Model measurement feedback signaling
By configuring general and dedicated ML measurement items for wireless communication systems and optimizing ML measurement feedback using RRC messages, the degradation of model performance caused by drift was solved, and the efficiency of model monitoring and signaling resource utilization were improved.
Patent Information
- Application Number
- CN202580029444.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2024-05-06
- Filing Date
- 2025-04-30
- Publication Date
- 2026-11-17
AI Technical Summary
In wireless communication systems, existing technologies have failed to effectively manage the lifecycle of AI/ML models, resulting in model performance degradation due to data/model drift, and high signaling overhead affecting the efficiency of ML measurement feedback.
By configuring ML measurement items for wireless communication systems, classifying them into general and special items, and transmitting configuration information via RRC messages, the ML measurement feedback is optimized using indexes and priority sorting, reducing uplink resource usage and improving the accuracy of model performance monitoring.
It achieves efficient ML measurement feedback signaling, reduces signaling overhead, improves the accuracy and efficiency of model performance monitoring, and adapts to model reconfiguration in different environments.
Smart Images

Figure CN123125938A_ABST
Abstract
Description
Technical Field
[0001] This disclosure relates to AI / ML-based ML measurements, wherein techniques are presented for pre-configuring and signaling specific information about ML measurement items applicable to radio access networks. Background Technology
[0002] Within 3GPP (3rd Generation Partnership Project), one of the selected research projects 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 this AI / ML research project is "Study on AI / ML for NR Air Interface." The objective of this research project is to identify general AI / ML frameworks and areas where benefits can be derived from using AI / ML-based technologies and use cases. According to 3GPP, the primary objective of this research project is to study AI / ML frameworks for the air interface by considering performance, complexity, and potential specification impacts from the target use cases. Specifically, AI / ML models, terminology, and descriptions for identifying the general and specific characteristics of the framework are included as one of the key areas of work. Regarding AI / ML frameworks, we are investigating various aspects, and one of the key projects is the lifecycle management of AI / ML models, which includes multiple mandatory stages such as model training, model deployment, model inference, model monitoring, and model updates.
[0003] Furthermore, in 3GPP, a two-sided (AI / ML) model is defined as a paired AI / ML model on which joint inference is performed, where joint inference includes AI / ML inference performed jointly across the UE and the network. Additionally, for a one-sided (AI / ML) model, a UE-side (AI / ML) model is defined as an AI / ML model where inference is performed entirely at the UE, and a network-side (AI / ML) model is defined as an AI / ML model where inference is performed entirely at the network. Currently, AI / ML specification work is in the stage of discussion for a work project for version 19. Earlier, in 3GPP TR 37.817 of version 17, entitled “Study on enhancement for Data Collection for NR and EN-DC,” UE (User Equipment) mobility was also considered as one of the AI / ML use cases, and one scenario for model training / inference was that both functions resided within the RAN node. Subsequently, a new working project, "Artificial Intelligence (AI) / Machine Learning (ML) for NG-RAN," was launched in version 18 to specify data collection enhancements and signaling support within the existing NG-RAN interface and architecture. For this proactive standardization effort, RAN-based AI / ML models are considered crucial for both the network and the UE to meet any desired model operations (e.g., model training, inference, selection, handover, updates, monitoring, etc.). In the RAN, signaling is critical for communication between the UE and the network, as it occurs across different layers of the protocol stack—primarily L1 (Layer 1), L2 (Layer 2), and RRC (Radio Resource Control). RRC, a Layer 3 protocol used on the air interface between the UE and base stations (e.g., gNB in 5G, eNB in LTE), primarily functions to establish, configure, maintain, and release the radio resources and connections required for communication. Model information can be signaled to pair the network-side model and the UE-side model for various lifecycle management (LCM) operations. However, the signaling overhead for instructing model information can be very high, especially when processing model-based LCM between the base station (BS / gNB) and multiple UEs. Model training is one of the most critical parts of model deployment in LCM, and currently there are no defined specifications for signaling methods and network-UE behavior to identify the datasets required for model updates / retraining, as any activated model can be affected by model / data drift. When ML conditions change, the enabled AI / ML model may suffer performance degradation due to data / model drift.In this scenario, model retraining / updating can be performed. For example, when a trained ML model is deployed in a RAN, if the target ML conditions do not perfectly match the true ML conditions measured for a particular model operation, the model's inference performance can easily degrade.
