Reporting channel state information (CSI) for performance monitoring of machine learning based csi
By reporting ground-truth CSI with higher resolution, the network entity can monitor and correct ML based CSI errors, enhancing communication performance and reducing power consumption.
Patent Information
- Application Number
- PCT/CN2024/102291
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-06-28
- Publication Date
- 2026-01-02
AI Technical Summary
In machine learning (ML) based channel state information (CSI) reporting, errors can become substantial due to mismatched ML models for compression and prediction between user equipment (UE) and the network entity, leading to performance issues.
The UE reports ground-truth CSI using a codebook with higher resolution than other CSI reports, allowing the network entity to compare ML based CSI with ground-truth CSI to monitor performance and reduce errors, and configures CSI-RS resources and codebooks to manage reporting and measurement.
This approach reduces errors in ML based CSI by enabling performance monitoring and ensures accurate reporting, thereby improving communication efficiency and reducing power consumption.
Smart Images

Figure CN2024102291_02012026_PF_FP_ABST
Abstract
Description
REPORTING CHANNEL STATE INFORMATION (CSI) FOR PERFORMANCE MONITORING OF MACHINE LEARNING BASED CSIFIELD
[0001] This disclosure relates generally to wireless communications and, more particularly, to machine learning based channel state information (CSI) .BACKGROUND
[0002] This background description is provided for the purpose of generally presenting the context of the disclosure. Work of the presently named inventors, to the extent as described in this background section, as well as aspects of the description that may not otherwise qualify as prior art at the time of filing, is neither expressly nor impliedly admitted as prior art against the present disclosure.
[0003] In multiple-input multiple-output (MIMO) systems, channel state information (CSI) enables a network entity (NE) to select the digital precoder for a user equipment (UE) . Usually, the network entity 104 configures the UE to provide a CSI report using RRC signaling, e.g., CSI-ReportConfig. The network entity configures the UE to use channel state information reference signal (CSI-RS) as channel measurement resource (CMR) for the UE to measure the downlink channel. The network entity may also configure interference measurement resource (IMR) for the UE to measure interference.
[0004] Based on the configured CMR and its associated IMR, the UE is able to identify the CSI, which may include at least one of rank indicator (RI) , precoder matrix indicator (PMI) , channel quality indicator (CQI) and layer indicator (LI) . RI and PMI are used to indicate the digital precoder, CQI is used to indicate the signal-to-interference plus noise (SINR) status in order to assist the network entity 104 to determine the modulation and coding scheme (MCS) , and LI is used to identify the strongest layer for the reported precoder indicated by RI and PMI.
[0005] Currently, the UE reports a precoder to the network entity 104, indicating the antenna co-phasing between two polarizations (e.g., Type 1 single-panel codebook, in Scheme A) , or a wideband beam index for layers based on measured beams (e.g., Type 1 single-panel codebook, in Scheme B) , or the UE reports a precoder for multiple beams for each layer (e.g., Type2 or enhanced Type2 codebook) . In machine learning (ML) based CSI reporting, the UE reports CSI based on ML based compression and / or prediction, including one or more ML model inputs (e.g., channel matrix, channel eigenvector, beam combining matrix, etc. ) . Using the ML based compressed CSI, the network entity 104 performs ML based CSI reconstruction to calculate the decompressed channel. The UE may also calculate a predicted CSI based on previous measurements and transmit the predicted CSI with or without ML based compression for the network entity 104 to reconstruct the ML based CSI. The ML based prediction and / or compression may benefit from performance monitoring to reduce or avoid related errors.SUMMARY
[0006] The present disclosure provides methods, systems, and techniques for reporting channel state information (CSI) for performance monitoring for machine learning (ML) based CSI. The methods herein provide for CSI feedback for performance monitoring of ML based CSI, such as CSI report configuration for reporting ground-truth CSI as well as the content and mechanism for the report. For example, in an ML based CSI report, the UE reports CSI based on ML based compression and / or prediction. Because of the compression and / or prediction related to ML models, errors could become substantial when various conditions become mismatched between the UE and the network entity (e.g., using mismatched ML models for compression, decompression, or prediction) . To monitor the performance of the ML based CSI, the network entity may compare the ML based CSI and a ground-truth CSI reported by the UE to avoid excessive errors.
[0007] According to general aspects of this disclosure, a method for wireless communications by a user equipment (UE) includes receiving, from a network entity, a configuration configuring a channel state information-reference signal (CSI-RS) resource set for channel measurement and indicating a first codebook configuration for a first type of CSI report having a higher CSI quantization resolution than that of a second codebook configuration for a second type of CSI report. The first and second type of CSI reports are associated with machine learning (ML) based CSI. The method further includes receiving, from the network entity, a CSI reference signal (CSI-RS) according to the CSI-RS resource set, and transmitting, to the network entity, the first type of CSI report based on measurements of the CSI-RS.
[0008] In aspects, the method further includes transmitting, to the network entity, UE capability information for supporting the first codebook configuration for the first type of CSI report and the second codebook configuration for the second type of CSI report.
[0009] In some cases, the method further includes receiving, from the network entity, a triggering signal that triggers the first type of CSI report or associated measurements on the CSI-RS, and transmitting, to the network entity, the second type of CSI report.
[0010] In aspects, the configuration further configures at least one of: a first CSI-RS resource set for channel measurement associated with the first type of CSI report, and a second CSI-RS resource set for channel measurement associated with the second type of CSI report; the first codebook configuration for the first type of CSI report, and the second codebook configuration for the second type of CSI report; a first CSI report configuration for the first type of CSI report associated with performance monitoring of the ML based CSI, and a second CSI report configuration for the second type of CSI report associated with reporting the ML based CSI, wherein the second CSI report configuration is associated to the first CSI report configuration; a report quantity indicating at least one precoding matrix indicator (PMI) report; a frequency granularity; an interference measurement resource; a configuration of thresholds for a measurability determination for the CSI report; a configuration for a CSI triggering window; a configuration for a CSI measurement window; or a configuration for a CSI reporting window.
[0011] In some cases, the second CSI report configuration is different from the first CSI report configuration, wherein the first CSI report configuration and the second CSI report configuration are for a bandwidth part (BWP) or a serving cell.
[0012] In some cases, the first and second CSI-RS resource sets include CSI-RS resources from a common antenna port or a plurality of different antenna ports, wherein the CSI-RS resources includes multiple CSI-RS resource groups each including CSI-RS resources from different antenna ports, and wherein different CSI-RS resource groups are configured in different slots.
[0013] In aspects, the configuration includes: a first CSI report sub-configuration for the first type of CSI report for performance monitoring of ML based CSI; and a second CSI report sub- configuration for the second type of CSI report indicating a model identifier (ID) for the ML based CSI.
[0014] In aspects, the first and the second codebook configurations include Type2 codebook, enhanced Type2 (eType2) codebook, or eType2-Doppler codebook, and wherein a first codebook for the first type of CSI report is for a ground-truth CSI report and a second codebook for the second type of CSI report is for ML based CSI report.
[0015] In some cases, a first parameter associated the first codebook has a higher resolution than a second parameter associated with the second codebook, wherein the first and second parameters include at least one of: a number of reported beams; a number of non-zero-coefficients for beam combining matrix; a number of horizontal antenna ports; a number of vertical antenna ports; an oversampling factor in horizontal dimension; an oversampling factor in vertical dimension; an oversampling factor in frequency domain; or a number of time instances for measuring CSI.
[0016] In aspects, the configuration indicates at least one of: reporting the first type of CSI report for first future instances based on non-ML prediction and non-ML compression; reporting the first type of CSI report for second future instances based on ML prediction and non-ML compression; reporting the first type of CSI report for third future instances based on non-ML prediction and ML compression; reporting the first type of CSI report for a first transmission occasion of the CSI-RS based ML compression; or reporting the first type of CSI report for a second transmission occasion of the CSI-RS based non-ML compression.
[0017] In aspects, the first type of CSI report includes at least one of: a precoding matrix indicator (PMI) ; a rank indicator (RI) and a PMI; a PMI and a channel quality indicator (CQI) ; or an RI, a PMI, and a CQI.
[0018] In some cases, the first CSI report configuration further indicates a frequency granularity for the first type of CSI report, the frequency granularity indicating whether the first type of CSI report is measured based on a wideband operation or a subband operation.
[0019] In aspects, the method further includes determining, at the UE, whether a transmission occasion for the CSI-RS is measurable based on at least one of: a measured reference signal received power (RSRP) being below a first threshold; a measured signal-to-interference plus noise ratio (SINR) being below a second threshold; a failure to receive the transmission occasion of the CSI-RS; a delay offset between the transmission occasion of the CSI-RS and a reference downlink channel or signal is above a third threshold; an offset between the transmission occasion of the CSI-RS and a first slot of the CSI report being below a minimum processing delay; a number of CSI processing units (CPUs) exceeding a maximum number of CPUs; channel estimation error being above a fourth threshold; or a minimum, a maximum, or an average value of RSRP or SINR for one or more antenna ports of the CSI-RS. The UE then transmits, to the network entity, a measurable status for the first type of CSI report when the transmission occasion is measurable.
[0020] In aspects, the configuration further includes a triggering window, which is characterized by a first periodicity, a first duration, and a first slot offset for a first slot of the triggering window. The method further includes transmitting the first type of CSI report in response to receiving, from the network entity, a first downlink control information (DCI) within the triggering window, and ignoring a second DCI outside the triggering window.
[0021] In aspects, the configuration further includes a reporting window for the transmitting the first type of CSI report, which is characterized by a second periodicity, a second duration, and a second slot offset for a second slot of the reporting window. The method further includes transmitting the first type of CSI report in response to receiving a valid DCI that triggers the first type of CSI report within the reporting window, and dropping the first type of CSI report in response to receiving an invalid DCI that triggers the first type of CSI report outside the reporting window.
[0022] According to general aspects of this disclosure, a method for wireless communications by a network entity, the method includes transmitting, to a UE, a configuration configuring a CSI-RS resource set for channel measurement and indicating a first codebook configuration for a first type of CSI report having a higher CSI quantization resolution than that of a second codebook configuration for a second type of CSI report, the first and second type of CSI reports being associated with ML based CSI. The method further includes transmitting, to the UE, a CSI-RS according to the CSI-RS resource set, and receiving, from the UE, the first type of CSI report based on measurements of the CSI-RS.
[0023] In aspects, the configuration further configures at least one of: a first CSI-RS resource set for channel measurement associated with the first type of CSI report, and a second CSI-RS resource set for channel measurement associated with the second type of CSI report; the first codebook configuration for the first type of CSI report, and the second codebook configuration for the second type of CSI report; a first CSI report configuration for the first type of CSI report associated with performance monitoring of the ML based CSI, and a second CSI report configuration for the second type of CSI report associated with reporting the ML based CSI, wherein the second CSI report configuration is associated to the first CSI report configuration; a report quantity indicating at least one PMI report; a frequency granularity; an interference measurement resource; a configuration of thresholds for a measurability determination for the CSI report; a configuration for a CSI triggering window; a configuration for a CSI measurement window; or a configuration for a CSI reporting window.
[0024] In aspects, the configuration includes a first CSI report sub-configuration for the first type of CSI report for performance monitoring of ML based CSI, and a second CSI report sub-configuration for the second type of CSI report indicating a model ID for the ML based CSI.
[0025] In aspects, the first and the second codebook configurations comprise Type2 codebook, eType2 codebook, or eType2-Doppler codebook, and wherein a first codebook for the first type of CSI report is for a ground-truth CSI report and a second codebook for the second type of CSI report is for ML based CSI report.
[0026] According to general aspects of this disclosure, an apparatus includes one or more radio frequency (RF) modems; a processor coupled to the one or more RF modems; and at least one memory storing executable instructions. The executable instructions manipulate at least one of the processor or the one or more RF modems to perform the above methods, which are discussed in details herein.BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Fig. 1 illustrates a diagram of a wireless communications system that includes multiple user equipments (UEs) and network entities in communication over one or more cells, according to aspects of this disclosure.
