figure 6 This is an exemplary signaling flow for establishing ML signaling modes across NTN, TN, and UE sides.

[0038] Figure 7 This is an example signaling flow for configuring the ML signaling mode between the NTN and the UE.

[0039] Figure 8 This is an exemplary flowchart for reselecting an ML cluster index. Detailed Implementation

[0040] The detailed description set forth below with reference to the accompanying drawings is intended as a description of various configurations and is not intended to represent only configurations in which the concepts described herein can 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 can be practiced without these specific details. In particular, although terms from 3GPP 5G NR may be used in this disclosure to exemplify embodiments herein, this should not be construed as limiting the scope of the invention.

[0041] Some embodiments of the ideas contemplated herein will now be described more fully with reference to the accompanying drawings. However, other embodiments are also included within the scope of the subject matter disclosed herein, and the disclosed subject matter should not be construed as being limited to 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.

[0042] Generally, all terms used herein should be interpreted according to their ordinary meaning in the relevant art, unless a different meaning is expressly given and / or implied in the context of their use. Unless otherwise expressly stated, all references to one / an / an element, device, component, element, step, etc., are openly interpreted as referring to at least one instance of said element, device, component, element, step, etc. The steps of any method disclosed herein need not be performed in the exact order disclosed, unless a step is explicitly described as occurring after or before another step, and / or it is implied that a step must occur after or before another step. Any feature of any embodiment disclosed herein may be applied to any other embodiment, where appropriate. Similarly, any advantage of any embodiment may be applied to any other embodiment, and vice versa. Other objects, features, and advantages of the appended embodiments will become apparent from the following description.

[0043] In some embodiments, the more general term "network node" may be used, and it may correspond to any type of radio network node or any network node that communicates with a UE (directly or via another node) and / or another network node. Examples of network nodes are NodeB, MeNB, ENB, network nodes belonging to MCG or SCG, base stations (BS), multi-standard radio (MSR) radio nodes (such as MSR BS), eNodeB, gNodeB, network controller, radio network controller (RNC), base station controller (BSC), repeater, donor node controlling repeater, base transceiver station (BTS), access point (AP), transport point, transport node, RRU, RRH, nodes in distributed antenna system (DAS), core network nodes (e.g., mobile switching center (MSC), mobility management entity (MME), etc.), operations and maintenance (O&M), operations support system (OSS), self-optimizing network (SON), location nodes (e.g., evolved servicing mobile location center (E-SMLC)), minimized drive test (MDT), test equipment (physical node or software), etc.

[0044] In some embodiments, the non-limiting terms User Equipment (UE) or Wireless Device may be used, and they may refer to any type of wireless device that communicates with a network node and / or another UE in a cellular or mobile communication system. Examples of UEs are target devices, device-to-device (D2D) UEs, machine-type UEs or UEs capable of machine-to-machine (M2M) communication, PDAs, PADs, tablet computers, mobile terminals, smartphones, laptop embedded devices (LEE), laptop mounted devices (LME), USB dongles, UE class M1, UE class M2, ProSe UE, V2V UE, V2X UE, etc.

[0045] Additionally, terms such as base station / gNodeB and UE should be considered non-restrictive and, in particular, do not imply any hierarchical relationship between the two; generally, "gNodeB" can be considered device 1 and "UE" can be considered device 2, and the two devices communicate with each other via a radio channel. Furthermore, in the following text, a transmitter or receiver can be either a gNodeB (gNB) or a UE.

[0046] As those skilled in the art will understand, aspects of the embodiments can be embodied as a system, device, method, or program product. Therefore, embodiments can take the form of purely hardware embodiments, purely software embodiments (including firmware, resident software, microcode, etc.), or embodiments combining software and hardware aspects.

[0047] For example, the disclosed embodiments may be implemented as hardware circuitry including custom-designed very large-scale integration (“VLSI”) circuitry 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, etc.). As another example, the disclosed embodiments may include one or more physical or logical blocks of executable code, which may, for example, be organized as objects, procedures, or functions.

[0048] Furthermore, embodiments may take the form of a program product embodied in one or more computer-readable storage devices that store machine-readable code, computer-readable code, and / or program code (hereinafter referred to as code). The storage device may be tangible, non-transitory, and / or non-transferable. The storage device may not contain signals. In one embodiment, the storage device uses only signals to access the code.

[0049] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable storage medium. A computer-readable storage medium may be a storage device for storing code. A storage device may be, for example, but not limited to, electronic, magnetic, optical, electromagnetic, infrared, holographic, micromechanical, or semiconductor systems, devices, or apparatuses, or any suitable combination of the foregoing.

