Method of distributed partitioned-model monitoring

Abstract

The present application describes methods of data-driven AI / ML model signaling for efficient model monitoring with machine learning model operation in wireless mobile communication systems including base stations (e.g., gNB) and mobile stations (e.g., UE). The index-based model partitioning with model properties is used to reduce signaling overhead through distributed model monitoring when a model drift occurs.

Description

[0001] TITLE

[0002] Method of distributed partitioned-model monitoring

[0003] TECHNNICAL FIELD

[0004] The present disclosure relates to AI / ML based applicable model update report signaling, where techniques for pre-configuring and signaling the model properties and partitioning for the efficient monitoring of machine learning model operation are presented.

[0005] BACKGROUND

[0006] In 3GPP (3rd Generation Partnership Project), one of the selected study items as the approved Release 18 package is AI / ML (artificial intelligence / machine learning) as described in the related document (RP-213599) addressed in 3GPP TSG RAN (Technical Specification Group Radio Access Network) meeting #94e. The official title of AI / ML study item is “Study on AI / ML for NR Air Interface”, and currently RAN WG1 and WG2 are actively working on specification. The goal of this study item is to identify a common AI / ML framework and areas of obtaining gains using AI / ML based techniques with use cases.

[0007] According to 3GPP, the main objective of this study item is to study AI / ML frameworks for air-interfaces with target use cases by considering performance, complexity, and potential specification impacts. In particular, AI / ML models, terminology, and descriptions to identify common and specific characteristics for a framework will be one key work scope. Regarding AI / ML frameworks, various aspects are under consideration for investigation and one key item is about the lifecycle management of AI / ML models where multiple stages are included as mandatory for model training, model deployment, model inference, model monitoring, model updating, etc.

[0008] Earlier, in 3GPP TR 37.817 for Release 17 titled as “Study on enhancement for Data Collection for NR and EN-DC”, UE mobility was also considered as one of the AI / ML use cases and one of the scenarios for model training / inference is that both functions are located within a RAN node. Following, in Release 18, the new work item of “Artificial Intelligence (Al) / Machine Learning (ML) for NG-RAN” was initiated to specify data collection enhancements and signaling support within existing NG-RAN interfaces and architectures.

[0009] For the above active standardization works, currently there is no specification defined for signaling methods or network (e.g., gNB) / mobile station (e.g., UE) behaviors about supporting an UE status update reporting about AI / ML model operation when multiple LCM (lifecycle management) operations are enabled on a device such as model training and inferencing and / or updating, etc., for one or more particular application scenarios with different set of ML features / functionalities.

[0010] Since applicable conditions to support the enabled LCM operations can dynamically change due to in-device condition change and / or external condition change, a model drift can occur as model performance is degraded along with the related condition changes. To detect such a model drift, model monitoring is one of the key phases in LCM operations and the follow-up countermeasures such as model switching, model re-training or model de-activation are commonly used. For example, model transfer is needed from one node to another node when the existing model is replaced with an alternative one. Additional signaling overhead can be significant to execute such a model transfer.

[0011] US 2020201 727 A1 teaches technologies for monitoring performance of a machine learning model which includes receiving, by an unsupervised anomaly detection function, digital time series data for a feature metric; where the feature metric is computed for a feature that is extracted from an online system over a time interval; where the machine learning model is to produce model output that relates to one or more users' use of the online system; using the unsupervised anomaly detection function, detecting anomalies in the digital time series data; labeling a subset of the detected anomalies in response to a deviation of a time-series prediction model from a predicted baseline model exceeding a predicted deviation criterion; creating digital output that identifies the feature as associated with the labeled subset of the detected anomalies; causing, in response to the digital output, a modification of the machine learning model.

[0012] US 2021 133 632 A1 discloses systems and methods to provide an open, unified platform to build, validate, deliver, and monitor models for data science at scale. These systems and methods may accelerate research, spark collaboration, increase iteration speed, and remove deployment friction to deliver impactful models. In particular, users may be allowed to visualize statistics about models and monitor models in real-time via a graphical user interface provided by the systems.