[0028] Fig. 2A illustrates an example diagram of artificial intelligence or machine learning (AI / ML) based channel state information (CSI) compression, in accordance with aspects of this disclosure.
[0029] Fig. 2B illustrates an example diagram of AI / ML based CSI prediction, in accordance with aspects of this disclosure.
[0030] Fig. 2C illustrates an example for AI / ML based joint CSI compression and prediction based on a single AI / ML model, in accordance with aspects of this disclosure.
[0031] Fig. 2D illustrates an example for AI / ML based joint CSI compression and prediction based on separate AI / ML models, in accordance with aspects of this disclosure.
[0032] Fig. 3 illustrates an example diagram of CSI report for performance monitoring for AI / ML based CSI, in accordance with aspects of this disclosure.
[0033] Fig. 4 illustrates an example diagram of UE behavior for the CSI report for performance monitoring for AI / ML based CSI, in accordance with aspects of this disclosure.
[0034] Fig. 5 illustrates an example diagram of network entity behavior for the CSI report for performance monitoring for AI / ML based CSI, in accordance with aspects of this disclosure.
[0035] Fig. 6 illustrates an example for channel state information-reference signal (CSI-RS) configuration based on multiple resource groups, in accordance with aspects of this disclosure.
[0036] Fig. 7 illustrates an example for the time-domain configuration for the CSI-RS for the first and second CSI report configurations, in accordance with aspects of this disclosure.
[0037] Fig. 8 illustrates an example diagram of configuration of CSI report for performance monitoring and AI / ML based CSI report in different CSI report sub-configurations, in accordance with aspects of this disclosure.
[0038] Fig. 9 illustrates an example for the UE behavior to report a measurability status of the CSI-RS, in accordance with aspects of this disclosure.
[0039] Fig. 10A illustrates an example for the CSI report based on a CSI triggering window, in accordance with aspects of this disclosure.
[0040] Fig. 10B illustrates an example for the CSI report based on a CSI reporting window, in accordance with aspects of this disclosure.
[0041] Fig. 10C illustrates an example for the CSI report based on a CSI measurement window, in accordance with aspects of this disclosure.
[0042] Fig. 11 illustrates an example flowchart of a method performed by a UE, in accordance with aspects of this disclosure.
[0043] Fig. 12 illustrates an example flowchart of a method performed by a network entity, in accordance with aspects of this disclosure.
[0044] Fig. 13 is a diagram illustrating a hardware implementation for an example UE apparatus.
[0045] Fig. 14 is a diagram illustrating a hardware implementation for one or more example network entities.
[0046] Like numerals indicate like elements.DETAILED DESCRIPTION
[0047] The present disclosure provides methods, systems, and techniques for reporting channel state information (CSI) for performance monitoring for machine learning (ML) based CSI. The methods herein provide for CSI feedback for performance monitoring of ML based CSI, such as CSI report configuration for reporting ground-truth CSI as well as the content and mechanism for the report. For example, in an ML based CSI report, the UE reports CSI based on ML based compression and / or prediction. Because of the compression and / or prediction related to ML models, errors could become substantial when various conditions become mismatched between the UE and the network entity (e.g., using mismatched ML models for compression, decompression, or prediction) . To monitor the performance of the ML based CSI, the network entity may compare the ML based CSI and a ground-truth CSI reported by the UE to avoid excessive errors.
[0048] In examples herein, the UE reports the ground-truth CSI by reporting the CSI based on a codebook with a higher resolution (such as “Type2” or “enhanced Type2 (eType2) ” codebook types with higher resolution parameters) than that of other CSI reports. To achieve the higher resolution, the ground-truth CSI may be configured, for example, with a greater number of reported beams, more coefficients for beam combining matrix, higher resolution for coefficient quantization, a greater number of frequency domain (FD) basis, among other parameters. When the differences between the ground-truth CSI and the ML based CSI are within a threshold value, the network entity then continues using the ML based CSI.
[0049] The present disclosure provides methods of configuring and reporting the ground-truth CSI to address different use cases for the ML based CSI reporting, e.g., CSI compression, CSI prediction, and joint CSI compression and prediction. In aspects, for joint CSI compression and prediction, examples of methods are disclosed for solving performance monitoring challenges based on a single ML model or separate ML models. In aspects, the present disclosure provides methods of reporting the CSI with regard to different performance monitoring operations.
[0050] The present disclosure further provides methods of identifying the association or linkage between the CSI report for performance monitoring and the ML based CSI report, as the CSI report for performance monitoring of ML based CSI should be connected to one or more ML based CSI reports. When the network entity compares the reported ground-truth CSI and the reported ML based CSI, the UE may report the ground-truth CSI based on certain properties of the reported ML based CSI, e.g., the same number of layers, the same transmission occasion (s) of channel state information-reference signal (CSI-RS) , among others, for associating the performance monitoring CSI report with the one or more ML based CSI reports.
[0051] In addition, the UE may measure the CSI-RSs with measurement error. Such measurement error may lead to inaccurate ground-truth CSI. Accordingly, the inaccurate ground-truth CSI could result in incorrect performance monitoring. The present disclosure provides methods for reducing the impact from measurement error for performance monitoring. Moreover, for performance monitoring, the network entity may not need to trigger the CSI report frequently. The present disclosure provides methods for reducing the UE power consumption and memory by triggering only necessary CSI reports.
[0052] Aspects of this disclosure for initiating transmission of a beam report include a wireless communication method by a UE. The example method includes receiving, from a network entity, a configuration configuring a CSI-RS resource set for channel measurement and indicating a first codebook configuration for a first type of CSI report having a higher CSI quantization resolution than that of a second codebook configuration for a second type of CSI report. The first and second type of CSI reports are associated with machine learning (ML) based CSI. The UE receives, from the network entity, a CSI-RS according to the CSI-RS resource set. The UE then transmits, to the network entity, the first type of CSI report based on measurements of the CSI-RS. For example, the first type of CSI report is a ground-truth CSI report for the network entity to monitor the performance of ML based CSI.
[0053] Complimentary aspects of the disclosure include an example method of configuring or accepting a UE to initiate transmitting a beam report by a network entity. The example method includes transmitting, to a UE, a configuration configuring a CSI-RS resource set for channel measurement and indicating a first codebook configuration for a first type of CSI report having a higher CSI quantization resolution than that of a second codebook configuration for a second type of CSI report. The first and second type of CSI reports being associated with ML based CSI. The network entity transmits, to the UE, a CSI-RS according to the CSI-RS resource set, and receives, from the UE, the first type of CSI report based on measurements of the CSI-RS.
[0054] Fig. 1 illustrates a diagram 100 of a wireless communications system associated with multiple 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 may 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) .
[0055] Operations of the base station (BS) 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 may enable flexibility in network designs. The various units of the disaggregated base station architecture, or the disaggregated RAN architecture, may be configured for wired or wireless communication with at least one other unit. For example, the base stations (BSs) 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 BSs 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 / BSs 104.
[0056] 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 may 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 BS 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 BS 104e of the cell 190e via cross-cell communication beams 136-138 of the RU 106a and the BS 104e.
[0057] 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.
[0058] 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 may control both real-time and non-real-time features of control plane and user plane communications of the RUs 106.
[0059] Any combination of the RU 106, the DU 108, and the CU 110, or reference thereto individually, may correspond to a BS 104. Thus, the BS 104 may include at least one of the RU 106, the DU 108, or the CU 110. The BSs 104 provide the UEs 102 with access to a core network. The BSs 104 may relay communications between the UEs 102 and the core network (not shown) . The BSs 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. ”
[0060] Transmissions from a UE 102 to a BS 104 / RU 106 are referred to as uplink (UL) transmissions, whereas transmissions from the BS 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 BS 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 BS 104d / RU 106d.
[0061] Communication links between the UEs 102 and the BSs 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 BSs 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) .
[0062] 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.
[0063] The UEs 102 and the BSs 104 / RUs 106 may each include multiple antennas. The multiple 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 BSs 104 / RUs 106 may or may not be the same.
[0064] In further examples, beamformed signals may be communicated between a first base station / RU 106a and a second BS 104e. For instance, the BS 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 BS 104e. The RU 106a may receive the beamformed signal from the BS 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 BS 104e transmits a downlink beamformed signal to the UE 102e based on the communication beams 138 in one or more transmit directions of the BS 104e. The UE 102e receives the downlink beamformed signal from the BS 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 BS 104e based on the UE communication beams 130 in one or more transmit directions of the UE 102e, such that the BS 104e may receive the uplink beamformed signal from the UE 102e in one or more receive directions of the BS 104e.
[0065] The BS 104 may include and / or be referred to as a network entity. That is, “network entity” may refer to the BS 104 or at least one unit of the BS 104, such as the RU 106, the DU 108, and / or the CU 110. The BS 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 BS 104 or an entity at the BS 104 may 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 BS 104e and the base station / RU 106a. In such cases, the BS 104e may be a master node and the base station / RU 160a may be a secondary node.
[0066] Uplink / downlink signaling may also be communicated via a satellite positioning system (SPS) 114. In an example, the SPS 114 associated with the cell 190c may be in communication with one or more UEs 102, such as the UE 102c, and one or more BSs 104 / RUs 106, such as the RU 106c. The SPS 114 may correspond to one or more of a Global Navigation Satellite System (GNSS) , a global position system (GPS) , a non-terrestrial network (NTN) , or other satellite position / location system. The SPS 114 may be associated with LTE signals, NR signals (e.g., based on round trip time (RTT) and / or multi-RTT) , wireless local area network (WLAN) signals, a terrestrial beacon system (TBS) , sensor-based information, NR enhanced cell ID (NR E-CID) techniques, downlink angle-of-departure (DL-AoD) , downlink time difference of arrival (DL-TDOA) , uplink time difference of arrival (UL-TDOA) , uplink angle-of-arrival (UL-AoA) , and / or other systems, signals, or sensors.
[0067] In Fig. 1, any of the UEs 102 may include a CSI report component 140 configured to receive, from the BS 104, a configuration that configures a CSI-RS resource set for channel measurement. The configuration also indicates a first codebook configuration for a first type of CSI report having a higher CSI quantization resolution than that of a second codebook configuration for a second type of CSI report. The first and second type of CSI reports are associated with machine learning (ML) based CSI. The CSI report component 140 then receives, from the BS 104, a CSI-RS according to the CSI-RS resource set and transmits, to the BS 104, the first type of CSI report based on measurements of the CSI-RS. Correspondingly, the BS 104 includes a CSI configuration component 150 for transmitting the configuration and receiving the first type of CSI report from the UE 102.
[0068] 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.
[0069] For Type1 single-panel codebook, the network entity 104 may configure two schemes for the CSI feedback. For example, according to the third generation partnership project (3GPP) technical specification (TS) , in Scheme A, for each layer, the UE 102 reports the precoder indicating the antenna co-phasing between two polarizations. The precoder for a layer may be:
[0070] where vl, m indicates the beam for each polarization (e.g., see 3GPP TS 38.214 section 5.2.2.2.1) , l=0, 1, …, N1O1-1, m=0, 1, …, N2O2-1, indicates the antenna co-phasing between two polarizations, and in one example it is as follows, where n=0, 1, 2, 3:
[0071] The UE 102 reports a first PMI information indicating the l and m for each layer for the wideband precoder, and for each subband, the UE 102 reports a second PMI information indicating value of n for each layer for the corresponding subband. The reported precoder and the precoder used for CQI calculation should be normalized. Thus, for NL layers, the precoder for each layer should be multiplied by
[0072] In Scheme B, the UE 102 reports NL wideband beam index for NL layers based on the beams in W1, where each beam index corresponding to one layer. A beam index indicates the value of (l, m) in equation (3) .
