Method for monitoring the performance of machine learning based channel state information prediction
The implementation of life cycle management for ML based CSI prediction through separate CMRs for performance monitoring and prediction improves accuracy and reduces overhead in 5G wireless systems, addressing the limitations of existing ML models.
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- GOOGLE LLC
- Filing Date
- 2025-01-15
- Publication Date
- 2026-07-23
AI Technical Summary
The accuracy of machine learning (ML) based channel state information (CSI) prediction in 5G wireless communication systems is influenced by the performance of the ML model, leading to reduced accuracy in certain scenarios, and existing performance monitoring techniques result in significant overhead.
Implementing life cycle management (LCM) for ML based CSI prediction by configuring separate CSI report configurations for performance monitoring and CSI prediction, using distinct channel measurement resources (CMRs), allowing for performance monitoring information to be associated with CSI prediction, thereby reducing overhead and improving accuracy.
Enhances the accuracy of ML based CSI prediction by optimizing the use of CMRs for performance monitoring and prediction, minimizing overhead, and ensuring robust communication links.
Smart Images

Figure CN2025072455_23072026_PF_FP_ABST
Abstract
Description
METHOD FOR MONITORING THE PERFORMANCE OF MACHINE LEARNING BASED CHANNEL STATE INFORMATION PREDICTIONTECHNICAL FIELD
[0001] The present disclosure relates generally to wireless communication, and more particularly, to life cycle management (LCM) for channel state information (CSI) prediction.BACKGROUND
[0002] The Third Generation Partnership Project (3GPP) specifies a radio interface referred to as fifth generation (5G) new radio (NR) (5G NR) . An architecture for a 5G NR wireless communication system includes a 5G core (5GC) network, a 5G radio access network (5G-RAN) , a user equipment (5G UE) , etc. The 5G NR architecture seeks to provide increased data rates, decreased latency, and / or increased capacity compared to prior generation cellular communication systems.
[0003] Wireless communication systems, in general, provide various telecommunication services (e.g., telephony, video, data, messaging, etc. ) based on multiple-access technologies, such as orthogonal frequency division multiple access (OFDMA) technologies, that support communication with multiple UEs. Improvements in mobile broadband continue the progression of such wireless communication technologies. For example, in some scenarios, a network entity may configure a channel state information (CSI) report configuration for the UE to perform CSI prediction using a machine learning (ML) model. The accuracy of the ML based CSI prediction can be influenced by the performance of the ML model, which is trained according to certain scenarios. Because the ML model may not be suitable for some scenarios, the accuracy of the CSI prediction may be reduced. The UE may perform a performance monitoring technique to improve the accuracy of the ML based CSI prediction. However, this performance monitoring technique may result in a large overhead. BRIEF SUMMARY
[0004] The following presents a simplified summary of one or more aspects in order to provide a basic understanding of such aspects. This summary is not an extensive overview of all contemplated aspects. This summary neither identifies key or critical elements of all aspects nor delineates the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to the more detailed description that is presented later.
[0005] To maintain a robust communication link, fifth generation (5G) mobile communication systems use beam management for identifying a strongest beam pair between a user equipment (UE) and a network entity, such as a base station or a unit of a base station. The UE performs beam measurement by measuring a reference signal received power (RSRP) of a beam. The UE measures the RSRP based on a channel state information reference signal (CSI-RS) transmitted via multiple beams. The UE performs a search for a beam that has the highest measured RSRP. After the UE identifies the beam that has the highest measured RSRP, the UE performs beam reporting via channel state information (CSI) feedback. The network entity can configure CSI feedback using a CSI report configuration. The CSI report configuration configures a channel measurement resource (CMR) , an interference measurement resource (IMR) , a codebook for the CSI report, CSI feedback for multiple codewords, and / or an uplink resource for the CSI feedback. The UE measures the CSI-RS and transmits the CSI feedback in a CSI report based on the CSI report configuration. The CSI report enables the network entity to determine a precoder for beamforming procedures.
[0006] In some scenarios, a network entity may configure the CSI report configuration for the UE to perform CSI prediction. For example, the network entity configures the CSI report configuration for the UE to report the predicted rank indicator (RI) , precoding matrix indicator (PMI) , or channel quality indicator (CQI) for one or more slots after the CSI report slot. The UE can perform the CSI prediction using a machine learning (ML) model. The accuracy of the ML based CSI prediction can be influenced by the performance of the ML model, which is trained according to certain scenarios. Because the ML model may not be suitable for some scenarios, the accuracy of the CSI prediction may be reduced. The UE may perform a performance monitoring technique to improve the accuracy of the ML based CSI prediction. For example, the UE reports the ground-truth CSI to the network entity and the network entity compares the ML based predicted CSI and the ground-truth CSI. However, this performance monitoring technique may result in a large overhead.
[0007] Aspects of the present disclosure address the above-noted and other deficiencies by implementing techniques for life cycle management (LCM) for ML based CSI prediction. A UE receives a first CSI report configuration indicating at least one CMR for the performance monitoring and a second CSI report configuration indicating at least one CMR for the CSI prediction. The UE transmits, to the network entity, a CSI report based on the first CSI report configuration, the CSI report including performance monitoring information for the CSI prediction. In another example, the UE receives, from the network entity, a third CSI report configuration indicating a linkage between the first CSI report configuration and the second CSI report configuration.
[0008] According to some aspects, the UE receives, from a network entity, a first CSI report configuration for performance monitoring associated with a first CMR and a second CSI report configuration for CSI prediction associated with a second CMR. The UE receives, from the network entity, a first CSI-RS on the first CMR and a second CSI-RS on the second CMR. The UE transmits, to the network entity, a CSI report based on the first CSI report configuration, the CSI report including performance monitoring information for the first CMR, the performance monitoring information being associated with the CSI prediction for the second CMR.
[0009] According to some aspects, the network entity transmits, to a UE, a first CSI report configuration for performance monitoring associated with a first CMR and a second CSI report configuration for CSI prediction associated with a second CMR. The network entity transmits, to the UE, a first CSI-RS on the first CMR and a second CSI-RS on the second CMR. The network entity receives, from the UE, a CSI report based on the first CSI report configuration, the CSI report including performance monitoring information for the first CMR, the performance monitoring information being associated with the CSI prediction for the second CMR.BRIEF DESCRIPTION OF THE DRAWINGS
[0010] FIG. 1 illustrates a diagram of a wireless communications system that includes a plurality of user equipments (UEs) and network entities in communication over one or more cells according to an embodiment.
[0011] FIG. 2 illustrates an example of channel state information (CSI) prediction technique according to an embodiment.
[0012] FIG. 3 is a signaling diagram illustrating an example of a life cycle management (LCM) procedure for model inference according to an embodiment.
[0013] FIG. 4A illustrates an example of a sliding window based CSI prediction according to an embodiment.
[0014] FIG. 4B illustrates an example of a non-sliding window based CSI prediction according to an embodiment.
[0015] FIG. 5A illustrates an example for report configuration for performance monitoring for CSI prediction according to an embodiment.
[0016] FIG. 5B illustrates an example for linked report configurations for performance monitoring for CSI prediction.
[0017] FIG. 6A illustrates an example for report configuration for performance monitoring for CSI prediction according to an embodiment.
[0018] FIG. 6B illustrates an example for monitoring report based on flexible timing of the channel measurement resource (CMR) according to an embodiment.
[0019] FIG. 7A illustrates an example for the inference and monitoring based on the same CMR(s) according to an embodiment.
[0020] FIG. 7B illustrates an example for the inference and monitoring based on different CMR(s) according to an embodiment.
[0021] FIG. 8 illustrates an example for the CSI calculation scheme indicated by the network entity according to an embodiment.
[0022] FIG. 9 illustrates an example for the CSI calculation scheme reported by the UE according to an embodiment.
[0023] FIG. 10 is a flowchart of a method of wireless communication at a UE according to an embodiment.
[0024] FIG. 11 is a flowchart of a method of wireless communication at a network entity according to an embodiment.
[0025] FIG. 12 is a diagram illustrating a hardware implementation for an example UE apparatus according to an embodiment.
[0026] FIG. 13 is a diagram illustrating a hardware implementation for one or more example network entities according to an embodiment.DETAILED DESCRIPTION
[0027] FIG. 1 illustrates a diagram 100 of a wireless communications system associated with a plurality of cells 190. The wireless communications system includes user equipments (UEs) 102 and base stations / network entities 104. Some base stations may include an aggregated base station architecture and other base stations may include a disaggregated base station architecture. The aggregated base station architecture utilizes a radio protocol stack that is physically or logically integrated within a single radio access network (RAN) node. A disaggregated base station architecture utilizes a protocol stack that is physically or logically distributed among two or more units (e.g., radio unit (RU) 106, distributed unit (DU) 108, central unit (CU) 110) . For example, a CU 110 is implemented within a RAN node, and one or more DUs 108 may be co-located with the CU 110, or alternatively, may be geographically or virtually distributed throughout one or multiple other RAN nodes. The DUs 108 may be implemented to communicate with one or more RUs 106. Any of the RU 106, the DU 108 and the CU 110 can be implemented as virtual units, such as a virtual radio unit (VRU) , a virtual distributed unit (VDU) , or a virtual central unit (VCU) . The base station / network entity 104 (e.g., an aggregated base station or disaggregated units of the base station, such as the RU 106 or the DU 108) , may be referred to as a transmission reception point (TRP) .
[0028] Operations of the base station 104 and / or network designs may be based on aggregation characteristics of base station functionality. For example, disaggregated base station architectures are utilized in an integrated access backhaul (IAB) network, an open-radio access network (O-RAN) network, or a virtualized radio access network (vRAN) , which may also be referred to a cloud radio access network (C-RAN) . Disaggregation may include distributing functionality across the two or more units at various physical locations, as well as distributing functionality for at least one unit virtually, which can enable flexibility in network designs. The various units of the disaggregated base station architecture, or the disaggregated RAN architecture, can be configured for wired or wireless communication with at least one other unit. For example, the base stations 104d, 104e and / or the RUs 106a, 106b, 106c, 106d may communicate with the UEs 102a, 102b, 102c, 102d, and / or 102s via one or more radio frequency (RF) access links based on a Uu interface. In examples, multiple RUs 106 and / or base stations 104 may simultaneously serve the UEs 102, such as by intra-cell and / or inter-cell access links between the UEs 102 and the RUs 106 / base stations 104.
[0029] The RU 106, the DU 108, and the CU 110 may include (or may be coupled to) one or more interfaces configured to transmit or receive information / signals via a wired or wireless transmission medium. For example, a wired interface can be configured to transmit or receive the information / signals over a wired transmission medium, such as via the fronthaul link 160 between the RU 106d and the baseband unit (BBU) 112 of the base station 104d associated with the cell 190d. The BBU 112 includes a DU 108 and a CU 110, which may also have a wired interface (e.g., midhaul link) configured between the DU 108 and the CU 110 to transmit or receive the information / signals between the DU 108 and the CU 110. In further examples, a wireless interface, which may include a receiver, a transmitter, or a transceiver, such as an RF transceiver, configured to transmit and / or receive the information / signals via the wireless transmission medium, such as for information communicated between the RU 106a of the cell 190a and the base station 104e of the cell 190e via cross-cell communication beams 136-138 of the RU 106a and the base station 104e.
[0030] The RUs 106 may be configured to implement lower layer functionality. For example, the RU 106 is controlled by the DU 108 and may correspond to a logical node that hosts RF processing functions, or lower layer PHY functionality, such as execution of fast Fourier transform (FFT) , inverse FFT (iFFT) , digital beamforming, physical random access channel (PRACH) extraction and filtering, etc. The functionality of the RU 106 may be based on the functional split, such as a functional split of lower layers.
[0031] The RUs 106 may transmit or receive over-the-air (OTA) communication with one or more UEs 102. For example, the RU 106b of the cell 190b communicates with the UE 102b of the cell 190b via a first set of communication beams 132 of the RU 106b and a second set of communication beams 134b of the UE 102b, which may correspond to inter-cell communication beams or, in some examples, cross-cell communication beams. For instance, the UE 102b of the cell 190b may communicate with the RU 106a of the cell 190a via a third set of communication beams 134a of the UE 102b and a fourth set of communication beams 136 of the RU 106a. DUs 108 can control both real-time and non-real-time features of control plane and user plane communications of the RUs 106.