[0004] US 2021326701A1 describes a method for transmitting measurement results to other nodes for neural network training and a method for reporting UE capabilities to a server and configuring neural network parameters.
[0005] US 2022400373A1 discloses a method performed by a UE to: send UE capability information to a BS indicating at least one radio capability of the UE and at least one machine learning (ML) capability of the UE, and receive ML configuration information from the BS indicating at least one neural network function based on the UE capability information.
[0006] US 2022330012A1 discloses performing an ML process based on at least one initial ML capability of a UE, and determining at least one updated ML capability for the ML process corresponding to the update of at least one initial ML capability.
[0007] WO2023272718A1 illustrates UE indications for support of end-to-end multi-block machine learning applications with blocks of multi-block machine learning applications.
[0008] US 2022377844A1 discloses a network sending a request to train an ML model to activate ML model training, and a device sending an ML model training result indicating the trained ML model based on receiving the ML model training request. Summary of the Invention
[0009] This disclosure addresses the cited problems through the proposed embodiments and describes a method for performing advanced model measurement feedback signaling by configuring ML measurement items for a model set in a wireless communication system. The method includes: classifying the configured ML measurement items into general ML measurement items and special ML measurement items; mapping a model set to be associated with the ML measurement items; and providing mapping information about the models and associated ML measurement items.
[0010] In some embodiments of the method according to the first aspect, the method is characterized in that a general ML measurement item can be applied to all models for measurement.
[0011] In some embodiments of the method according to the first aspect, the method is characterized in that a dedicated ML measurement item can be applied to a specific model for measurement.
[0012] In some embodiments of the method according to the first aspect, the method is characterized in that configuration information regarding general / dedicated ML measurements can be sent via RRC messages.
[0013] In some embodiments of the method according to the first aspect, the method is characterized in that two or more ML measurement items can be grouped into subsets, such that index / ID information can be configured for one or more subsets of the ML measurement items.
[0014] In some embodiments of the method according to the first aspect, the method is characterized in that ML measurements or indexed subsets of ML measurements can be sent via RRC messages.
[0015] In some embodiments of the method according to the first aspect, the method is characterized in that the mapping relationship between the model and the ML measurement items can be sent via system information or dedicated RRC signaling.
[0016] In some embodiments of the method according to the first aspect, the method is characterized in that a priority ordering of ML measurement feedback can be configured for each ML measurement item or subset of ML measurement items or general / dedicated ML measurement item.
[0017] In some embodiments of the method according to the first aspect, the method is characterized in that UL resources can be scheduled for use with priority-ordered ML measurement feedback.
[0018] In some embodiments of the method according to the first aspect, the method is characterized in that a priority index can be sent to the UE for repricing (e.g., when an unscheduled ML measurement feedback is requested).
[0019] In some embodiments of the method according to the first aspect, the method is characterized in that when an unscheduled ML measurement feedback is requested, a priority index is sent to the UE for repriority reordering.
[0020] In some embodiments of the method according to the first aspect, the method is characterized in that, for a group of UEs using the same model across UEs, ML measurement feedback can be requested only from any selected UE.
[0021] In some embodiments of the method according to the first aspect, the method is characterized in that the ML measurement item can be one or more sets of parameters to be measured for the model.
[0022] In some embodiments of the method according to the first aspect, the method is characterized in that the indication of general / specific ML measurement items can be associated with a mapping table.
[0023] In some embodiments of the method according to the first aspect, the method is characterized in that the ML measurement items associated with the model can be further associated with a general / specific ML measurement item category.
[0024] In some embodiments of the method according to the first aspect, the method is characterized in that any updates to the mapping relationship information can also be indicated via L1 / L2 or RRC signaling.
[0025] According to a second aspect, this disclosure relates to an apparatus for performing advanced model measurement feedback signaling by configuring ML measurement items for a model set applied to multiple cells in a wireless communication system. The apparatus includes a wireless transceiver and a processor coupled to a memory storing computer program instructions configured to perform the steps according to the first aspect of this application.
[0026] According to a third aspect, this disclosure relates to a user equipment that includes the means according to the second aspect.
[0027] According to the fourth aspect, this disclosure relates to a gNB that includes the means according to the second aspect.