[0013] US 2022 027 749 A1 discloses a dataset that is received for processing by a machine learning model. A scoring payload for the dataset and that regards the machine learning model is also received. A set of features of the machine learning model is determined by analyzing the scoring payload. The scoring payload is structured in accordance with the set of features such that the structured scoring payload is ready for analysis for a monitor of the machine learning model.

[0014] US 2022 321 647 A1 discloses methods for managed machine learning (ML) in a communication network, such as by one or more first network functions (NFs) of the communication network. Such methods include determining whether processing of an ML model in the communication network should be distributed to one or more user equipment (UEs) operating in the communication network, based on characteristics of the respective UEs. Such methods also include, based on determining that the processing of the ML model should be distributed to the one or more UEs, establishing trusted execution environments (TEEs) in the respective UEs and distributing the ML model for processing in the respective TEEs. Other embodiments include complementary methods for UEs, as well as UEs and NFs (or communication networks) configured to perform such methods.

[0015] WO 2022 008 037 A1 discloses a method comprising: checking whether a terminal indicates to a network its capability to execute and / or to train a machine learning model; monitoring whether the terminal is in an inability state; informing the network that the terminal is in the inability state if the terminal indicated the capability and the terminal is in the inability state, wherein, in the inability state, the terminal is not able to execute and / or train the machine learning model, or the terminal is not able to execute and / or train the machine learning model at least with a predefined performance.

[0016] BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The disclosed invention will be further discussed in the following based on preferred embodiments presented in the attached drawings. However, the disclosed invention may be embodied in many different forms and should not be construed as limited to said preferred embodiments. Rather, said preferred embodiments are provided for thoroughness and completeness, and fully convey the scope of the invention to the skilled person. The following detailed description refers to the attached drawings, in which:

[0018] Figure 1 is an exemplary table of a mapping relationship for partitioned-models;

[0019] Figure 2 is an exemplary block diagram of a model structure type A for partitioned-models;

[0020] Figure 3 is an exemplary block diagram of model structure type B for partitioned-models;

[0021] Figure 4 is an exemplary block diagram of a partitioned-model distribution procedure for network and UE sides;

[0022] Figure 5 is a signaling flow of monitoring partitioned-models;

[0023] Figure 6 is a flowchart of a procedure of monitoring partitioned-models for the network side; and

[0024] Figure 7 is a flowchart of procedure of monitoring partitioned-models for the UE side. DETAILED DESCRIPTION

[0025] The detailed description set forth below, with reference to the annexed drawings, is intended as a description of various configurations and is not intended to represent the only configurations in which the concepts described herein may be practiced. The detailed description includes specific details for the purpose of providing a thorough understanding of the various concepts. However, it will be apparent to those skilled in the art that these concepts may be practiced without these specific details. In particular, although terminology from 3GPP 5G NR may be used in this disclosure to exemplify embodiments herein, this should not be seen as limiting the scope of the invention.

[0026] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Other embodiments, however, are contained within the scope of the subject matter disclosed herein, the disclosed subject matter should not be construed as limited to only the embodiments set forth herein; rather, these embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art.

[0027] Generally, all terms used herein are to be interpreted according to their ordinary meaning in the relevant technical field, unless a different meaning is clearly given and / or is implied from the context in which it is used. All references to a / an / the element, apparatus, component, means, step, etc. are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any methods disclosed herein do not have to be performed in the exact order disclosed, unless a step is explicitly described as following or preceding another step and / or where it is implicit that a step must follow or precede another step. Any feature of any of the embodiments disclosed herein may be applied to any other embodiment, wherever appropriate. Likewise, any advantage of any of the embodiments may apply to any other embodiments, and vice versa. Other objectives, features and advantages of the enclosed embodiments will be apparent from the following description. In some embodiments, a more general term “network node” may be used and may correspond to any type of radio network node or any network node, which communicates with a UE (directly or via another node) and / or with another network node. Examples of network nodes are NodeB, MeNB, ENB, a network node belonging to MCG or SCG, base station (BS), multi-standard radio (MSR) radio node such as MSR BS, eNodeB, gNodeB, network controller, radio network controller (RNC), base station controller (BSC), relay, donor node controlling relay, base transceiver station (BTS), access point (AP), transmission points, transmission nodes, RRU, RRH, nodes in distributed antenna system (DAS), core network node (e.g. Mobile Switching Center (MSC), Mobility Management Entity (MME), etc), Operations & Maintenance (O&M), Operations Support System (OSS), Self Optimized Network (SON), positioning node (e.g. Evolved- Serving Mobile Location Centre (E-SMLC)), Minimization of Drive Tests (MDT), test equipment (physical node or software), another UE, etc.

