Wireless device for CSI reporting and method thereof

Abstract

A method, system and apparatus are disclosed. A method in a network node configured to communicate with a user equipment (UE) is described. The method includes configuring the UE to report a performance monitoring outcome in a channel state information (CSI) report for a CSI prediction model when one or more aperiodic CSI reference signal (CSI-RS) resources are used for channel measurements and performing one or more actions based on the configuration to the UE.

Description

[0001] WIRELESS DEVICE FOR CSI REPORTING AND METHOD THEREOF

[0002] The present application claims the benefit of and the priority to U.S. Provisional Patent Application No. 63 / 754777, filed 2025-02-06, the disclosure of which is hereby incorporated herein by reference in its entirety.

[0003] TECHNICAL FIELD

[0004] The present disclosure relates to wireless communications, and in particular, to user equipment for reporting of performance monitoring results for channel state information prediction.

[0005] BACKGROUND

[0006] The Third Generation Partnership Project (3GPP) has developed and is developing standards for Fourth Generation (4G) (also referred to as Long Term Evolution (LTE)) and Fifth Generation (5G) (also referred to as New Radio (NR)) wireless communication systems. Such systems provide, among other features, broadband communication between network nodes, such as base stations, and mobile user equipments (UE), as well as communication between network nodes and between UEs. The 3GPP is also developing standards for Sixth Generation (6G) wireless communication networks.

[0007] Artificial Intelligence (Al) and Machine Learning (ML) have been investigated, both in academia and industry, as promising tools to optimize the design of the airinterface in wireless communication networks. Example use cases include: (A) using autoencoders for Channel State Information (CSI) compression to reduce the feedback overhead and improve channel prediction accuracy; (B) using deep neural networks for classifying Line-of-Sight (LOS) and Non-LOS (NLOS) conditions to enhance the positioning accuracy; (C) using reinforcement learning for beam selection at the network side and / or the UE side to reduce the signaling overhead and beam alignment latency; and (D) using deep reinforcement learning to learn an optimal precoding policy for complex Multiple Input Multiple Output (MIMO) precoding problems.

[0008] In 3GPP NR standardization work, a release 18 (Rel-18) study item on AI / ML for the NR air interface has been completed. This study item explores the benefits of augmenting the air-interface with features enabling improved support of AI / ML based algorithms for enhanced performance and / or reduced complexity / overhead. Through studying a few selected use cases such as CSI feedback, beam management, andpositioning, this study item aims at laying the foundation for future air-interface use cases leveraging AI / ML techniques.

[0009] An important part in Al development and operation is the lifecycle management (LCM) of the AI / ML model, such as model training, model deployment, model inference, model monitoring, model updating, and AI / ML functionality.

[0010] In a 3GPP NR Rel-18 AI / ML for NR air interface study item, the LCM procedure was studied for cases where an AI / ML model has a model ID with associated information and / or for cases in which a given functionality is provided by some AI / ML operations. Two types of LCM operations were studied in 3GPP NR Rel-18: functionality-based LCM and model-ID based LCM. Functionality refers to an AI / ML-enabled Feature or Feature Group(FG) enabled by configuration(s), where configuration(s) is(are) supported based on conditions indicated by UE capability. Correspondingly, functionality-based LCM operates based on, at least, one configuration of an AI / ML-enabled Feature / FG or specific configurations of an AI / ML-enabled Feature / FG. In functionality-based LCM, the network indicates activation / deactivation / fallback / switching of AI / ML functionality via 3GPP signaling (e.g., Radio Resource Control (RRC), Medium Access Control - Control Element (MAC-CE), Downlink Control Information (DCI), etc.). Models may not be identified at the network (NW), and the UE may perform model-level LCM. Whether and how much awareness and / or interaction the network node should have about model -lev el LCM requires further study. For functionality identification, there may be either one or more than one functionalities defined within an AI / ML-enabled feature, where AI / ML-enabled Feature refers to a Feature where AI / ML may be used.

[0011] In model-ID-based LCM, models are identified at the network node, and Network / UE may activate / deactivate / select / switch individual AI / ML models via model ID. A model may be associated with specific configurations / conditions associated with UE capability of an AI / ML-enabled Feature / FG and additional conditions (e.g., scenarios, sites, and datasets) as determined / identified between the UE-side and the network node-side. An AI / ML model identified by a model ID may be logical, and how it maps to physical AI / ML model(s) may be up to implementation.

[0012] FIG. 1 shows an example of a functional framework for AI / ML (e.g., for NR Air Interface) that can be used for studying model LCM aspects for different Al for PHY use cases. The general framework includes the following:

[0013] Data Collection is a function that provides input data to the Model Training, Management, and Inference functions.o Training Data: Data needed as input for the AI / ML Model Training function.

[0014] o Monitoring Data: Data needed as input for the Management of AI / ML models or AI / ML functionalities.

[0015] o Inference Data: Data needed as input for the AI / ML Inference function.

[0016] Model Training is a function that performs AI / ML model training, validation, and testing which may generate model performance metrics which can be used as part of the model testing procedure. The Model Training function is also responsible for data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) based on Training Data delivered by a Data Collection function, if required.

[0017] o Trained / Updated Model: In case of having a Model Storage function, this is used to deliver trained, validated, and tested AI / ML models to the Model Storage function, or to deliver an updated version of a model to the Model Storage function.

[0018] Management is a function that oversees the operation (e.g., selection and / or (de)activation and / or switching and / or fallback) and monitoring (e.g., performance) of AI / ML models or AI / ML functionalities. This function is also responsible for making decisions to ensure the proper inference operation based on data received from the Data Collection function and the Inference function.

[0019] o Management Instruction: Information needed as input to manage the Inference function. Concerning information may include selection / (de)activation / switching of AI / ML models or AI / ML-based functionalities, fallback to non-AI / ML operation (i.e., not relying on inference process), etc.

[0020] o Model Transfer / Delivery Request: Used to request model(s) to the Model Storage function.

[0021] o Performance Feedback / Retraining Request: Information needed as input for the Model Training function, e.g., for model (re)training or updating purposes.

[0022] Inference is a function that provides outputs from the process of applying AI / ML models or AI / ML functionalities, using the data that is provided by theData Collection function (i.e., Inference Data) as an input. The Inference function is also responsible for data preparation (e.g., data pre-processing and cleaning, formatting, and transformation) based on Inference Data delivered by a Data Collection function, if required.

[0023] o Inference Output: Data used by the Management function to monitor the performance of AI / ML models or AI / ML functionalities.

[0024] Model Storage is a function responsible for storing trained / updated models that can be used to perform the Inference function.

[0025] o The Model Storage function in FIG. 1 may be only intended as a reference point (if any) when applicable for protocol terminations, model transfer / deli very, and related processes. It should be stressed that its purpose does not encompass restricting the actual storage locations of models. Therefore, the specification impact of all data / information / instruction flows (i.e., the arrows in FIG. 1) to / from this function should be studied case by case.

[0026] o Model Transfer / Delivery: Used to deliver an AI / ML model to the Inference function.

[0027] For CSI prediction using UE side AI / ML model use case studied in Rel-18 AI / ML for NR air interface study item, at least the following aspects have been proposed on performance monitoring for functionality-based LCM:

[0028] - Type 1:

[0029] o The UE calculates the performance metric(s).

[0030] o The UE reports performance monitoring output that facilitates functionality fallback decision at the network.

[0031] ■ Performance monitoring output details can be further defined. ■ The network node may configure threshold criterion to facilitate UE side performance monitoring (if needed).

[0032] o The network node makes decision(s) of functionality fallback operation (fallback mechanism to legacy CSI reporting).

[0033] - Type 2:

[0034] o The UE reports predicted CSI and / or the corresponding ground-truth. o The network node calculates the performance metrics.

[0035] o The network node makes decision(s) of functionality fallback operation (fallback mechanism to legacy CSI reporting).- Type 3:

[0036] o The UE calculates the performance metric(s).

[0037] o The UE reports performance metric(s) to the network node.

[0038] o The network node makes decision(s) of functionality fallback operation (fallback mechanism to legacy CSI reporting).

[0039] - Functionality selection / activation / deactivation / switching as defined for other UE side use cases can be reused, if applicable.

[0040] Configuration and procedure for performance monitoring.

[0041] CSI-RS configuration for performance monitoring.

[0042] - Performance metric including at least intermediate KPI,e.g., Normalized Mean Square Error (NMSE) or Squared Generalized Cosine Similarity (SGCS).

[0043] - UE report, including periodic / semi-persistent / aperiodic reporting, and event driven report.