[0028] According to a fifth aspect, this disclosure relates to a wireless communication system for performing advanced model measurement feedback signaling by configuring ML measurement items for a model set, wherein the wireless communication system includes a user equipment according to a third aspect and a gNB according to a fourth aspect, wherein the user equipment and the gNB each include a processor coupled to a memory storing computer program instructions configured to perform the steps of the first aspect of this application as claimed in claims 1 to 16.
[0029] According to a sixth 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 the method according to a first aspect of this disclosure. The computer program product may be in 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.
[0030] According to a seventh 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 of the embodiments of this disclosure. Attached Figure Description
[0031] Figure 1 This is an example table showing the mapping between model sets and associated ML measurement items.
[0032] Figure 2 This is an exemplary table showing the mapping between categorized general ML measurements and specialized ML measurements to subsets of ML measurement items.
[0033] Figure 3 This is an exemplary flowchart of configuring measurement items for a model set on the network side.
[0034] Figure 4 This is an exemplary flowchart for measuring configured measurement items on the UE side.
[0035] Figure 5 This is an exemplary signaling flow for ML measurement feedback with priority ordering. Detailed Implementation
[0036] 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 the 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. Specifically, 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.
[0037] Some embodiments of the examples 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 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.
[0038] 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 a / an / said element, device, component, part, step, etc., should be interpreted openly as referring to at least one instance of that element, device, component, part, 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 following or preceding another step, and / or it implies that a step must follow or precede another step. Where appropriate, any feature of any embodiment of the embodiments disclosed herein may be applied to any other embodiment. Similarly, any advantage of any embodiment in the embodiments 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.
[0039] In some embodiments, the more general term "network node" may be used, and this term may correspond to any type of radio network node or any network node that communicates with the UE (directly or via another node) and / or with 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.
[0040] In some embodiments, the non-limiting terms User Equipment (UE) or Wireless Device may be used, and the term may refer to any type of wireless device that communicates with a network node and / or with 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 (LEEs), laptop mounted devices (LMEs), USB dongles, UE class M1, UE class M2, ProSe UEs, V2V UEs, V2X UEs, etc.
[0041] Furthermore, 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 as device 1 and "UE" can be considered as device 2, and the two devices communicate with each other through a radio channel. Also, in the following text, a transmitter or receiver can be a gNodeB (gNB) or a UE.
[0042] As those skilled in the art will understand, aspects of the embodiments can be embodied as a system, apparatus, method, or program product. Therefore, embodiments can take the form of an all-hardware embodiment, an all-software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects.
[0043] For example, the disclosed embodiments can 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 can 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.
[0044] Furthermore, embodiments may take the form of a program product embodied in one or more computer-readable storage devices, which 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 embody signals. In one embodiment, the storage device uses only signals to access the code.
[0045] 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, apparatuses, or devices, or any suitable combination of the foregoing.
[0046] 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, apparatus, or device.
[0047] 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").
[0048] 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 the embodiments can be practiced without one or more of these specific details or using other methods, components, materials, etc. In other instances, well-known structures, materials, or operations are not described in detail to avoid obscuring aspects of the embodiments. Throughout the specification, references to “an embodiment,” “embodiment,” or similar language mean that a particular feature, structure, or characteristic described in connection with the 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 “including,” “comprising,” “having,” and variations thereof mean “including, but not limited to.” Unless expressly stated otherwise, the enumerated list of items does not imply that any or all of these items are mutually exclusive. Unless otherwise expressly stated, the terms “a,” “an,” and “the” also mean “one or more.”
[0049] The following description of aspects of embodiments is based on 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, a 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.
[0050] The code can 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.
[0051] The code can also be loaded onto a computer, other programmable data processing apparatus or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device, thereby producing a computer-implemented process, such that the code executing on the computer or other programmable apparatus provides a process for implementing the functions / actions specified in the flowchart and / or block diagram.
[0052] The flowcharts and / or block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, 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.
[0053] 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 consecutively depicted boxes 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.
[0054] 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 fact, 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.
[0055] The description of the elements in each figure can be referenced to the elements in the preceding figures. Throughout all figures, the same numbers refer to the same elements, including alternative embodiments of the same elements.
[0056] The detailed description set forth below with reference to the accompanying drawings is intended to describe various configurations and is not intended to represent only the 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 terminology from, for example, 5G NR may be used in this disclosure to illustrate embodiments herein, this should not be considered as limiting the scope of this disclosure.