[0073] For each subband, the UE 102 calculates the co-phasing between two polarizations, and compressed the polarizations from N3 subbands into Mv coefficients based on Mv frequency domain (FD) basis. Then for one layer the precoder for all the subbands may be generated as equation (4)
[0074] where is a 2 by Mv matrix and WFD is a Mv by N3 matrix indicating Mv FD basis from a set of FD basis, e.g., discrete Fourier transform (DFT) basis as defined in 3GPP TS 38.214 section 5.2.2.2.5, based on number of subbands. The UE 102 may apply a time offset to keep the first coefficient always from the first FD basis. Thus, it reports a subset of or all the coefficients from the 2 by Mv matrix and Mv-1 FD basis. The reported precoder and the precoder used for CQI calculation should be normalized. Thus, for NL layers, the precoder for each layer should be multiplied by
[0075] For Type2 / eType2 codebook, the UE 102 reports the precoder based on similar approach as scheme B for Type1 codebook, where the UE 102 may report more than one beams for each layer. Thus, the UE 102 may report L beams for each layer in W1, and the enhanced beam combining matrix is a 2L by Mv matrix. The UE 102 may report one or multiple non-zero-power coefficients for the enhanced beam combining matrix and it may report amplitude and phase for each coefficient. Note that in the following paragraphs of this application, Type2 codebook may indicate Type2 codebook or eType2 codebook.
[0076] For artificial intelligence (AI) or machine learning (ML) based CSI report (generally referred to as ML based CSI report herein) , the UE 102 may report CSI based on ML based compression and / or prediction, as illustrated in Figs. 2A-2D and described below.
[0077] Fig. 2A illustrates an example diagram 210 of artificial intelligence or machine learning (AI / ML) based CSI compression, in accordance with aspects of this disclosure. Herein, the AI / ML based CSI may also be referred to as ML based CSI. As shown, upon measuring 220a CSI from one or more transmission occasions of CSI-RS, the UE calculates 230 the AI / ML model input, e.g., channel matrix, channel eigenvector, or beam combining matrix, based on the one or more transmission occasions of CSI-RS for channel measurement, and performs the AI / ML based CSI generation, e.g., compression of channel matrix, channel eigenvector or AI / ML compressed beam combining matrix W2 for each layer or multiple layers. The UE reports 240 the constructed or compressed CSI, e.g., the compressed channel matrix, channel eigenvector or compressed beam combining matrix for each layer or multiple layers in the CSI. On the network entity 104 side, the network entity 104 performs 250 AI / ML based CSI reconstruction to calculate the decompressed channel, decompressed channel eigenvector or decompressed beam combining matrix, and reconstructs 260 the CSI for the one or more transmissions occasions of CSI-RS.
[0078] Fig. 2B illustrates an example diagram 212 of AI / ML based CSI prediction, in accordance with aspects of this disclosure. As shown, upon measuring 220b CSI from one or more transmission occasions of CSI-RS, the UE calculates 232 the AI / ML model input, e.g., channel matrix, channel eigenvector, or beam combining matrix, based on one or multiple transmission occasions of CSI-RS for channel measurement in the past, performs 242 the AI / ML based CSI prediction to calculate the predicted CSI for one or more future instances, e.g., predicted channel matrix, channel eigenvector or AI / ML compressed beam combining matrix W2 for each layer or multiple layers, performs the CSI construction based on the predicted CSI, and reports constructed CSI. The UE compresses 243 the predicted CSI for the one or more future instances. On the network entity side, the network entity 104 performs 252 AI / ML based CSI reconstruction. The CSI generation and reconstruction may be based on non-AI / ML techniques, e.g., existing codebook (Type1 or Type2 codebook) . The network entity 104 reconstructs 262 the predicted CSI for one or more future instances.
[0079] Fig. 2C illustrates an example diagram 214 of AI / ML based joint CSI compression and prediction based on a single AI / ML model, in accordance with aspects of this disclosure. For AI / ML based compression and prediction, UE can perform the CSI prediction and compression based on one AI / ML model or separate AI / ML models. As shown, upon measuring 220c CSI from one or more transmission occasions of CSI-RS, the UE calculates the AI / ML model input, e.g., channel matrix, channel eigenvector, or beam combining matrix, based on the one or more transmission occasions of CSI-RS for channel measurement. The UE performs 234 the AI / ML based CSI prediction to calculate the predicted CSI for one or more future instances, e.g., predicted channel matrix, channel eigenvector or AI / ML compressed beam combining matrix W2 for each layer or multiple layers. The UE compresses 244 the predicted CSI for one or more future instances, based on the predicted CSI, and reports, to the network entity, the constructed CSI, e.g., the compressed channel matrix, channel eigenvector or compressed beam combining matrix for each layer or multiple layers in the CSI. On the network entity 104 side, the network entity 104 performs 254 AI / ML based CSI reconstruction to decompress the predicted CSI, including the decompressed channel, decompressed channel eigenvector or decompressed beam combining matrix, and reconstructs 264 the CSI for the one or more transmissions occasions of CSI-RS.
[0080] Fig. 2D illustrates an example diagram 216 of AI / ML based joint CSI compression and prediction based on separate AI / ML models, in accordance with aspects of this disclosure. As shown, upon measuring 220d CSI from one or more transmission occasions of CSI-RS, the UE uses different AI / ML models for CSI prediction 236 and CSI generation 246 (including, e.g., construction and compression) . The UE reports 248 the compressed predicted CSI for one or more future instances to the network entity. On the network entity 104 side, the network entity 104 performs 256 AI / ML based CSI reconstruction to decompress the predicted CSI, including the decompressed channel, decompressed channel eigenvector or decompressed beam combining matrix, and reconstructs 266 the CSI for the one or more transmissions occasions of CSI-RS.
[0081] Fig. 3 illustrates an example diagram 300 of CSI report for performance monitoring for AI / ML based CSI, in accordance with aspects of this disclosure. As shown, the UE 102 may optionally report 302 the UE capabilities indicating the supported configurations for the CSI report for performance monitoring for ML based CSI. For example, the UE 102 reports at least one of the UE 102 capabilities: whether the UE 102 supports reporting CSI for performance monitoring and AI / ML based CSI using one CSI report configuration, separate CSI report configurations, or both; whether the UE 102 supports separate performance monitoring or joint performance monitoring for AI / ML based joint CSI prediction and compression; the supported codebook type (s) for CSI report for performance monitoring; the supported high resolution codebook configurations for the CSI report for performance monitoring; the supported report quantity for the CSI report for performance monitoring; the recommended or supported periodicity or minimum periodicity for the CSI triggering / measurement / reporting window; the recommended or supported window size or minimum window size for the CSI triggering / measurement / reporting window; or the maximum number of configured CSI report configuration for performance monitoring in a slot or across slots in a component carrier (CC) or across CCs in a band or band combination.
[0082] Based on the received UE capabilities, the network entity 104 transmits 304 a control signaling configuring at least a first CSI report configuration for performance monitoring. For example, the control signaling includes a first CSI-RS resource set for channel measurement, a codebook configuration with high resolution CSI quantization, a report quantity indicating at least PMI report. In the first CSI report configuration, the network entity 104 may optionally configure the frequency granularity for CSI measurement, configuration of AI / ML based CSI report, interference measurement resource, thresholds for measurability determination for CSI report, and / or CSI triggering / measurement / reporting window.
[0083] For the configuration of AI / ML based CSI report, the network entity 104 may configure, via the control signaling, at least one of the followings: an AI / ML model identifier (ID) , an association ID for scenario and network entity 104 antenna information indication, a dataset ID for candidate model selection, a codebook configuration for AI / ML based CSI and so on.When the control signaling includes the configuration of AI / ML based CSI report, the CSI report configuration is denoted as the third CSI report configuration (e.g., the first CSI report configuration is used to indicate performance monitoring CSI configuration, while the thirds CSI report configuration is used to include both performance monitoring and AI / ML based CSI configuration) . In some cases, the network entity 104 may configure a second CSI report configuration for AI / ML based CSI report including at least a second CSI-RS resource set for channel measurement. The second CSI report configuration may be linked to the first CSI report configuration.
[0084] The network entity 104 may transmit 304 the control signaling by RRC signaling, e.g., RRCReconfiguration or CSI-ReportConfig. The network entity 104 may provide some of the configurations or update some of the configurations by medium access control (MAC) control element (CE) , e.g., MAC CE activating the (semi-persistent) CSI report, or downlink control information (DCI) , e.g., different triggering states for the DCI triggering the (aperiodic) CSI report may correspond to different configurations.
[0085] The UE 102 receives 308 CSI-RS or CSI-IM on the configured CSI-RS resources and performs respective channel measurement and interference measurement. In some implementations, for semi-persistent CSI report or aperiodic CSI report, the network entity may transmit MAC CE or DCI activating or triggering the CSI report. For semi-persistent CSI-RS or aperiodic CSI-RS, the network entity 104 may transmit 306 MAC CE or DCI to activate or trigger the CSI-RS. For example, the MAC CE or DCI triggers at least one of: the configured CSI report, the configured CSI-RS resources for channel measurement, or the configured CSI-RS / CSI-IM resources for interference measurement.
[0086] The UE 102 then transmits 310 the CSI report to the network entity 104. The CSI report includes at least a first CSI for performance monitoring and optionally including a second CSI for AI / ML based CSI report. The UE 102 may transmit the CSI report by an RRC message, e.g., an RRC message for performance monitoring, MAC CE, e.g., a MAC CE for performance monitoring, or uplink control information (UCI) on physical uplink control channel (PUCCH) , e.g., short PUCCH (PUCCH with less than 4 symbols) or long PUCCH (PUCCH with 4 or more symbols) or physical uplink shared channel (PUSCH) .
[0087] Fig. 4 illustrates an example diagram 400 of UE behavior for the CSI report for performance monitoring for AI / ML based CSI, in accordance with aspects of this disclosure. As shown, the UE optionally transmits 402 the UE capability regarding the supported configurations for CSI report for performance monitoring for AI / ML based CSI. The UE receives 404 a control signaling, which configures at least a first CSI report configuration for performance monitoring for AI / ML based CSI.
[0088] The control signaling may include at least a CSI-RS resource set for channel measurement, a codebook configuration with high resolution CSI quantization, and a report quantity indicating at least PMI report. The control signaling may optionally include configuration of frequency granularity for CSI measurement, configuration of AI / ML based CSI report, interference measurement resource, configuration of thresholds for measurability determination for CSI report, or configuration for CSI triggering / measurement / reporting window. In some cases, the control signaling may optionally configure a second CSI report configuration for AI / ML based CSI report, and includes at least a second CSI-RS resource set for channel measurement. The second CSI report configuration is linked to the first CSI report configuration.
[0089] The UE may optionally receive 406, from the network entity, a MAC CE or DCI triggering the configured CSI report and / or the configured CSI-RS resources for channel measurement and / or the configured CSI-RS / CSI-IM resources for interference measurement. The UE receives 408, from the network entity, one or more CSI-RS on the configured CSI-RS resources (or CSI-RS resource sets) for channel measurement and / or the configured CSI-RS / CSI-IM resources for interference measurement. The UE transmits 410, to the network entity, a CSI report including at least a first CSI for performance monitoring and optionally including a second CSI for AI / ML based CSI report.
[0090] In this disclosure, unless specified, a RRC signaling may indicate a RRC reconfiguration message from network entity 104 to UE, 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 gNB. In some implementations, the network entity may receive the UE capability from a UE or from a core network (e.g., Access and Mobility Management Function (AMF) ) or another network entity.
[0091] Fig. 5 illustrates an example diagram 500 of network entity behavior for the CSI report for performance monitoring for AI / ML based CSI, in accordance with aspects of this disclosure. The network entity behavior is complementary to the UE behavior as shown in Figs. 3 and 4. As shown, the network entity optionally receives 502 the UE capability regarding the supported configurations for CSI report for performance monitoring for AI / ML based CSI. The network entity transmits 504 a control signaling to the UE. The control signaling configures at least a first CSI report configuration for performance monitoring for AI / ML based CSI. Like in the example diagram 400, the control signaling may include at least a CSI-RS resource set for channel measurement, a codebook configuration with high resolution CSI quantization, and a report quantity indicating at least PMI report. The control signaling may optionally include configuration of frequency granularity for CSI measurement, configuration of AI / ML based CSI report, interference measurement resource, configuration of thresholds for measurability determination for CSI report, or configuration for CSI triggering / measurement / reporting window. In some cases, the control signaling may optionally configure a second CSI report configuration for AI / ML based CSI report, and includes at least a second CSI-RS resource set for channel measurement. The second CSI report configuration is linked to the first CSI report configuration.