[0028] In some embodiments, the non-limiting term user equipment (UE) or wireless device may be used and may refer to any type of wireless device communicating with a network node and / or with another UE in a cellular or mobile communication system. Examples of UE are target device, device to device (D2D) UE, machine type UE or UE capable of machine to machine (M2M) communication, PDA, PAD, Tablet, mobile terminals, smart phone, laptop embedded equipped (LEE), laptop mounted equipment (LME), USB dongles, UE category Ml, UE category M2, ProSe UE, V2V UE, V2X UE, etc.

[0029] Additionally, terminologies such as base station / gNodeB and UE should be considered non-limiting and in particular do not imply a certain hierarchical relation between the two; in general, “gNodeB” could be considered as device 1 and “UE” could be considered as device 2 and these two devices communicate with each other over some radio channel. And in the following the transmitter or receiver could be either gNodeB (gNB), or UE. As will be appreciated by one skilled in the art, aspects of the embodiments may be embodied as a system, apparatus, method, or computer program product.

[0030] Accordingly, embodiments may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, micro-code, etc.) or an embodiment combining software and hardware aspects.

[0031] For example, the disclosed embodiments may be implemented as a hardware circuit comprising custom very-large-scale integration (“VLSI”) circuits or gate arrays, off-the-shelf semiconductors such as logic chips, transistors, or other discrete components. The disclosed embodiments may also be implemented in programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices, or the like. As another example, the disclosed embodiments may include one or more physical or logical blocks of executable code which may, for instance, be organized as an object, procedure, or function.

[0032] Furthermore, embodiments may take the form of a computer program product embodied in one or more computer readable storage devices storing machine readable code, computer readable code, and / or program code, referred hereafter as code. The storage devices may be tangible, non- transitory, and / or non-transmission. The storage devices may not embody signals. In a certain embodiment, the storage devices only employ signals for accessing code

[0033] Any combination of one or more computer readable medium may be utilized. The computer readable medium may be a computer readable storage medium. The computer readable storage medium may be a storage device storing the code. The storage device may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, holographic, micromechanical, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing.

[0034] More specific examples (a non-exhaustive list) of the storage device would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random-access memory (“RAM”), a read-only memory (“ROM”), an erasable programmable read-only memory (“EPROM” or Flash memory), a portable compact disc read-only memory (“CD-ROM”), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0035] Code for carrying out operations for embodiments may be any number of lines and may be written in any combination of one or more programming languages including an object-oriented programming language such as Python, Ruby, Java, Smalltalk, C++, or the like, and conventional procedural programming languages, such as the “C” programming language, or the like, and / or machine languages such as assembly languages. The code may execute entirely on the user’s computer, partly on the user’s computer, as a stand-alone software package, partly on the user’s computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user’s computer through any type of network, including a local area network (“LAN”), wireless LAN (“WLAN”), or a wide area network (“WAN”), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider (“ISP”)).

[0036] Furthermore, the described features, structures, or characteristics of the embodiments may be combined in any suitable manner. In the following description, numerous specific details are provided, such as examples of programming, software modules, user selections, network transactions, database queries, database structures, hardware modules, hardware circuits, hardware chips, etc., to provide a thorough understanding of embodiments. One skilled in the relevant art will recognize, however, that embodiments may be practiced without one or more of the specific details, or with other methods, components, materials, and so forth. In other instances, well-known structures, materials, or operations are not shown or described in detail to avoid obscuring aspects of an embodiment. Reference throughout this specification to “one embodiment,” “an embodiment,” or similar language means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases “in one embodiment”, “in an embodiment”, and similar language throughout this specification may, but do not necessarily, all refer to the same embodiment, but mean “one or more but not all embodiments” unless expressly specified otherwise. The terms “including”, “comprising”, “having”, and variations thereof mean “including but not limited to”, unless expressly specified otherwise. An enumerated listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise. The terms “a”, “an”, and “the” also refer to “one or more” unless expressly specified otherwise.