[0050] More specific examples of storage devices (a non-exhaustive list) will include the following: electrical connections having one or more wires, portable computer floppy disks, hard disks, random access memory (“RAM”), read-only memory (“ROM”), erasable programmable read-only memory (“EPROM” or flash memory), portable optical disc read-only memory (“CD-ROM”), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium can be any tangible medium that can contain or store programs for use by or in conjunction with an instruction execution system, device, or apparatus.

[0051] The code used to perform the operations of the embodiments can be any number of lines and can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Python, Ruby, Java, Smalltalk, C++, etc., as well as conventional procedural programming languages ​​such as the "C" programming language, and / or machine languages ​​such as assembly language. The code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer via any type of network, including a local area network ("LAN"), a wireless LAN ("WLAN"), or a wide area network ("WAN"), or can be connected to an external computer (e.g., via the Internet through an Internet service provider ("ISP").

[0052] Furthermore, the features, structures, or characteristics described in the embodiments can be combined in any suitable manner. Numerous specific details, such as examples of programming, software modules, user selection, network transactions, database queries, database structures, hardware modules, hardware circuits, hardware chips, etc., are provided in the following description to provide a thorough understanding of the embodiments. However, those skilled in the art will recognize that those embodiments can be practiced without one or more specific details or using other methods, components, materials, etc. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects of the embodiments. References to “an embodiment,” “embodiment,” or similar language throughout the specification mean that a particular feature, structure, or characteristic described in connection with that embodiment is included in at least one embodiment. Therefore, unless expressly stated otherwise, the phrases “in one embodiment,” “in an embodiment,” and similar language appearing throughout the specification may, but not necessarily all, refer to the same embodiment, but rather mean “one or more, but not all, embodiments.” Unless expressly stated otherwise, the terms “comprising,” “including,” “having,” and variations thereof mean “including, but not limited to,” “including.” Unless expressly stated otherwise, an enumeration list of items does not imply that any or all of the items are mutually exclusive. Unless otherwise expressly stated, the terms “a,” “an,” and “the / said” also mean “one or more.”

[0053] The following description refers to schematic flowcharts and / or schematic block diagrams of methods, apparatus, systems, and program products according to embodiments. It should be understood that each block of the schematic flowcharts and / or schematic block diagrams, and combinations of blocks of the schematic flowcharts and / or schematic block diagrams, can be implemented by code. This code can 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 instructions executable via the processor of the computer or other programmable data processing apparatus establish components for implementing the functions / actions specified in the flowcharts and / or block diagrams.

[0054] The code may also be stored in a storage device that can instruct a computer, other programmable data processing device or other device to operate in a particular manner, such that the instructions stored in the storage device produce an article of art, which includes instructions that implement the functions / actions specified in the flowchart and / or block diagram.

[0055] The code may also be loaded onto a computer, other programmable data processing device or other apparatus to cause a series of operational steps to be executed on the computer, other programmable device or other apparatus, thereby producing a computer-implemented process, such that the code executing on the computer or other programmable device provides a process for implementing the functions / actions specified in the flowchart and / or block diagram.

[0056] The flowcharts and / or block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of devices, systems, methods, and program products according to various embodiments. In this regard, each block in the flowcharts and / or block diagrams may represent a module, segment, or portion of code, which includes one or more executable instructions for implementing a specified logical function.

[0057] It should also be noted that in some alternative implementations, the functions indicated within the boxes may not appear in the order shown in the figures. For example, depending on the functionality involved, two boxes shown consecutively may actually be executed substantially simultaneously, or these boxes may sometimes be executed in reverse order. Other steps and methods that are functionally, logically, or effectively equivalent to one or more boxes or portions thereof in the illustrated figures are conceivable.

[0058] While various arrow and line types may be used in flowcharts and / or block diagrams, they should be understood not to limit the scope of the corresponding embodiments. In practice, some arrows or other connectors may be used only to indicate the logical flow of the depicted embodiment. For example, an arrow may indicate a wait or monitoring period of unspecified duration between enumeration steps in a depicted embodiment. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, may be implemented by a system based on dedicated hardware or a combination of dedicated hardware and code that performs the specified function or action.

[0059] The description of the elements in each figure can be referenced to the elements in the preceding figures. In all figures, similar designations refer to similar elements, including alternative embodiments of similar elements.