[0032] Any combination of the RU 106, the DU 108, and the CU 110, or reference thereto individually, may correspond to a base station 104. Thus, the base station 104 may include at least one of the RU 106, the DU 108, or the CU 110. The base stations 104 provide the UEs 102 with access to a core network. The base stations 104 may relay communications between the UEs 102 and the core network (not shown) . The base stations 104 may be associated with macrocells for higher-power cellular base stations and / or small cells for lower-power cellular base stations. For example, the cell 190e may correspond to a macrocell, whereas the cells 190a-190d may correspond to small cells. Small cells include femtocells, picocells, microcells, etc. A network that includes at least one macrocell and at least one small cell may be referred to as a “heterogeneous network. ”
[0033] Transmissions from a UE 102 to a base station 104 / RU 106 are referred to as uplink (UL) transmissions, whereas transmissions from the base station 104 / RU 106 to the UE 102 are referred to as downlink (DL) transmissions. Uplink transmissions may also be referred to as reverse link transmissions and downlink transmissions may also be referred to as forward link transmissions. For example, the RU 106d utilizes antennas of the base station 104d of cell 190d to transmit a downlink / forward link communication to the UE 102d or receive an uplink / reverse link communication from the UE 102d based on the Uu interface associated with the access link between the UE 102d and the base station 104d / RU 106d.
[0034] Communication links between the UEs 102 and the base stations 104 / RUs 106 may be based on multiple-input and multiple-output (MIMO) antenna technology, including spatial multiplexing, beamforming, and / or transmit diversity. The communication links may be associated with one or more carriers. The UEs 102 and the base stations 104 / RUs 106 may utilize a spectrum bandwidth of Y MHz (e.g., 5, 10, 15, 20, 100, 400, 800, 1600, 2000, etc. MHz) per carrier allocated in a carrier aggregation of up to a total of Yx MHz, where x component carriers (CCs) are used for communication in each of the uplink and downlink directions. The carriers may or may not be adjacent to each other along a frequency spectrum. In examples, uplink and downlink carriers may be allocated in an asymmetric manner, with more or fewer carriers allocated to either the uplink or the downlink. A primary component carrier and one or more secondary component carriers may be included in the component carriers. The primary component carrier may be associated with a primary cell (PCell) and a secondary component carrier may be associated with a secondary cell (SCell) .
[0035] Some UEs 102, such as the UEs 102a and 102s, may perform device-to-device (D2D) communications over sidelink. For example, a sidelink communication / D2D link utilizes a spectrum for a wireless wide area network (WWAN) associated with uplink and downlink communications. Such sidelink / D2D communication may be performed through various wireless communications systems, such as wireless fidelity (Wi-Fi) systems, Bluetooth systems, Long Term Evolution (LTE) systems, New Radio (NR) systems, etc.
[0036] The UEs 102 and the base stations 104 / RUs 106 may each include a plurality of antennas. The plurality of antennas may correspond to antenna elements, antenna panels, and / or antenna arrays that may facilitate beamforming operations. For example, the RU 106b transmits a downlink beamformed signal based on a first set of communication beams 132 to the UE 102b in one or more transmit directions of the RU 106b. The UE 102b may receive the downlink beamformed signal based on a second set of communication beams 134b from the RU 106b in one or more receive directions of the UE 102b. In a further example, the UE 102b may also transmit an uplink beamformed signal (e.g., sounding reference signal (SRS) ) to the RU 106b based on the second set of communication beams 134b in one or more transmit directions of the UE 102b. The RU 106b may receive the uplink beamformed signal from the UE 102b in one or more receive directions of the RU 106b. The UE 102b may perform beam training to determine the best receive and transmit directions for the beamformed signals. The transmit and receive directions for the UEs 102 and the base stations 104 / RUs 106 may or may not be the same.
[0037] In further examples, beamformed signals may be communicated between a first base station / RU 106a and a second base station 104e. For instance, the base station 104e of the cell 190e may transmit a beamformed signal to the RU 106a based on the communication beams 138 in one or more transmit directions of the base station 104e. The RU 106a may receive the beamformed signal from the base station 104e of the cell 190e based on the RU communication beams 136 in one or more receive directions of the RU 106a. In further examples, the base station 104e transmits a downlink beamformed signal to the UE 102e based on the communication beams 138 in one or more transmit directions of the base station 104e. The UE 102e receives the downlink beamformed signal from the base station 104e based on UE communication beams 130 in one or more receive directions of the UE 102e. The UE 102e may also transmit an uplink beamformed signal to the base station 104e based on the UE communication beams 130 in one or more transmit directions of the UE 102e, such that the base station 104e may receive the uplink beamformed signal from the UE 102e in one or more receive directions of the base station 104e.
[0038] The base station 104 may include and / or be referred to as a network entity. That is, “network entity” may refer to the base station 104 or at least one unit of the base station 104, such as the RU 106, the DU 108, and / or the CU 110. The base station 104 may also include and / or be referred to as a next generation evolved Node B (ng-eNB) , a next generation NB (gNB) , an evolved NB (eNB) , an access point, a base transceiver station, a radio base station, a radio transceiver, a transceiver function, a basic service set (BSS) , an extended service set (ESS) , a TRP, a network node, network equipment, or other related terminology. The base station 104 or an entity at the base station 104 can be implemented as an IAB node, a relay node, a sidelink node, an aggregated (monolithic) base station, or a disaggregated base station including one or more RUs 106, DUs 108, and / or CUs 110. A set of aggregated or disaggregated base stations may be referred to as a next generation-radio access network (NG-RAN) . In some examples, the UE 102a operates in dual connectivity (DC) with the base station 104e and the base station / RU 106a. In such cases, the base station 104e can be a master node and the base station / RU 160a can be a secondary node.
[0039] Still referring to FIG. 1, in certain aspects, any of the UEs 102 may include a channel state information (CSI) report component 140 configured to receive, from a network entity 104, a first CSI report configuration for performance monitoring associated with a first channel measurement resource (CMR) and a second CSI report configuration for CSI prediction associated with a second CMR; receive, from the network entity 104, a first CSI-reference signal (RS) on the first CMR and a second CSI-RS on the second CMR; transmit, to the network entity 104, a CSI report based on the first CSI report configuration, the CSI report including performance monitoring information for the first CMR, the performance monitoring information being associated with the CSI prediction for the second CMR.
[0040] In certain aspects, any of the base stations 104 or a network entity of the base stations 104 may include a CSI report configuration component 150 configured to transmit, to a UE 102, a first CSI report configuration for performance monitoring associated with a first CMR and a second CSI report configuration for CSI prediction associated with a second CMR. The network entity transmits, to the UE 102, a first CSI-RS on the first CMR and a second CSI-RS on the second CMR. The network entity receives, from the UE 102, a CSI report based on the first CSI report configuration, the CSI report including performance monitoring information for the first CMR, the performance monitoring information being associated with the CSI prediction for the second CMR.
[0041] Accordingly, FIG. 1 describes a wireless communication system that may be implemented in connection with aspects of one or more other figures described herein. Further, although the following description may be focused on 5G NR, the concepts described herein may be applicable to other similar areas, such as 5G-Advanced and future versions, LTE, LTE-advanced (LTE-A) , and other wireless technologies, such as 6G.
[0042] FIG. 2 illustrates a diagram 200 of example for CSI prediction. The network entity 104 may configure the UE 102 to perform the CSI prediction 212. In a CSI report configuration, the network entity 104 may configure the UE 102 to report the predicted rank indicator (RI) , precoding matrix indicator (PMI) , channel quality indicator (CQI) for one or multiple slots after CSI report slot 207. As shown in FIG. 2, the UE 102 may measure historical CSI (e.g., 202A, 204A, 206A) based on channel measurement resource (CMR) in the measurement window 208, predict the future CSI (s) in the prediction window 210 (starting from the CSI report slot 207) , and report the predicted CSI (s) (e.g., 202B, 204B, 206B) to the network entity 104.
[0043] Accordingly, FIGs. 1-2 describe example environments in which various aspects of life cycle management (LCM) for ML based CSI prediction that may be implemented in connection with aspects of one or more other figures described herein, such as aspects illustrated in FIGs. 3-13.
[0044] FIG. 3 is a signaling diagram 300 illustrating communications between a UE 102 and a network entity 104 for the LCM for model inference (e.g., CSI prediction) . The network entity 104 may correspond to a base station or a unit of a base station, such as the RU 106, the DU 108, the CU 110, etc.
[0045] In some examples, the UE 102 may transmit 302, to the network entity 104, (and the network entity 104 may receive 302 from the UE 102) , a UE capability report indicating supported features for LCM for model inference. The UE capability report may include at least one of: minimum or maximum or preferred number of transmission occasions for CMR for measurement and / or for inference; minimum or maximum or preferred number of transmission occasions for CMR for measurement for monitoring; supported prediction window duration; supported offset between measurement window (e.g. observation window) and prediction window; whether to support sliding or non-sliding filtering; supported time-domain behavior (s) for the CMR and / or the report for inference and / or monitoring; the temporal pattern of the measurement and prediction (e.g., intervals between every two consecutive transmission occasions and number of transmission occasions for measurement and / or prediction) ; supported report content (s) for the monitoring result report; supported maximum number of activated report configuration (s) for CSI prediction inference or monitoring per component carrier (CC) or across CCs in a band or band combination; supported maximum number of configured report configuration (s) for CSI prediction inference or monitoring per CC or across CCs in a band or band combination.
[0046] Based on the UE capabilities, the network entity 104 transmits 304, to the UE 102, (and the UE 102 receives 304 from the network entity 104) a control signaling configuring a first report configuration for performance monitoring including at least one CMR, configuring a second report configuration for model inference including at least one CMR, and optionally configuring a linkage between the first and second report configurations.
[0047] The network entity 104 may transmit the control signaling via radio resource control (RRC) signaling, e.g., RRCReconfiguration. In some implementations, the network entity 104 may configure at least one inference related parameters for CSI prediction in the control signaling, e.g., a subset of parameters in the report configuration. In response to the control signaling, the UE 102 may report the applicable inference related parameter (s) to the network entity 104. The network entity 104 may configure full parameters or remaining parameters for the report configuration (s) for inference or monitoring for CSI prediction in another control signaling, e.g., a control signaling after receiving the UE report of the applicable inference parameters for CSI prediction.
[0048] The network entity 104 may provide some of the configurations or update some of the configurations in the control signaling 304 by medium access control (MAC) control element (CE) , e.g., MAC CE activating the (semi-persistent) report, or downlink control information (DCI) , e.g., different triggering states for the DCI triggering the (aperiodic) report may correspond to different configurations.
[0049] The network entity 104 and UE 102 may perform 306 activation or deactivation of the first or second report configuration. For example, the network entity 104 may transmit a control signaling activating or deactivating the configured first or second report configuration. Alternatively, the UE 102 may report the activation or deactivation status for the first and / or second report configuration.
[0050] The UE 102 receives 308, from the network entity 104 (and the network entity 104 transmits 308 to the UE 102) one or more transmission occasion of CMRs configured in the first or second report configuration.
[0051] After receiving the one or more transmission occasion of CMRs configured in the first and / or second report configuration, the UE 102 performs 309 a performance monitoring of the model inference. The performance monitoring may be referred to as model monitoring.
[0052] Then, the UE 102 transmits 310, to the network entity 104, (and the network entity 104 receives 310 from the UE 102) a report including the monitoring results for the first report configuration and optionally include the inference results for the second report configuration.
[0053] After that, the network entity 104 and UE 102 may perform 312 further activation or deactivation or update of the first and / or second report configuration.
[0054] In this disclosure, unless specified, an RRC signaling may indicate a RRC reconfiguration message from a network entity 104 to UE 102, or a system information block (SIB) , where the SIB can be an existing SIB (e.g., SIB1) or a new SIB (e.g., SIB J, where J is an integer above 21) transmitted by the network entity 104. In some implementations, the network entity 104 may receive the UE capability from a UE 102 or from a core network (e.g., access and mobility management function (AMF) ) or another network entity.
[0055] In some aspects, the UE 102 may perform a sliding window based CSI prediction. FIG. 4A illustrates an example 400 of a sliding window based CSI prediction according to an embodiment. As shown in FIG. 4A, the UE 102 may perform the CSI prediction 412 based on the most recent K CMR transmission occasions before the CSI reference resource 409. The UE 102 may perform CSI measurements at slot (s) 402A, 404A, 406A (e.g., measured CSI 1, measured CSI 2, …measured CSI K) within the measurement window 408. The CSI measurements 402A, 404A, 406A are the inputs to the ML based CSI prediction model 412 to predict the CSIs (e.g., 402B, 404B, 406B) in future slot (s) (e.g., predicted CSI 1, predicted CSI 2, …predicted CSI N) within the prediction window 410.