[0092] The network entity may optionally transmit 506, to the UE, a MAC CE or DCI triggering the configured CSI report and / or the configured CSI-RS resources for channel measurement and / or the configured CSI-RS / CSI-IM resources for interference measurement. The network entity transmits 508, to the UE, one or more CSI-RS on the configured CSI-RS resources (or CSI-RS resource sets) for channel measurement and / or the configured CSI-RS / CSI-IM resources for interference measurement. The network entity receives 510, from the UE, a CSI report including at least a first CSI for performance monitoring, and optionally including a second CSI for AI / ML based CSI report.
[0093] Referring to Figs. 3-5, various embodiments of the control signaling configuring the CSI report are described below. For example, the control signaling may indicate separate CSI report configurations for performance monitoring and AI / ML based CSI report (option 1) . That is, the network entity 104 may configure at least two CSI report configurations in one bandwidth part (BWP) or a serving cell. Of the at least two CSI report configurations, the first CSI report configuration may be used for performance monitoring and the second CSI report configuration may be used for AI / ML based CSI report. In some implementations, the network entity 104 may indicate that the first CSI report configuration and the second CSI report configuration are linked or associated with each other.
[0094] In an embodiment, in the first CSI report configuration, the network entity 104 may configure a set of CSI-RS resource (s) for channel measurement. If one CSI-RS resource is configured, the UE calculates the CSI based on one or multiple transmission occasions of the CSI-RS resource. If multiple CSI-RS resources are configured, the CSI-RS resources may be from the same or different antenna ports. The UE may calculate the CSI based on one or multiple transmission occasions of all the CSI-RS resources. Alternatively, the CSI-RS resources may be divided into several CSI-RS resource groups, and the CSI-RS resources within a CSI-RS resource group are from different antenna ports, and different CSI-RS resource groups may be configured in different slots, as shown in Fig. 6.
[0095] Fig. 6 illustrates an example 600 for channel state information-reference signal (CSI-RS) configuration based on multiple resource groups, in accordance with aspects of this disclosure. As shown in Fig. 6, the network entity may configure the number of CSI-RS resources 612a-c and 622a-c per group or number of CSI-RS resource groups 630a-c. The CSI-RS resources 1, 3, and 5 (612a-c) are a CSI-RS resource 610 from a first set of antenna ports. The CSI-RS resources 2, 4, and 6 (622a-c) are a CSI-RS resource 620 from a second set of antenna ports. The network entity may configure the interval between every two consecutive CSI-RS resource groups (630a-c) . Accordingly, the UE may calculate the CSI based on the CSI-RS resource groups 630a-c. The CSI-RS resource may be periodic, semi-persistent, or aperiodic.
[0096] In some embodiments, the network entity 104 may configure the same value for at least one of the following parameters for the CSI-RS for channel measurement in the first and second CSI report configuration: bandwidth, time-domain behavior (aperiodic, periodic, semi-persistent) , number of ports, transmission configuration indication (TCI) state, power offset between the CSI-RS and SSB, power offset between the CSI-RS and PDSCH, CSI-RS resource ID, CSI-RS resource set ID, and so on. With regard to the impact of channel variation, the network entity 104 may configure the transmission occasion of each CSI-RS resource in the first CSI report configuration with up to Y slot offset compared to the transmission occasion of each CSI-RS resource in the second CSI report configuration as shown in Fig. 7.
[0097] Fig. 7 illustrates an example 700 for the time-domain configuration for the CSI-RS for the first and second CSI report configurations, in accordance with aspects of this disclosure. As shown, the network entity may configure CSI-RS resource 710 for the first CSI report configuration, and CSI-RS resource 720 for the second CSI report configuration. The CSI-RS resource 2 (722a-b) are a CSI-RS resource 720 of the second CSI report configuration. The CSI-RS resource 1 (712 and 714) are a CSI-RS resource 710 of the first CSI report configuration. When the CSI-RS resource 1 (712) is outside of the CSI-RS resource 2 (722a) by Y slot 730, the CSI-RS resource 1 is considered invalid. Otherwise, when the CSI-RS resource 1 (714) is within the CSI-RS resource 2 (722b) by Y slot 730, the CSI-RS resource 1 (714) is considered valid. The network entity configures the value of Y slot 730. Alternatively, the value of Y slot 730 may be pre-defined, e.g., 1 or 2. Or the value of Y slot 730 may be reported by the UE 102 with the UE capability. The UE may receive the CSI-RS resources for both CSI report configuration from the same UE antenna port (s) and / or the same spatial reception filter.
[0098] In some implementations, the network entity 104 may configure interference measurement resource (s) (IMR (s) ) , e.g., CSI-RS resource (s) for interference measurement or CSI interference measurement (CSI-IM) resource (s) in the first CSI report configuration. In some other implementations, the network entity 104 may configure CSI-RS for channel measurement only in the first CSI report configuration. Thus, the network entity 104 may refrain from configuring IMR in the first CSI report configuration.
[0099] In some implementations, the network entity 104 may configure common codebook subset restriction (CBSR) for the first and second CSI report configuration. In some other implementations, the network entity 104 may refrain from configuring CBSR for the first and / or second CSI report configuration.
[0100] In an embodiment, in the first CSI report configuration, the network entity 104 may configure the CSI report based on a Type2 / eType2 codebook, e.g., the codebookType may be set as type2 or typeII-Doppler.
[0101] In some implementations, the network entity 104 may configure the parameters for the codebook based on higher resolution, e.g., the network entity 104 may configure the UE to report more beams, e.g., more than 6 beams (L>6) , more FD basis, e.g., pv larger than 1 / 2, and / or more non-zero-power (NZP) coefficients, e.g., beta larger than 3 / 4, where L, pv and beta are defined, for example, in 3GPP TS section 5.2.2.2.5. The network entity 104 may refrain from configuring such codebook for other types of CSI report, e.g., CSI report with a different report quantity as the first CSI report or CSI report based on a different minimum processing delay and / or CPU occupancy rule or CSI report based on a different type of CSI report configuration compared to the first CSI report configuration.
[0102] The network entity 104 may configure number of horizontal antenna ports (N1) , number of vertical antenna ports (N2) , oversampling factor in horizontal for spatial domain (SD) basis selection (O1) and oversampling factor in vertical for SD basis selection (O2) . The network entity 104 may configure larger value of (O1, O2) for high resolution beam selection. The network entity 104 may configure the UE to report layer-common layer-specific beams (i.e., SD basis) , e.g., to report common or separate beam indexes for each layer. The network entity 104 may configure the UE to report polarization-common or polarization-specific beams, (i.e., SD basis) , e.g., to report common or separate beam indexes for each polarization. The network entity 104 may configure the UE to report the strongest coefficient and / or other NZP coefficient based on smaller quantization step size or based on a greater number of bits.
[0103] The network entity 104 may configure FD basis oversampling factor O3 for high resolution compression in frequency domain. Then the network entity 104 and UE may determine the candidate FD basis m for the WFD as equation (5) , where N3 indicates the number of subbands, which may be configured by the network entity 104 or determined based on the bandwidth of the CSI-RS for channel measurement.
[0104] In some implementations, when the network entity 104 may configure the UE to report CSIs for multiple time-domain instances, it may configure the number of reported Doppler Domain (DD) basis. The network entity 104 may further configure the oversampling factor O4 for DD basis report. Then the network entity 104 and UE may determine the DD basis m as equation (6) , where N4 indicates the number of time-domain instances for the CSI report.
[0105] CSI instances may be configured according to the following examples. In some embodiments, the CSI report for future instance is based on non-AI / ML prediction and non-AI / ML compression (option A) . For example, in the first CSI report configuration, the network entity 104 may configure the UE 102 to report the CSI for future time instances. The network entity 104 may configure the future time instance (s) for the CSI report. In one example, the network entity 104 may configure the slot offset based on the first slot of the CSI report or the CSI reference resource, where the CSI reference resource may be defined as X slots before the first slot of the CSI report. The value of X may be pre-defined or reported by UE capability or configured by the network entity 104. In one example, the CSI reference resource may be defined as in 3GPP TS 38.214 section 5.2.2.5. The network entity 104 may configure a codebook, e.g., Type2 / eType2 / eType2-Doppler for the CSI report. The network entity 104 may configure the CSI prediction is based on non-AI / ML operation. Figure 8a illustrates one example for the CSI report for future instance based on non-AI / ML prediction and non-AI / ML compression.
[0106] In some embodiments, the CSI report for future instance is based on AI / ML prediction and non-AI / ML compression (option B) . For example, in the first CSI report configuration, the network entity 104 may configure the UE to report the CSI for future time instances. The network entity 104 may configure the future time instance (s) for the CSI report. In one example, the network entity 104 may configure the slot offset based on the first slot of the CSI report or the CSI reference resource, where the CSI reference resource may be defined as X slots before the first slot of the CSI report. The value of X may be pre-defined or reported by UE capability or configured by the network entity 104. In one example, the CSI reference resource may be defined as 3GPP TS 38.214 section 5.2.2.5. The network entity 104 may configure a codebook for CSI generation, e.g., Type2 / eType2 / eType2-Doppler codebook. The network entity 104 may configure the CSI prediction is based on AI / ML operation.
[0107] In some embodiments, the CSI report for future instance is based on non-AI / ML prediction and AI / ML compression (option C) . For example, in the first CSI report configuration, the network entity 104 may configure the UE to report the CSI for future time instances. The network entity 104 may configure the future time instance (s) for the CSI report. In one example, the network entity 104 may configure the slot offset based on the first slot of the CSI report or the CSI reference resource, where the CSI reference resource may be defined as X slots before the first slot of the CSI report. The value of X may be pre-defined or reported by UE capability or configured by the network entity 104. In one example, the CSI reference resource may be defined as 3GPP TS 38.214 section 5.2.2.5. The network entity 104 may configure the CSI generation is based on AI / ML. The network entity 104 may configure the CSI prediction is based on non-AI / ML operation.
[0108] In some embodiments, the CSI report for one or more transmission occasions of the CSI-RS is based on AI / ML compression (option D) . For example, in the first CSI report configuration, the network entity 104 may configure the UE to report the CSI for one or multiple transmission occasions of the CSI-RS resource (s) for channel measurement. In one example, the network entity 104 may configure number of transmission occasions M, and the UE calculates the CSI based on the M transmission occasions, e.g., most recent M transmission occasions, before the CSI-RS reference resource. UE may report the UE capability indicating the supported maximum value of M. The network entity 104 may configure the CSI generation is based on AI / ML.
[0109] In some embodiments, the CSI report for one or more transmission occasions of the CSI-RS is based on non-AI / ML compression (option E) . For example, in the first CSI report configuration, the network entity 104 may configure the UE 102 to report the CSI for one or multiple transmission occasions of the CSI-RS resource (s) for channel measurement. In one example, the network entity 104 may configure number of transmission occasions M, and the UE 102 calculates the CSI based on the M transmission occasions before the CSI-RS reference resource. The network entity 104 may configure a codebook for CSI generation, e.g., Type2 / eType2 / eType2-Doppler codebook. Then the UE 102 performs the CSI generation based on the codebook.
[0110] In some embodiments, multiple types of CSI reports are based on different CSI calculation options. For example, the network entity 104 may configure the UE 102 to report one or multiple types of CSI based on multiple of options from option A to option E. The UE 102 may report the UE capability indicating the supported options for the CSI report for performance monitoring.
[0111] In some implementations, in the first CSI report configuration, the network entity 104 may configure the UE 102 to report PMI only (scheme A) . In one example, the network entity 104 may configure the reportQuantity in the CSI report configuration as ‘PMI’ . The UE 102 may report the PMI based on a number of layers, where the number of layers may be predefined, e.g., 1, or configured by the network entity 104 via RRC signaling, MAC CE or DCI, or reported by the UE capability, or be determined based on at least one of the followings: maximum number of layers for the PDSCH transmission, maximum number of layers for the CSI report in the second CSI report configuration, or number of layers for a CSI report for the second CSI report configuration, e.g., most recent CSI report before the CSI reference resource for the CSI report for the first CSI report configuration.