[0044] - The UE may make decision within the same functionality on model selection, activation, deactivation, switching operation transparent to the network node. For intermediate KPI based performance monitoring of an AI / ML-based CSI prediction feature, a monitoring data sample should include both the channel measurements within an observation window and the channel measurements within the associated prediction window. The channel measurements within the observation window are used for creating model input, which is then fed to the AI / ML model for generating a model output as predicted CSI. The measurements within the prediction window are used for creating ground truth label to be compared with the predicted CSI.

[0045] An intermediate KPI (e.g., NMSE or SGCS) per monitoring data sample can be derived by comparing a CSI prediction model output with the corresponding ground truth label. Therefore, thepredicted CSI for the one or more future time instances is compared with the channel measurements(s) corresponding to the one or more future time instances. Sufficient monitoring data samples may be needed to ensure reliable and accurate model performance monitoring results, based on which LCM operation decisions will be made.

[0046] For monitoring the performance of a UE-sided AI / ML model, if the performance monitoring is performed at UE-side, such as type 1 or type 3 monitoring mentioned above, a UE can report the model performance monitoring results to the network node, so that the network node takes the UE reported model performance information into account when making model level or functionality level LCM decisions, such as fallback to non-AL / ML algorithm, functionality / model switching, etc..When the report configuration for CSI Performance monitoring and the report configuration for CSI inference are configured respectively, the coordination of measurement resources, report triggering, and data collection for performance evaluation adds complexity to system design and implementation.

[0047] SUMMARY

[0048] Some embodiments advantageously provide methods, systems, and apparatuses for triggering and configuration for user equipment reporting of performance monitoring results for channel state information prediction.

[0049] According to an aspect of the present disclosure, a method is provided for configuring performance monitoring reporting in a wireless communication system. The method includes configuring a user equipment with a first channel state information (CSI) report configuration for reporting predicted CSI and a second CSI report configuration for reporting performance monitoring results of a CSI prediction model or algorithm. The first CSI report configuration is associated with the second CSI report configuration via a configuration identifier (ID) of the first CSI report configuration being included in the second CSI report configuration.

[0050] In some further embodiments, the method further includes configuring the user equipment with channel measurement resource configurations that specify aperiodic CSI reference signal resources for generating model input data and ground truth labels for performance evaluation.

[0051] In some further embodiments, the method also includes transmitting downlink control information (DCI) signaling to trigger reporting of the performance monitoring (PM) results, where the DCI signaling is coordinated with triggering of the predicted CSI reporting. For example, the first and second CSI report configurations may be triggered using separate DCI signaling transmitted at different time instances. In another example, the first and second CSI report configurations may be triggered using a single DCI signaling that schedules both reports on different uplink transmission occasions.

[0052] In some further embodiments, the DCI signaling to trigger a PM report based on the second CSI report configuration is transmitted no later than the receiving of a CSI prediction report based on the associated first CSI report configuration. Alternatively, the triggering DCI is transmitted no later than the first resource of a CSI-RS resource set for measurement input to generate the CSI prediction report.

[0053] According to another aspect of the present disclosure, a method is provided forperformance monitoring reporting by a user equipment (UE) in a wireless communication system. The UE receives a first CSI report configuration for CSI inference reporting and a second CSI report configuration for CSI PM result. The first CSI report configuration is associated with the second CSI report configuration via its configuration identifier being included in the second CSI report configuration.

[0054] The method further includes receiving a DCI signaling triggering a CSI PM result report as per the second CSI report configuration. Then, the UE reports performance monitoring result including performance metrics such as intermediate KPI(s), according to the second CSI report configuration. The reported performance metrics are generated based on comparison between predicted CSI according to the associated first CSI report configuration and the corresponding ground truth label.

[0055] In some further embodiments, the performance monitoring results may be calculated per individual monitoring data sample comprising predicted channel state information and corresponding ground truth labels. Alternatively, the performance monitoring results may be calculated using statistics derived from multiple monitoring data samples collected over a time window.

[0056] In some further embodiments, the UE receives another DCI for triggering a CSI reference reporting based on the associated first CSI report configuration. Alternatively, a single DCI triggering both the CSI PM result report and the CSI inference report which are respectively generated based on the pair of associated CSI report configurations.

[0057] BRIEF DESCRIPTION OF THE DRAWINGS

[0058] A more complete understanding of the present embodiments, and the attendant advantages and features thereof, will be more readily understood by reference to the following detailed description when considered in conjunction with the accompanying drawings wherein:

[0059] FIG. 1 shows an example functional framework for AI / ML;

[0060] FIG. 2 shows an example CMR enhancement for Type II CSI prediction at a UE; FIG. 3 is a schematic diagram of an example network architecture illustrating a communication system according to principles disclosed herein;

[0061] FIG. 4 is a block diagram of a network node in communication with a user equipment over a wireless connection according to some embodiments of the present disclosure;

[0062] FIG. 5 is a flowchart of an example process implemented by a user equipmentaccording to some embodiments of the present disclosure;

[0063] FIG. 6 is a flowchart of an example process in a network node according to some embodiments of the present disclosure;

[0064] FIG. 7 is a flowchart of an example process in a user equipment according to some embodiments of the present disclosure;

[0065] FIG. 8 shows example signaling for CSI-PM reporting with AP CSI-RS resource according to some embodiments of the present disclosure;

[0066] FIG. 9 shows an example of two separate DCI signaling for CSI-inference reporting and CSI-PM reporting with AP CSI-RS resource according to some embodiments of the present disclosure;

[0067] FIG. 10 an example of separate DCI signaling for CSI-inference reporting and CSI-PM reporting with AP CSI-RS resource according to some embodiments of the present disclosure;

[0068] FIG. 11 shows an example of single DCI signaling for CSI-inference reporting and CSI-PM reporting with AP CSI-RS resource according to some embodiments of the present disclosure;

[0069] FIG. 12 shows another example use of a single DCI signalling to trigger both the CSI-inference report and CSI-PM report according to some embodiments of the present disclosure;

[0070] FIG. 13 shows an example use of different DCI signaling for triggering CSI-inference report and CSI-PM report according to some embodiments of the present disclosure; and

[0071] FIG. 14 shows an example use of a single DCI signaling for CSI-inference report(s) and CSI-PM report with AP CSI-RS resource according to some embodiments of the present disclosure.

[0072] DETAILED DESCRIPTION

[0073] Before describing in detail exemplary embodiments, it is noted that the embodiments reside primarily in combinations of apparatus components and processing steps related to triggering and configuration for user equipment reporting of performance monitoring results for CSI prediction. Accordingly, components have been represented where appropriate by conventional symbols in the drawings, showing only those specific details that are pertinent to understanding the embodiments so as not to obscure the disclosure with details that will be readily apparent to those of ordinary skill in the arthaving the benefit of the description herein.

[0074] As used herein, relational terms, such as “first” and “second,” “top” and “bottom,” and the like, may be used solely to distinguish one entity or element from another entity or element without necessarily requiring or implying any physical or logical relationship or order between such entities or elements. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the concepts described herein. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and / or “including” when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0075] In embodiments described herein, the joining term, “in communication with” and the like, may be used to indicate wireless communication, which may be accomplished by radio signaling, for example. One having ordinary skill in the art will appreciate that multiple components may interoperate and modifications and variations are possible of achieving the communication.

[0076] In some embodiments described herein, the term “coupled,” “connected,” and the like, may be used herein to indicate a connection, although not necessarily directly, and may include wired and / or wireless connections.

[0077] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the concepts described herein. As used herein, the singular forms “a”, “an” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes” and / or “including” when used herein, specify the presence of stated features, integers, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0078] The term “network node” used herein can be any kind of network node comprised in a radio network which may further comprise any of base station (BS), radio base station, g Node B (gNB), evolved Node B (eNB or eNodeB), Node B, multi-standard radio (MSR) radio node such as MSR BS, multi-cell / multicast coordination entity (MCE), relay node, donor node controlling relay, radio access point (AP), transmission points,transmission nodes, Remote Radio Unit (RRU) Remote Radio Head (RRH), a core network node (e.g., mobile management entity (MME), self-organizing network (SON) node, a coordinating node, positioning node, MDT node, etc.), an external node (e.g., 3rd party node, a node external to the current network), nodes in distributed antenna system (DAS), a spectrum access system (SAS) node, an element management system (EMS), etc. The network node may also comprise test equipment.

[0079] In some embodiments, the non-limiting terms wireless device (WD) or a user equipment (UE) are used interchangeably. The UE herein can be any type of user equipment capable of communicating with a network node or another UE over radio signals, such as a wireless device (WD). The UE may also be a radio communication device, target device, device to device (D2D) UE, machine type UE or UE capable of machine to machine communication (M2M), low-cost and / or low-complexity UE, a sensor equipped with UE, Tablet, mobile terminals, smart phone, laptop embedded equipped (LEE), laptop mounted equipment (LME), USB dongles, Customer Premises Equipment (CPE), an Internet of Things (loT) device, or a Narrowband loT (NB-IOT) device etc.