[0057] 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.
[0058] In the example shown, the RAN includes a base station (BS). Of course, the RAN can 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.
[0059] The UE is located within the coverage area of the BS. The coverage area of the BS corresponds to, for example, an area where the UE can decode PDCCHs sent by the BS.
[0060] Examples of wireless devices suitable for implementing any of the methods discussed in this disclosure at the UE correspond to means that provide wireless connectivity to a RAN 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 (manned or unmanned) vehicle, a GPS device, etc., or any other device capable of running applications that require the exchange of data with a remote receiver via a wireless device.
[0061] 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 (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 that will be executed by the one or more processors to implement all or part of the steps of a method for exchanging data performed on the UE side according to any of the embodiments disclosed herein.
[0062] 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, which 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.
[0063] AI / ML models are data-driven algorithms that apply AI / ML techniques to generate output sets based on input sets.
[0064] 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 an entity can mean a network node / function (e.g., gNB, LMF, etc.), UE, proprietary server, etc.
[0065] AI / ML model inference is the process of using a trained AI / ML model to produce an output set based on an input set.
[0066] AI / ML model testing is a sub-process of training used to evaluate 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.
[0067] 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.
[0068] AI / ML model transfer is the delivery of AI / ML models via the air interface in a manner opaque to 3GPP signaling. The delivery consists of parameters of a model structure known at the receiving end, or a new model with parameters. The delivery can include a complete model or a partial model.
[0069] AI / ML model validation is a subprocess of training used to evaluate 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.
[0070] Data collection is the process by which network nodes, management entities, or user-defined users (UEs) collect data for the purposes of AI / ML model training, data analysis, and inference.
[0071] Federated learning / federated training is a machine learning technique that trains AI / ML models across multiple decentralized edge nodes (e.g., UE, gNB), with each node performing local model training using local data samples. This technique requires multiple interactions between models but does not require exchanging local data samples.
[0072] Functionality identification is the process / method of identifying AI / ML functionality to achieve a shared understanding between the New Work (NW) and User Experience (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.
[0073] Model activation refers to enabling AI / ML models for specific AI / ML-enabled features.
[0074] Model deactivation means deactivating the AI / ML model for a specific AI / ML enabled feature.
[0075] Model download refers to the transfer of a model from the network to the UE.
[0076] Model identification is the process / method of identifying AI / ML models to achieve a common understanding between the New Workspace (NW) and the User Experience (UE). The process / method of model identification may or may not be applicable, and information about the AI / ML model may be shared during model identification.
[0077] Model monitoring is the process of monitoring the inference performance of AI / ML models.
[0078] Model parameter update is the process of updating the model parameters.
[0079] Model selection is the process of choosing an AI / ML model from among multiple models used for the same AI / ML enabling feature to be activated. Model selection may or may not be performed simultaneously with model activation.
[0080] Model switching deactivates the currently active AI / ML model and activates a different AI / ML model for a specific AI / ML enabling feature.
[0081] Model update is the process of updating the model parameters and / or model structure.
[0082] Model upload is the transfer of the model from the UE to the network.
[0083] Network-side (AI / ML) models are AI / ML models that perform inference entirely at the network level.
[0084] Offline field data is data collected from the field and used for offline training of AI / ML models.
[0085] 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 for inference or delivered for inference. Note 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.
[0086] Online field data refers to data collected from the field and used for online training of AI / ML models.
[0087] Online training is an AI / ML training process in which the model used for inference is trained (typically continuously) as new training samples arrive (nearly in real-time). Note that the concepts of (near) real-time and non-real-time depend on the context and are related to the inference timescale. This definition is for guidance only.
[0088] 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 performed via online or offline training. This note can be removed when we define the term "fine-tuning".
[0089] Reinforcement learning (RL) is the process of training an AI / ML model based on inputs (also known as states) and feedback signals (also known as rewards) generated by the model's outputs (also known as actions) in the environment in which the model interacts with it.
[0090] Semi-supervised learning is the process of training a model using a mixture of labeled and unlabeled data.
[0091] Supervised learning is the process of training a model based on the input and its corresponding labels.