[0112] In some implementations, in the first CSI report configuration, the network entity 104 may configure the UE 102 to report RI and PMI (scheme B) . In one example, the network entity 104 may configure the reportQuantity in the CSI report configuration as ‘RI-PMI’ . The network entity 104 may configure a RI restriction indicating the candidate RI (s) . If one RI is configured in the RI restriction, the UE 102 report the PMI only based on the indicated RI. The UE 102 reports the RI and PMI corresponding to the reported RI. In some implementations, the UE 102 may determine the RI based on the RI reported in a CSI report for the second CSI report configuration, e.g., most recent CSI report before the CSI reference resource for the CSI report for the first CSI report configuration.
[0113] In some implementations, in the first CSI report configuration, the network entity 104 may configure the UE 102 to report PMI and CQI (scheme C) . In one example, the network entity 104 may configure the reportQuantity in the CSI report configuration as ‘PMI-CQI’ . The UE 102 may report the PMI based on a number of layers, where the number of layers may be predefined, e.g., 1, or configured by the network entity 104, or reported by the UE capability, or be determined based on at least one of the followings: maximum number of layers for the PDSCH transmission, maximum number of layers for the CSI report in the second CSI report configuration, or number of layers for a CSI report for the second CSI report configuration, e.g., most recent CSI report before the CSI reference resource for the CSI report for the first CSI report configuration. The UE 102 may calculate the CQI based on the reported PMI.
[0114] In some implementations, in the first CSI report configuration, the network entity 104 may configure the UE 102 to report RI, PMI, and CQI (scheme D) . In one example, the network entity 104 may configure the reportQuantity in the CSI report configuration as ‘RI-PMI-CQI’ . The network entity 104 may configure a RI restriction indicating the candidate RI (s) . If one RI is configured in the RI restriction, the UE 102 report the PMI only based on the indicated RI.
[0115] In some implementations, the UE 102 reports the RI and PMI corresponding to the reported RI (scheme D1) . In some implementations, the UE 102 may determine the RI based on the RI reported in a CSI report for the second CSI report configuration, e.g., most recent CSI report before the CSI reference resource for the CSI report for the first CSI report configuration. The UE 102 may calculate the CQI based on the reported RI and PMI.
[0116] In some other implementations, the UE 102 may calculate and report the PMI based on a number of layers, e.g., maximum number of layers for PDSCH transmission or CSI report, and the UE 102 may report the RI indicating the layers for CQI calculation (scheme D2) . In one example, the UE 102 reports the RI indicating the number of layers v and calculate the CQI based on the first v layers from the reported PMI. In another example, the UE 102 reports the RI as a bitmap indicating the layer index for CQI calculation. Bit x (starting from bit 1) may indicate whether layer x is used or not for CQI calculation.
[0117] In some other implementations, the UE 102 may report two PMIs (scheme D3) . The first PMI is based on the reported RI, and the UE 102 calculates the CQI based on the RI and the first PMI. The second PMI is based on a number of layers, e.g., maximum number of layers for PDSCH transmission or CSI report, or number of layers for a CSI report for the second CSI report configuration, e.g., most recent CSI report before the CSI reference resource for the CSI report for the first CSI report configuration.
[0118] In some implementations, the network entity 104 may configure the report quantity based on one of the schemes from scheme A to scheme D (including scheme D1 to scheme D3) . The UE 102 may report the UE capability indicating the supported scheme (s) .
[0119] In an embodiment, in the first CSI report configuration, the network entity 104 may configure the frequency granularity for the RI / PMI / CQI report. The frequency granularity configuration may include whether the RI / PMI / CQI is measured and reported based on wideband operation, e.g., the whole bandwidth of the CSI-RS, or subband operation. For subband operation, the network entity 104 may further configure one or multiple subband (s) for the RI / PMI / CQI report. The network entity 104 may configure the frequency granularity separately or commonly for RI / PMI / CQI. In some implementations, the UE 102 may always report wideband RI. In some other implementations, the network entity 104 may configure the same frequency granularity for the first CSI report configuration and the second CSI report configuration.
[0120] In an embodiment, if the network entity 104 configures multiple CSI-RS resources for channel measurement in the first CSI report configuration, which are based on different TCI states, the UE 102 may calculate and report the CSI based on one or multiple of the CSI-RS resources. The CSI-RS resource (s) for the CSI report may be configured by the network entity 104 via RRC signaling, MAC CE or DCI, or determined based on the CSI-RS resource for a CSI report for the second CSI report configuration, e.g., most recent CSI report before the CSI reference resource for the CSI report for the first CSI report configuration. Alternatively, the UE 102 may report one or multiple CRIs additionally indicating the CSI-RS resource (s) for channel measurement.
[0121] In an embodiment, when cell discontinuous transmission (DTX) is configured and activated by the network entity 104, the UE 102 may not receive the CSI-RS associated with a CSI report configuration with the report quantity including at least PMI or RI during the cell DTX non-active period (s) . The UE 102 may receive the CSI-RS associated with a CSI report configuration with the report quantity including at least PMI or RI during the cell DTX active period (s) .
[0122] In one example, during non-active periods of cell DTX if cell DTX is activated for a serving cell, the UE 102 is not expected to receive the periodic CSI-RS and semi-persistent CSI-RS on the serving cell configured in CSI report configuration in CSI-ReportConfig associated with the higher layer parameter reportQuantity comprising at least ‘RI’ or ‘PMI’ .
[0123] In another example, if the cell DTX is activated for a serving cell, the most recent CSI measurement occasion of semi-persistent CSI-RS resource or periodic CSI-RS resource on the serving cell occurs in active periods of cell DTX for CSI report configured by CSI-ReportConfig associated with the higher layer parameter reportQuantity comprising at least ‘RI’ or ‘PMI’ .
[0124] In another example, for the CSI report configuration in CSI-ReportConfig associated with the higher layer parameter reportQuantity comprising at least ‘RI’ or ‘PMI’ , the UE 102 reports a CSI report only if receiving at least X CSI-RS transmission occasion of each periodic CSI-RS resource or semi-persistent CSI-RS resource on a serving cell with cell DTX activated 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. The value of X may be configured by the network entity 104 or pre-defined, e.g., X=1, or reported by the UE 102.
[0125] In an embodiment, the network entity 104 may configure a third CSI report configuration for performance monitoring and AI / ML based CSI report (option 2 -one CSI report configuration for performance monitoring and AI / ML based CSI report) . Compared to the aforementioned CSI configuration (option 1 -separate CSI report configurations for performance monitoring and AI / ML based CSI report) , the difference is that the network entity 104 may provide additional configuration (s) for the AI / ML based CSI report in the CSI report configuration for performance monitoring, and UE may report at least two CSIs. Of the two or more CSIs, the first CSI is for performance monitoring based on the report option and scheme, and the second CSI is for AI / ML based CSI report.
[0126] Fig. 8 illustrates an example diagram of a CSI report configuration 810 for performance monitoring and AI / ML based CSI report in different CSI report sub-configurations, in accordance with aspects of this disclosure. As shown, the network entity 104 may configure at least two CSI report sub-configurations 812 and 814 in the CSI report configuration 810. The sub-configuration 812 is for performance monitoring, having a codebook configuration of, e.g., Type2 / eType2 / eType2-Doppler codebook, with a report quantity configuration. The sub-configuration 814 may be for AI / ML based CSI report, having a configuration for AI / ML based CSI report, including, e.g., model ID, associated ID, dataset ID, codebook configuration for AI / ML based CSI, and the like, with a report quantity configuration.
[0127] On CSI-RS configuration, in an embodiment, in the third CSI report configuration (e.g., 810) , the network entity 104 may configure common CSI-RS resources for channel measurement for performance monitoring and the AI / ML based CSI report. Alternatively, the network entity 104 may configure separate CSI-RS resources for channel measurement for performance monitoring and the AI / ML based CSI report. The network entity 104 may configure the same value for at least one of the following parameters for the CSI-RS for channel measurement for performance monitoring and the AI / ML based CSI report: bandwidth, time-domain behavior (aperiodic, periodic, semi-persistent) , number of ports, transmission configuration indication (TCI) state, power offset between the CSI-RS and SSB, power offset between the CSI-RS and PDSCH, and so on. With regard to the impact of channel variation, the network entity 104 may configure the transmission occasion of each CSI-RS resource for performance monitoring with up to Y slot offset compared to the transmission occasion of each CSI-RS resource for the AI / ML based CSI report. The value of Y may be pre-defined, e.g., 1 or 2, or reported by the UE capability, or configured by the network entity.
[0128] In some implementations, in the third CSI report configuration, the network entity 104 may configure common interference measurement resource (s) (IMR) , e.g., CSI-RS resource (s) for interference measurement or CSI-IM resource (s) , for performance monitoring and the AI / ML based CSI report. Alternatively, the network entity 104 may configure separate IMRs for performance monitoring and the AI / ML based CSI report. Alternatively, the network entity 104 may configure the IMR for AI / ML based CSI report only.
[0129] In an embodiment, in the third CSI report configuration, the network entity 104 may configure the codebook based on the same scheme as option 1 (separate CSI report configurations for performance monitoring and AI / ML based CSI report) for CSI report for performance monitoring.
[0130] In an embodiment, in the third CSI report configuration, if common CSI-RS resource (s) for channel measurement are configured for performance monitoring and AI / ML based CSI, the network entity 104 may configure the common CSI instances or CSI-RS transmission occasions for the CSI report performance monitoring and AI / ML based CSI.
[0131] In some implementations, in the third CSI report configuration, if separate CSI-RS resource (s) for channel measurement are configured for performance monitoring and AI / ML based CSI, the network entity 104 may configure separate CSI instances or CSI-RS transmission occasions for the CSI report for performance monitoring and AI / ML based CSI. In one example, the network entity 104 may configure the CSI instances or CSI-RS transmission occasion information in each CSI report sub-configuration.
[0132] In an embodiment, in the third CSI report configuration, the network entity 104 configures separate CSI report quantities for CSI report for performance monitoring and AI / ML based CSI. In one example, the network entity 104 may configure different report quantities in different CSI report sub-configurations.
[0133] In some other implementations, in the third CSI report configuration, the network entity 104 may configure the UE to report the CSI based on one of the Scheme A to Scheme D and AI / ML based CSI. For AI / ML based CSI, the network entity 104 may configure the UE to report one or multiple of the components including CRI, RI, PMI, CQI, and LI. The UE may calculate the RI / PMI based on the CSI-RS resource (s) for channel measurement corresponding to the reported CRI or configured by the network entity 104 and an AI / ML model corresponding to the AI / ML based CSI. The UE may calculate the CQI and LI based the reported CRI / RI / PMI.
[0134] In some implementations, the network entity 104 may configure or indicate whether the CSI report corresponding to the third CSI report configuration should include the CSI for performance monitoring, AI / ML based CSI or both. The network entity 104 may provide the configuration or indicating by RRC signaling, MAC CE, or DCI.
[0135] On CSI report mechanisms, in an embodiment, for the CSI report corresponding to the first or third CSI report configuration, the UE may report the CSI based on one of the following mechanisms: RRC message, e.g., an RRC message for performance monitoring, MAC CE, e.g., a MAC CE for performance monitoring, or uplink control information (UCI) on PUCCH, e.g., short PUCCH (PUCCH with less than 4 symbols) or long PUCCH (PUCCH with 4 or more symbols) or PUSCH.
[0136] The network entity 104 may configure the UE report the CSI corresponding to the first or third CSI report configuration periodically, semi-persistently or aperiodically. The UE may report the UE capability indicating whether it supports periodic, semi-persistent or aperiodic CSI report for performance monitoring.