[0080] Note that although terminology from one particular wireless system, such as, for example, 3GPP LTE and / or New Radio (NR) and / or 6G, may be used in this disclosure, this should not be seen as limiting the scope of the disclosure to only the aforementioned system. It is contemplated that other 3GPP systems may make use of the concepts and arrangements disclosed herein. For example, a disclosure relating to NR may also be implementable in a 6G system, a disclosure relating to 6G may also be implementable in a NRsystem. Other wireless systems, including without limitation Wide Band Code Division Multiple Access (WCDMA), Worldwide Interoperability for Microwave Access (WiMax), Ultra Mobile Broadband (UMB) and Global System for Mobile Communications (GSM), may also benefit from exploiting the ideas covered within this disclosure.

[0081] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. It will be further understood that terms used herein should be interpreted as having a meaning that is consistent with their meaning in the context of this specification and the relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.

[0082] Referring again to the drawing figures, in which like elements are referred to by like reference numerals, there is shown in FIG. 3 a schematic diagram of a communicationsystem 10, according to an embodiment, such as a 3 GPP-type cellular network that may support standards such as NR (5G) and / or 6G, which comprises an access network 12, such as a radio access network, and a core network 14. The core network 14 includes one or more network nodes 15. The access network 12 comprises a plurality of network nodes 16a, 16b, 16c (referred to collectively as network nodes 16), such as NBs, eNBs, gNBs or other types of wireless access points, each defining a corresponding coverage area 18a, 18b, 18c (referred to collectively as coverage areas 18). Each network node 16a, 16b, 16c is connectable to the core network 14 over a wired or wireless connection 20. A first user equipment (UE) 22a located in coverage area 18a is configured to wirelessly connect to, or be paged by, the corresponding network node 16a. A second UE 22b in coverage area 18b is wirelessly connectable to the corresponding network node 16b. While a plurality of UEs 22a, 22b (collectively referred to as user equipments 22) are illustrated in this example, the disclosed embodiments are equally applicable to a situation where a sole UE is in the coverage area or where a sole UE is connecting to the corresponding network node 16. Note that although only two UEs 22 and three network nodes 16 are shown for convenience, the communication system may include many more UEs 22 and network nodes 16.

[0083] As one example, in certain embodiments, access network 12 may contain some access network nodes 16 that support 3GPP radio access technologies (RAT), such as LTE or NR, while other access network nodes 16 support (or the same access network nodes 16 additionally support) non-3GPP RATs, such as Wi-Fi or a proprietary RAT. As another example, communication system 10 may support multiple generations of related communication standards (e.g., 4G, 5G and 6G 3GPP communication standards) and, as a result, may include an access network 12 and / or a core network 14 that supports multiple different standard generations or may include multiple access networks 12 and / or multiple core networks 14 with individual networks supporting different standards generations.

[0084] Also, it is contemplated that a UE 22 can be in simultaneous communication and / or configured to separately communicate with more than one network node 16 and more than one type of network node 16. For example, a UE 22 can have dual connectivity with a network node 16 that supports LTE and the same or a different network node 16 that supports NR. As an example, UE 22 can be in communication with an eNB for LTE / E-UTRAN, a gNB for NR / NG-RAN (i.e. being configured for multiradio dual connectivity (MR-DC), such as E-UTRAN (Evolved-UMTS Terrestrial Radio Access Network) New Radio - Dual Connectivity (EN-DC) and / or Wi-Fi.A network node 16 is configured to include a node management unit 24 which is configured to perform any step and / or task and / or process and / or method and / or feature described in the present disclosure, e.g., network node functions. A user equipment 22 is configured to include a UE management unit 26 which is configured to perform any step and / or task and / or process and / or method and / or feature described in the present disclosure, e.g., UE functions.

[0085] Example implementations, in accordance with an embodiment, of the UE 22 and network node 16 discussed in the preceding paragraphs will now be described with reference to FIG. 4.

[0086] The communication system 10 includes a network node 16 provided in a communication system 10 and including hardware 28 enabling it to communicate with the UE 22. The hardware 28 may include a communication interface 29 comprising a radio interface 30 for setting up and maintaining at least a wireless connection 32 with a UE 22 located in a coverage area 18 served by the network node 16. The radio interface 30 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and / or one or more RF transceivers. The radio interface 30 includes an array of antennas 34 to radiate and receive signal(s) carrying electromagnetic waves.

[0087] In the embodiment shown, the hardware 28 of the network node 16 further includes processing circuitry 36. The processing circuitry 36 may include a processor 38 and a memory 40. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 36 may comprise integrated circuitry for processing and / or control, e.g., one or more processors and / or processor cores and / or FPGAs (Field Programmable Gate Array) and / or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 38 may be configured to access (e.g., write to and / or read from) the memory 40, which may comprise any kind of volatile and / or nonvolatile memory, e.g., cache and / or buffer memory and / or RAM (Random Access Memory) and / or ROM (Read-Only Memory) and / or optical memory and / or EPROM (Erasable Programmable Read-Only Memory).

[0088] Thus, the network node 16 further has software 42 stored internally in, for example, memory 40, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the network node 16 via an external connection. The software 42 may be executable by the processing circuitry 36. The processing circuitry 36 may be configured to control any of the methods and / or processes described herein and / or to cause such methods, and / or processes to be performed, e.g., by network node 16.Processor 38 corresponds to one or more processors 38 for performing network node 16 functions described herein. The memory 40 is configured to store data, programmatic software code and / or other information described herein. In some embodiments, the software 42 may include instructions that, when executed by the processor 38 and / or processing circuitry 36, causes the processor 38 and / or processing circuitry 36 to perform the processes described herein with respect to network node 16. For example, processing circuitry 36 of the network node 16 may include node management unit 24 which is configured to perform any step and / or task and / or process and / or method and / or feature described in the present disclosure, e.g., network node functions.

[0089] The network node 16 may be composed of multiple distinct network entities (e.g., a NodeB entity and a RNC entity, or a BTS entity and a BSC entity, etc.), which may each have or utilize their own respective physical components. In certain scenarios in which the network node 16 comprises multiple such entities (e.g., BTS and BSC), one or more of the separate entities may be shared among several network nodes.

[0090] The antenna 34 may include one or more antennas, or antenna arrays, configured to send and / or receive wireless signals. The antenna 34 may be coupled to the radio front-end circuitry in radio interface 30 and may be any type of antenna capable of transmitting and receiving data and / or signals wirelessly. In certain embodiments, the antenna 34 is separate from the network node 16 and connectable to the network node 16 through one or more interfaces or ports.

[0091] Network node 15 can include one or more components described above with respect to network node 16, e.g., communication interface 29, radio interface 30, antenna 34, ports, processing circuitry 36, processor 38, memory 40 and software 42. These elements of network node 15 can be arranged such that network node 15 can perform various core network functions. Network node 15 can communicate wirelessly or via a wired connection with network nodes 16 via communication link 59.

[0092] The communication system 10 further includes the UE 22 already referred to. The UE 22 may have hardware 44 that may include a radio interface 46 configured to set up and maintain a wireless connection 32 with a network node 16 serving a coverage area 18 in which the UE 22 is currently located. The radio interface 46 may be formed as or may include, for example, one or more RF transmitters, one or more RF receivers, and / or one or more RF transceivers. The radio interface 46 includes an array of antennas 48 to radiate and receive signal(s) carrying electromagnetic waves.

[0093] The hardware 44 of the UE 22 further includes processing circuitry 50. Theprocessing circuitry 50 may include a processor 52 and memory 54. In particular, in addition to or instead of a processor, such as a central processing unit, and memory, the processing circuitry 50 may comprise integrated circuitry for processing and / or control, e.g., one or more processors and / or processor cores and / or FPGAs (Field Programmable Gate Array) and / or ASICs (Application Specific Integrated Circuitry) adapted to execute instructions. The processor 52 may be configured to access (e.g., write to and / or read from) memory 54, which may comprise any kind of volatile and / or nonvolatile memory, e.g., cache and / or buffer memory and / or RAM (Random Access Memory) and / or ROM (Read-Only Memory) and / or optical memory and / or EPROM (Erasable Programmable Read-Only Memory).

[0094] Thus, the UE 22 may further comprise software 56, which is stored in, for example, memory 54 at the UE 22, or stored in external memory (e.g., database, storage array, network storage device, etc.) accessible by the UE 22. The software 56 may be executable by the processing circuitry 50. The software 56 may include a client application 58. The client application 58 may be operable to provide a service to a human or non-human user via the UE 22.