[0056] FIG. 4B illustrates an example 450 of a non-sliding window based CSI prediction according to an embodiment. For the non-sliding window based CSI prediction, the UE 102 may perform the CSI prediction 462 within a prediction window 460 based on the K CMR transmission occasions in the most recent measurement window 458 for the CMR (s) before the CSI reference resource 459 as shown in FIG. 4B. The UE 102 may perform CSI measurements at slot (s) 452A, 454A, 456A (e.g., measured CSI 1, measured CSI 2, …measured CSI K) within the measurement window 458. The UE 102 uses CSI prediction 462 to predict the CSIs (e.g., 452B, 454B, 456B) in future slot (s) (e.g., predicted CSI 1, predicted CSI 2, …predicted CSI N) within the prediction window 460.
[0057] While the following descriptions are based on the sliding window based CSI prediction as described in connection with FIG. 4A, the following descriptions can be applied to the non-sliding window based CSI prediction. For the non-sliding window based CSI prediction, “the most recent Kp or Kp’ transmission occasions” can be replaced by “the Kp or Kp’ transmission occasions in the most recent measurement window” .
[0058] FIG. 5A illustrates an example 500 of report configuration for performance monitoring for CSI prediction according to an embodiment. As illustrated in FIG. 5A, a report configuration 502 for performance monitoring includes first CMR (s) for model inference 504, second CMR (s) for model monitoring 506, measurement window for model inference 508, measurement window for model monitoring 512, report quantity and report type for model monitoring 514, and frequency-domain granularity for model inference and monitoring 516. As shown, the report configuration 502 for performance monitoring may optionally include prediction window for model inference 510 and event configuration for event triggered performance monitoring report 518.
[0059] In an embodiment, the network entity 104 may configure a report configuration for performance monitoring to include information including at least one of: a first list of synchronization signal block (SSB) or CSI-RS resources or SSB or CSI-RS resource sets for model inference (first CMR (s) ) , one CMR may refer to one or multiple SSB / CSI-RS resources or resource sets for channel measurement; a second list of SSB or CSI-RS resources or SSB or CSI-RS resource sets for model monitoring (second CMR (s) ) ; measurement window for model inference, e.g., the number of transmission occasions for the first CMRs for measurement, the location of the last or first transmission occasions for the first CMRs for measurement; prediction window for model inference, e.g., slots for predicted CSI (s) , which may be the same as the measurement window for model monitoring; measurement window for model monitoring, e.g., the number of transmission occasions for the second CMRs for measurement, the location of the last or first transmission occasions for the second CMRs for measurement; report quantity, e.g., square ground-truth cosine similarity (SGCS) between the predicted CSI for model inference and measured CSI for model monitoring, channel quality (e.g., CQI, layer-1 signal-to-interference-plus-noise ratio (L1-SINR) , layer-1 reference signal received power (L1-RSRP) ) or channel quality offset based on predicted CSI for model inference and measured CSI for model monitoring, whether the predicted CSI meets the criteria for in-sync or out-of-sync; frequency granularity for the model inference / monitoring, e.g., wideband CSI or CSI for one or multiple subband (s) , subband size (number of resource blocks (RBs) per subband) ; time-domain behavior for the performance monitoring report, e.g., aperiodic, semi-persistent, periodic or event triggered; configuration for event detection, e.g., counter / timer / threshold (s) for the event detection to trigger the report, time-domain window for the event detection; whether the CSI prediction is sliding or non-sliding prediction.
[0060] In some implementations, the network entity 104 may configure the report configuration 502 for performance monitoring using, e.g., CSI-ReportConfig. Then, the network entity 104 may configure or trigger the corresponding report via RRC signaling, MAC-CE, or DCI, for the UE to report the results for performance monitoring.
[0061] In some implementations, the network entity 104 may configure the UE 102 to measure (K+N) transmission occasions of CMR in the measurement window. The network entity 104 may configure the UE 102 to measure the first K transmission occasions in the measurement window for inference, and to predict N CSIs in the slot for the remaining transmission occasions in the measurement window. The UE 102 may measure N CSIs for the remaining transmission occasions in the measurement window as the measured CSIs for monitoring.
[0062] FIG. 5B illustrates an example 550 for an example 550 of linked report configurations for performance monitoring for CSI prediction. In some implementations, the network entity 104 may configure the information for the report configuration as described above using two linked report configurations, e.g., CSI-ReportConfig, as shown in FIG. 5B. As illustrated in FIG. 5B, the first report configuration 552A includes the configurations for model inference and the second report configuration 552B includes the configurations for model monitoring.
[0063] As shown in FIG. 5B, the first report configuration 552A (with ID = x) includes first CMR (s) for model inference 554; codebook configuration including the measurement window, prediction window, and codebook for PMI prediction 570; report quantity and report type for model inference 564A; and frequency-domain granularity for model inference 566A. The first report configuration 552A may optionally include CSI prediction scheme (AI / ML based scheme or non-AI / ML based scheme) 574.
[0064] As further illustrated in FIG. 5B, the second report configuration 552B includes linked report configuration ID = x 572; measurement window for model monitoring 558; and report quantity and report type for model monitoring 564B. The second report configuration 552B may optionally include second CMR (s) for model monitoring 556, frequency-domain granularity for model monitoring 566B, and event configuration for event triggered performance monitoring report 568.
[0065] As shown, the linked report configuration ID = x 572 links the first report configuration 552A and the second report configuration 552B. Then, the network entity 104 may configure or trigger the first report configuration 552A or the second report configuration 552B or both linked reports via RRC signaling, MAC-CE, or DCI, for the UE 102 to report the results for model inference, performance monitoring or both. The network entity 104 may configure the first report configuration 552A and the second report configuration 552B in the same BWP or serving cell. Alternatively, the network entity 104 may configure the first report configuration 552A and the second report configuration 552B in different BWPs or serving cells. The network entity 104 may configure the first CMR (s) and the second CMR (s) in the same BWP or serving cell. Alternatively, the network entity 104 may configure the first CMR (s) and the second CMR (s) in different BWPs or serving cells.
[0066] In some implementations, the network entity 104 may configure the CSI report configuration for model inference whether the CSI prediction is based on the AI / ML or not. In one example, the network entity 104 may configure whether an enhanced CSI processing unit (eCPU) is occupied or not or configure the number of occupied eCPUs for a CSI report configuration for the CSI prediction. In another example, the network entity 104 may configure the minimum processing delay for the CSI prediction, where a first minimum processing delay may correspond to non-AI / ML based CSI prediction and a second minimum processing delay may correspond to the AI / ML based CSI prediction. In another example, the network entity 104 may configure whether additional processing delay for the CSI prediction is enabled or not. For AI / ML based CSI prediction, the additional processing delay may be enabled.
[0067] Alternatively, if a CSI report configuration for model inference linked with the report configuration for performance monitoring, the network entity 104 and the UE 102 may determine the CSI report configuration for model inference is based on the AI / ML; otherwise, the network entity 104 and the UE 102 may determine it is based on the non-AI / ML.
[0068] In some implementations, the network entity 104 may configure the time-domain behavior for the linked report configurations based on at least one of: aperiodic report for model inference and aperiodic report for model monitoring; aperiodic report for model inference and semi-persistent report for model monitoring; aperiodic report for model inference and periodic report for model monitoring; aperiodic report for model inference and event-triggered report for model monitoring; semi-persistent report for model inference and aperiodic report for model monitoring; semi-persistent report for model inference and semi-persistent report for model monitoring; semi-persistent report for model inference and periodic report for model monitoring; semi-persistent report for model inference and event-triggered report for model monitoring; periodic report for model inference and aperiodic report for model monitoring; periodic report for model inference and semi-persistent report for model monitoring; periodic report for model inference and periodic report for model monitoring; or periodic report for model inference and event-triggered report for model monitoring.
[0069] In some embodiments, the UE 102 may indicate the supported combination (s) for the above described the time-domain behavior for the linked report configuration in the UE capability.
[0070] In some implementations, the network entity 104 may trigger the linked report configurations in a joint triggering mode. Thus, the network entity 104 may trigger the linked report by a control signaling, e.g., RRC signaling, MAC-CE, or DCI. Then, the UE 102 may transmit the report including the results for both model inference and model monitoring.
[0071] In some other implementations, the network entity 104 may trigger the linked report configurations in separate triggering mode. Thus, the network entity 104 may trigger the first report configuration (for model inference) using a first control signaling, e.g., a first RRC signaling, MAC-CE, or DCI and trigger the second report configuration (for model monitoring) using a second control signaling, e.g., a second RRC signaling, MAC-CE, or DCI. The UE 102 may calculate the results for the second report configuration based on the measured or reported results corresponding to the first report configuration.
[0072] FIG. 6A illustrates an example 600 for monitoring report for performance monitoring for CSI prediction according to an embodiment. As shown in FIG. 6A, the UE 102 may perform CSI measurements at slot (s) 602A, 604A, 606A (e.g., measured CSI 1, measured CSI 2, …measured CSI K) within the measurement window 608 for input to the CSI prediction model 612 to predict the CSIs (e.g., 602B, 604B, 606B) in future slot (s) (e.g., predicted CSI 1, predicted CSI 2, …predicted CSI N) within the prediction window for inference and measurement window for monitoring 610. In one example, as shown in FIG. 6A, the UE 102 may calculate the results for the second report configuration based on the measured or reported results for the most recent first report X symbols / slots / milli-seconds before the second control signaling or before the second CMR (s) , where the value of X may be predefined, e.g., X= 0, or configured by the network entity 104, or reported by the UE 102.
[0073] As illustrated in FIG. 6A, the prediction window for the inference is the same as the measurement window for the monitoring. In other examples, the prediction window for the inference and the measurement window for the monitoring are different, e.g., the measurement window for monitoring is part of the prediction window for the inference. The overlapping part between the measurement window for monitoring and the prediction window for the inference may be continuous or non-continuous duration in time domain.
[0074] Regarding the UE memory, the maximum duration for the UE 102 to store the CSI report for inference results may be predefined or reported by the UE capability. The UE 102 may flush the memory for the stored CSI report after the memory reaches the maximum duration for the storing. Then, for a monitoring report, if the UE 102 cannot identify a stored CSI report for inference, the UE 102 may drop the monitoring report or may report outdated results.
[0075] FIG. 6B illustrates an example 650 for monitoring report based on flexible timing of the CMR according to an embodiment. In some implementations, as shown in FIG. 6B, to align the timing for the CSI prediction 662 and CSI measurement for monitoring, the network entity 104 may configure or indicate additional slot offset (e.g., CMR with additional offset 1 666 and CMR with additional offset 2 668) for the CMR (s) for the CSI measurement for monitoring by RRC signaling, MAC-CE, or DCI. Alternatively, the network entity 104 may configure multiple sets of CMR (s) (e.g., CMR set 1 666 and CMR set 2 668) for the CSI measurement for monitoring, where different CMR sets may correspond to different time-domain location, and indicate one of CMR sets for a monitoring results report 664. In some implementations, the network entity 104 and UE 102 may determine the CMR set for the measurement for monitoring based on the reported CSI for CSI prediction. As shown in FIG. 6B, the UE 102 may perform CSI measurements at slot (s) 652A, 654A, 656A within the measurement window 658. The CSI measurements 652A, 654A, 656A are the inputs to the ML based CSI prediction model 662 to predict the CSIs (e.g., 652B, 654B, 656B) in future slot (s) within the prediction window for inference and measurement window for monitoring 660. As illustrated in FIG. 6B, the network entity 104 and UE 102 may determine the first CMR set (e.g., CMR set 1) 666 is used for the measurement for monitoring.
[0076] In some implementations, the network entity 104 may configure whether the triggering of the linked report configurations for performance monitoring is based on joint triggering or separate triggering.
[0077] FIG. 7A illustrates an example 700 for the inference and monitoring based on the same CMR (s) according to an embodiment.
[0078] In some implementations, the first CMRs and the second CMRs may be identical. Thus, the network entity 104 may configure the first CMR (s) and the network entity 104 and UE 102 may determine the second CMR (s) should be the same as the first CMR(s) . In one example, the first and second CMRs are based on the same periodic or semi-persistent CSI-RSs. Then, the network entity 104 may configure which transmission occasions of the CMR (s) are in the measurement window and which are in the prediction window. Optionally, the network entity 104 may indicate whether the CMR (s) in the prediction window is transmitted or not on the corresponding transmission occasion (s) . For example, the network entity 104 may not always transmit the CMR (s) in the prediction window. When some triggering condition (s) is met, e.g., the network entity 104 determines that the performance is below a predefined threshold (e.g., becomes worse) , or the predicted result (s) is below a predefined threshold (e.g., becomes worse) , the network entity 104 may start the transmission of the CMR (s) in the prediction window for the UE 102 to perform performance monitoring.