[0137] In an embodiment, the UE may determine whether a transmission occasion for the CSI-RS resource (s) is measurable or not. The UE may determine a transmission occasion for a CSI-RS resource is not measurable if it identifies one or more of the followings situations, and may determine a transmission occasion for a CSI-RS resource is measurable otherwise. The situations include at least one of:
[0138] ● The measured reference signal received power (RSRP) , e.g., layer 1 reference signal received power (L1-RSRP) , for the CSI-RS resource is below a first threshold;
[0139] ● The measured signal-to-interference plus noise ratio (SINR) , e.g., layer 1 signal-to-interference plus noise ratio (L1-SINR) , for the CSI-RS resource is below a second threshold;
[0140] ● UE failed to receive the transmission occasion of the CSI-RS resource;
[0141] ● The delay offset between the transmission occasion of the CSI-RS resource and a reference downlink channel / signal is above a third threshold, e.g., cyclic prefix (CP) size, where the reference downlink channel / signal may be configured by the network entity 104 or pre-defined, e.g., PDSCH or CSI-RS in the indicated TCI state for PDSCH or SSB associated with the indicated TCI state for PDSCH;
[0142] ● The offset between the transmission occasion of the CSI-RS resource and the first slot of the CSI report is below the minimum processing delay;
[0143] ● The number of CSI processing units (CPUs) exceeds the maximum number of CPUs and the CSI or CSI report is with lower priority than other CSI or CSI report; or
[0144] ● Channel estimation error (CEE) , e.g., maximum or minimum or average mean square error (MSE) for the subcarriers for the CSI-RS resource for channel measurement for each port or across all the ports, is above a fourth threshold.
[0145] In some implementations, the UE 102 may measure the RSRP / SINR based on one or multiple antenna ports of the CSI-RS resource, where the antenna port (s) may be pre-defined, e.g., the first antenna port or the first two antenna ports or all the antenna ports for the CSI-RS resource, or configured by the network entity 104. If the UE 102 measures the RSRP / SINR based on multiple antenna ports of the CSI-RS resource, the UE 102 may determine the measurable status based on minimum, maximum or average (e.g., linear average) RSRP / SINR for the antenna ports.
[0146] In some implementations, for a UE 102 with multiple antenna ports, it may measure the RSRP / SINR based on the minimum or average or maximum RSRP / SINR measured from the multiple UE 102 antenna ports.
[0147] In some implementations, the first / second / third / fourth thresholds may be pre-defined or configured by the network entity 104 or reported by the UE 102 via UE capability.
[0148] In some implementations, the minimum processing delay for the CSI report configuration may be pre-defined or reported by UE capability. The network entity 104 and UE 102 may determine the minimum processing delay based on at least one of the followings: codebook type, the number of instances or CSI-RS transmission occasions for CSI report, interval between every two instances or CSI-RS transmission occasions, the report quantity and a UE capability. In one example, two types of minimum processing delay may be pre-defined and the UE 102 may report a UE capability indicating which type of minimum processing delay it supports. For the third CSI report configuration, the network entity 104 and UE 102 may determine the minimum processing delay based on the maximum or sum of the minimum processing delay for CSI report for performance monitoring and the AI / ML based CSI report.
[0149] In some implementations, the number of CPUs for the CSI report configuration may be pre-defined or reported by UE capability. The network entity 104 and UE 102 may determine the number of CPUs based on at least one of the followings: codebook type, the number of instances or CSI-RS transmission occasions for CSI report, the report quantity and a UE capability. In one example, two types of CPU occupancy rules may be pre-defined and the UE 102 may report a UE capability indicating which type of CPU occupancy rule it supports. For the third CSI report configuration, the network entity 104 and UE 102 may determine the number of CPUs based on the maximum or sum of the number of CPUs for CSI report for performance monitoring and the AI / ML based CSI report.
[0150] In some implementations, in the CSI report, the UE 102 may report an indicator indicating the CSI is invalid or drop the CSI report if it identifies at least one of the transmission occasions of a CSI-RS resource for channel measurement is not measurable or if none of the transmission occasions of a CSI-RS resource for channel measurement is measurable. The indicator may be an independent indicator. In one example, the UE 102 may report the indicator in CSI part 1 in long PUCCH or PUSCH. Alternatively, the indication of invalid CSI is based on the reported CRI / RI / PMI / CQI. Thus, one of the states of the CRI / RI / PMI / CQI may indicate the CSI is invalid.
[0151] In some other implementations, the UE 102 may report valid CSI if it identifies at least M transmission occasions of each CSI-RS resource for channel measurement are measurable, where the value of M may be predefined, e.g., 1, or configured by the network entity 104 or reported by the UE 102. The UE 102 may report an indicator indicating the reported CSI is valid CSI.
[0152] In some other implementations, the UE 102 may determine whether a subband CSI is valid or not, and report an indicator indicating whether a subband CSI is valid or not, or whether a subband CSI is reported or not.
[0153] Fig. 9 illustrates an example 900 for the UE behavior to report a measurability status of the CSI-RS, in accordance with aspects of this disclosure. As shown, the UE first determines 901 the measurability status for each transmission occasion of the CSI-RS resource (s) for channel measurement. The UE determines 903 if the measurability status for each transmission occasion of the CSI-RS resource (s) for channel measurement meet the criteria to report valid CSI report. If so (following the “Yes” branch) , the UE reports 905, to the network entity, the measured CSI corresponding to the CSI report configuration and optionally reports an indicator indicating the CSI is valid. Otherwise (following the “No” branch) , the UE reports 907 an indicator indicating the CSI is invalid, or UE drops the CSI report.
[0154] In an embodiment, for the CSI report for performance monitoring, the network entity 104 may configure the UE reports one or multiple of the followings for each CSI:
[0155] ● RSRP, e.g., L1-RSRP, for each of the CSI-RS resource for channel measurement;
[0156] ● SINR, e.g., L1-SINR, for each of the CSI-RS resource for channel measurement; or
[0157] ● Channel estimation error (CEE) , e.g., maximum or minimum or average mean square error (MSE) for the subcarriers for the CSI-RS resource for channel measurement for each port or across all the ports.
[0158] In some implementations, the UE may measure and report the RSRP / SINR / CEE in wideband manner, e.g., the whole bandwidth of the CSI-RS resource for channel measurement. In some other implementations, the network entity 104 may configure whether the UE should measure and report RSRP / SINR / CEE in wideband manner or subband manner. The network entity 104 may further configure the number of subbands, subband size and / or subband index (es) for the subband RSRP / SINR / CEE measurement and report. The network entity 104 may configure the common or separate subband configuration for the CSI report and the RSRP / SINR / CEE report.
[0159] Then based on the UE report, the network entity 104 can determine whether the reported CSI is valid or not for the performance monitoring.
[0160] In some implementations, the network entity 104 may configure the UE to perform the CSI report based on the combination of option 1 and option 2. Thus, UE determines whether the CSI is valid or not. If the CSI is valid, UE reports the RSRP / SINR / CEE in addition to the CSI; otherwise, UE reports an indication indicating the CSI is invalid, or UE drops the CSI report.
[0161] Fig. 10A illustrates an example 1010 for the CSI report based on a CSI triggering window, in accordance with aspects of this disclosure. As shown, the network entity 104 may configure a CSI triggering window 1040 for the CSI report, e.g., for the first / third CSI report configuration for performance monitoring. The network entity 104 transmits CSI-RS resource 1 (1012) and DCIs 1022 and 1024 to the UE. Because the DCI 1022 is outside of the CSI triggering window 1040, the DCI 1022 is considered invalid and the UE 102 ignores the DCI 1022. In some aspects, the UE 102 may determine that the invalid DCI 1022 is an error case. The DCI 1024 is within the CSI triggering window 1040, and is therefore considered valid. In response to the DCI 1024, the UE 102 transmits the CSI report 1032 to the network entity 104.
[0162] The network entity 104 may configure at least one of the followings for the triggering window: the periodicity of the triggering window, the duration of the triggering window and the slot offset for the first slot of each triggering window. Then the network entity 104 may transmit the DCI within the triggering window, which triggers the CSI report. The network entity 104 may refrain from transmitting a DCI outside the triggering window, which triggers the CSI report. Alternatively, the UE 102 ignores the DCI outside the triggering window, which triggers the CSI report.
[0163] Fig. 10B illustrates an example 1020 for the CSI report based on a CSI reporting window, in accordance with aspects of this disclosure. As shown, the network entity 104 may configure a reporting window 1050 for the CSI report, e.g., for the first / third CSI report configuration for performance monitoring. The network entity 104 transmits CSI-RS resource 1 (1014) and DCIs 1025 and 1027 to the UE. Because the DCI 1025 is triggering a CSI report 1033 outside of the CSI reporting window 1050, the DCI 1025 is considered invalid and the UE 102 ignores the DCI 1025. In some aspects, the UE 102 may determine that the invalid DCI 1025 is an error case. In some aspects, the UE 102 may drop the CSI report based on the invalid DCI 1025. The DCI 1027 is triggering a CSI report 1034 within the CSI reporting window 1050, and is therefore considered valid. In response to the DCI 1027, the UE 102 transmits the CSI report 1034 to the network entity 104.
[0164] The network entity 104 may configure at least one of the followings for the reporting window 1050: the periodicity of the reporting window, the duration of the reporting window and the slot offset for the first slot of each reporting window. Then the network entity 104 may transmit the DCI triggering the CSI report in the reporting window. The network entity 104 may refrain from transmitting a DCI triggering the CSI report outside the reporting window. Alternatively, the UE 102 ignores the DCI triggering the CSI report outside the reporting window.
[0165] Fig. 10C illustrates an example 1030 for the CSI report based on a CSI measurement window, in accordance with aspects of this disclosure. As shown, the network entity 104 may configure a measurement window 1060 for the CSI report, e.g., for the first / third CSI report configuration for performance monitoring. The network entity 104 transmits CSI-RS resource 1 (1016) and DCI 1028 to the UE. The DCI 1028 triggers the CSI report 1036, which falls within the CSI measurement window 1060, and is therefore valid. In response to the DCI 1028, the UE 102 transmits the CSI report 1036 to the network entity 104.
[0166] The network entity 104 may configure at least one of the followings for the measurement window 1060: the periodicity of the measurement window, the duration of the measurement window and the slot offset for the first slot of each measurement window. Then the UE 102 only measures the transmission occasion (s) of the CSI-RS resources for the CSI report within the most recent measurement window before the CSI reference resource. The UE 102 reports the CSI based on the received transmission occasion (s) of the CSI-RS resources for the CSI report within the corresponding measurement window.
[0167] Fig. 11 illustrates a flowchart of a method 1100 of wireless communication at a UE. With reference to Fig. 1, 3-5, and 13, the method may be performed by the UE 102, the UE apparatus 1302, etc., which may include the memory 1326', 1306', 1316, and which may correspond to the entire UE 102 or the entire UE apparatus 1302, or a component (e.g., the CSI configuration component 140) of the UE 102 or the UE apparatus 1302, such as the wireless baseband processor 1326 and / or the application processor 1306.
[0168] As shown in Fig. 11, the method 1100 starts where the UE optionally transmits 1102, to a network entity, UE capability information for supporting a first codebook configuration for a first type of CSI report (e.g., a ground-truth CSI report) and a second codebook configuration for a second type of CSI report (e.g., a ML based CSI report) (similar to operations 302 and 402 of Figs. 3 and 4) .
[0169] The UE receives 1104, from the network entity, a configuration configuring a CSI-RS resource set for channel measurement and indicating a first codebook configuration for a first type of CSI report having a higher CSI quantization resolution than that of a second codebook configuration for a second type of CSI report, the first and second type of CSI reports being associated with ML based CSI (similar to operations 304 and 404 of Figs. 3 and 4) .
[0170] The UE receives 1108, from the network entity, a CSI-RS according to the CSI-RS resource set (similar to operations 308 and 408 of Figs. 3 and 4) .
[0171] The UE transmits 1110, to the network entity, the first type of CSI report based on measurements of the CSI-RS (similar to operations 310 and 410 of Figs. 3 and 4) .
[0172] In aspects, the method further includes transmitting, to the network entity, UE capability information for supporting the first codebook configuration for the first type of CSI report and the second codebook configuration for the second type of CSI report.