[0095] The processing circuitry 50 may be configured to control any of the methods and / or processes described herein and / or to cause such methods, and / or processes to be performed, e.g., by UE 22. The processor 52 corresponds to one or more processors 52 for performing UE 22 functions described herein. The UE 22 includes memory 54 that is configured to store data, programmatic software code and / or other information described herein. In some embodiments, the software 56 and / or the client application 58 may include instructions that, when executed by the processor 52 and / or processing circuitry 50, causes the processor 52 and / or processing circuitry 50 to perform the processes described herein with respect to UE 22. For example, the processing circuitry 50 of the user equipment 22 may include a UE management unit 26 which is configured to perform any step and / or task and / or process and / or method and / or feature described in the present disclosure, e.g., UE functions.

[0096] In some embodiments, the inner workings of the network node 16 and UE 22 may be as shown in FIG. 4 and independently, the surrounding network topology may be that of FIG. 3.

[0097] The wireless connection 32 between the UE 22 and the network node 16 is in accordance with the teachings of the embodiments described throughout this disclosure. More precisely, the teachings of some of these embodiments may improve the data rate,latency, and / or power consumption and thereby provide benefits such as reduced user waiting time, relaxed restriction on file size, better responsiveness, extended battery lifetime, etc. In some embodiments, a measurement procedure may be provided for the purpose of monitoring data rate, latency and other factors on which the one or more embodiments improve.

[0098] Although FIGs. 3 and 4 show various “units” such as node management unit 24 and UE management unit 26 as being within a respective processor, it is contemplated that these units may be implemented such that a portion of the unit is stored in a corresponding memory within the processing circuitry. In other words, the units may be implemented in hardware or in a combination of hardware and software within the processing circuitry.

[0099] As aforementioned, when two different CSI report configurations are used for configuring the predicted CSI report (denoted as CSI-inference report) and the performance monitoring result report (denoted as CSI-PM report), respectively, there are still problems with:

[0100] • how to trigger these two CSI reports;

[0101] • whether / how to link these two CSI report configurations; and

[0102] • whether / how to link the channel measurement resources for these two CSI report configurations.

[0103] One or more embodiments provide methods for the network node to configure a UE to report a performance monitoring outcome or result in a CSI report for an AI / non-AI based CSI prediction model / algorithm when aperiodic CSI-RS resources are used for channel measurements. Also, related embodiments provide methods for a UE to receive the report configurations and act measurement and reporting according to the triggered configuration(s). One or more embodiments include one or mor of the following:

[0104] • DCI signaling for triggering the performance monitoring report.

[0105] • The configuration / indication of the channel measurement resources for creating the performance monitoring report.

[0106] • Linking between the measurement resources for inference report and measurement resources for performance monitoring report.

[0107] • Linking between the CSI report for inference and the CSI report for performance monitoring.

[0108] In some embodiments, two different CSI report configurations are used for configuring the predicted CSI report (denoted as CSI-inference report) and the performance monitoring output report (denoted as CSI-PM report), respectively. In someother embodiments, AI / non-AI based CSI prediction may be used for a configured Al / non-AI model / algorithm, which is reported back to the network. Some embodiments provide signaling and configurations to enable a UE to report the performance monitoring result of an AI / non-AI based CSI prediction, as a CSI report, when aperiodic CSI-RS resources are used for channel measurements.

[0109] Some embodiments provide a network node configured to trigger and configure a UE to report performance monitoring result for a CSI prediction feature reusing the legacy CSI reporting framework when aperiodic CSI-RS resources are used for channel measurements. In addition, related embodiments provide a UE configured to receiving CSI report configurations and triggering DCI(s) and performing the measurement and reporting according to the triggered report configuration(s). The UE reported model performance information can be used by the network node to assist its decision making on model level or functionality level LCM decisions (e.g., fallback to non-AL / ML algorithm, functionality / model switching, etc.), hence, ensure the Al based CSI prediction performance in the field.

[0110] FIG. 5 is a flowchart of a method performed by a user equipment 22 configured to communicate with a network node 16 in a communication system. The UE 22 receives, at step 502, one or more report configurations for CSI inferences, one of which is associated with a report configuration for CSI performance monitoring configured (step 504) for the UE 22. The association of those two report configurations is realized by a configuration identifier of the CSI inference report configuration included in the report configuration for CSI performance monitoring.

[0111] In step 506, the UE receives DCI signaling for triggering a CSI PM report. The method 500 concludes with step 508, where the wireless device transmits a CSI PM report according to the CSI PM report configuration indicated by the DCI. The flowchart of Figure 5 although displayed in a sequential order, does not preclude other possible order of process, for example, the report configuration for CSI inference might be received later than the associated report configuration for CSI-PM, as long as the DCI trigger is received in a good timing. The method 500 demonstrates the coordination between CSI inference reporting and performance monitoring reporting through the association established in step 504 and the triggering mechanism implemented in step 506.

[0112] FIG. 6 is a flowchart of an example process in a network node 16. One or more blocks described herein may be performed by one or more elements of network node 16 such as by one or more of processing circuitry 36 (including the node management unit24), processor 38, and / or radio interface 30. Network node 16 such as via processing circuitry 36 and / or processor 38 and / or radio interface 30 is configured to configure (Block SI 00) the UE 22 to report a performance monitoring result in a CSI report for a CSI prediction model when one or more aperiodic CSI reference signal (CSI-RS) resources are used for channel measurements for input of the CSI prediction model and / or generating ground truth label of the performance monitoring result.

[0113] In some embodiments, the CSI prediction model is an artificial intelligence (Al) based CSI prediction model or a non- Al based CSI prediction model.

[0114] In some embodiments, the configuring includes a first CSI report configuration for CSI-inference report and a second CSI report configuration for CSI performance monitoring (CSI-PM) report.

[0115] In a further embodiment, the first CSI report configuration is associated with the second CSI report configuration via a configuration identifier of the first CSI report configuration being included in the second CSI report configuration configured for the UE.

[0116] In some embodiments, the performance monitoring outcome is calculated per monitoring data sample.

[0117] In some other embodiments, the method further includes transmitting different downlink control information (DCI) signaling for triggering the CSI-PM report (SI 02) and triggering the CSI-inference report.

[0118] In some embodiments, the CSI-PM report is configured with an explicit channel measurement resource (CMR) for performance monitoring without linking to the first CSI report configuration.

[0119] In some other embodiments, the first CSI report configuration and the second CSI report configuration are linked.

[0120] In some embodiments, the method further includes transmitting a single DCI signaling (SI 02) for triggering the CSI-PM report and the CSI-inference report.

[0121] In some other embodiments, the performance monitoring outcome is calculated using multiple monitoring data samples.

[0122] In some embodiments, the method further includes receiving, from the UE 22, a CSI prediction for the CSI prediction model.

[0123] FIG. 7 illustrates a flowchart for a method 700 implemented by a wireless device for channel state information performance monitoring report configuration and transmission involving multiple CSI inference report configurations. In step 702, wherethe wireless device receives multiple channel state information, CSI, inference report configurations. The method 700 then proceeds to step 704, where the wireless device receives a CSI performance monitoring, PM, report configuration associated with a plurality of CSI inference report configurations of the multiple CSI inference report configurations, wherein the CSI PM report configuration comprises configuration IDs of those associated CSI inference report configurations.

[0124] In step 706, the wireless device receives a triggering DCI for a CSI PM report according to the CSI PM report configuration. The method 700 continues to step 708, where the wireless device generates a CSI PM result based on multiple pairs of samples, each of which comprises a ground truth label and CSI inference based on one of the multiple associated inference report configurations. Then, in step 710, where the wireless device reports the CSI PM result according to the CSI PM report configuration. The CSI PM result is reported regardless whether the CSI inferences under the associated CSI inference report configurations had been triggered or not.

[0125] In some embodiments, the method further includes receiving, from the network node 16, triggering DCIs for the CSI inferences under the associated CSI inference configuration, as complementary to the method embodiments implemented in the UE 22.

[0126] Different report configuration methods have been proposed to enable a UE reporting performance monitoring results for a UE-sided CSI prediction algorithm model / algorithm, by reusing the CSI reporting framework. More specifically, new value(s) for parameter reportQuantity are introduced in the CSI-ReportConfig Information Element (IE) as defined in 3GPP TS 38.331 V18.4.0 to support network node configuring a UE to report a performance monitoring result in a CSI report. The performance monitoring result can be reported together with the predicted CSI generated by the CSI prediction model / algorithm in the same CSI report, or a dedicated CSI report is configured for the UE to report the performance monitoring result.

[0127] Having described the general process flow of arrangements of the disclosure and having provided examples of hardware and software arrangements for implementing the processes and functions of the disclosure, the sections below provide details and examples of arrangements for triggering and configuration for user equipment reporting of performance monitoring results for channel state information prediction.