[0079] Then, as shown in FIG. 7A, the UE 102 can measure the transmission occasions of the CMR in measurement window 708 for model inference. For example, the UE 102 may perform CSI measurements at slot (s) 702A, 704A, 706A (e.g., measured CSI 1, measured CSI 2, …measured CSI K) within the measurement window 708. The UE 102 can perform CSI prediction 712 to predict CSIs 702B, 704B, 706B (e.g., predicted CSI 1, predicted CSI 2, …predicted CSI N) in the prediction window 710 and measure the transmission occasions of the CMR (e.g., measured CSI 1, measured CSI 2, …measured CSI N) in the prediction window 710. Then, the UE 102 can transmit the monitoring results based on the predicted CSI and measured CSI (e.g., 702B, 704B, 706B) in the prediction window 710.
[0080] FIG. 7B illustrates an example 750 for the inference and monitoring based on different CMR (s) according to an embodiment.
[0081] In some other implementations, the first CMRs and the second CMRs may be based on different downlink-reference signal (DL-RS) resources. The network entity 104 may configure the same value for the first and second CMRs based on at least one of: serving cell, bandwidth part (BWP) , bandwidth, RBs, subcarriers, power offset between the CSI-RS and SSB, power offset between the CSI-RS and physical downlink shared channel (PDSCH) , number of ports, intervals between every two consecutive CMRs, time-domain behavior (e.g., aperiodic, semi-persistent, or periodic) , transmission configuration indicator / quasi-co-location (TCI / QCL) configuration.
[0082] In one example, the first and / or second CMR (s) may be aperiodic CSI-RS (s) . The network entity 104 may transmit the second CMRs in the prediction window 760 in the same slots for CSI prediction and the first CMRs in the measurement window 758. As shown in FIG. 7B, for example, the UE 102 may perform CSI measurements at slot (s) 752A, 754A, 756A (e.g., measured CSI 1, measured CSI 2, …measured CSI K) within the measurement window 758. Then, the UE 102 may calculate the predicted CSI (e.g., predicted CSI 1, predicted CSI 2, …predicted CSI N) using CSI prediction 762 and based on the first CMRs (e.g., CMR 1, CMR 2, …CMR K) . The UE 102 may calculate the measured CSI for monitoring (e.g., measured CSI 1, measured CSI 2, …measured CSI N) based on the second CMRs (e.g., CMR K+1, CMR K+2, …CMR K+N) . Then, the UE 102 can transmit the monitoring results based on the predicted CSI and measured CSI (e.g., 752B, 754B, 756B) in the prediction window 760.
[0083] In some implementations, the measurement window for monitoring and the prediction window for inference may be fully or partially overlapped. In some aspects, the transmission occasions of the second CMRs in the measurement window for monitoring may be based on the slots for the CSI prediction in the prediction window. Thus, the UE 102 and network entity 104 may determine the prediction window based on the measurement window for monitoring.
[0084] In an embodiment, for performance monitoring for CSI prediction, the UE 102 may report at least one of: SGCS (s) between the measured CSI (s) for monitoring and predicted CSI (s) for inference; CQI / L1-RSRP / L1-SINR for the measured CSI (s) for monitoring; CQI / L1-RSRP / L1-SINR for the predicted CSI (s) for inference; CQI / L1-RSRP / L1-SINR offset between the measured CSI (s) for monitoring and predicted CSI (s) for inference; whether the performance for CSI prediction is out-of-sync or in-sync; whether the CSI prediction fails or not, e.g. ; whether the CSI prediction is applicable or not, measured wideband / subband RI / PMI / CQI for one or multiple slots in the measurement window for monitoring; or predicted wideband / subband RI / PMI / CQI for one or multiple slots in the prediction window for monitoring.
[0085] In some implementations, the UE 102 may report the SGCS per layer (or for one layer, e.g., the first layer) , and / or per subband, and / or per predicted / measured CSI pair. In some other implementations, the UE 102 may report the average / minimum / maximum SGCS across layers and / or subbands and / or predicted / measured CSI pairs. In one example, for layer k, the UE 102 calculate the SGCS between measured CSI m and predicted CSI n as follows: where S indicates the number of subbands; wm, s, k indicates the measured or quantized precoder corresponding to CSI m, subband s and layer k; AHindicates the conjugate transpose of matrix A.
[0086] In some implementations, if the average or minimum or maximum or one or multiple of the SGCS or CQI / L1-RSRP / L1-SINR offset between the measured CSI (s) for monitoring and predicted CSI (s) for inference is above a first threshold, the UE 102 may determine the CSI prediction is in-sync; otherwise, the UE 102 may determine the CSI prediction is out-of-sync. In some aspects, if the average or minimum or maximum or one or multiple of the SGCS or CQI / L1-RSRP / L1-SINR offset between the measured CSI (s) for monitoring and predicted CSI (s) for inference is below a second threshold, the UE may determine the CSI prediction is out-of-sync. The threshold (s) above may be predefined or configured by the network entity 104 or reported by the UE 102.
[0087] In some implementations, if the UE 102 detects X or more than X out-of-sync within a time window predefined or configured by the network entity 104, the UE 102 may determine the performance failure for the CSI prediction; otherwise, the UE 102 may determine the performance success for the CSI prediction. In some aspects, if the UE 102 detects Y or more than Y in-sync within a time window predefined or configured by the network entity 104, the UE 102 may determine the performance success for the CSI prediction. The value of X and Y may be predefined or configured by the network entity 104 or reported by the UE 102.
[0088] In an embodiment, for the model inference, the UE 102 may report at least one of: predicted RI; predicted wideband / subband PMI (s) for one or multiple slots in the prediction window; or predicted wideband / subband CQI (s) for one or multiple slots in the prediction window.
[0089] In some implementations, when the UE 102 is triggered to report the results for the linked report configurations for the model inference and model monitoring, the UE 102 may report the results above for model monitoring and / or the results above for model inference.
[0090] In an embodiment, when the UE 102 is configured with cell discontinuous transmission (DTX) and the cell DTX is activated, the UE 102 may report the inference results corresponding to the report configuration for model inference after the UE 102 receives Kp transmission occasions for the CMRs in the active period (s) of the cell DTX. Kp may indicate the number of measured transmission occasions for the measurement window. Kp may be configured by the network entity 104 or reported by the UE 102 or predefined. The UE 102 may drop the report or report outdated results, if the UE 102 fails to receive Kp transmission occasions for the CMRs in the active period (s) of the cell DTX.
[0091] In an example, for the CSI report configuration in CSI-ReportConfig configured with the codebookType set to ‘typeII-Doppler-r18’ or ‘typeII-Doppler-PortSelection-r18’ , the UE 102 reports a CSI report only if the UE 102 receives at least Kp CSI-RS transmission occasions of each periodic CSI-RS resource or semi-persistent CSI-RS resource on a serving cell with cell DTX activated, which is defined in 3GPP TS 38.321, for channel measurement and / or interference measurement in active periods of cell DTX of the serving cell no later than CSI reference resource, and the UE 102 drops the CSI report otherwise.
[0092] The CSI reference resource is defined in 3GPP TS 38.214 section 5.2.2.5. In some implementations, the network entity 104 and UE 102 may determine CSI reference resource based on the minimum processing delay for the corresponding report and the report slot. In one example, if the first slot for the report is slot n, the CSI reference resource is in slot n-Zref’ .
[0093] In another example, if the higher layer parameter timeRestrictionForChannelMeasurements in CSI-ReportConfig is set to "Configured"and the CSI report configuration in CSI-ReportConfig configured with the codebookType set to 'typeII-Doppler-r18'or 'typeII-Doppler-PortSelection-r18'a nd periodic or semi-persistent CSI-RS resource (s) for channel measurement, the UE shall derive the channel measurements for computing CSI reported in uplink slot n based on only the most recent, no later than the CSI reference resource, in cell DTX active period of a serving cell if cell DTX is activated, Kp occasions of NZP CSI-RS, which is defined in 3GPP TS 38.211, associated with the CSI resource setting on the serving cell.
[0094] In some implementations, when the UE 102 is configured with cell DTX and the cell DTX is activated, the UE 102 may report the monitoring results corresponding to the report configuration for model monitoring if at least one of the condition occurs: the UE 102 receives Kp transmission occasions for the CMRs in the measurement window for inference in the active period (s) of the cell DTX; or the UE 102 receives Kp’transmission occasions for the CMRs in the measurement window for monitoring in the active period (s) of the cell DTX, where Kp’ may be configured by the network entity 104 or reported by the UE 102 or predefined. The UE 102 may drop the report or report outdated monitoring results, otherwise.
[0095] In an embodiment, the UE 102 may report the monitoring results if at least one of the condition occurs: the UE 102 receives Kp transmission occasions for the CMRs in the measurement window for inference in the active time of discontinuous reception (DRX) after CSI report (re) configuration, serving cell activation, BWP change, or activation of semi-persistent CSI (SP-CSI) ; or the UE 102 receives Kp’ transmission occasions for the CMRs in the measurement window for monitoring in the active time of the DRX after CSI report (re) configuration, serving cell activation, BWP change, or activation of SP-CSI. The UE 102 may drop the report or report outdated monitoring results, otherwise.
[0096] In one possible implementation, if the prediction window or monitoring window is in the inactive time of cell DTX, the UE 102 may drop the measurement results derived in the measurement window related to the prediction window, or stop prediction in the prediction window, or stop monitoring in the monitoring window.
[0097] In another embodiment, the UE 102 may receive the CMRs for the model inference and / or model monitoring during the inactive period (s) of the cell DTX or the inactive time of the DRX. The UE 102 may report whether the UE 102 supports to measure the CMRs for the model inference and / or model monitoring during the inactive period (s) of the cell DTX or the inactive time of the DRX. The network entity 104 may configure whether the UE 102 shall measure the CMRs for the model inference and / or model monitoring during the inactive period (s) of the cell DTX or the inactive time of the DRX.
[0098] In an embodiment, the UE 102 may transmit the monitoring results and / or the inference results as described above via: RRC message, e.g., UAI; MAC-CE on configured grant-physical uplink shared channel (CG-PUSCH) , dynamic grant-physical uplink shared channel (DG-PUSCH) or PUSCH scheduled by random access response (RAR) or PUSCH for MsgA, or uplink control information (UCI) on physical uplink control channel (PUCCH) configured or scheduled by the network entity 104 or CG-PUSCH, DG-PUSCH or PUSCH scheduled by RAR or PUSCH for MsgA.
[0099] When transmitting the results as UCI, the UE 102 may transmit the UCI based on a single CSI part in short PUCCH, e.g., PUCCH with less than 4 symbols, and may transmit the UCI on CSI part 1 or CSI part 2 or both CSI part 1 and 2 in long PUCCH, e.g., PUCCH with 4 or more than 4 symbols, or PUSCH.
[0100] The network entity 104 may configure the UE 102 to transmit the report in periodic, semi-persistent, or aperiodic manner.
[0101] Alternatively, the UE 102 may transmit the report based on event triggered manner. Thus, the UE 102 may transmit the report when the UE 102 detects at least one of: the UE detects X out-of-sync for a CSI prediction within a time window; the UE detects Y in-sync for a CSI prediction within a time window; a prohibit timer for the monitoring results report for a CSI prediction is outdated; the change of the average / minimum / maximum or one or multiple of the SGCS or CQI / L1-RSRP / L1-SINR offset between the measured CSI (s) for monitoring and predicted CSI (s) for inference is above a threshold Z; the SGCS (s) between the measured CSI (s) for monitoring and predicted CSI (s) for inference is below or equals to a threshold L; the prediction accuracy is below or equals to a threshold M; or the difference of the predicated beam information and the measured one is above or equals to a threshold N. The value of X / Y / Z / L / M / N may be predefined or configured by the network entity 104 or reported by the UE 102. The UE 102 may start or restart the prohibit timer after the report configuration for monitoring is configured or activated. The UE 102 may reset the prohibit timer after it transmit the report for the monitoring.
[0102] For event triggered manner, the UE 102 may transmit an uplink channel, e.g., PUCCH / PUSCH / PRACH, to request the uplink resource for the report or notify the transmission of the report to the network entity 104, where the network entity may configure the resource for the uplink channel.
[0103] In an embodiment, for the configured or activated report configuration for inference / monitoring results report, the network entity 104 and UE 102 may determine the number of occupied CSI processing units (CPUs) based on at least one of: number of transmission occasions for the CMR for the measurement of inference (K) ; or number of transmission occasions for the CMR for the measurement of monitoring (N) .
[0104] In one example, the number of CPUs is aK+bN+c, where {a, b, c} may be predefined or reported by the UE 102 or configured by the network entity 104. In another example, the number of CPUs is max {aK, bN} +c or min {aK, bN} +c.
[0105] The network entity 104 and UE 102 may determine the number of eCPUs for inference based on the value of K and N, e.g., aK+bN+c, max {aK, bN} +c or min {aK, bN} +c, or a pre-defined value, e.g., 1, or a value reported by the UE 102 or configured by the network entity 104.