[0173] In some cases, the method further includes receiving, from the network entity, a triggering signal that triggers the first type of CSI report or associated measurements on the CSI-RS, and transmitting, to the network entity, the second type of CSI report.
[0174] In aspects, the configuration further configures at least one of: a first CSI-RS resource set for channel measurement associated with the first type of CSI report, and a second CSI-RS resource set for channel measurement associated with the second type of CSI report; the first codebook configuration for the first type of CSI report, and the second codebook configuration for the second type of CSI report; a first CSI report configuration for the first type of CSI report associated with performance monitoring of the ML based CSI, and a second CSI report configuration for the second type of CSI report associated with reporting the ML based CSI, wherein the second CSI report configuration is associated to the first CSI report configuration; a report quantity indicating at least one precoding matrix indicator (PMI) report; a frequency granularity; an interference measurement resource; a configuration of thresholds for a measurability determination for the CSI report; a configuration for a CSI triggering window; a configuration for a CSI measurement window; or a configuration for a CSI reporting window.
[0175] In some cases, the second CSI report configuration is different from the first CSI report configuration, wherein the first CSI report configuration and the second CSI report configuration are for a bandwidth part (BWP) or a serving cell.
[0176] In some cases, the first and second CSI-RS resource sets include CSI-RS resources from a common antenna port or a plurality of different antenna ports, wherein the CSI-RS resources includes multiple CSI-RS resource groups each including CSI-RS resources from different antenna ports, and wherein different CSI-RS resource groups are configured in different slots.
[0177] In aspects, the configuration includes: a first CSI report sub-configuration for the first type of CSI report for performance monitoring of ML based CSI; and a second CSI report sub-configuration for the second type of CSI report indicating a model identifier (ID) for the ML based CSI.
[0178] In aspects, the first and the second codebook configurations include Type2 codebook, enhanced Type2 (eType2) codebook, or eType2-Doppler codebook, and wherein a first codebook for the first type of CSI report is for a ground-truth CSI report and a second codebook for the second type of CSI report is for ML based CSI report.
[0179] In some cases, a first parameter associated the first codebook has a higher resolution than a second parameter associated with the second codebook, wherein the first and second parameters include at least one of: a number of reported beams; a number of non-zero-coefficients for beam combining matrix; a number of horizontal antenna ports; a number of vertical antenna ports; an oversampling factor in horizontal dimension; an oversampling factor in vertical dimension; an oversampling factor in frequency domain; or a number of time instances for measuring CSI.
[0180] In aspects, the configuration indicates at least one of: reporting the first type of CSI report for first future instances based on non-ML prediction and non-ML compression; reporting the first type of CSI report for second future instances based on ML prediction and non-ML compression; reporting the first type of CSI report for third future instances based on non-ML prediction and ML compression; reporting the first type of CSI report for a first transmission occasion of the CSI-RS based ML compression; or reporting the first type of CSI report for a second transmission occasion of the CSI-RS based non-ML compression.
[0181] In aspects, the first type of CSI report includes at least one of: a precoding matrix indicator (PMI) ; a rank indicator (RI) and a PMI; a PMI and a channel quality indicator (CQI) ; or an RI, a PMI, and a CQI.
[0182] In some cases, the first CSI report configuration further indicates a frequency granularity for the first type of CSI report, the frequency granularity indicating whether the first type of CSI report is measured based on a wideband operation or a subband operation.
[0183] In aspects, the method further includes determining, at the UE, whether a transmission occasion for the CSI-RS is measurable based on at least one of: a measured reference signal received power (RSRP) being below a first threshold; a measured signal-to-interference plus noise ratio (SINR) being below a second threshold; a failure to receive the transmission occasion of the CSI-RS; a delay offset between the transmission occasion of the CSI-RS and a reference downlink channel or signal is above a third threshold; an offset between the transmission occasion of the CSI-RS and a first slot of the CSI report being below a minimum processing delay; a number of CSI processing units (CPUs) exceeding a maximum number of CPUs; channel estimation error being above a fourth threshold; or a minimum, a maximum, or an average value of RSRP or SINR for one or more antenna ports of the CSI-RS. The UE then transmits, to the network entity, a measurable status for the first type of CSI report when the transmission occasion is measurable.
[0184] In aspects, the configuration further includes a triggering window, which is characterized by a first periodicity, a first duration, and a first slot offset for a first slot of the triggering window. The method further includes transmitting the first type of CSI report in response to receiving, from the network entity, a first downlink control information (DCI) within the triggering window, and ignoring a second DCI outside the triggering window.
[0185] In aspects, the configuration further includes a reporting window for the transmitting the first type of CSI report, which is characterized by a second periodicity, a second duration, and a second slot offset for a second slot of the reporting window. The method further includes transmitting the first type of CSI report in response to receiving a valid DCI that triggers the first type of CSI report within the reporting window, and dropping the first type of CSI report in response to receiving an invalid DCI that triggers the first type of CSI report outside the reporting window.
[0186] Fig. 12 is a flowchart of a method 1200 of wireless communication at a network entity. The method 1200 is complementary to the method 1100 of Fig. 11. With reference to Figs. 1, 3, 5, and 14, the method 1200 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, the CU 110, an RU processor 1406, a DU processor 1426, a CU processor 1446, etc. The one or more network entities 104 may include memory 1406’ / 1426’ / 1446’ , which may correspond to an entirety of the one or more network entities 104, or a component of the one or more network entities 104, such as the RU processor 1406, the DU processor 1426, or the CU processor 1446.
[0187] As shown in Fig. 12, the network entity optionally receives 1202, from a UE, UE capability information for supporting a first codebook configuration for a first type of CSI report (e.g., a ground-truth CSI report) and a second codebook configuration for a second type of CSI report (e.g., a ML based CSI report) (similar to operations 302 and 402 of Figs. 3 and 4) .
[0188] The network entity transmits 1204, to the UE, a configuration configuring a CSI-RS resource set for channel measurement and indicating a first codebook configuration for a first type of CSI report having a higher CSI quantization resolution than that of a second codebook configuration for a second type of CSI report, the first and second type of CSI reports being associated with ML based CSI (similar to operations 304 and 404 of Figs. 3 and 4) .
[0189] The network entity transmits 1208, to the UE, a CSI-RS according to the CSI-RS resource set (similar to operations 308 and 408 of Figs. 3 and 4) .
[0190] The network entity receives 1210, from the UE, the first type of CSI report based on measurements of the CSI-RS (similar to operations 310 and 410 of Figs. 3 and 4) .
[0191] In aspects, the configuration further configures at least one of: a first CSI-RS resource set for channel measurement associated with the first type of CSI report, and a second CSI-RS resource set for channel measurement associated with the second type of CSI report; the first codebook configuration for the first type of CSI report, and the second codebook configuration for the second type of CSI report; a first CSI report configuration for the first type of CSI report associated with performance monitoring of the ML based CSI, and a second CSI report configuration for the second type of CSI report associated with reporting the ML based CSI, wherein the second CSI report configuration is associated to the first CSI report configuration; a report quantity indicating at least one PMI report; a frequency granularity; an interference measurement resource; a configuration of thresholds for a measurability determination for the CSI report; a configuration for a CSI triggering window; a configuration for a CSI measurement window; or a configuration for a CSI reporting window.
[0192] In aspects, the configuration includes a first CSI report sub-configuration for the first type of CSI report for performance monitoring of ML based CSI, and a second CSI report sub-configuration for the second type of CSI report indicating a model ID for the ML based CSI.
[0193] In aspects, the first and the second codebook configurations comprise Type2 codebook, eType2 codebook, or eType2-Doppler codebook, and wherein a first codebook for the first type of CSI report is for a ground-truth CSI report and a second codebook for the second type of CSI report is for ML based CSI report.
[0194] A UE apparatus 1302, as described in Fig. 13, may perform the method 1100. The one or more network entities (or BS) 104, as described in Fig. 14, may perform the method 1200.
[0195] Fig. 13 is a diagram 1300 illustrating an example of a hardware implementation for a UE apparatus 1302. The UE apparatus 1302 may be the UE 102, a component of the UE 102, or may implement UE functionality. The UE apparatus 1302 may include an application processor 1306, which may have on-chip memory 1306’ . In examples, the application processor 1306 may be coupled to a secure digital card 1308 and / or a display 1310. The application processor 1306 may also be coupled to a sensor (s) module 1312, a power supply 1314, an additional module of memory 1316, a camera 1318, and / or other related components. For example, the sensor (s) module 1312 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.
[0196] The UE apparatus 1302 may further include a wireless baseband processor 1326, which may be referred to as a modem. The wireless baseband processor 1326 may have on-chip memory 1326'. Along with, and similar to, the application processor 1306, the wireless baseband processor 1326 may also be coupled to the sensor (s) module 1312, the power supply 1314, the additional module of memory 1316, the camera 1318, and / or other related components. The wireless baseband processor 1326 may be additionally coupled to one or more subscriber identity module (SIM) card (s) 1320 and / or one or more transceivers 1330 (e.g., wireless RF transceivers) .
[0197] Within the one or more transceivers 1330, the UE apparatus 1302 may include a Bluetooth module 1332, a WLAN module 1334, an SPS module 1336 (e.g., GNSS module) , and / or a cellular module 1338. The Bluetooth module 1332, the WLAN module 1334, the SPS module 1336, and the cellular module 1338 may each include an on-chip transceiver (TRX) , or in some cases, just a transmitter (TX) or just a receiver (RX) . The Bluetooth module 1332, the WLAN module 1334, the SPS module 1336, and the cellular module 1338 may each include dedicated antennas and / or utilize antennas 1340 for communication with one or more other nodes. For example, the UE apparatus 1302 may communicate through the transceiver (s) 1330 via the antennas 1340 with another UE 102 (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.
[0198] The wireless baseband processor 1326 and the application processor 1306 may each include a computer-readable medium / memory 1326', 1306', respectively. The additional module of memory 1316 may also be considered a computer-readable medium / memory. Each computer-readable medium / memory 1326', 1306', 1316 may be non-transitory. The wireless baseband processor 1326 and the application processor 1306 may each be responsible for general processing, including execution of software stored on the computer-readable medium / memory 1326', 1306', 1316. The software, when executed by the wireless baseband processor 1326 / application processor 1306, causes the wireless baseband processor 1326 / application processor 1306 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 1326 / application processor 1306 when executing the software. The wireless baseband processor 1326 / application processor 1306 may be a component of the UE 102. The UE apparatus 1302 may be a processor chip (e.g., modem and / or application) and include just the wireless baseband processor 1326 and / or the application processor 1306. In other examples, the UE apparatus 1302 may be the entire UE 102 and include the additional modules of the apparatus 1302.
[0199] As discussed in Fig. 1 and implemented with respect to Figs. 3 and 4, the CSI report component 140 is configured to receive, from a network entity, a configuration configuring a CSI-RS resource set for channel measurement and indicating a first codebook configuration for a first type of CSI report having a higher CSI quantization resolution than that of a second codebook configuration for a second type of CSI report. The first and second type of CSI reports are associated with machine learning (ML) based CSI. The CSI report component 140 is configured to receive, from the network entity, a CSI-RS according to the CSI-RS resource set. After channel measurements, the CSI report component 140 transmits, to the network entity, the first type of CSI report based on measurements of the CSI-RS.
[0200] The CSI report component 140 may be within the application processor 1306 (e.g., at 140a) , the wireless baseband processor 1326 (e.g., at 140b) , or both the application processor 1306 and the wireless baseband processor 1326. 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.
[0201] Fig. 14 is a diagram 1400 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 1446, which may have on-chip memory 1446'. In some aspects, the CU 110 may further include an additional module of memory 1456 and / or a communications interface 1448, both of which may be coupled to the CU processor 1446. The CU 110 may communicate with the DU 108 through a midhaul link 162, such as an F1 interface between the communications interface 1448 of the CU 110 and a communications interface 1428 of the DU 108.