[0128] In 3GPP NR Rel-18, channel measurement resource (CMR) enhancement for Type II CSI prediction at UE (a.k.a. Enhanced Type II predicted PMI) has been introduced, e.g., the measurement part shown in FIG. 2, where a burst of K G {4, 8, 12} same CSI-RSresources are configured to the UE in a single CSI-RS resource set. More specifically, FIG. 2 shows an example CMR enhancement for Rel-18 Type II CSI prediction at UE, i.e., illustration of CMR and Rel-18 Type II CSI reporting with AP CSI-RS resource. The burst of CSI-RS resources is aperiodically (AP) triggered using a single downlink control information (DCI). The K CSI-RS resources are used for the UE to extract time domain channel properties of the channel, based on which a future CSI can be predicted.

[0129] Alternatively, the network node may also configure a legacy periodic (P) or semi-persistent (SP) CSI-RS resource. The CSI-RS resources are uniformly spaced in time, separated by m e {1, 2} slots, within the resource set.

[0130] For the Rel-18 Type II predicted PMI enhancement, a UE can be configured by gNB to report predicted PMIs for N4E {1, 2, 4, 8} time slots, see the Rel-18 Type II PMI part in Figure 2. Note that the prediction herein is relative to the CSI-RS reference resource. The predicted N4PMIs are supposed to reflect the channels with d E {1, m] slots separation, starting from 8 E 0,1,21 slots into the future relative to the UL slot

[0131]

[0132] in which the predicted CSI is reported. For AP CSI-RS burst, m E {1,2}, while for P / SP CSI-RS, m is the CSI-RS periodicity. The spacing d between the N4PMIs and offset 6 relative to the CSI-RS reference resource can be configured by the gNB via RRC signaling. The N4PMIs are compressed in a beam-frequency -Doppler domain, and the compressed PMI is reported to the gNB in a single CSI report.

[0133] Al-based UE-side CSI prediction introduced in NR Rel-18 as an Al for PHY use case is specified in NR Rel-19 work item on AI / ML for the NR air interface. One or more AI / ML models can be trained and deployed at a UE for the Al-based CSI-prediction feature. During model inference, a UE is configured by the gNB to measure a set of historical CSI-RSs (e.g., the K CSI-RS measurements in the observation window shown in Figure 2) and then report a predicted CSI in the scheduled UL slot for one or multiple future time instances (e.g., the N4future tine instances in Figure 2) using its AI / ML model(s).

[0134] Some embodiments provide aperiodic (AP)-CSI-inference and AP-CSI-PM reporting PM per sample and / or AP-CSI-RS resource, for example, as shown in FIGS. 8-12. Some other embodiments provide AP-CSI-inference and AP-CSI-PM reporting, with PM over multiple samples and / or semi persistent (SP)-CSI-RS bursts (e.g., as shown in FIGS. 13 and 14).

[0135] In some embodiments, UE 22 receives signaling of CSI prediction performance report configuration for an AI / non-AI based CSI prediction model / algorithm from anetwork, based on which the UE 22 derives one or more performance monitoring result(s), and reports the derived performance monitoring result(s) to the network node 16. The AI / non-AI based CSI prediction model / algorithm may be implemented at the UE 22 and can be an Al-based scheme (e.g., a neural network model trained by using a large dataset and then deployed at the UE 22) or non-AI based scheme (e.g., an Auto-Regression based algorithm, or a Kalman-filer based algorithm).

[0136] The network node 16 may refer to a gNB, e.g. the gNB-CU or the gNB-DU, the OAM, or a core network node 15, e.g. the NWDAF, or any other network node.

[0137] In some embodiments, a CSI prediction model / algorithm is described without being limited to predicting the PMIs or raw channels for one or multiple future time instances. Examples of predicted CSI include predicted PMI(s), predicted raw channel(s), predicted Rank Indicators (RIs), predicted Reference Signal Received Power (RSRP), predicted Channel Quality Indicators (CQIs), predicted CSI-RS Resource Indicators (CRIs), predicted top-K strongest beams, predicted top-K cells.

[0138] A model input sample for CSI prediction comprises multiple CSI-RS measurements spread over time on a set of K aperiodic CSI-RS resources. Referring to Figure 2, the input samples are those measured CSIs on the aperiodic K CSI-RS resources, shown as the CSI-RS resource in a burst, within the observation window .

[0139] A model output sample for CSI prediction comprises predicted CSI for the N4prediction time instances, for example, the predicted CSIs on the N4time slots within the prediction window as shown in FIG. 2.

[0140] For CSI prediction using UE-sided AI / ML models, the UE 22 reports predicted PMI in a CSI report (denoted as CSI-inference report in this disclosure) to the network node 16 in the format of the Rel-18 “typeII-Doppler-r!8” codebook as defined in 3GPP TS 38.214 V18.4.0. The model output format is up to UE implementation. Different AI / ML model designs can result in different model output formats, e.g.,

[0141] a) The model output is predicted raw channel per prediction time instance for all the N4prediction time instances. The predicted raw channels are then used for calculating predicted PMIs according to the Rel-18 “typeII-Doppler-r!8” codebook as defined in 3GPP TS 38.214 VI 8.4.0.

[0142] b) The model output is predicted PMI following the Rel-16 type II CSI codebook per prediction time instance for all the N4prediction time instances. The predicted Rel-16 type II PMIs are then compressed into a PMI following the Rel-18 “typeII-Doppler-r!8” codebook as defined in 3GPP TS 38.214 V18.4.0.c) The model directly outputs a predicted PMIs following the Rel-18 “typell- Doppler-rl8” codebook for the N4prediction time instances.

[0143] A ground truth label for performance monitoring can be obtained using measured CSI(s) for the corresponding one or multiple prediction time instances, for example, the measured CSIs on the N4time slots as shown in FIG. 2.

[0144] To acquire accurate performance metrics for the reported CSI, it can be beneficial to define the ground truth label format as “typell-Doppler-rl 8” codebook for calculating the intermediate KPI, regardless which model output format is used for the AI / ML model. The ground truth label in the format of “typell-Doppler-rl 8” codebook can be obtained by compressing the measured CSIs on the N4prediction time instances according to section 5.2.2.2.10 of 3GPP TS 38.214 V18.4.0. The intermediate KPI is calculated using the UE reported predicted CSI and the ground-truth label, both represented in the format of “typell-Doppler-rl 8” codebook.

[0145] To reduce the CSI-RS overhead for performance monitoring, in some cases, it is sufficient for the network node 16 to check the quality of the predicted CSI for only part of the prediction time instances, for example, the predicted CSI for the first prediction time instance. More specifically, the network node 16 can configure a UE 22 with a pair of a first and a second CSI-RS resource sets, where the first resource set consists of K CSI-RS resources and the second resource set consists of n CSI-RS resource, with K > 1 and 1 < n < N4. The measurements on the K CSI-RS resources in the first resource set are used by the UE 22 to create a model input, which is then fed to the CSI prediction model to generate a model output. The measurements on the n CSI-RS resources in the second resource set are used by the UE 22 to create a ground-truth label in the format of “typell-Doppler-rl8” codebook. Based on the model output, the UE 22 generates a predicted CSI for the n CSI-RS resources in the format of “typell-Doppler-rl 8” codebook. The intermediate KPI is calculated using the predicted CSI and the ground-truth label for the n CSI-RS resources.

[0146] The method for signaling and configuration of the performance monitoring output report is not limited to the case that the ground truth format must be “typeII-Doppler-r!8” codebook.

[0147] To support intermediate KPI calculation, a monitoring data sample can be represented as {predicted CSI, ground-truth label}, where the predicted CSI is obtained based on the model output and the associated ground truth label is generated based on actual measurements.An intermediate KPI per monitoring data sample {predicted CSI, ground-truth label} can be defined as e.g., the SGCS or NMSE between the predicted CSI and the ground-truth label.

[0148] The performance monitoring metrics for UE-sided CSI prediction use case can be defined as:

[0149] • Option 1 : intermediate KPI per monitoring data sample

[0150] • Option 2: Statistics of the intermediate KPI over K monitoring data samples, e.g., the mean and variance of the intermediate KPI associated to the collected monitoring data samples within a time window; percentage of monitoring data samples that fulfill certain condition(s).

[0151] Option 1 may be useful if the UE 22 can feedback the predicted CSI and the corresponding intermediate KPI to the network node 16 in the same CSI report. This enables network node 16 to know the quality of the received predicted CSI, thus, making better decisions on scheduling and downlink transmission for the future time slots.

[0152] An intermediate KPI of a single monitoring data sample may not indicate whether the CSI prediction model is functioning properly or not. A low SGCS value of a monitoring data sample may be due to the reason that the channel is hard to predict (i. e. , the SGCS value is expected to be low) or the Al model is not working well (i. e. , the SGCS value should be high). Hence, to enable the network node 16 to make reliable functionality-based LCM operation decisions, e.g., fallback to legacy CSI reporting and root cause analysis in case the UE 22 performance drop, statistics of the intermediate KPI over multiple monitoring data samples, i.e., Option 2, is needed.