[0106] If the number of CPUs or number of eCPUs exceeds the maximum number of CPUs or eCPUs predefined or reported by the UE 102 or configured by the network entity 104, the UE 102 may drop the report or report outdated results for the CSI report configuration.
[0107] In an embodiment, when the CSI request field on a DCI triggers a CSI report (s) on PUSCH, if the first uplink symbol to carry the corresponding CSI report (s) including the effect of the timing advance, starts earlier than at symbol Zref, the UE 102 may ignore the scheduling DCI if no HARQ-ACK or transport block is multiplexed on the PUSCH.
[0108] When the CSI request field on a DCI triggers a CSI report (s) on PUSCH, if the first uplink symbol to carry the n-th CSI report including the effect of the timing advance, starts earlier than at symbol Z'ref (n) , the UE may ignore the scheduling DCI if the number of triggered reports is one and no hybrid automatic repeat request acknowledgment (HARQ-ACK) or transport block is multiplexed on the PUSCH; otherwise, the UE 102 is not required to update the CSI for the n-th triggered CSI report.
[0109] The network entity 104 and UE 102 may determine the value of {Zref, Z'ref } for the CSI report for the inference / monitoring based on at least one of: number of transmission occasions for the CMR for the measurement of inference (K) ; maximum or minimum or reference interval between every two transmission occasions for the CMR for the measurement of inference (T) ; number of transmission occasions for the CMR for the measurement of monitoring (N) ; or maximum or minimum or reference interval between every two transmission occasions for the CMR for the measurement of monitoring (Q) .
[0110] In one example, Zref = Z+ (K-1) T+ (N-1) Q, Z'ref =Z’ , where {Z, Z’ } may denote the minimum processing delay for the CSI report, e.g., {Z, Z’ } = {Z2, Z2’ } defined in 3GPP TS 38.214 section 5.4. In another example, the UE 102 may report the UE capability on the minimum processing delay for the CSI report.
[0111] In an embodiment, for a CSI report configuration for model inference and / or model monitoring for the CSI prediction, the network entity 104 may further configure the activation / deactivation status.
[0112] The network entity 104 may transmit a control signaling for the CSI report configuration activation / deactivation, the control signaling configuring at least one of: serving cell index for the target CSI report configuration (s) ; BWP index for the target CSI report configuration (s) ; CSI report configuration ID (s) for the target CSI report configuration (s) ; or activation / deactivation status for the target CSI report configuration (s) .
[0113] The network entity 104 may transmit the control signaling by RRC signaling, MAC-CE, or DCI. The network entity 104 and UE 102 may apply the control signaling after Y symbols / slots / milli-seconds (ms) after receiving the last symbol of the PDSCH / PDCCH with the control signaling or transmitting the last symbol of the PUCCH or PUSCH with the ACK of the PDSCH / PDCCH with the control signaling. The value of Y may be pre-defined, e.g., Y = 3ms or 28 symbols, or configured by the network entity 104 or reported by the UE 102.
[0114] In some implementations, before receiving the activation or deactivation signaling for a CSI report configuration for model inference and / or model monitoring for the CSI prediction, the network entity 104 and UE 102 may determine its activation or deactivation status based on a default state. The default activation or deactivation status may be predefined, e.g., activated / deactivated, or configured by the network entity 104, or reported by the UE 102, or determined based on the time-domain behavior for the CSI report configuration. For example, the default status for the periodic CSI report configuration is ‘activated’ , and the default status for the semi-persistent / aperiodic CSI report configuration is ‘deactivated’ .
[0115] In some implementations, the network entity 104 may configure whether the dynamic activation / deactivation for a CSI report configuration is enabled or not.
[0116] In some implementations, for the linked CSI report configuration for model inference and monitoring, if one of the linked CSI report configurations is deactivated, the network entity 104 and UE 102 may determine the linked CSI report configurations are deactivated. In one example, if the CSI report configuration for inference is deactivated, the network entity 104 and UE 102 may determine the CSI report configuration for monitoring is deactivated.
[0117] In some implementations, the network entity 104 may configure a time window indicating how long the activation or deactivation status for the report configuration will last. After the time window, a default activation or deactivation status may be applied to the report configuration.
[0118] In an embodiment, for a CSI report configuration for model inference and / or model monitoring for the CSI prediction, the UE 102 may further report whether the report configuration is applicable / activated or not. The network entity 104 and UE 102 may determine the activation / deactivation status for the CSI report configuration based on the UE report.
[0119] The UE 102 may transmit the report by RRC signaling, e.g., UAI, MAC-CE, or UCI. The network entity 104 and UE may apply the UE report after Y’ symbols / slots / ms after the last symbol of the PUSCH / PUCCH with the control signaling. Alternatively, the network entity 104 may transmit a response to the UE 102 report by PDSCH / PDCCH. Then, the network entity 104 and UE 102 may apply the UE report after Y’s ymbols / slots / ms after the last symbol of the PDSCH / PDCCH with the response. The value of Y’ may be pre-defined, e.g., Y’ = 3ms or 28 symbols, or configured by the network entity 104 or reported by the UE 102.
[0120] In some implementations, the network entity 104 may configure whether the UE 102 report based dynamic activation / deactivation for a CSI report configuration is enabled or not.
[0121] In some implementations, the UE 102 may report a time window indicating how long the activation / deactivation status for the report configuration will last. After the time window, a default activation / deactivation status may be applied to the report configuration.
[0122] In an embodiment, for a CSI report configuration for model inference and / or model monitoring for the CSI prediction, the network entity 104 or the UE 102 may determine the CSI report configuration is deactivated if at least one of the condition occurs: the serving cell for the CSI report configuration is deactivated; the BWP for the CSI report configuration is deactivated; the CMR (s) for the CSI report configuration is deactivated; a timer for the CSI report configuration expires; the beam or link quality, e.g., L1-RSRP / L1-SINR / L3-RSRP / L3-SINR / RSRQ, for at least one DL-RS, e.g., CMR, or serving cell is below a threshold, where the threshold may be predefined or configured by the network entity 104 or reported by the UE 102; or the change of beam or link quality, e.g., L1-RSRP / L1-SINR / L3-RSRP / L3-SINR / RSRQ, for at least one DL-RS, e.g., CMR, or serving cell is below or above a threshold, where the threshold may be predefined or configured by the network entity 104 or reported by the UE 102.
[0123] Common or separate conditions or configurations as described above may be applied to determine whether to activate or deactivate the report configuration for inference or monitoring. In some implementations, if the CSI prediction accuracy, e.g., SGCS / CQI, is better than a threshold, e.g., the network entity 104 or the UE 102 may determine the corresponding report configuration for monitoring is deactivated, e.g., within a time window configured by the network entity 104 or predefined or reported by the UE 102. In some other implementations, if the bean or link quality for a DL-RS or current serving cell is below another threshold, the network entity 104 or the UE 102 may determine the corresponding report configuration for the inference or monitoring is deactivated.
[0124] The UE 102 may start or restart a timer for the CSI report configuration after the CSI report configuration is configured or activated. The UE 102 may reset the timer after transmitting a report for the CSI report configuration or after receiving a control signaling triggering the report. The UE 102 may stop the timer for the CSI report configuration after the CSI report configuration is deactivated. In some implementations, when the timer expires, the UE 102 may fallback to use non-AI / ML based CSI prediction.
[0125] For deactivated CSI report configuration, the UE 102 may drop the corresponding report or report outdated results. For activated CSI report configuration, the UE 102 may report the inference or monitoring results.
[0126] In an embodiment, for a CSI report configuration for CSI prediction, e.g., a codebook with PMI prediction is configured, the network entity 104 may configure whether the CSI prediction is based on AI / ML or non-AI / ML. To indicate whether the CSI prediction is based on AI / ML or non-AI / ML for the CSI report configuration, the network entity 104 may configure at least one of: whether eCPU is occupied or number of eCPUs. The network entity 104 or the UE 102 may determine the AI / ML based CSI prediction is enabled if at least one eCPU is occupied, and may determine the non-AI / ML based CSI prediction is enabled otherwise; additional processing delay for the CSI report. The network entity 104 or the UE 102 may determine the AI / ML based CSI prediction is enabled if the additional processing delay is not zero, and may determine the non-AI / ML based CSI prediction is enabled otherwise; whether a report configuration for monitoring is linked or not. The network entity 104 or the UE 102 may determine the AI / ML based CSI prediction is enabled if a report configuration for monitoring is linked, and may determine the non-AI / ML based CSI prediction is enabled otherwise; or whether dynamic activation / deactivation is enabled or not. The network entity 104 or the UE 102 may determine the AI / ML based CSI prediction is enabled if dynamic activation / deactivation for the CSI report configuration is enabled, and may determine the non-AI / ML based CSI prediction is enabled otherwise.
[0127] The network entity 104 may provide the configuration above by RRC signaling, MAC-CE, or DCI. In the configuration, the network entity 104 may further configure the serving cell index, BWP index and CSI report configuration ID for the target CSI report configuration (s) for CSI prediction.
[0128] In some implementations, before receiving the CSI calculation information for a CSI report configuration for model inference and / or model monitoring for the CSI prediction, the network entity 104 and UE may determine the CSI calculation information is based on a default CSI calculation scheme. The default CSI calculation scheme may be predefined, e.g., AI / ML based or non-AI / ML based, or configured by the network entity 104, or reported by the UE 102, or determined based on the time-domain behavior for the CSI report configuration. For example, the default CSI calculation for the periodic CSI report configuration is non-AI / ML based, and the default status for the semi-persistent / aperiodic CSI report configuration is AI / ML based.
[0129] FIG. 8 illustrates an example 800 for the CSI calculation scheme indicated by the network entity according to an embodiment. As illustrated in FIG. 8, the network entity 104 indicates the CSI calculation scheme for the configured CSI report configuration list 802 as “1001” . As shown, the CSI calculation scheme “1001” configures the CSI calculation scheme for the report configuration 1 804 and the report configuration 4 806 to be AI / ML based.
[0130] In an embodiment, for a CSI report configuration for CSI prediction, e.g., a codebook with PMI prediction is configured, the UE 102 may report whether the CSI report configuration is based on AI / ML or not.
[0131] In some implementations, the UE 102 may provide the information on whether a CSI is based on AI / ML or not by the CSI report. In one example, in the CSI report, the UE may report whether it is based on AI / ML or not.
[0132] In some other implementations, in the CSI report, the UE 102 may report two CSIs: the first CSI is based on AI / ML and the second CSI is based on non-AI / ML. The UE 102 may report absolute value for the two CSIs. In one example, the UE 102 may report common or separate RI for both CSIs, and PMI / CQI for each CSI. Alternatively, the UE 102 may report differential values for the two CSIs. In one example, the UE 102 may report common RI for both CSIs, separate PMIs for each CSI and absolute CQI for one CSI and differential CQI for the other CSI.
[0133] In some other implementations, the UE 102 may provide the information on whether a CSI report configuration is based on AI / ML or not by an RRC message, e.g., UAI or RRC reconfiguration complete, MAC-CE, or UCI. In one example, the network entity 104 may configure a list of CSI report configurations, and the UE 102 may report whether at least one of the CSI report configurations is based on AI / ML or not. The UE 102 may report the information on CSI calculation by at least one of: whether eCPU is occupied or number of eCPUs. The network entity 104 or the UE 102 may determine the AI / ML based CSI prediction is enabled if at least one eCPU is occupied, and may determine the non-AI / ML based CSI prediction is enabled otherwise; additional processing delay for the CSI report. The network entity 104 or the UE 102 may determine the AI / ML based CSI prediction is enabled if the additional processing delay is not zero, and may determine the non-AI / ML based CSI prediction is enabled otherwise; whether a linked report configuration for monitoring is activated or not. The network entity 104 or the UE 102 may determine the AI / ML based CSI prediction is enabled if a linked report configuration for monitoring is activated, and may determine the non-AI / ML based CSI prediction is enabled otherwise; whether the CSI report configuration can be activated / deactivated. The network entity 104 or the UE 102 may determine the AI / ML based CSI prediction is enabled if the CSI report configuration can be activated / deactivated, and may determine the non-AI / ML based CSI prediction is enabled otherwise.
[0134] In the report, the UE 102 may further report the serving cell index, BWP index and CSI report configuration ID for the target CSI report configuration (s) for CSI prediction.
[0135] In some implementations, before reporting the CSI calculation information for a CSI report configuration for model inference and / or model monitoring for the CSI prediction, the network entity 104 and UE 102 may determine the CSI calculation information is based on a default CSI calculation scheme. The default CSI calculation scheme may be predefined, e.g., AI / ML based or non-AI / ML based, or configured by the network entity 104, or reported by the UE 102, or determined based on the time-domain behavior for the CSI report configuration. For example, the default CSI calculation for the periodic CSI report configuration is non-AI / ML based, and the default status for the semi-persistent / aperiodic CSI report configuration is AI / ML based.