[0092] The dual-sided (AI / ML) model is a paired AI / ML model on which joint inference is performed, where joint inference includes AI / ML inference performed jointly across the UE and the network, i.e., the first part of the inference is performed by the UE first, and then the rest is performed by the gNB, or vice versa.
[0093] The UE-side (AI / ML) model is an AI / ML model that performs inference entirely at the UE.
[0094] Unsupervised learning is the process of training a model without labeled data.
[0095] From a 3GPP perspective, a proprietary format model is a vendor / equipment-specific, proprietary format ML model. These proprietary format models are mutually unrecognizable across vendors and, when shared, hide model design information from other vendors.
[0096] 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.
[0097] The following explanation provides a detailed description of the mechanism for pre-configuring and signaling specific information about online model training by configuring UE behavior sets. 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 in maintaining model performance because model performance, such as inference and / or training, depends on different model execution environments with varying configuration parameters. To address this, collaboration between the UE and gNB is crucial for tracking model performance and reconfiguring models to suit different environments. Since model performance cannot be consistently maintained due to drift, AI / ML models require model monitoring after deployment, followed by providing update feedback for retraining / updating the model or selecting an alternative model. When deploying AI / ML model-enabled wireless communication networks, it is then important to consider how to manage the active AI / ML models for wireless devices through reconfiguration during operations such as model training, inference, and updates. As the number of models used at the UE increases, ML measurement feedback can become overloaded due to significant signaling overhead. For example, if K models are available at the UE, K measurement feedback signaling may be required to support the use of K models. In this method, ML measurement items can be pre-configured for a model set, such that the configured ML measurement items are categorized into general ML measurement items (e.g., applicable to all models for measurement) and specific ML measurement items (e.g., applicable to a specific model for measurement). Configuration information indicating general and / or specific ML measurement items can be transmitted via RRC messages. Two or more ML measurement items can be grouped into subsets, allowing index / ID information to be configured for one or more subsets of ML measurement items. The (indexed) ML measurement subset configuration can be sent via RRC messages. The mapping between models and ML measurement items can be sent via system information or dedicated RRC signaling.Priority ordering of ML measurement feedback can also be configured for each ML measurement item, subset of ML measurement items, or general / dedicated ML measurement item. UL resources can then be scheduled for use with prioritized ML measurement feedback. If unscheduled ML measurement feedback is requested, the priority index can be sent to the UE for repriority ordering. For UE groups using the same model across UEs, ML measurement feedback can be requested only from any selected UE. Model sets are mapped to associated ML measurement items.
[0098] A model can be represented as a model ID. ML measurement items can be one or more sets of parameters to be measured for the model. Indications for general / dedicated ML measurement items can be associated with a mapping table. ML measurement items associated with a model (e.g., Mea_Set #i) can be further associated with general / dedicated ML measurement item categories. Classified general and dedicated ML measurements are associated with subsets of ML measurement items (e.g., Mea_SubSet A and Mea_SubSet B), respectively. This mapping information can be sent via system information or dedicated RRC signaling. Any updates to the mapping information can also be indicated via L1 / L2 or RRC signaling. The proposed configuration enables scalable and efficient ML measurement reporting across multiple UEs, thereby reducing uplink resource usage and improving the accuracy of model performance monitoring.
[0099] Figure 1 An exemplary table illustrating the mapping between model sets and associated ML measurement items is shown. In this example, two or more ML measurement items can be grouped into subsets, allowing index / ID information to be configured for one or more subsets of ML measurement items. The (indexed) ML measurement subset configuration can be sent via RRC messages. The mapping between models and ML measurement items can be sent via system information or dedicated RRC signaling. Priority sorting of ML measurement feedback can also be configured for each ML measurement item, subset of ML measurement items, or general / dedicated ML measurement item.
[0100] Figure 2An exemplary table illustrating the mapping between categorized general and specific ML measurements and subsets of ML measurement items is shown. In this example, ML measurement items are categorized into general ML measurement items (e.g., applicable to all models for measurement) and specific ML measurement items (e.g., applicable to a specific model for measurement). ML measurement items associated with a model (e.g., Mea_Set #i) can be further associated with general / specific ML measurement item categories. The categorized general and specific ML measurements are associated with subsets of ML measurement items (e.g., Mea_SubSet A and Mea_SubSet B), respectively. Configuration information indicating general and / or specific ML measurement items can be transmitted via RRC messages.