[0037] Aspects of the embodiments are described below with reference to schematic flowchart diagrams and / or schematic block diagrams of methods, apparatuses, systems, and program products according to embodiments. It will be understood that each block of the schematic flowchart diagrams and / or schematic block diagrams, and combinations of blocks in the schematic flowchart diagrams and / or schematic block diagrams, can be implemented by code. This code may be provided to a processor of a general-purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the fimctions / acts specified in the flowchart diagrams and / or block diagrams

[0038] The code may also be stored in a storage device that can direct a computer, other programmable data processing apparatus, or other devices to function in a particular manner, such that the instructions stored in the storage device produce an article of manufacture including instructions which implement the function / act specified in the flowchart diagrams and / or block diagrams.

[0039] The code may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus, or other devices to produce a computer implemented process such that the code which execute on the computer or other programmable apparatus provide processes for implementing the functions / acts specified in the flowchart diagrams and / or block diagrams.

[0040] The flowchart diagrams and / or block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of apparatuses, systems, methods, and program products according to various embodiments. In this regard, each block in the flowchart diagrams and / or block diagrams may represent a module, segment, or portion of code, which includes one or more executable instructions of the code for implementing the specified logical function(s).

[0041] It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the Figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. Other steps and methods may be conceived that are equivalent in function, logic, or effect to one or more blocks, or portions thereof, of the illustrated Figures.

[0042] Although various arrow types and line types may be employed in the flowchart and / or block diagrams, they are understood not to limit the scope of the corresponding embodiments. Indeed, some arrows or other connectors may be used to indicate only the logical flow of the depicted embodiment. For instance, an arrow may indicate a waiting or monitoring period of unspecified duration between enumerated steps of the depicted embodiment. It will also be noted that each block of the block diagrams and / or flowchart diagrams, and combinations of blocks in the block diagrams and / or flowchart diagrams, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and code.

[0043] The description of elements in each figure may refer to elements of proceeding figures. Like numbers refer to like elements in all figures, including alternate embodiments of like elements. The following explanation will provide the detailed description of the mechanism about data-driven AI / ML model signaling for quasi-based ML model operation in wireless mobile communication system including base station (e.g., gNB) and mobile station (e.g., UE)

[0044] AI / ML lifecycle can be split into several stages such as data collection / pre-processing, model training, model testing / validation, model deployment / update, model monitoring, model switching / selection etc., where each stage is equally important to achieve target performance with any specific model(s). In applying AI / ML model for any use case or application, one of the challenging issues is to manage the lifecycle of AI / ML model. This is mainly because a data / model drift occurs during model deployment / inference which results in performance degradation of the AI / ML model. Model drift occurs, when dataset statistically change after the model is deployed and when model inference capability is impacted due to unseen data as input. In a similar aspect, the statistical property of a dataset and the relationship between input and output for the trained model can be changed with drift occurrence. Then, model adaptation is required to support operations such as model switching, re-training, fallback, etc.

[0045] When AI / ML model enabled wireless communication network is deployed, it is then important to consider how to handle an adaptation of the AI / ML model under operations such as model training, inference, monitoring, updating, etc.

[0046] Based on the specific network-UE ML collaboration in deployment scenarios (e.g., UE mobility case), ML applicable conditions for LCM operations can be significantly changed with different mobility ranges over time by degrading any activated LCM operations. When model drift occurs on either UE or network side, the complete model needs to be replaced through model transfer or re-training / updating which increases signaling overhead, particularly for the case when the model size is large.

[0047] According to a first aspect of the invention, a method of distributed monitoring in a wireless network comprises a step of segmenting a target AI / ML model into multiple partitioned-models. The method further comprises a step of configuring a mapping relationship between the partitioned-models, the mapping relationship containing property information and index information for each of the partitioned-models. The method further comprises a step if receiving one of the partitioned-models and its associated property information and index information. The method further comprises a step of monitoring the received partitioned-model using the received property information. The method further comprises a step of reporting of a model monitoring update, if the monitoring indicates a model drift for the received partitioned-model.