[0136] FIG. 9 illustrates an example 900 for the CSI calculation scheme reported by the UE according to an embodiment. The UE 102 may indicate a CSI report configuration is based on AI / ML or not. As shown in FIG. 9, for example, the UE 102 indicates the reported applicable AI / ML based CSI report of the configured CSI report configuration list 902 as “1001” . The reported applicable AI / ML based CSI report “1001” configures the CSI report configuration 1 904 and the CSI report configuration 4 906 to be AI / ML based.
[0137] FIGs. 2-9 illustrate various aspects of LCM for ML based CSI prediction that may be implemented in connection with aspects of one or more other figures described herein. FIGs. 10-11 show methods for implementing one or more aspects of FIGs. 2-9. In particular, FIG. 10 shows an implementation by the UE 102 of the one or more aspects of FIGs. 2-9. FIG. 11 shows an implementation by the network entity 104 of the one or more aspects of FIGs. 2-9.
[0138] FIG. 10 illustrates a flowchart 1000 of a method of wireless communication at a UE. With reference to FIGs. 1-9, the method may be performed by the UE 102. In embodiments, the UE 102 may transmit 1002, to the network entity104, a UE capability report. For example, referring to FIG. 3, the UE 102 transmits 302, to the network entity 104, a UE capability report indicating the supported features for life cycle management for model inference. The UE capability report indicates at least one of: a number of transmission occasions for the first CMR for the performance monitoring; a number of transmission occasions for the second CMR for the CSI prediction; a supported prediction window duration; a supported offset between the measurement window and the prediction window; a supported type of filtering; a supported time-domain behavior for the first CMR and second CMR; a supported time-domain behavior for the CSI report for CSI prediction and performance monitoring; a temporal pattern of the measurement and the CSI prediction; a supported report content for the performance monitoring information; a supported maximum number of activated report configurations for the CSI prediction or the performance monitoring per component carrier, CC, or across CCs in a band or band combination; or a supported maximum number of CSI report configurations for the CSI prediction or the performance monitoring per CC or across CCs in a band or band combination.
[0139] In embodiments, the UE 102 receives 1004, from the network entity 104, a first CSI report configuration for performance monitoring associated with a first CMR and a second CSI report configuration for CSI prediction associated with a second CMR. For example, referring to FIG. 3, the UE 102 receives 304 from the network entity 104, a control signaling configuring a first report configuration for performance monitoring including at least one CMR, configuring a second report configuration for model inference including at least one CMR, and optionally configuring a linkage between the first and second report configurations.
[0140] In embodiments, the UE 102 may perform 1006, with the network entity 104, a procedure for an activation or deactivation of at least one of the first CSI report configuration or the second CSI report configuration. For example, referring to FIG. 3, the network entity 104 and UE 102 performs 306 activation or deactivation of the first or second report configuration.
[0141] In embodiments, the UE 102 receives 1008, from the network entity, a first CSI-RS on the first CMR, and a second CSI-RS on the second CMR. For example, referring to FIG. 3, the UE 102 receives 308, from the network entity 104 one or more transmission occasion of CMRs configured in the first or second report configuration.
[0142] In embodiments, the UE 102 transmits 1010, to the network entity 104, a CSI report based on the first CSI report configuration, the CSI report including performance monitoring information for the first CMR, the performance monitoring information being associated with the CSI prediction for the second CMR. For example, referring to FIG. 3, the UE 102 transmits 310, to the network entity 104, a report including the monitoring results for the first report configuration and optionally include the inference results for the second report configuration.
[0143] In embodiments, the UE 102 may perform 1012, with the network entity 104, a procedure for an activation or deactivation of at least one of the first CSI report configuration or the second CSI report configuration. For example, referring to FIG. 3, the UE and the network entity 104 perform 312 further activation or deactivation or update of the first or second report configuration.
[0144] FIG. 10 describes a method from a UE-side of a wireless communication link, whereas FIG. 11 describes a method from a network-side of the wireless communication link.
[0145] FIG. 11 is a flowchart 1100 of a method of wireless communication at a network entity. With reference to FIGs. 1-9, the method may be performed by one or more network entities 104, which may correspond to a base station or a unit of the base station, such as the RU 106, the DU 108, and / or the CU 110. In embodiments, the network entity 104 may receive 1102, from a UE 102, a UE capability report. For example, referring to FIG. 3, the network entity 104 may receive 302 from the UE 102, a UE capability report indicating the supported features for life cycle management for model inference.
[0146] In embodiments, the network entity 104 transmits 1104, to the UE 102, a first channel state information, CSI, report configuration for performance monitoring associated with a first channel measurement resource, CMR, and a second CSI report configuration for CSI prediction associated with a second CMR. For example, referring to FIG. 3, the network entity 104 transmits 304, to the UE 102, a control signaling configuring a first report configuration for performance monitoring including at least one CMR, configuring a second report configuration for model inference including at least one CMR, and optionally configuring a linkage between the first and second report configurations.
[0147] In embodiments, the network entity 104 may perform 1106, with the UE 102, a procedure for an activation or deactivation of at least one of the first CSI report configuration or the second CSI report configuration. For example, referring to FIG. 3, the network entity 104 and UE 102 performs 306 activation or deactivation of the first or second report configuration.
[0148] In embodiments, the network entity 104 transmits 1108, to the UE 102, a first channel state information-reference signal, CSI-RS, on the first CMR, and a second CSI-RS on the second CMR. For example, referring to FIG. 3, the network entity 104 transmits 308 to the UE 102, one or more transmission occasion of CMRs configured in the first or second report configuration.
[0149] In embodiments, the network entity 104 receives 1110, from the UE 102, a CSI report based on the first CSI report configuration, the CSI report including performance monitoring information for the first CMR, the performance monitoring information being associated with the CSI prediction for the second CMR. For example, referring to FIG. 3, the network entity 104 receives 310, from the UE 102, a report including the monitoring results for the first report configuration and optionally include the inference results for the second report configuration.
[0150] In embodiments, the network entity 104 may perform 1112, with the UE 102, a procedure for an activation or deactivation of at least one of the first CSI report configuration or the second CSI report configuration. For example, referring to FIG. 3, the network entity 104 and the UE 102 perform 312 further activation or deactivation or update of the first or second report configuration.
[0151] A UE apparatus 1202, as described in FIG. 12, may perform the method of flowchart 1000. The one or more network entities 104, as described in FIG. 13, may perform the method of flowchart 1100.
[0152] FIG. 12 is a diagram 1200 illustrating an example of a hardware implementation for a UE apparatus 1202. The UE apparatus 1202 may be the UE 102, a component of the UE 102, or may implement UE functionality. The UE apparatus 1202 may include an application processor 1206, which may have on-chip memory 1206’ . In examples, the application processor 1206 may be coupled to a secure digital (SD) card 1208 and / or a display 1210. The application processor 1206 may also be coupled to a sensor (s) module 1212, a power supply 1214, an additional module of memory 1216, a camera 1218, and / or other related components. For example, the sensor (s) module 1212 may control a barometric pressure sensor / altimeter, a motion sensor such as an inertial management unit (IMU) , a gyroscope, accelerometer (s) , a light detection and ranging (LIDAR) device, a radio-assisted detection and ranging (RADAR) device, a sound navigation and ranging (SONAR) device, a magnetometer, an audio device, and / or other technologies used for positioning.
[0153] The UE apparatus 1202 may further include a wireless baseband processor 1226, which may be referred to as a modem. The wireless baseband processor 1226 may have on-chip memory 1226'. Along with, and similar to, the application processor 1206, the wireless baseband processor 1226 may also be coupled to the sensor (s) module 1212, the power supply 1214, the additional module of memory 1216, the camera 1218, and / or other related components. The wireless baseband processor 1226 may be additionally coupled to one or more subscriber identity module (SIM) card (s) 1220 and / or one or more transceivers 1230 (e.g., wireless RF transceivers) .
[0154] Within the one or more transceivers 1230, the UE apparatus 1202 may include a Bluetooth module 1232, a WLAN module 1234, an SPS module 1236 (e.g., GNSS module) , and / or a cellular module 1238. The Bluetooth module 1232, the WLAN module 1234, the SPS module 1236, and the cellular module 1238 may each include an on-chip transceiver (TRX) , or in some cases, just a transmitter (TX) or just a receiver (RX) . The Bluetooth module 1232, the WLAN module 1234, the SPS module 1236, and the cellular module 1238 may each include dedicated antennas and / or utilize antennas 1240 for communication with one or more other nodes. For example, the UE apparatus 1202 can communicate through the transceiver (s) 1230 via the antennas 1240 with another UE (e.g., sidelink communication) and / or with a network entity 104 (e.g., uplink / downlink communication) , where the network entity 104 may correspond to a base station or a unit of the base station, such as the RU 106, the DU 108, or the CU 110.
[0155] The wireless baseband processor 1226 and the application processor 1206 may each include a computer-readable medium / memory 1226', 1206', respectively. The additional module of memory 1216 may also be considered a computer-readable medium / memory. Each computer-readable medium / memory 1226', 1206', 1216 may be non-transitory. The wireless baseband processor 1226 and the application processor 1206 may each be responsible for general processing, including execution of software stored on the computer-readable medium / memory 1226', 1206', 1216. The software, when executed by the wireless baseband processor 1226 / application processor 1206, causes the wireless baseband processor 1226 / application processor 1206 to perform the various functions described herein. The computer-readable medium / memory may also be used for storing data that is manipulated by the wireless baseband processor 1226 / application processor 1206 when executing the software. The wireless baseband processor 1226 / application processor 1206 may be a component of the UE 102. The UE apparatus 1202 may be a processor chip (e.g., modem and / or application) and include just the wireless baseband processor 1226 and / or the application processor 1206. In other examples, the UE apparatus 1202 may be the entire UE 102 and include the additional modules of the apparatus 1202.
[0156] As discussed in FIG. 1 and implemented with respect to FIG. 10, the CSI report component 140 is configured to receive, from a network entity, a first CSI report configuration for performance monitoring associated with a first CMR and a second CSI report configuration for CSI prediction associated with a second CMR; receive, from the network entity, a first CSI-RS on the first CMR and a second CSI-RS on the second CMR; transmit, to the network entity, a CSI report based on the first CSI report configuration, the CSI report including performance monitoring information for the first CMR, the performance monitoring information being associated with the CSI prediction for the second CMR.
[0157] The CSI report component 140 may be within the application processor 1206 (e.g., at 140a) , the wireless baseband processor 1226 (e.g., at 140b) , or both the application processor 1206 and the wireless baseband processor 1226. The CSI report component 140a-140b may be one or more hardware components specifically configured to carry out the stated processes / algorithm, implemented by one or more processors configured to perform the stated processes / algorithm, stored within a computer-readable medium for implementation by the one or more processors, or a combination thereof.
[0158] FIG. 13 is a diagram 1300 illustrating an example of a hardware implementation for one or more network entities 104. The one or more network entities 104 may be a base station, a component of a base station, or may implement base station functionality. The one or more network entities 104 may include, or may correspond to, at least one of the RU 106, the DU, 108, or the CU 110. The CU 110 may include a CU processor 1346, which may have on-chip memory 1346'. In some aspects, the CU 110 may further include an additional module of memory 1356 and / or a communications interface 1348, both of which may be coupled to the CU processor 1346. The CU 110 can communicate with the DU 108 through a midhaul link 162, such as an F1 interface between the communications interface 1348 of the CU 110 and a communications interface 1328 of the DU 108.
[0159] The DU 108 may include a DU processor 1326, which may have on-chip memory 1326'. In some aspects, the DU 108 may further include an additional module of memory 1336 and / or the communications interface 1328, both of which may be coupled to the DU processor 1326. The DU 108 can communicate with the RU 106 through a fronthaul link 160 between the communications interface 1328 of the DU 108 and a communications interface 1308 of the RU 106.
[0160] The RU 106 may include an RU processor 1306, which may have on-chip memory 1306'. In some aspects, the RU 106 may further include an additional module of memory 1316, the communications interface 1308, and one or more transceivers 1330, all of which may be coupled to the RU processor 1306. The RU 106 may further include antennas 1340, which may be coupled to the one or more transceivers 1330, such that the RU 106 can communicate through the one or more transceivers 1330 via the antennas 1340 with the UE 102.