[0060] The detailed description set forth below with reference to the accompanying drawings is intended as a description of various configurations and is not intended to represent 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 example, although 3GPP terms, such as 5G NR, may be used in this disclosure to exemplify embodiments herein, this should not be construed as limiting the scope of this disclosure.

[0061] This disclosure relates to a wireless communication system, which may be, for example, a 5G NR wireless communication system. More specifically, it refers to a RAN (Radio Access Network) within the wireless communication system for exchanging data with a UE via radio signals. For example, the RAN may transmit data to the UE (Downlink DL), such as data received from the core network (CN). The RAN may also receive data from the UE (Uplink UL), which may be forwarded to the CN.

[0062] In the illustrated example, the RAN includes a base station (BS). Of course, the RAN may include more than one BS to increase the coverage of the wireless communication system. Depending on the implemented wireless communication standard, each of these BSs may be referred to as an NB, eNodeB (or eNB), gNodeB (or gNB in ​​the case of a 5G NR wireless communication system), access point, etc.

[0063] The UE is located within the coverage of the BS. The coverage of the BS corresponds, for example, to an area where the UE can decode the PDCCH transmitted by the BS.

[0064] Examples of wireless devices suitable for implementing any of the methods discussed in this disclosure at the UE correspond to devices that provide wireless connectivity to a RAN (Radio Range) of a wireless communication system and can be used to exchange data with said RAN. Such wireless devices may be included in the UE. The UE may be, for example, a cellular phone, a wireless modem, a wireless communication device, a handheld device, a laptop computer, etc. The UE may also be an Internet of Things (IoT) device, such as a wireless camera, a smart sensor, a smart meter, smart glasses, a vehicle (manned or unmanned), a GPS device, etc., or any other equipment capable of running applications that require the exchange of data with a remote receiver via a wireless device.

[0065] The wireless device includes one or more processors and one or more memories. The one or more processors may include, for example, 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 memory (magnetic hard disk, solid-state drive, optical disk, electronic storage, 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 some of the steps of a method for exchanging data executed on the UE side according to any embodiment of the embodiments disclosed herein.

[0066] The wireless device may also include a main radio (MR) unit. The MR unit corresponds to the main wireless communication unit of the wireless device and is used to exchange data with the BS of the RAN using radio signals. The MR unit can implement one or more wireless communication protocols and can be, for example, a 3G, 4G, 5G, NR, WiFi, WiMax, or other transceivers. In a preferred embodiment, the MR unit corresponds to a 5G NR wireless communication unit.

[0067] AI / ML models are data-driven algorithms that use AI / ML techniques to generate a set of outputs based on a set of inputs.

[0068] AI / ML model delivery is a general term that refers to delivering an AI / ML model from one entity to another in any way. Note that "entity" can mean network node / function (e.g., gNB, LMF, etc.), UE, proprietary server, etc.

[0069] AI / ML model inference is the process of using a trained AI / ML model to produce a set of outputs based on a set of inputs.

[0070] AI / ML model testing is a sub-process of training that evaluates the performance of the final AI / ML model using a different dataset than that used for model training and validation. Unlike AI / ML model validation, testing does not assume subsequent tuning of the model.

[0071] AI / ML model training is the process of training an AI / ML model in a data-driven manner [by learning input / output relationships], and obtaining a trained AI / ML model for inference.

[0072] AI / ML model delivery is conducted via the air interface in a manner opaque to 3GPP signaling. The delivery consists of parameters representing a model structure known at the receiving end, or a new model with parameters. The delivery may include a complete model or a partial model.

[0073] AI / ML model validation is a subprocess of training that evaluates the quality of an AI / ML model using a different dataset than the one used for model training. This helps in selecting model parameters that generalize to datasets other than those used for model training.

[0074] Data collection is the process by which network nodes, management entities, or user-defined users (UEs) collect data for the purpose of AI / ML model training, data analysis, and inference.

[0075] Federated learning / federated training is a machine learning technique that trains AI / ML models across multiple distributed edge nodes (e.g., UE, gNB), with each edge node performing local model training using local data samples. This technique requires multiple interactions between models but does not exchange local data samples.

[0076] Functionality identification is the process / method of identifying AI / ML functionality to achieve a common understanding between the NW and UE. Note that information about AI / ML functionality can be shared during functionality identification. The location where AI / ML functionality resides depends on the specific use case and sub-use case.

[0077] Model activation refers to enabling AI / ML models for specific AI / ML-enabled features.

[0078] Model deactivation means disabling the AI / ML model for specific AI / ML-enabled features.