[0153] Some examples of signaling and configurations for CSI-PM report are provided hereinafter.

[0154] As an option, a UE can be configured to derive a performance monitoring output per monitoring data sample.

[0155] Case 1: Different DCI signaling for triggering a CSI-PM report and triggering a CSI-inference report. FIG. 8 shows example signaling for CSI-PM reporting with aperiodic (AP) CSI-RS resource, where PM is calculated per sample.

[0156] In some embodiments, an aperiodic CSI-inference report and an aperiodic CSI-PM report are triggered independently by using two different DCIs signaling.

[0157] Case la: The CSI-PM report is configured with explicit CMR for performance monitoring without linking to a CSI-inference report configuration.

[0158] In a first embodiment, the CSI-PM report configuration and the CSI-inferencereport configuration are independently configured without any linkage. In the example shown in FIG. 8, the CSI-PM report configuration points to two different CSI resource configurations, for example, two different CSI-ResourceConfig as defined in 3GPP TS 38.331 V18.4.0. The first CSI resource configuration is used for channel measurement for the purpose of generating the predicted CSI. The second CSI resource configuration is used for channel measurement for the purpose of creating a ground-truth label associated to the predicted CSI. Each CSI-ResourceConfig contains a set of aperiodic CSI-RS bursts. The first aperiodic CSI-RS burst contained in the first CSI-ResourceConfig (e.g., burst 1 shown in FIG. 8) consists of K CSI-RS resources, with K>1, where the measurements on the K CSI-RS resources are used for creating a model input. The UE 22 uses the model input and the AI / ML CSI prediction model / algorithm to generate a predicted CSI. The second aperiodic CSI-RS burst contained in the second CSI-ResourceConfig (e.g., burst 2 shown in FIG. 8) consists of N4 CSI-RS resources, with N4>=1, where the measurements on the N4 CSI-RS resources are used for creating a ground-truth label associated to the predicted CSI. The UE 22 uses the predicted CSI and the ground-truth label to obtain a performance monitoring output and reports the performance monitoring output as performance monitoring result (denoted as CSI-PM report in FIG. 8) on the scheduled PUSCH atthe UL slotn2.

[0159] In an embodiment, the CSI-PM report configuration contains one or more CSI-RS resource configuration(s), which explicitly configures the CSI resource setting(s) for channel measurement for CSI-PM reporting without linking to a CSI-inference report configuration. As an example, a CSI-PM report configuration contains a single CSI-RS resource configuration ID, which explicitly configures the CSI-RS resource setting for both CSI-RS burst 1 and the CSI-RS burst 2. As another example, a CSI-PM report configuration contains two CSI-RS resource configuration IDs, which explicitly configures the CSI-RS resource settings for CSI-RS burst 1 and the CSI-RS resource settings for CSI-RS burst 2, respectively.

[0160] In an alternative embodiment, the CSI-PM report configuration points to a single CSI resource configurations. A single CSI-ResourceConfig contains two sets of aperiodic CSI-RS resource sets. The first aperiodic CSI-RS burst contained in the first aperiodic resource set (e.g., burst 1 shown in FIG. 8) consists of K CSI-RS resources, with K>1, where the measurements on the K CSI-RS resources are used for creating a model input. The UE 22 uses the model input and the AI / ML CSI prediction model / algorithm to generate a predicted CSI. The second aperiodic CSI-RS burst contained in the secondaperiodic resource set (e.g., burst 2 shown in 8) consists of N4 CSI-RS resources, with N4>=1, where the measurements on the N4 CSI-RS resources are used for creating a ground-truth label associated to the predicted CSI. The UE 22 uses the predicted CSI and the ground-truth label to obtain a performance monitoring output and reports the performance monitoring result (denoted as CSI-PM report in FIG. 8) on the scheduled PUSCH atthe UL slotn2.

[0161] In yet another alternative embodiment, the CSI-PM report configuration points to a single CSI resource configuration. A single CSI-ResourceConfig contains one aperiodic CSI-RS resource set with K + N4aperiodic CSI-RS resources. The first aperiodic CSI-RS burst (e.g., burst 1 shown in ) consisting of the first K>1 aperiodic CSI-RS resources in the aperiodic CSI-RS resource set, where the measurements on the K CSI-RS resources are used for creating a model input. The UE 22 uses the model input and the AI / ML CSI prediction model / algorithm to generate a predicted CSI. The second aperiodic CSI-RS burst (e.g., burst 2 shown in ) consisting of the last N4 aperiodic CSI-RS resources in the aperiodic CSI-RS resource set, with N4>=1, where the measurements on the N4 CSI-RS resources are used for creating aground-truth label associated to the predicted CSI. The UE 22 uses the predicted CSI and the ground-truth label to obtain a performance monitoring output and reports the performance monitoring result (denoted as CSI-PM report in ) on the scheduled PUSCH at the UL slot n2.

[0162] In case la, there is no coupling between a CSI-inference report configuration and a CSI-PM report configuration. In an embodiment, a CSI-PM report is triggered without triggering a CSI-inference report as the example shown in FIG. 8, or a CSI-PM report is triggered together with a CSI-inference report using two separate DCI signaling as the example shown in FIG. 9. More specifically, FIG. 9 shows an example of two separate DCI signaling for CSI-inference reporting and CSI-PM reporting with AP CSI-RS resource, where PM is calculated per sample.

[0163] In an embodiment, the two DCI signaling are received in the same slot. In another embodiment, the two DCI signaling are received in different slots.

[0164] For both examples shown in FIGS. 8 and 9, the DCI signaling for triggering the CSI-PM report shall be received before the first CSI-RS resource in the aperiodic CSI-RS burst 1. The time offset between the DL slot for the DCI and the DL slot for the first CSI-RS resource in the aperiodic CSI-RS burst 1 can be indicated in the DCI signaling. As an example, the candidate values for time offset defined by any one of aperiodicTriggeringOffset, aperiodicTriggeringOffset-rl6, or aperiodicTriggeringOffset-rl7 in the NZP-CSI-RS-ResourceSet ir£oxmawn element of 3GPP TS 38.331 V18.4.0 can be reused for the CSI-PM reporting.

[0165] Case lb: The CSI-PM report configuration is linked to a CSI-inference report configuration

[0166] In an embodiment, the CSI-PM report configuration contains a CSI-RS resource configuration, which explicitly configures the CSI-RS resources within the aperiodic CSI-RS burst 2 (i.e., the one used for creating ground truth label). In addition, the CSI-PM report configuration is linked to a CSI-inference report configuration, which includes a CSI-RS resource configuration that explicitly configures the CSI-RS resources within the aperiodic CSI-RS burst 1 (i.e., the one used for creating model input).

[0167] FIG. 10 shows an example of two separate DCI signaling for CSI-inference reporting and CSI-PM reporting with AP CSI-RS resource, where PM is calculated per sample. As an example shown in FIG. 10, the UE 22 obtains the predicted CSI using the aperiodic CSI-RS burst 1 indicated in the CSI-inference report configuration, and it obtains the ground-truth label using aperiodic CSI-RS burst 2 indicated in the CSI-PM report configuration. Then, the UE 22 uses the predicted CSI and the ground-truth label to obtain a performance monitoring output and reports the performance monitoring result (denoted as CSI-PM report in FIG. 10) on scheduled PUSCH at the UL slot n2.

[0168] In an embodiment, the link between the CSI-PM report and the CSI-inference report is indicated via at least one of the following methods:

[0169] • include the CSI-inference report configuration ID in the CSI-PM report configuration

[0170] • include the CSI-PM report configuration ID in the CSI-inference configuration • include the CSI-RS reference resource for CSI-inference report configuration in the CSI-PM report configuration

[0171] • Both CSI-PM report and CSI-inference report are configured within a single CSI report configuration, where at least one of them is configured as a CSI report sub configuration.

[0172] There is a coupling between a CSI-inference report configuration and a CSI-PM report configuration. Hence, a CSI-PM report can only be triggered if the associated CSI-inference report is triggered.

[0173] If the DCI for triggering the CSI-PM report is sent after the UL slot where the CSI-inference report is reported, the UE 22 may already discard the predicted CSI and the measurements on aperiodic CSI-RS burst 1. In such case, the UE 22 cannot compute anintermediated KPI based performance monitoring output. In an embodiment, the DCI for triggering the CSI-PM report shall be sent in a DL slot that is no later than the UL slot with CSI-inference report. In addition, it requires time for the UE 22 to decode the information contained in the DCI, hence, in another embodiment, the time difference, denoted at dt in FIG. 10, between the DL slot for the DCI triggering the CSI-PM report and the UL slot for UE reporting CSI-inference report may be larger than the computation time needed for the UE 22 to do the DCI decoding.