[0161] The on-chip memory 1306', 1326', 1346'a nd the additional modules of memory 1316, 1336, 1356 may each be considered a computer-readable medium / memory. Each computer-readable medium / memory may be non-transitory. Each of the processors 1306, 1326, 1346 is responsible for general processing, including execution of software stored on the computer-readable medium / memory. The software, when executed by the corresponding processor (s) 1306, 1326, 1346 causes the processor (s) 1306, 1326, 1346 to perform the various functions described herein. The computer-readable medium / memory may also be used for storing data that is manipulated by the processor (s) 1306, 1326, 1346 when executing the software. In examples, the CSI report configuration component 150 may sit at any of the one or more network entities 104, such as at the CU 110; both the CU 110 and the DU 108; each of the CU 110, the DU 108, and the RU 106; the DU 108; both the DU 108 and the RU 106; or the RU 106.
[0162] As discussed in FIG. 1 and implemented with respect to FIG. 11, the CSI report configuration component 150 is configured to transmit, to a UE 102, a first CSI report configuration for performance monitoring associated with a first CMR and a second CSI report configuration for CSI prediction associated with a second CMR. The network entity transmits, to the UE 102, a first CSI-RS on the first CMR and a second CSI-RS on the second CMR. The network entity receives, from the UE 102, a CSI report based on the first CSI report configuration, the CSI report including performance monitoring information for the first CMR, the performance monitoring information being associated with the CSI prediction for the second CMR.
[0163] The CSI report configuration component 150 may be within one or more processors of the one or more network entities 104, such as the RU processor 1306 (e.g., at 150a) , the DU processor 1326 (e.g., at 150b) , and / or the CU processor 1346 (e.g., at 150c) . The CSI report configuration component 150a-150c may be one or more hardware components specifically configured to carry out the stated processes / algorithm, implemented by one or more processors 1306, 1326, 1346 configured to perform the stated processes / algorithm, stored within a computer-readable medium for implementation by the one or more processors 1306, 1326, 1346, or a combination thereof.
[0164] The specific order or hierarchy of blocks in the processes and flowcharts disclosed herein is an illustration of example approaches. Hence, the specific order or hierarchy of blocks in the processes and flowcharts may be rearranged. Some blocks may also be combined or deleted. Dashed lines may indicate optional elements of the diagrams. The accompanying method claims present elements of the various blocks in an example order, and are not limited to the specific order or hierarchy presented in the claims, processes, and flowcharts.
[0165] The detailed description set forth herein describes various configurations in connection with the drawings and does not 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 explanation of various concepts. However, these concepts may be practiced without these specific details. In some instances, well known structures and components are shown in block diagram form in order to avoid obscuring such concepts.
[0166] Aspects of wireless communication systems, such as telecommunication systems, are presented with reference to various apparatuses and methods. These apparatuses and methods are described in the following detailed description and are illustrated in the accompanying drawings by various blocks, components, circuits, processes, call flows, systems, algorithms, etc. (collectively referred to as “elements” ) . These elements may be implemented using electronic hardware, computer software, or combinations thereof. Whether such elements are implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system.
[0167] An element, or any portion of an element, or any combination of elements may be implemented as a “processing system” that includes one or more processors. Examples of processors include microprocessors, microcontrollers, graphics processing units (GPUs) , central processing units (CPUs) , application processors, digital signal processors (DSPs) , reduced instruction set computing (RISC) processors, systems-on-chip (SoC) , baseband processors, field programmable gate arrays (FPGAs) , programmable logic devices (PLDs) , state machines, gated logic, discrete hardware circuits, and other similar hardware configured to perform the various functionality described throughout this disclosure. One or more processors in the processing system may execute software, which may be referred to as software, firmware, middleware, microcode, hardware description language, or otherwise. Software shall be construed broadly to mean instructions, instruction sets, code, code segments, program code, programs, subprograms, software components, applications, software applications, software packages, routines, subroutines, objects, executables, threads of execution, procedures, functions, or any combination thereof.
[0168] If the functionality described herein is implemented in software, the functions may be stored on, or encoded as, one or more instructions or code on a computer-readable medium, such as a non-transitory computer-readable storage medium. Computer-readable media includes computer storage media and can include a random-access memory (RAM) , a read-only memory (ROM) , an electrically erasable programmable ROM (EEPROM) , optical disk storage, magnetic disk storage, other magnetic storage devices, combinations of these types of computer-readable media, or any other medium that can be used to store computer executable code in the form of instructions or data structures that can be accessed by a computer. Storage media may be any available media that can be accessed by a computer.
[0169] Aspects, implementations, and / or use cases described herein may be implemented across many differing platform types, devices, systems, shapes, sizes, and packaging arrangements. For example, the aspects, implementations, and / or use cases may come about via integrated chip implementations and other non-module-component based devices, such as end-user devices, vehicles, communication devices, computing devices, industrial equipment, retail / purchasing devices, medical devices, artificial intelligence (AI) -enabled devices, machine learning (ML) -enabled devices, etc. The aspects, implementations, and / or use cases may range from chip-level or modular components to non-modular or non-chip-level implementations, and further to aggregate, distributed, or original equipment manufacturer (OEM) devices or systems incorporating one or more techniques described herein.
[0170] Devices incorporating the aspects and features described herein may also include additional components and features for the implementation and practice of the claimed and described aspects and features. For example, transmission and reception of wireless signals necessarily includes a number of components for analog and digital purposes, such as hardware components, antennas, RF-chains, power amplifiers, modulators, buffers, processor (s) , interleavers, adders / summers, etc. Techniques described herein may be practiced in a wide variety of devices, chip-level components, systems, distributed arrangements, aggregated or disaggregated components, end-user devices, etc., of varying configurations.
[0171] The description herein is provided to enable a person skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects. Thus, the claims are not limited to the aspects described herein, but are to be interpreted in view of the full scope of the present disclosure consistent with the language of the claims.
[0172] Reference to an element in the singular does not mean “one and only one” unless specifically stated, but rather “one or more. ” Terms such as “if, ” “when, ” and “while” do not imply an immediate temporal relationship or reaction. That is, these phrases, e.g., “when, ” do not imply an immediate action in response to or during the occurrence of an action, but simply imply that if a condition is met then an action will occur, but without requiring a specific or immediate time constraint for the action to occur. The terms “may” , “might” , and “can” , as used in this disclosure, often carry certain connotations. For example, “may” refers to a permissible feature that may or may not occur, “might” refers to a feature that probably occurs, and “can” refers to a capability (e.g., capable of) . The phrase “For example” often carries a similar connotation to “may” and, therefore, “may” is sometimes excluded from sentences that include “for example” or other similar phrases.
[0173] Unless specifically stated otherwise, the term “some” refers to one or more. Combinations such as “at least one of A, B, or C” or “one or more of A, B, or C” include any combination of A, B, and / or C, such as A and B, A and C, B and C, or A and B and C, and may include multiples of A, multiples of B, and / or multiples of C, or may include A only, B only, or C only. Sets should be interpreted as a set of elements where the elements number one or more. Terms or articles such as “a” , “an” , and / or “the” may refer to one of an item, feature, element, etc., that the term or article precedes, or may refer to more than one of said item, feature, element, etc. that the term or article precedes. For example, the recitation “awidget” does not preclude reference to multiples of said widget, as “multiple widgets” necessarily includes “awidget” . Hence, the recitation “awidget” may be interpreted as “at least one widget” or, similarly, interpreted as “one or more widgets” .
[0174] Unless otherwise specifically indicated, ordinal terms such as “first” and “second” do not necessarily imply an order in time, sequence, numerical value, etc., but are used to distinguish between different instances of a term or phrase that follows each ordinal term.
[0175] Reference numbers, as used in the specification and figures, are sometimes cross-referenced among drawings to denote same or similar features. A feature that is exactly the same in multiple drawings may be labeled with the same reference number in the multiple drawings. A feature that is similar among the multiple drawings, but not exactly the same, may be labeled with reference numbers that have different leading numbers but have one or more of the same trailing numbers (e.g., 206, 306, 406, etc., may refer to similar features in the drawings) . Hence, like numbers may refer to like actions.
[0176] Structural and functional equivalents to elements of the various aspects described throughout this disclosure that are known or later come to be known to those of ordinary skill in the art are expressly incorporated herein by reference and are encompassed by the claims. The words “module, ” “mechanism, ” “element, ” “device, ” and the like may not be a substitute for the word “means. ” As such, no claim element is to be construed as a means plus function unless the element is expressly recited using the phrase “means for. ” As used herein, the phrase “based on” shall not be construed as a reference to a closed set of information, one or more conditions, one or more factors, or the like. In other words, the phrase “based on A” , where “A” may be information, a condition, a factor, or the like, shall be construed as “based at least on A” unless specifically recited differently.
[0177] The following examples are illustrative only and may be combined with other examples or teachings described herein, without limitation.
[0178] Example 1 is a method of wireless communication at a UE, including receiving, from a network entity, a first channel state information, CSI, report configuration for performance monitoring associated with a first channel measurement resource, CMR, and a second CSI report configuration for CSI prediction associated with a second CMR; receiving, from the network entity, a first channel state information-reference signal, CSI-RS, on the first CMR and a second CSI-RS on the second CMR; and transmitting, to the network entity, a CSI report based on the first CSI report configuration, the CSI report including performance monitoring information for the first CMR, the performance monitoring information being associated with the CSI prediction for the second CMR.
[0179] Example 2 may be combined with example 1 and further includes that the transmitting the CSI report including: transmitting the CSI report based on the second CSI report configuration, the CSI report further including CSI prediction information for the second CMR.
[0180] Example 3 may be combined with any examples 1-2 and further includes receiving, from the network entity, a third CSI report configuration indicating a linkage between the first CSI report configuration and the second CSI report configuration.
[0181] Example 4 may be combined with any examples 1-3 and further includes determining that the first CMR and the second CMR are a same CMR.
[0182] Example 5 may be combined with any examples 1-4 and further includes that the performance monitoring information includes at least one of: squared generalized cosine similarity, SGCS, between a measured CSI for the performance monitoring and a predicted CSI; channel quality indicator, CQI, layer-1 reference signal received power, L1-RSRP, or layer-1 signal-to-interference-plus-noise ratio, L1-SINR, for the measured CSI for the performance monitoring; first channel information for the predicted CSI for the CSI prediction; second channel information for the performance monitoring and the predicted CSI; a first indication of a sync status for the CSI prediction; a second indication of a failure status for the CSI prediction; measured wideband or subband RI, PMI, or CQI for one or more slots in a measurement window associated with the performance monitoring; or predicted wideband or subband RI, PMI, or CQI for the one or more slots in a prediction window associated with the performance monitoring.
[0183] Example 6 may be combined with any examples 1-5 and further includes receiving, from the network entity, a cell discontinuous transmission, DTX, configuration; and activating the cell DTX configuration; and further includes that the CSI report includes CSI prediction information for a machine learning, ML, model inference after the UE receives a number of measured transmission occasions for the measurement window in an active period of a cell DTX.
[0184] Example 7 may be combined with any examples 1-5 and further includes that the transmitting the CSI report including transmitting the CSI report via at least one of: a radio resource control, RRC, message; a medium access control-control element, MAC-CE, on a physical uplink shared channel, PUSCH; uplink control information, UCI, on a physical uplink control channel, PUCCH; or UCI on a PUSCH.
[0185] Example 8 may be combined with any examples 1-7 and further includes determining a number of occupied CSI processing units, CPUs, based on at least one of: a second number of transmission occasions for the second CMR associated with the CSI prediction; or a first number of transmission occasions for the first CMR associated with the performance monitoring.
[0186] Example 9 may be combined with any examples 1-8 and further includes performing, with the network entity, a procedure for an activation or deactivation of at least one of the first CSI report configuration or the second CSI report configuration and further includes that the performing the procedure includes at least one of: receiving, from the network entity, an indicator associated with a status of the activation or deactivation; determining the status of the activation or deactivation based on the CSI report; or determining the deactivation of at least one of the first CSI report configuration or the second CSI report configuration based on a triggering condition.
[0187] Example 10 may be combined with example 9 and further includes that the triggering condition includes at least one of: a serving cell for the first CSI report configuration being deactivated; a bandwidth part, BWP, for the first CSI report configuration being deactivated; the first CMR for the first CSI report configuration being deactivated; an expiration of a timer for the first or the second CSI report configuration; a beam or link quality for at least one downlink reference signal, DL-RS, or serving cell being below a first threshold; or a change of the beam or link quality, by a second threshold, for the at least one DL-RS or serving cell.
[0188] Example 11 may be combined with any examples 1-10 and further includes receiving, from the network entity, a third indication that the CSI prediction is based on a machine learning, ML, model.
[0189] Example 12 may be combined with any examples 1-10 and further includes that the CSI report includes an indication that the CSI prediction is based on a machine learning, ML, model.