[0079] Model download refers to the transfer of a model from the network to the UE.

[0080] Model identification is the process / method of identifying AI / ML models to facilitate a shared understanding between the NW and UE. The process / method of model identification may or may not be applicable, and information about the AI / ML model may be shared during the model identification process.

[0081] Model monitoring is the process of monitoring the inference performance of AI / ML models.

[0082] Model parameter update is the process of updating the model parameters.

[0083] Model selection is the process of choosing the AI / ML model to activate from among multiple models for the same AI / ML-enabled feature. Model selection may or may not be performed simultaneously with model activation.

[0084] Model switching deactivates the currently active AI / ML model and activates a different AI / ML model for specific AI / ML-enabled features.

[0085] Model update is the process of updating the model parameters and / or model structure.

[0086] Model upload is the transfer of the model from the UE to the network.

[0087] A network-side (AI / ML) model is an AI / ML model in which inference is performed entirely at the network.

[0088] Offline field data is data collected from the field and used for offline training of AI / ML models.

[0089] Offline training is an AI / ML training process in which a model is trained on a collected dataset, and the trained model is later used or delivered for inference. It is noted that this definition is for guidance only. There may be cases that do not fully meet this definition but can still be classified as offline training according to accepted conventions.

[0090] Online field data is data collected from the field and used for online training of AI / ML models.

[0091] Online training is an AI / ML training process in which the model being used for inference is trained (near) real-time (and often continuously) as new training samples arrive. It's worth noting that the concepts of (near) real-time and non-real-time are context-dependent and relative to the inference timescale. This definition is for guidance only.

[0092] There may be cases that don't fully meet this definition but can still be classified as online training according to accepted conventions. Note that fine-tuning / retraining can be done via online or offline training. This note can be removed when we define the term "fine-tuning".

[0093] Reinforcement learning (RL) is the process of training an AI / ML model in an environment in which the model interacts, based on inputs (also known as states) and feedback signals (also known as rewards) generated by the model's outputs (also known as actions).

[0094] Semi-supervised learning is the process of training a model using a mixture of labeled and unlabeled data.

[0095] Supervised learning is the process of training a model based on the input and its corresponding labels.

[0096] A two-sided (AI / ML) model is a paired AI / ML model on which joint inference is performed, where joint inference includes AI / ML inference jointly performed across the UE and the network, i.e., the first part of the inference is performed by the UE first, and then the remaining part is performed by the gNB, or vice versa.

[0097] The UE-side (AI / ML) model is an AI / ML model in which inference is performed entirely at the UE.

[0098] Unsupervised learning is the process of training a model without labeled data.

[0099] From 3GPP's perspective, a proprietary format model is an ML model with a vendor / device-specific proprietary format. These proprietary format models are mutually unrecognizable across vendors and hide model design information from other vendors when shared.

[0100] From 3GPP's perspective, open format models are formatted ML models that are mutually identifiable across vendors and allow interoperability. They are mutually identifiable between vendors and do not hide model design information from other vendors when shared.

[0101] The following explanation provides a detailed description of the mechanism for pre-configuring and signaling specific information about online model training by configuring a set of UE behaviors. AI / ML-based technologies are currently applied to many different applications, and based on observed potential benefits, 3GPP has also begun its technology research for application to multiple use cases. The AI / ML lifecycle can be broken down into several phases, such as data collection / preprocessing, model training, model testing / validation, model deployment / update, and model monitoring, each of which is equally important for achieving the target performance of any particular model. One of the challenging issues when applying AI / ML models to any use case or application is managing the AI / ML model lifecycle. This is primarily because data / model drift occurs during model deployment / inference, and it can lead to performance degradation of the AI / ML model. Fundamentally, dataset statistics change after the model is deployed, and the model's inference capabilities are also affected by unseen data as input. Similarly, the statistical properties of the dataset and the relationship between the input and output of the trained model can change with drift. In this context, model training or retraining is a critical issue within the critical issues of model performance maintenance, because model performance, such as inference and / or training, depends on different model execution environments with varying configuration parameters.

[0102] To address this issue, collaboration between the UE and gNB is crucial for tracking model performance and reconfiguring models to suit different environments. Since model performance can become unstable due to drift, AI / ML models require post-deployment monitoring to provide update feedback for retraining / updating the model or selecting an alternative model. When deploying wireless communication networks with AI / ML enabled models, it is important to consider how to handle the reconfiguration of active AI / ML models for wireless devices during operations such as model training, inference, and updates.