[0101] Figure 3 An exemplary flowchart for configuring measurement items for a model set on the network side is shown. In this example, mapping information can be sent via system information or dedicated RRC signaling. Any updates to the mapping information can also be indicated via L1 / L2 or RRC signaling.
[0102] Figure 4 An exemplary flowchart for measuring configured measurement items on the UE side is shown. In this example, for a group of UEs using the same model across UEs, ML measurement feedback can be requested only from any selected UE. Model sets are mapped to associated ML measurement items. A model can be represented as a model ID. An ML measurement item can be one or more sets of parameters to be measured against the model. Indicators of general / specific ML measurement items can be associated with a mapping table.
[0103] Figure 5 An exemplary signaling flow for ML measurement feedback with priority ordering is shown. In this example, priority ordering of ML measurement feedback can also be configured for each ML measurement item, a subset of ML measurement items, or a general / dedicated ML measurement item.
Claims
1. A method for performing advanced model measurement feedback signaling at a UE by configuring ML measurement items for a model set at a network entity in a wireless communication system, comprising: • Categorize configured ML measurement items into general ML measurement items and special ML measurement items; • Map the model set to be associated with ML measurement items; • Provides information on the mapping relationship between the model and associated ML measurement items.
2. The method according to claim 1, wherein the general ML measurement items can be applied to all models for measurement.
3. The method according to any one of the preceding claims, wherein a dedicated ML measurement item can be applied to a specific model for measurement.
4. The method according to any one of the preceding claims, wherein configuration information regarding general / dedicated ML measurements can be sent via RRC messages.
5. The method according to any one of the preceding claims, wherein two or more ML measurement items can be grouped into subsets, such that index / ID information can be configured for one or more subsets of the ML measurement items.
6. The method according to any one of the preceding claims, wherein ML measurements or an indexed subset of ML measurements can be sent via RRC messages.
7. The method according to any one of the preceding claims, wherein the mapping relationship between the model and the ML measurement item can be transmitted via system information or dedicated RRC signaling.
8. The method according to any one of the preceding claims, wherein a priority ordering of ML measurement feedback can be configured for each ML measurement item or subset of ML measurement items or general / specific ML measurement item.
9. The method according to any one of the preceding claims, wherein UL resources can be scheduled for use with prioritized ML measurement feedback.
10. The method according to any one of the preceding claims, wherein the priority index is sent to the UE for repricing (e.g., when an unscheduled ML measurement feedback is requested).
11. The method according to any one of the preceding claims, wherein when the unscheduled ML measurement feedback is requested, a priority index is sent to the UE for repriority reordering.
12. The method according to any one of the preceding claims, wherein for a group of UEs using the same model across UEs, it is possible to request ML measurement feedback only from any selected UE.
13. The method according to any one of the preceding claims, wherein the ML measurement item can be one or more sets of parameters to be measured for the model.
14. The method according to any one of the preceding claims, wherein the indication of a general / specific ML measurement item can be associated with a mapping table.
15. The method according to any one of the preceding claims, wherein the ML measurement items associated with the model can be further associated with a general / specific ML measurement item category.
16. The method according to any one of the preceding claims, wherein any updates to the mapping relationship information can also be indicated via L1 / L2 or RRC signaling.
17. An apparatus for performing advanced model measurement feedback signaling by configuring ML measurement items for a model set applied to multiple cells in a wireless communication system, the apparatus comprising a wireless transceiver and a processor coupled to a memory, the memory storing computer program instructions configured to implement the steps of claims 1 to 16.
18. A user equipment comprising the means according to claim 17.
19. A gNB comprising the apparatus according to claim 17.
20. A wireless communication system for performing advanced model measurement feedback signaling by configuring ML measurement items for a model set, wherein the wireless communication system includes a user equipment according to claim 18 and a gNB according to claim 19, wherein the user equipment and the gNB each include a processor coupled to a memory storing computer program instructions configured to perform the steps according to claims 1 to 16.
Citation Information
Patent Citations
Architecture for machine learning (ML) assisted communications networks
US20210326701A1
Methods and apparatus for UE reporting of time varying ML capability
US20220330012A1
ML model training procedure
US20220377844A1
Machine learning model configuration in wireless networks
US20220400373A1
Capability indication for a multi-block machine learning model
WO2023272718A1