[0174] Case 2: A single DCI signaling for triggering both CSI-PM report and CSI-inference report.

[0175] FIG. 11 shows an example of single DCI signaling trigger CSI-inference reporting and CSI-PM reporting with AP CSI-RS resource, where PM is calculated per sample. An example shown in FIG. 11, a single DCI can be designed to trigger both the CSI-inference report and CSI-PM report, whenever a performance monitoring report is required by the network node 16. In this example, the CSI-inference report and the CSI-PM report are scheduled to be fed back on different UL slots. More specifically, the CSI-inference report is sent before the prediction time window, so that the network node 16 can use the predicted CSI to make (within the duration 8) timely scheduling decisions for the future time slots. The CSI-PM report is sent after the last CSI-RS resource in the aperiodic CSI-RS bust 2, since the UE 22 needs to measure the CSI-RS resources in burst 2 to create ground truth label for calculating the performance monitoring output.

[0176] In an embodiment, a single DCI signaling is used for triggering both the CSI-PM report and the CSI-inference report, where the CSI-PM report and CSI-inference report are scheduled to be transmitted on different UL slots / PUSCHs.

[0177] The CMR configuration for the CSI-PM report can either use Case la and Case lb. In an embodiment, the CSI-PM report configuration contains one or more CSI-RS resource configuration(s), which explicitly configures the CSI resource setting(s) for the aperiodic CSI-RS burst 1 and burst 2. As an example, a CSI-PM report configuration contains a single CSI-RS resource configuration ID, which explicitly configures the CSI-RS resource setting for both CSI-RS burst 1 and the CSI-RS burst 2. As another example, a CSI-PM report configuration contains two CSI-RS resource configuration IDs, which explicitly configures the CSI-RS resource settings for CSI-RS burst 1 and the CSI-RS resource settings for CSI-RS burst 2, respectively.

[0178] In another embodiment, the CSI-PM report configuration contains one CSI-RS resource configuration (e.g., points to one CSI-ResourceConfig), which explicitlyconfigures the CSI resource setting for the aperiodic CSI-RS burst 2 only. The UE 22 uses the CSI-inference report triggered by the same DCI and the ground truth label derived from the measurements on the aperiodic CSI-RS burst 2 to calculate the performance monitoring output.

[0179] FIG. 12 shows another example of using a single DCI signalling to trigger both the CSI-inference report and CSI-PM report. That is, FIG. 12 shows an example of single DCI signaling for CSI-inference reporting and CSI-PM reporting with AP CSI-RS resource, where the PM is calculated per sample. In this example, the CSI-inference report and the CSI-PM report are scheduled to be sent over the same UL slot / PUSCH. More specifically, the CSI-inference report and the CSI-PM report are sent on an UL slot that is after the last CSI-RS resource in the aperiodic CSI-RS bust 2, since the UE 22 needs to measure the CSI-RS resources in burst 2 to create ground truth label for calculating the performance monitoring output. In this case, the DCI signaling only needs to schedule one PUSCH for the CSI-inference and CSI-PM reporting. However, the predicted CSI carried on the CSI-inference report becomes outdated, hence, the CSI-inference report may not be useful for the network node 16 from making DL PDSCH scheduling perspective, but it may still be useful for performance monitoring and error analysis for the CSI prediction model / functionality at the UE 22.

[0180] In an embodiment, a single DCI signaling is used for triggering both the CSI-PM report and the CSI-inference report, where the CSI-PM report and CSI-inference report are scheduled to be transmitted on the same UL slots / PUSCHs.

[0181] In some embodiments, the CSI-PM report and the CSI-inference report are configured in a same CSI report configuration, while they are configured as separate CSI report sub configurations. In this way, a single DCI can be used to trigger the said CSI report with two sub configurations.

[0182] As another option, a UE 22 can be configured to derive a performance monitoring output based on multiple monitoring data samples.

[0183] FIG. 13 shows an example of using different DCI signaling for triggering CSI-inference report and CSI-PM report, where the CSI-PM report is derived based on multiple monitoring data samples. In this example, the CMR configuration for the CSI-PM report is self-contained and not linked to any CSI-inference report configurations. Hence, similar to Case la for Option 1, the CSI-PM report can be triggered regardless of if there is a CSI-inference report configured associated to its monitoring data samples.

[0184] Different rules can be used for aligning between the network node 16 and the UE22 regarding the valid monitoring data samples to use for calculating the performance monitoring output.

[0185] In an embodiment, the validity of monitoring data samples is determined based on the CMR configuration for the CSI-PM report, where the CSI-PM report explicitly configures the CSI-RS resource setting for the channel measurements associated to multiple monitoring data samples.

[0186] As an example, the CMR configuration in the CSI-PM report configuration explicitly configures the CSI-RS resource setting for multiple pairs of the aperiodic CSI-RS burst 1 and the aperiodic CSI-RS burst 2 that are associated to multiple monitoring data samples (e.g., sample 1 and sample 2 shown in FIGS. 13 and 14). Even if there is no DCI triggering a CSI-inference report associated to a monitoring data sample, e.g., sample 2 in FIG. 13, the UE 22 may still consider this monitoring data sample as a valid sample for performance monitoring output calculation. More specifically, FIG. 13 and FIG. 14 show example uses of separate DCI signaling for CSI-inference report(s) and CSI-PM report with AP CSI-RS resource, where PM is calculated over multiple samples. The difference between FIG. 14 and FIG. 13 lies in that Sample 2 in FIG. 13 is not triggered by DCI for CSI inference report however still may be considered as basis / samples for generating ground truth label in CSI-PM report at slot n3.

[0187] In another embodiment, the validity of monitoring data samples is determined based on the CSI-PM report configuration together with one or more CSI-inference report configuration(s).

[0188] As an example, the CMR configuration in the CSI-PM report configuration explicitly configures the CSI-RS resource setting for multiple pairs of the aperiodic CSI-RS burst 1 and the aperiodic CSI-RS burst 2, which are associated to multiple candidates of monitoring data samples (e.g., sample 1 and sample 2 shown in FIG. 13). If there is no DCI triggering a CSI-inference report associated to a monitoring data sample (e.g., sample 2 shown in FIG. 13), then, the UE 22 may not consider this monitoring data sample (e.g., sample 2 shown in FIG. 13) as a valid sample for performance monitoring output calculation.

[0189] In an embodiment, one or more candidate monitoring data samples are indicated by the CMR configuration for the CSI-PM report, where the CSI-PM report configuration explicitly configures the CSI-RS resource setting for the channel measurements associated to multiple monitoring data samples. In another embodiment, a candidate monitoring data sample is considered as a valid sample when the associated CSI-inference report isconfigured.

[0190] As another example, the CMR configuration in the CSI-PM report configuration configures the CSI-RS resource setting only for multiple aperiodic CSI-RS bursts 2 associated to the ground truth labels for multiple candidates of monitoring data samples (e.g., sample 1 and sample 2 shown in FIG. 14). If there is no DCI triggering a CSI-inference report associated to a candidate monitoring data sample (e.g., sample 2 shown in FIG. 13) for a CSI-PM reporting, then, the UE 22 may not consider this monitoring data sample (e.g., sample 2 shown in FIG. 13) as a valid sample for performance monitoring output calculation.

[0191] In an embodiment, one or more candidate monitoring data samples are indicated by the CMR configuration for the CSI-PM report, where the CSI-PM report configuration configures the CSI-RS resource setting for only the channel measurements associated to ground-truth labels for the one or more multiple monitoring data sample candidates. In another embodiment, a candidate monitoring data sample is considered as a valid sample when the associated CSI-inference report is configured.

[0192] In another embodiment, the association between a CSI-inference report and a candidate monitoring data sample for a CSI-PM report can be indicated by one or more of the following methods:

[0193] o including the CSI-inference report configuration ID in the CSI-PM report configuration,

[0194] o including the CSI-PM report configuration ID in the CSI-inference configuration,

[0195] o including the CSI-RS reference resource for CSI-inference report configuration in the CSI-PM report configuration,

[0196] o including the CSI-PM report configuration ID in the DCI signaling triggering the CSI-inference report, and

[0197] o including the CSI-inference configuration ID in the DCI signaling triggering the CSI-PM report.