[0190] Example 13 may be combined with any examples 1-12 and further includes transmitting, to the network entity, a UE capability report indicating at least one of: a number of transmission occasions for the first CMR for the performance monitoring; a number of transmission occasions for the second CMR for the CSI prediction; a supported prediction window duration; a supported offset between the measurement window and the prediction window; a supported type of filtering; a supported time-domain behavior for the first CMR and second CMR; a supported time-domain behavior for the CSI report for CSI prediction and performance monitoring; a temporal pattern of the measurement and the CSI prediction; a supported report content for the performance monitoring information; a supported maximum number of activated report configurations for the CSI prediction or the performance monitoring per component carrier, CC, or across CCs in a band or band combination; or a supported maximum number of CSI report configurations for the CSI prediction or the performance monitoring per CC or across CCs in a band or band combination.
[0191] Example 14 is a method of wireless communication at a network entity, including transmitting, to a user equipment, UE, a first channel state information, CSI, report configuration for performance monitoring associated with a first channel measurement resource, CMR, and a second CSI report configuration for CSI prediction associated with a second CMR; transmitting, to the UE, a first channel state information-reference signal, CSI-RS, on the first CMR and a second CSI-RS on the second CMR; and receiving, from the UE, a CSI report based on the first CSI report configuration, the CSI report including performance monitoring information for the first CMR, the performance monitoring information being associated with the CSI prediction for the second CMR.
[0192] Example 15 may be combined with example 14 and further includes that the receiving the CSI report including: receiving the CSI report based on the second CSI report configuration, the CSI report further including CSI prediction information for the second CMR.
[0193] Example 16 may be combined with any examples 14-15 and further includes transmitting, to the UE, a third CSI report configuration indicating a linkage between the first CSI report configuration and the second CSI report configuration.
[0194] Example 17 may be combined with any examples 14-16 and further includes determining that the first CMR and the second CMR are a same CMR.
[0195] Example 18 may be combined with any examples 14-17 and further includes that the performance monitoring information includes at least one of: squared generalized cosine similarity, SGCS, between a measured CSI for the performance monitoring and a predicted CSI; channel quality indicator, CQI, layer-1 reference signal received power, L1-RSRP, or layer-1 signal-to-interference-plus-noise ratio, LI-SINR, for the measured CSI for the performance monitoring; first channel information for the predicted CSI for the CSI prediction; second channel information for the performance monitoring and the predicted CSI; a first indication of a sync status for the CSI prediction; a second indication of a failure status for the CSI prediction; measured wideband or subband RI, PMI, or CQI for one or more slots in a measurement window associated with the performance monitoring; or predicted wideband or subband RI, PMI, or CQI for the one or more slots in a prediction window associated with the performance monitoring.
[0196] Example 19 may be combined with any examples 14-18 and further includes transmitting, to the UE, a cell discontinuous transmission, DTX, configuration and further includes that the CSI report includes CSI prediction information for a machine learning, ML, model inference after the UE receives a number of measured transmission occasions for the measurement window in an active period of a cell DTX.
[0197] Example 20 may be combined with any examples 14-18 and further includes that the receiving the CSI report including receiving the CSI report via at least one of: a radio resource control, RRC, message; a medium access control-control element, MAC-CE, on a physical uplink shared channel, PUSCH; uplink control information, UCI, on a physical uplink control channel, PUCCH; or UCI on a PUSCH.
[0198] Example 21 may be combined with any examples 14-20 and further includes determining a number of occupied CSI processing units, CPUs, based on at least one of: a second number of transmission occasions for the second CMR associated with the CSI prediction; or a first number of transmission occasions for the first CMR associated with the performance monitoring.
[0199] Example 22 may be combined with any examples 14-21 and further includes performing, with the UE, a procedure for an activation or deactivation of at least one of the first CSI report configuration or the second CSI report configuration and further includes that the performing the procedure includes: transmitting, to the UE, an indicator associated with a status of the activation or deactivation.
[0200] Example 23 may be combined with example 22 and further includes that the triggering conditions includes at least one of: a serving cell for the first CSI report configuration being deactivated; a bandwidth part, BWP, for the first CSI report configuration being deactivated; the first CMR for the first CSI report configuration being deactivated; an expiration of a timer for the first and the second CSI report configuration; a beam or link quality for at least one downlink reference signal, DL-RS, or serving cell being below a first threshold; or a change of the beam or link quality, by a second threshold, for the at least one DL-RS or serving cell.
[0201] Example 24 may be combined with any examples 14-23 and further includes transmitting, to the UE, a third indication that the CSI prediction is based on the ML model.
[0202] Example 25 may be combined with any examples 14-24 and further includes that the CSI report includes an indication that the CSI prediction is based on the ML model.
[0203] Example 26 may be combined with any examples 14-25 and further includes receiving, from the UE, a UE capability report indicating at least one of: a number of transmission occasions for the second CMR for the CSI prediction; a number of transmission occasions for the first CMR for the performance monitoring; a supported prediction window duration; a supported offset between the measurement window and the prediction window; a supported type of filtering; a supported time-domain behavior for the first CMR and second CMR; a supported time-domain behavior for the CSI report for CSI prediction or performance monitoring; a temporal pattern of the measurement and the CSI prediction; a supported report content for the performance monitoring information; a supported maximum number of activated report configurations for the CSI prediction or the performance monitoring per component carrier, CC, or across CCs in a band or band combination; or a supported maximum number of CSI report configurations for the CSI prediction or the performance monitoring per CC or across CCs in a band or band combination.
[0204] Example 27 is an apparatus for wireless communication for implementing a method as in any of examples 1-26.
[0205] Example 28 is an apparatus for wireless communication including means for implementing a method as in any of examples 1-26.
[0206] Example 29 is a non-transitory computer-readable medium storing computer executable code, the code when executed by a processor causes the processor to implement a method as in any of examples 1-26.
[0207] Example 30 is a computer program product for implementing a method as in any of Examples 1-26.
Claims
A method of wireless communication at a user equipment, UE, (102) , comprising:receiving (304) , from a network entity (104) , a first channel state information, CSI, report configuration for performance monitoring associated with a first channel measurement resource, CMR, and a second CSI report configuration for CSI prediction associated with a second CMR;receiving (308) , from the network entity (104) , a first channel state information-reference signal, CSI-RS, on the first CMR and a second CSI-RS on the second CMR; andtransmitting (310) , to the network entity (104) , a CSI report based on the first CSI report configuration, the CSI report including performance monitoring information for the first CMR, the performance monitoring information being associated with the CSI prediction for the second CMR.The method of claim 1, wherein the transmitting the CSI report comprises:transmitting (310) the CSI report based on the second CSI report configuration, the CSI report further including CSI prediction information for the second CMR.The method of any of claims 1-2, further comprising:receiving (304) , from the network entity (104) , a third CSI report configuration indicating a linkage between the first CSI report configuration and the second CSI report configuration.The method of any of claims 1-3, further comprising:determining that the first CMR and the second CMR are a same CMR.The method of any of claims 1-4, wherein the performance monitoring information includes at least one of:squared generalized cosine similarity, SGCS, between a measured CSI for the performance monitoring and a predicted CSI;channel quality indicator, CQI, layer-1 reference signal received power, L1-RSRP, or layer-1 signal-to-interference-plus-noise ratio, L1-SINR, for the measured CSI for the performance monitoring;first channel information for the predicted CSI for the CSI prediction;second channel information for the performance monitoring and the predicted CSI;a first indication of a sync status for the CSI prediction;a second indication of a failure status for the CSI prediction;measured wideband or subband rank indicator, RI, precoding matrix indicator, PMI, or CQI for one or more slots in a measurement window associated with the performance monitoring; orpredicted wideband or subband RI, PMI, or CQI for the one or more slots in a prediction window associated with the performance monitoring.The method of any of claims 1-5, further comprising:receiving, from the network entity (104) , a cell discontinuous transmission, DTX, configuration; andactivating the cell DTX configuration;wherein the CSI report includes CSI prediction information for a machine learning, ML, model inference after the UE receives a number of measured transmission occasions for the measurement window in an active period of a cell DTX.The method of any of claims 1-5, wherein the transmitting (310) the CSI report comprises transmitting the CSI report via at least one of:a radio resource control, RRC, message;a medium access control-control element, MAC-CE, on a physical uplink shared channel, PUSCH;uplink control information, UCI, on a physical uplink control channel, PUCCH; orUCI on a PUSCH.The method of any of claims 1-7, further comprising:determining a number of occupied CSI processing units, CPUs, based on at least one of:a second number of transmission occasions for the second CMR associated with the CSI prediction; ora first number of transmission occasions for the first CMR associated with the performance monitoring.The method of any of claims 1-8, further comprising:performing (306, 312) , with the network entity (104) , a procedure for an activation or deactivation of at least one of the first CSI report configuration or the second CSI report configuration, wherein the performing (306) the procedure includes at least one of:receiving, from the network entity (104) , an indicator associated with a status of the activation or deactivation;determining the status of the activation or deactivation based on the CSI report; ordetermining the deactivation of at least one of the first CSI report configuration or the second CSI report configuration based on a triggering condition.The method of claim 9, wherein the triggering condition includes at least one of:a serving cell for the first CSI report configuration being deactivated;a bandwidth part, BWP, for the first CSI report configuration being deactivated;the first CMR for the first CSI report configuration being deactivated;an expiration of a timer for the first or the second CSI report configuration;a beam or link quality for at least one downlink reference signal, DL-RS, or serving cell being below a first threshold; ora change of the beam or link quality, by a second threshold, for the at least one DL-RS or serving cell.The method of any of claims 1-10, further comprising:receiving (304) , from the network entity (104) , a third indication that the CSI prediction is based on a machine learning, ML, model.The method of any of claims 1-10, wherein the CSI report includes an indication that the CSI prediction is based on a machine learning, ML, model.The method of any of claims 1-12, further comprising:transmitting (302) , to the network entity (104) , a UE capability report indicating at least one of:a number of transmission occasions for the first CMR for the performance monitoring;a number of transmission occasions for the second CMR for the CSI prediction;a supported prediction window duration;a supported offset between the measurement window and the prediction window;a supported type of filtering;a supported time-domain behavior for the first CMR and second CMR;a supported time-domain behavior for the CSI report for CSI prediction and performance monitoring;a temporal pattern of the measurement and the CSI prediction;a supported report content for the performance monitoring information;a supported maximum number of activated report configurations for the CSI prediction or the performance monitoring per component carrier, CC, or across CCs in a band or band combination; ora supported maximum number of CSI report configurations for the CSI prediction or the performance monitoring per CC or across CCs in a band or band combination.A method of wireless communication at a network entity (104) , comprising:transmitting (304) , to a user equipment, UE (102) , a first channel state information, CSI, report configuration for performance monitoring associated with a first channel measurement resource, CMR, and a second CSI report configuration for CSI prediction associated with a second CMR;transmitting (308) , to the UE (102) , a first channel state information-reference signal, CSI-RS, on the first CMR and a second CSI-RS on the second CMR; andreceiving (310) , from the UE (102) , a CSI report based on the first CSI report configuration, the CSI report including performance monitoring information for the first CMR, the performance monitoring information being associated with the CSI prediction for the second CMR.The method of claim 14, wherein the receiving the CSI report comprises:receiving (310) the CSI report based on the second CSI report configuration, the CSI report further including CSI prediction information for the second CMR.The method of any of claims 14-15, further comprising:transmitting (304) , to the UE (102) , a third CSI report configuration indicating a linkage between the first CSI report configuration and the second CSI report configuration.The method of any of claims 14-16, wherein the performance monitoring information includes at least one of:squared generalized cosine similarity, SGCS, between a measured CSI for the performance monitoring and a predicted CSI;channel quality indicator, CQI, layer-1 reference signal received power, L1-RSRP, or layer-1 signal-to-interference-plus-noise ratio, LI-SINR, for the measured CSI for the performance monitoring;first channel information for the predicted CSI for the CSI prediction;second channel information for the performance monitoring and the predicted CSI;a first indication of a sync status for the CSI prediction;a second indication of a failure status for the CSI prediction;measured wideband or subband rank indicator, RI, precoding matrix indicator, PMI, or CQI for one or more slots in a measurement window associated with the performance monitoring; orpredicted wideband or subband RI, PMI, or CQI for the one or more slots in a prediction window associated with the performance monitoring.The method of any of claims 14-17, further comprising:performing (306, 312) , with the UE (102) , a procedure for an activation or deactivation of at least one of the first CSI report configuration or the second CSI report configuration, wherein the performing (306) the procedure includes:transmitting, to the UE (102) , an indicator associated with a status of the activation or deactivation.An apparatus for wireless communication comprising a memory, a transceiver, and a processor coupled to the memory and the transceiver, the apparatus being configured to implement a method as in any of claims 1-18.