[0103] In this method, during NTN RAN-based ML model operation, one or more TN cells within the NTN cell coverage area are selected as an "ML cluster" to offload some (or all) of the ML signaling overhead. The ML cluster may consist of one or more TN cells. Furthermore, ML cluster mapping information is pre-configured (e.g., an index-based set of TN cells for ML signaling patterns), enabling ML configuration information, including the ML cluster mapping information, to be transmitted via system information or a dedicated RRC when necessary. In other words, an ML cluster refers to a group of one or more TN cells dynamically or statically determined within the NTN cell coverage area, which is assigned to the AI / ML model operation by offloading some or all of the ML signaling overhead. The ML cluster operates as an intermediate entity that facilitates ML signaling exchange between the source entity (e.g., NTN) and the target entity (e.g., TN, UE, or another network node), thereby optimizing ML signaling efficiency. The ML cluster mapping relationship, which defines the association between TN cells and ML clusters, can be pre-configured (e.g., using an index-based TN cell set) or dynamically updated based on network conditions, ML signaling patterns, or UE mobility. During UE mobility, the ML cluster configuration ensures the continuity of ML operations across TN cells within the ML cluster area.

[0104] For ML cluster mapping configuration, the UE can provide auxiliary information (e.g., ML conditions, ML capabilities, and / or supported model IDs) for ML signaling modes to be used in single-sided or double-sided models. A single-sided model is a model operation at either side of two entities, while a double-sided model is a model operation at both sides of two entities. The ML cluster mapping information can then be (non-)periodically updated to reflect any changes related to the TN cell set and associated ML signaling modes. In NTN RAN-based ML model operations, three ML signaling modes can be configured: ML cluster mode, hybrid ML mode, and direct ML mode. In direct ML mode, ML signaling exchange between the source and target entities is performed directly. In ML cluster mode, ML signaling exchange between the source and target entities is performed indirectly via an intermediate entity. In hybrid ML mode, both direct ML and ML cluster connections can be established, enabling any duplicate or separate ML signaling exchange between the source and target entities with or without an intermediate entity. For UEs operating in ML cluster or hybrid ML operation modes, the configured ML operation can continue across TN cells within the ML cluster area during UE mobility. For ML signaling mode switching, a 1-bit or 2-bit ML signaling mode switching message can be sent. For triggered mode switching, it can be based on ML condition measurements and device ML capability updates (e.g., using preset thresholds) and a list of supported models for each entity, where the pre-configured thresholds can be associated with measurements of ML applicability conditions (e.g., ML application, LCM status, ML capabilities, model characteristics, site, etc.) by taking into account wireless communication conditions (e.g., data traffic congestion, power-saving plans, link quality status, etc.). ML signaling modes can be switched based on: 1) semi-static mode switching (e.g., via RRC signaling) or 2) dynamic mode switching (e.g., L1 / L2 signaling).

[0105] Figure 1 An exemplary table of ML cluster mapping relationships is shown. In this example, the ML cluster mapping relationship information is pre-configured, and each ML cluster index or ID indicates the associated TN cell as a set of TN cells to support ML cluster-based ML operations. The ML cluster mapping relationship information can also be (non-)periodically updated to reflect any changes related to the TN cell set and the associated ML signaling patterns.

[0106] Figure 2An exemplary block diagram of ML signaling modes is shown. In this example, three ML signaling modes can be configured, such as ML cluster mode, hybrid ML mode, and direct ML mode. In direct ML mode, ML signaling exchange between the source entity and the target entity is performed directly. In ML cluster mode, ML signaling exchange between the source entity and the target entity is performed indirectly via an intermediate entity. In hybrid ML mode, both direct ML and ML cluster connections can be established, enabling any duplicate or separate ML signaling exchange between the source entity and the target entity with or without an intermediate entity. However, other types of network entities (e.g., mobile edge devices, UAVs / drones, etc.) can be applied to use ML signaling modes.

[0107] Figure 3 An exemplary flowchart for configuring ML cluster mapping relationships on the network side is shown. In this example, the ML cluster mapping relationship can be configured with a limited set of ML clusters with identifiers associated with TN cells. Alternatively, if configured, the UE can be virtually assigned to different ML clusters regardless of the TN cells they are connected to.

[0108] Figure 4 An exemplary flowchart is shown to activate ML operations using an ML cluster on the UE side. In this example, ML operations can be enabled using a configured ML cluster identified at the UE using mapping relationship information.