[0198] As will be appreciated by one of skill in the art, the concepts described herein may be embodied as a method, data processing system, computer program product and / or computer storage media storing an executable computer program. Accordingly, the concepts described herein may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects all generally referred to herein as a “circuit” or “module.” Any process, step,action and / or functionality described herein may be performed by, and / or associated to, a corresponding module, which may be implemented in software and / or firmware and / or hardware. Furthermore, the disclosure may take the form of a computer program product on a tangible computer usable storage medium having computer program code embodied in the medium that can be executed by a computer. Any suitable tangible computer readable medium may be utilized including hard disks, CD-ROMs, electronic storage devices, optical storage devices, or magnetic storage devices.

[0199] Some embodiments are described herein with reference to flowchart illustrations and / or block diagrams of methods, systems and computer program products. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer (to thereby create a special purpose computer), special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0200] These computer program instructions may also be stored in a computer readable memory or storage medium that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instruction means which implement the function / act specified in the flowchart and / or block diagram block or blocks.lt is to be understood that the functions / acts noted in the blocks may occur out of the order noted in the operational illustrations. 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 / acts involved. Although some of the diagrams include arrows on communication paths to show a primary direction of communication, it is to be understood that communication may occur in the opposite direction to the depicted arrows.

[0201] Many different embodiments have been disclosed herein, in connection with the above description and the drawings. It will be understood that it would be unduly repetitious and obfuscating to literally describe and illustrate every combination and subcombination of these embodiments. Accordingly, all embodiments can be combined inany way and / or combination, and the present specification, including the drawings, shall be construed to constitute a complete written description of all combinations and subcombinations of the embodiments described herein, and of the manner and process of making and using them, and shall support claims to any such combination or subcombination.

[0202] It will be appreciated by persons skilled in the art that the embodiments described herein are not limited to what has been particularly shown and described herein above. In addition, unless mention was made above to the contrary, it should be noted that all of the accompanying drawings are not to scale. A variety of modifications and variations are possible in light of the above teachings.Example embodiments:

[0203] Embodiment Al . A method in a network node configured to communicate with a user equipment (UE), the method comprising:

[0204] configuring the UE to report a performance monitoring outcome in a channel state information (CSI) report for a CSI prediction model when one or more aperiodic CSI reference signal (CSI-RS) resources are used for channel measurements; and performing one or more actions based on the configuring of the UE.

[0205] Embodiment A2. The method of Embodiment Al, wherein the CSI prediction model is an artificial intelligence (Al) based CSI prediction model or a non- Al based CSI prediction model.

[0206] Embodiment A3. The method of any one of Embodiments Al and A2, wherein configuring includes determining a first CSI report configuration and a second CSI report configuration, the first CSI report configuration being used for configuring a CSI-inference report, the second CSI report configuration being used for configuring a CSI performance monitoring (CSI-PM) report.

[0207] Embodiment A4. The method of Embodiment A3, wherein the performance monitoring outcome is calculated per monitoring data sample.

[0208] Embodiment A5. The method of Embodiment A4, wherein the method further includes:

[0209] transmitting different downlink control information (DCI) signaling for triggering the CSI-PM report and triggering the CSI-inference report.

[0210] Embodiment A6. The method of Embodiment A5, wherein the CSI-PM report is configured with an explicit channel measurement resource (CMR) for performance monitoring without linking to the first CSI report configuration.

[0211] Embodiment A7. The method of Embodiment A5, wherein the first CSI report configuration and the second CSI report configuration are linked.

[0212] Embodiment A8. The method of Embodiment A4, wherein the method furtherincludes transmitting a single DCI signaling for triggering the CSI-PM report and the CSI-inference report.

[0213] Embodiment A9. The method of Embodiment A3, wherein the performance monitoring outcome is calculated using multiple monitoring data samples.

[0214] Embodiment A10. The method of any one of Embodiments A1-A9, wherein the method further includes receiving, from the UE, a CSI prediction for the CSI prediction model.

[0215] Embodiment Bl . A network node configured to communicate with a user equipment (UE), the network node configured to, and / or comprising a radio interface and / or processing circuitry configured to perform one or more steps corresponding to one or both of Embodiments A1-A10.

[0216] Embodiment Cl . A method in a user equipment (UE) configured to communicate with a network node, the method comprising:

[0217] configuring the UE to report a performance monitoring outcome in a channel state information (CSI) report for a CSI prediction model when one or more aperiodic CSI reference signal (CSI-RS) resources are used for channel measurements, the configuring of the UE being based on one or both of a first CSI report configuration and a second CSI report configuration received from the network node; and

[0218] performing one or more actions based on the configuring of the UE.

[0219] Embodiment C2. The method of Embodiment Cl, wherein the method further includes one or more steps corresponding or complementary to any one of Embodiments A2-A10.

[0220] Embodiment DI . A user equipment (UE) configured to communicate with a network node, the UE configured to, and / or comprising a radio interface and / or processing circuitry configured to perform one or more steps corresponding to one or both of Embodiments Cl and C2.

Claims

CLAIMS1. A method implemented by a wireless device (22), WD, comprising: receiving, one or more channel state information, CSI, inference report configurations; receiving, a CSI performance monitoring, PM, report configuration associated with one of the one or more CSI inference report configurations; wherein the CSI PM report configuration comprises a configuration ID of the associated CSI inference report configuration;receiving, Downlink Control Information, DCI, signaling for triggering a CSI PM report according to the CSI PM report configuration; andtransmitting, a CSI PM report according to the CSI PM report configuration.

2. The method of Claim 1, wherein the CSI PM report configuration further comprises: an indication of CSI-RS resource set for deriving a non-predicted CSI for generating the CSI PM report.

3. The method of Claims 1 or 2, wherein the associated CSI inference report configuration further comprises information of report type as aperiodic report, and the CSI PM report configuration further comprises information of report type as aperiodic report.

4. The method of any of Claims 1 to 3, wherein the DCI for triggering the CSI PM report is received no later than an uplink slot for reporting a CSI inference report according to the associated CSI inference report configuration.

5. The method of any of the preceding claims, wherein the DCI for triggering the CSI PM report is received no later than starting CSI-RS resource for measurement input for CSI inference according to the associated CSI inference report configuration.

6. The method of the preceding claims, wherein the DCI for triggering the CSI PM report also triggers the CSI inference report according to the associated CSI inference report configuration.

7. The method of any of Claims 1 to 5, further comprising: receiving another DCI signaling for triggering the CSI inference report according to the associated CSI inference report configuration.

8. The method of any of the preceding claims, wherein the CSI PM report configuration is associated with multiple CSI inference report configurations of the one or more CSI inference report configurations, and the transmitted CSI PM report comprises performance monitoring result based on CSI inferences according to the multiple associated inference report configurations.

9. A method implemented by a network node (16), comprising:transmitting, to a wireless device (22), WD, one or more channel state information, CSI, inference report configurations;transmitting, to the WD (22), a CSI performance monitoring, PM, report configuration associated with one of the one or more CSI inference report configurations; wherein the CSI PM report configuration comprises a configuration ID of the associated CSI inference report configuration;transmitting, to the WD (22), Downlink Control Information, DCI, signaling for triggering a CSI PM report according to the CSI PM report configuration; and receiving, from the WD (22), a CSI PM report according to the CSI PM report configuration.

10. The method of Claim 9, wherein the CSI PM report configuration further comprises: an indication of CSI-RS resource set for deriving a non-predicted CSI for generating the CSI PM report.

11. The method of Claims 9 or 10, wherein the associated CSI inference report configuration further comprises information of report type as aperiodic report, and the CSI PM report configuration further comprises information of report type as aperiodic report.

12. The method of any of Claims 9 to 11, wherein the DCI for triggering the CSI PM report is transmitted no later than an uplink slot for reporting a CSI inference report according to the associated CSI inference report configuration.

13. The method of any of Claims 9 to 12, wherein the DCI for triggering the CSI PM report is transmitted no later than starting CSI-RS resource for measurement input for CSI inference according to the associated CSI inference report configuration.

14. The method of any of Claims 9 to 13, wherein the DCI for triggering the CSI PM report also triggers the CSI inference report according to the associated CSI inference report configuration.

15. The method of any of Claims 9 to 13, further comprising: transmitting another DCI signaling for triggering the CSI inference report according to the associated CSI inference report configuration.

16. The method of any of Claims 9 to 15, wherein the CSI PM report configuration is associated with multiple CSI inference report configurations of the one or more CSI inference report configurations, and the received CSI PM report comprises performance monitoring result based on CSI inferences according to the multiple associated inference report configurations.

17. A wireless device (22), WD, comprising:a radio interface (46) configured to communicate with a network node (16);a processor (52); anda memory (54) containing instructions executable by the processor (52) whereby the WD is operative to perform the method according to any of the claims 1 to 8.

18. A network node (16), comprising:a radio interface (30) configured to communicate with a wireless device (22); a processor (38); anda memory (40) containing instructions executable by the processor (38) whereby the network node (16) is operative to perform the method according to any of the claims 9 to 16.

Images