[0048] Advantageously, the property information contains a model description information and / or attribute data and / or model monitoring information and / or reference data.

[0049] Advantageously, the mapping relationship is signaled from one node of the wireless network to another node of the wireless network.

[0050] Advantageously, the type of communication between the nodes of the wireless network is MEC-to-UE or UE-to-UE.

[0051] Advantageously, the partitioned-models are sent to multiple UEs and each of the UEs executes the one or more received partitioned-models with the model monitoring information.

[0052] Advantageously, the target model is a paired model between multiple AI / ML models which are located in different nodes of the wireless network.

[0053] Advantageously, a fix maximum number of partitioned-models are determined by one of the following methods:

[0054] • Determination, by the network side, of the fix maximum number of partitioned-models as an implementation-specific configuration, or

[0055] • Determination of the fix maximum number of partitioned-models according to a pre-defined specifications, or • Determination of the fix maximum number based on a pre-configured target model type, format, functionality, and / or use case.

[0056] Advantageously, the reporting of the model monitoring update or a signaling of the mapping relationship between nodes of the wireless network is signaled via L1 , L2, or L3 signaling, or a RRC re-configuration message.

[0057] Advantageously, a preset model ID information is shared without a transfer of the partitioned-models, if the preset model ID is available for the partitioned-models.

[0058] According to a second aspect of the invention, an apparatus for distributed monitoring in a wireless network comprises a wireless transceiver, a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to implement steps of an above-described method.

[0059] According to a third aspect of the invention, a user equipment for distributed monitoring in a wireless network comprises the above-described apparatus, while the steps of receiving one of the partitioned models and its associated property information and index information, monitoring the received partitioned-model, and reporting of the model monitoring update is proceeded.

[0060] According to a fourth aspect of the invention, a base station for distributed monitoring in a wireless network comprises the above-described apparatus, while the steps of segmenting the target AI / ML model, configuring the mapping relationship, and transmitting the partitioned-models and the mapping relationship to other nodes in the wireless network are proceeded.

[0061] According to a fifth aspect of the invention, a wireless communication system for distributed monitoring in a wireless network, comprises the above-described base station and the above-described user equipment, the base station comprising a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to implement steps an above-described method, the user equipment comprises a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to implement steps of an above-described method.

[0062] In this method, the whole target model is segmented into multiple partitioned-models, wherein there are multiple methods of setting maximum number of partitioned-models. For example, firstly network side can determine to fix maximum number of partitioned-models as implementation-specific configuration. Secondly, maximum number of partitioned-models can be also pre-defined by specifications. Thirdly, it can be pre-configured by target model type / format / functionality and / or use case. In addition, the properties and / or parameters of each partitioned-models are configured individually and it can be sent through RRC signaling (e.g., RRC re-configuration message). Network side also has to configure index of the partitioned-models in order to identify each partitioned-models and the mapping relationship between partitioned-models and index is pre-configured. This mapping relationship tables can be multiple based on different target models, model applications / functionalities, etc. For example, network side decides to segment target model into multiple partitioned-models and the mapping relationship information is sent to UEs (e.g., through dedicated RRC message) so that and drifted partitioned-model(s) can be indicated to network using index value (e.g., through L1 / L2 or L3 signaling). On UE side, model monitoring configuration information is provided by network so that each partitioned-models can be monitored with different configuration setting such as monitoring pattern / cycle or period, reference (distribution) data, etc. for drift detection or model performance measure.

[0063] Figure 1 shows an exemplary table of mapping relationship for partitioned-models. The mapping relationship between partitioned-models and index is pre-configured. The properties of the associated partitioned-models include their own model description information and / or attribute data, in which partitioned-model monitoring information is also contained as well such as model monitoring cycle / period, reference data, etc. In model monitoring, drift detection can be based on any well-known metrics using statistical distance or similarity measurements. In the mapping relationship information, the property information can be only sent to each UEs having the associated partitioned-model(s). When mapping relationship information is received, UEs can perform model monitoring of the indexed partitioned-model(s) based on the property information.