[0109] Figure 5 An exemplary signaling flow for configuring ML signaling modes between NTN and TN is shown. In this example, the ML cluster is determined at the source entity (e.g., NTN) such that intermediate entities (e.g., TN) can be configured to support ML cluster-based ML operations at the location of the UE.

[0110] Figure 6 An exemplary signaling flow for establishing ML signaling patterns across the NTN, TN, and UE sides is illustrated. In this example, the UE-side model is configured to support ML cluster-based ML operations, enabling an intermediate entity (e.g., the TN) to provide ML data updates between the source and target entities. When there are a large number of UE devices with UE-side models, the signaling overhead carried between the NTN and the UE can be reduced by using ML clusters.

[0111] Figure 7 An exemplary signaling flow for configuring ML signaling mode between the NTN and the UE is shown. In this example, when ML clustering cannot be enabled for the UE, the ML signaling mode can be switched by sending an ML signaling mode request. When ML clustering mode is unavailable, direct ML or hybrid ML can be established.

[0112] Figure 8An exemplary flowchart for reselecting an ML cluster index is shown. In this example, when it is detected that the UE has exceeded the current ML cluster due to mobility or TN cell / link / ML conditions, an ML cluster can be reselected. When switching ML cluster indexes or IDs, the handover can also be performed dynamically via L1 / L2 signaling, as RRC messages can also be used.

Claims

1. A method for configuring NTN-based model signaling of ML cluster mapping relationship information in a wireless communication system, the method comprising: ● Identify the TN cell as an ML cluster; ● Offload some or all of the ML signaling overhead; ● Send ML cluster mapping information via system information or dedicated RRC; ● Configure three ML signaling modes, such as ML cluster mode, hybrid ML mode, and direct ML mode; ● Configure a limited set of ML clusters with identifiers associated with TN cells; ● Dynamically switch ML clusters (index or ID) via L1 / L2 signaling.

2. The method according to claim 1, wherein for the mapping configuration of the ML cluster, the UE is able to provide auxiliary information (e.g., such as ML conditions, ML capabilities and / or supported model IDs) for the ML signaling mode for single-sided or dual-sided models.

3. The method according to any one of the preceding claims, wherein the UE can also be virtually assigned to different ML clusters, regardless of the TN cells they are connected to.

4. The method according to any one of the preceding claims, wherein the ML cluster mapping relationship information can be (non)periodically updated by reflecting any changes related to the TN cell set and the associated ML signaling patterns.

5. The method according to any one of the preceding claims, wherein the ML signaling exchange between the source entity and the target entity is performed directly in direct ML mode.

6. The method according to any one of the preceding claims, wherein the ML signaling exchange between the source entity and the target entity is performed indirectly via an intermediate entity in ML cluster mode.

7. The method according to any one of the preceding claims, wherein in the hybrid ML mode, both direct ML and ML cluster connections can be established, enabling any duplicate or separate ML signaling exchange between the source entity and the target entity with or without an intermediary entity.

8. The method according to any one of the preceding claims, wherein for a UE in an ML cluster or hybrid ML operation mode, the configured ML operation can continue to be performed across TN cells within the ML cluster area during UE mobility.

9. The method according to claim 1, wherein for ML signaling mode switching, a 1-bit or 2-bit message for ML signaling mode switching can be configured.

10. The method according to claim 1, wherein the trigger mode switching is based on ML condition measurements and device ML capability updates (e.g., using a preset threshold) and the list of supported models for each entity, wherein the preset threshold is associated with measurements of ML applicability conditions (e.g., ML application, LCM status, ML capability, model characteristics, site, etc.) by taking into account wireless communication conditions (e.g., data service congestion, energy-saving plans, link quality status, etc.).

11. The method according to claim 1, wherein the ML signaling mode can be switched based on semi-static mode switching (e.g., via RRC signaling) or dynamic mode switching (e.g., L1 / L2 signaling).

12. An apparatus for configuring ML cluster mapping relationship information in a wireless communication system using an NTN-based model signaling method, the apparatus comprising a wireless transceiver, a processor coupled to a memory, the memory storing computer program instructions configured to implement the steps of claims 1 to 11.

13. A user equipment comprising the device according to claim 12.

14. A base station, the base station comprising the device according to claim 7.

15. A wireless communication system, wherein a gNB includes a processor coupled to a memory storing computer program instructions configured to implement the steps of claims 1 to 12, wherein a user equipment (UE) includes a processor coupled to a memory storing computer program instructions configured to implement the steps of claims 1 to 12.

16. A non-terrestrial network (NTN), the non-terrestrial network comprising the wireless communication system of claim 15.

Images