[0064] Figure 2 shows an exemplary block diagram of model structure type A for partitioned-models. In this exemplary model structure type, a target model is segmented into multiple partitioned-models that can be shared with multiple UEs so that each UEs can execute one or more partitioned-models with the pre-configured model monitoring information. There can be multiple target models for different applications and / or model functionalities. Determining UE group for partitioned-models is based on UE ML capability, model applicable conditions, etc. so that each partitioned-models on UE devices can be run properly. Partitioned-models can be flexibly configured as model partitioning is implementation-dependent.

[0065] Figure 3 is an exemplary block diagram of model structure type B for partitioned-models. In this exemplary model structure type, Model A is collaborated with multiple Model B-1 , Model B-2, ... , Model B- / V as these models are all located in different nodes. For example, Model A is in network side and Model B-1 through Model B-N are in UE side while each UEs have different Model B- / ( / =1 , ... , N). Network side is aware of the indexed Model B property information so that any drifted Model B at UE can be identified to perform model switching or re-training. In this case, Model A and Model B are the paired relationship to perform any target model.

[0066] Figure 4 shows an exemplary block diagram of partitioned-model distribution for network and UE sides. In this example, partitioned-models at multiple UE devices can be also collaborated with a single or multiple counterpart model(s) at the other node side in the deployment scenarios such as Network / MEC-to-UEs or UEs-to-UEs (note that MEC is multi-access edge computing device). There can be multiple methods of setting maximum number of partitioned-models to be allocated to UEs. For example, firstly network side can determine to fix maximum number of partitioned-models as implementation-specific configuration. Secondly, maximum number of partitioned-models can be also pre-defined by specifications. Thirdly, it can be pre-configured by target model type / format / functionality and / or use case. Among the partitioned-models at UEs, any drifted partitioned-model(s) can be reported to the network side so that a new model can be transferred or alternative model available at UE can be activated. Or the drifted partitioned-model(s) can be also removed from the overall LCM operation between network and UEs if necessary.

[0067] Figure 5 shows a signaling flow of monitoring partitioned-models. Network side configures index of the partitioned-models in order to identify each partitioned-models and the mapping relationship between partitioned-models and index is pre-configured. This mapping relationship tables can be multiple based on different target models, model applications / functionalities, etc. For example, network side decides to segment target model into multiple partitioned-models and the mapping relationship information is sent to UEs (e.g., through dedicated RRC message) so that and drifted partitioned-model(s) can be indicated to network using index value (e.g., through L1 / L2 or L3 signaling). On UE side, model monitoring configuration information is provided by network so that each partitioned-models can be monitored with different configuration setting such as monitoring pattern / cycle or period, reference (distribution) data, etc. for drift detection or model performance measure.

[0068] Figure 6 shows a flowchart of procedure of monitoring partitioned-models for network side. On network side, multiple partitioned-models are pre-configured so that those can be run on UE side. If the preset model IDs are available for partitioned-models, only model ID information can be shared without model transfer of partitioned-models. The mapping relationship information between partitioned-models and index is sent to UEs (e.g., through dedicated RRC message).

[0069] Figure 7 shows a flowchart of procedure of monitoring partitioned-models for UE side. On UE side, model monitoring is executed after activating the allocated partitioned-models for drift detection. And drifted partitioned-model(s) can then be indicated to network using index value (e.g., through L1 / L2 or L3 signaling). Model monitoring configuration information is provided by network so that each partitioned-models can be monitored with different configuration settings such as monitoring pattern / cycle or period, reference (distribution) data, etc. for drift detection or model performance measure.

[0070] Abbreviations:

[0071] Al Artificial intelligence BWP Bandwidth part CBG Code block group CLI Cross Link Interference CP Cyclic prefix CQI Channel quality indicator CPU CSI processing unit CRB Common resource block CRC Cyclic redundancy check CRI CSI-RS Resource Indicator CSI Channel state information CSI-RS Channel state information reference signal CSI-RSRP CSI reference signal received power CSI-RSRQ CSI reference signal received quality CSI-SINR CSI signal-to-noise and interference ratio CW Codeword DCI Downlink control information DL Downlink DM-RS Demodulation reference signals DRX Discontinuous Reception EPRE Energy per resource element IAB-MT Integrated Access and Backhaul - Mobile Terminal ID Identificator L1 -RSRP Layer 1 reference signal received power LI Layer Indicator LCM Life cycle management MCS Modulation and coding scheme ML Machine learning NW Network PDCCH Physical downlink control channel PDSCH Physical downlink shared channel PSS Primary Synchronisation signal PUCCH Physical uplink control channel QCL Quasi co-location PMI Precoding Matrix Indicator PRB Physical resource block PRG Precoding resource block group PRS Positioning reference signal PT-RS Phase-tracking reference signal RAN Radio Access Network RB Resource block RBG Resource block group Rl Rank Indicator RIV Resource indicator value RS Reference signal SCI Sidelink control information SLIV Start and length indicator value SR Scheduling Request SRS Sounding reference signal SS Synchronisation signal SSS Secondary Synchronisation signal SS-RSRP SS reference signal received power

[0072] SS-RSRQ SS reference signal received quality SS-SINR SS signal-to-noise and interference ratio TB Transport Block TCI Transmission Configuration Indicator TDM Time division multiplexing UE User equipment UL Uplink WG Work group

Claims

CLAIMS1 . A Method of distributed monitoring in a wireless network, comprising the steps:• Segmenting a target AI / ML model into multiple partitioned-models,• Configuring a mapping relationship between the partitioned-models, the mapping relationship containing property information and index information for each of the partitioned-models,• Receiving one of the partitioned-models and its associated property information and index information,• Monitoring the received partitioned-model using the received property information, and• Reporting of a model monitoring update, if the monitoring indicates a model drift for the received partitioned-model.

2. The method according to claim 1 , characterized in that the property information contains a model description information and / or attribute data and / or model monitoring information and / or reference data.

3. The method according to claim 1 or 2, characterized in that the mapping relationship is signaled from one node of the wireless network to another node of the wireless network.

4. The method according to claim 3, characterized in that the type of communication between the nodes of the wireless network is MEC-to-UE or UE-to-UE.

5. The method according to claim 2, characterized in that the partitioned-models are sent to multiple UEs and each of the UEs executes the one or more received partitioned-models with the model monitoring information.

6. The method according to any of the previous claims, characterized in that the target model is a paired model between multiple AI / ML models which are located in different nodes of the wireless network.

7. The method according to any of the previous claims, characterized in that a fix maximum number of partitioned-models are determined by one of the following methods:• Determination, by the network side, of the fix maximum number of partitioned-models as an implementation-specific configuration, or• Determination of the fix maximum number of partitioned-models according to a pre-defined specifications, or• Determination of the fix maximum number based on a pre-configured target model type, format, functionality, and / or use case.

8. The method according to any previous claims, characterized in that the reporting of the model monitoring update or a signaling of the mapping relationship between nodes of the wireless network is signaled via L1 , L2, or L3 signaling, or a RRC re-configuration message.

9. The method according to any previous claims, characterized in that a preset model ID information is shared without a transfer of the partitioned-models, if the preset model ID is available for the partitioned-models.

10. An apparatus for distributed monitoring in a wireless network comprises a wireless transceiver, a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to implement steps of the claims 1 to 9.11 . A user equipment for distributed monitoring in a wireless network comprises an apparatus according to claim 10, characterized in that the steps of receiving one of the partitioned models and its associated property information and index information, monitoring the received partitioned-model, and reporting of the model monitoring update is proceeded.

12. A base station for distributed monitoring in a wireless network comprises an apparatus according to claim 11 , characterized in that the steps of segmenting the target AI / ML model, configuring the mapping relationship, and transmitting the partitioned-models and the mapping relationship to other nodes in the wireless network are proceeded.

13. A wireless communication system for distributed monitoring in a wireless network, comprises the base station according to claim 12 and the user equipment according to claim 11 , characterized in that the base station comprises a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to implement steps of claims 1 to 9, wherein the user equipment comprises a processor coupled with a memory in which computer program instructions are stored, said instructions being configured to implement steps of the claims 1 to 9.

Images