[0202] The DU 108 may include a DU processor 1426, which may have on-chip memory 1426'. In some aspects, the DU 108 may further include an additional module of memory 1436 and / or the communications interface 1428, both of which may be coupled to the DU processor 1426. The DU 108 may communicate with the RU 106 through a fronthaul link 160 between the communications interface 1428 of the DU 108 and a communications interface 1408 of the RU 106.
[0203] The RU 106 may include an RU processor 1406, which may have on-chip memory 1406'. In some aspects, the RU 106 may further include an additional module of memory 1416, the communications interface 1408, and one or more transceivers 1430, all of which may be coupled to the RU processor 1406. The RU 106 may further include antennas 1440, which may be coupled to the one or more transceivers 1430, such that the RU 106 may communicate through the one or more transceivers 1430 via the antennas 1440 with the UE 102.
[0204] The on-chip memory 1406', 1426', 1446'a nd the additional modules of memory 1416, 1436, 1456 may each be considered a computer-readable medium / memory. Each computer-readable medium / memory may be non-transitory. Each of the processors 1406, 1426, 1446 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) 1406, 1426, 1446 causes the processor (s) 1406, 1426, 1446 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) 1406, 1426, 1446 when executing the software. In examples, the CSI 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.
[0205] The CSI configuration component 150 may perform various operations and signaling (such as the operations in Figs. 3 and 5) according to the examples provided herein and be within one or more processors of the one or more network entities 104, such as the RU processor 1406 (e.g., at 150a) , the DU processor 1426 (e.g., at 150b) , and / or the CU processor 1446 (e.g., at 150c) . As discussed in Fig. 1 and implemented with respect to Figs. 3 and 5, the CSI configuration component 150 is configured to transmit, to a UE, a configuration configuring a CSI-RS resource set for channel measurement and indicating a first codebook configuration for a first type of CSI report having a higher CSI quantization resolution than that of a second codebook configuration for a second type of CSI report. The first and second type of CSI reports are associated with ML based CSI. The CSI configuration component is configured to transmit, to the UE, a CSI-RS according to the CSI-RS resource set. The network entity 104 then receives, from the UE, the first type of CSI report based on measurements of the CSI-RS.
[0206] The CSI 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 1406, 1426, 1446 configured to perform the stated processes / algorithm, stored within a computer-readable medium for implementation by the one or more processors 1406, 1426, 1446, or a combination thereof.
[0207] The specific order or hierarchy of blocks in the processes and flowcharts disclosed herein are 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 example / 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.
[0208] 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.
[0209] 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.
[0210] 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, 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 may 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.
[0211] 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 may 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 may be used to store computer executable code in the form of instructions or data structures that may be accessed by a computer. Storage media may be any available media that may be accessed by a computer.
[0212] 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.
[0213] 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.
[0214] 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.
[0215] 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 “may, ” 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 “may” 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.
[0216] 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 may be interpreted as a set of elements where the elements number one or more.
[0217] 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. 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) . Sometimes an “X” is used to universally denote multiple variations of a feature. For instance, “X06” may universally refer to all reference numbers that end in “06” (e.g., 206, 306, 406, etc. ) .
[0218] It is noted that throughout this disclosure, a panel may mean that an antenna (port) group or an antenna (port) set. There may be more than one DL / UL beams associated with one panel. When one transmitting node (UE or the network entity) is performing a transmission via a panel, only one beam associated with the panel may be used to perform the transmission. For a transmitter comprising more than one panels, e.g., two panels, it may happen that two beams associated with the two panels respectively are used to perform a transmission.
[0219] It is noted that throughout this disclosure, the UE may have one or more of the following attributes or behaviors. The following attributes or behaviors of the UE may also imply associated attributes or behaviors of a network entity.
[0220] The UE may be configured with and / or served by the network entity in a serving cell.
[0221] The UE may (be configured to) communicate with the network entity in the serving cell.
[0222] The UE may be configured with one or more serving cells by the network entity, which may include the serving cell.
[0223] The UE may be activated or be indicated, by the network entity, to activate one or more serving cells, which may include the serving cell.
[0224] The UE may be configured and / or indicated, by the network entity, one or more BWP. The UE may be indicated and / or configured, by the network entity, a BWP (in the serving cell) .
[0225] In some cases, the BWP may be activated as an active BWP.
[0226] In some cases, the BWP may be referred to an active BWP
[0227] In some cases, the BWP may be an active DL BWP.
[0228] In some cases, the BWP may be an active UL BWP.
[0229] In some cases, the BWP may be an initial BWP.
[0230] In some cases, the BWP may be a default BWP.
[0231] In some cases, the BWP may be a dormant BWP.
[0232] The UE may be in one of RRC_CONNECTED state, RRC_INACTIVE state or RRC_IDLE state.
[0233] It is noted that throughout this disclosure, a neighboring cell may be referred to or replaced with one or some of the following: (1) a non-serving cell, (2) a cell with PCI different that of the serving cell, or (3) a TRP associated with a PCI different from that of the serving cell.
[0234] It is noted that throughout this disclosure, when a procedure or description is related to a serving cell, it may mean the procedure or description is related to an active (DL / UL) BWP in the serving cell.
[0235] It is noted that throughout this disclosure, a CSI report for target or candidate cell may be replaced with or referred to as a CSI report for LTM.
[0236] It is noted that throughout this disclosure, a CSI report for serving cell may be replaced with or referred to as a CSI report other than CSI report for LTM” , or a Type1 / 2 CSI report.
[0237] It is noted that throughout this disclosure, a serving cell index for a CSI report may be referred to as or stand for that a serving cell index of a serving cell where the CSI report is transmitted on, or a serving cell where the CSI report is configured for, or a serving cell where report configuration of the CSI report is configured in.
[0238] It is noted that throughout this disclosure, a panel may mean that an antenna (port) group or an antenna (port) set. There may be more than one DL / UL beams associated with one panel. When one transmitting node (UE or the network entity) is performing a transmission via a panel, only one beam associated with the panel may be used to perform the transmission. For a transmitter comprising more than one panels, e.g., two panels, it may happen that two beams associated with the two panels respectively are used to perform a transmission.
[0239] It is noted that throughout this disclosure, a TRP identifier may mean or be referred to a (candidate) value of a TRP identifier. The first TRP identifier may be a first candidate value of a TRP identifier or a first TRP identifier value. The second TRP identifier may be a second candidate value of a TRP identifier or a second TRP identifier value.
[0240] It is noted that throughout this disclosure, a panel identifier may mean or be referred to a (candidate) value of a panel identifier. The first panel identifier may be a first candidate value of a panel identifier or a first panel identifier value. The second panel identifier may be a second candidate value of a panel identifier or a second panel identifier value.
[0241] It is noted that throughout this disclosure, when a procedure or description is related to a serving cell, it may mean the procedure or description is related to an active (DL / UL) BWP in the serving cell.
[0242] It is noted that throughout this disclosure, an expression of “X / Y” may include meaning of “X or Y” . It is noted that throughout this disclosure, an expression of “X / Y” may include meaning of “X and Y” . It is noted that throughout this disclosure, an expression of “X / Y” may include meaning of “X and / or Y” . It is noted that throughout this disclosure, an expression of “ (A) B” or “B (A) ” may include concept of “only B” . It is noted that throughout this disclosure, an expression of “ (A) B” or “B (A) ” may include concept of “A+B” or “B+A” .
[0243] It is noted that some or all of the foregoing or the following embodiments may be jointly combined or formed to be a new or another one embodiment.
[0244] It is noted that the foregoing or the following embodiments may be used to solve at least (but not limited to) the issue (s) or scenario (s) mentioned in this disclosure.
[0245] The following additional considerations may apply to the foregoing and the following discussions.
[0246] It is noted that any two or more than two of the foregoing or the following paragraphs, (sub) -bullets, points, actions, or claims described in each method / embodiment / implementation may be combined logically, reasonably, and properly to form a specific method.
[0247] It is noted that any sentence, paragraph, (sub) -bullet, point, action, or claim described in each of the foregoing or the following embodiment (s) / implementations / concept (s) may be implemented independently and separately to form a specific method. Dependency, e.g., “based on, ” “more specifically, ” “where” or etc., in embodiment (s) / implementations / concept (s) mentioned in this disclosure is just one possible embodiment which would not restrict the specific method.
[0248] It is noted that, some or all of the following terminology and assumption may be used hereafter. A BS may include a network central unit or a network node in NR which is used to control one or multiple TRPs which are associated with one or multiple cells. Communication between BS and TRP (s) is via fronthaul. BS may be referred to as central unit (CU) , eNB, gNB, or NodeB. A TRP may include a transmission and reception point provides network coverage and directly communicates with UEs. TRP may be referred to as distributed unit (DU) or network node. A cell may include one or multiple associated TRPs, e.g., coverage of the cell is composed of coverage of all associated TRP (s) . One cell is controlled by one BS or a network entity. Cell may be referred to as TRP group (TRPG) . A serving beam may include a beam generated by a network node, e.g., TRP, which is configured to be used to communicate with the UE, such as, for transmission and / or reception. A candidate beam for a UE is a candidate of a serving beam. Serving beam may or may not be candidate beam.
[0249] A user device in which the techniques of this disclosure may be implemented (e.g., the UE 102) may be any suitable device capable of wireless communications such as a smartphone, a tablet computer, a laptop computer, a mobile gaming console, a point-of-sale (POS) terminal, a health monitoring device, a drone, a camera, a media-streaming dongle or another personal media device, a wearable device such as a smartwatch, a wireless hotspot, a femtocell, or a broadband router. Further, the user device in some cases may be embedded in an electronic system such as the head unit of a vehicle or an advanced driver assistance system (ADAS) . Still further, the user device may operate as an internet-of-things (IoT) device or a mobile-internet device (MID) . Depending on the type, the user device may include one or more general-purpose processors, a computer-readable memory, a user interface, one or more network interfaces, one or more sensors, etc.
[0250] Certain embodiments are described in this disclosure as including logic or a number of components or modules. Modules may be software modules (e.g., code stored on non-transitory machine-readable medium) or hardware modules. A hardware module is a tangible unit capable of performing certain operations and may be configured or arranged in a certain manner. A hardware module may comprise dedicated circuitry or logic that is permanently configured (e.g., as a special-purpose processor, such as a field programmable gate array (FPGA) or an application-specific integrated circuit (ASIC) ) to perform certain operations. A hardware module may also comprise programmable logic or circuitry (e.g., as encompassed within a general-purpose processor or other programmable processor) that is temporarily configured by software to perform certain operations. The decision to implement a hardware module in dedicated and permanently configured circuitry, or in temporarily configured circuitry (e.g., configured by software) may be driven by cost and time considerations.
[0251] When implemented in software, the techniques may be provided as part of the operating system, a library used by multiple applications, a particular software application, etc. The software may be executed by one or more general-purpose processors or one or more special-purpose processors.
[0252] 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” may 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, may be construed as “based at least on A” unless specifically recited differently.
[0253] Example Aspects
[0254] Example 1 is a method of wireless communications by a user equipment (UE) , the method comprising:
[0255] receiving, from a network entity, a configuration configuring a channel state information-reference signal (CSI-RS) resource set for channel measurement and indicating a first codebook configuration for a first type of CSI report having a higher CSI quantization resolution than that of a second codebook configuration for a second type of CSI report, the first and second type of CSI reports being associated with machine learning (ML) based CSI;
[0256] receiving, from the network entity, a CSI reference signal (CSI-RS) according to the CSI-RS resource set; and
[0257] transmitting, to the network entity, the first type of CSI report based on measurements of the CSI-RS.
[0258] Example 2 is a method of Examples 1, further comprising:
[0259] transmitting, to the network entity, UE capability information for supporting the first codebook configuration for the first type of CSI report and the second codebook configuration for the second type of CSI report.
[0260] Example 3 is a method of any one of Examples 1 to 2, further comprising:
[0261] receiving, from the network entity, a triggering signal that triggers the first type of CSI report or associated measurements on the CSI-RS; and
[0262] transmitting, to the network entity, the second type of CSI report.
[0263] Example 4 is a method of any one of Examples 1-3, wherein the configuration further configures at least one of:
[0264] a first CSI-RS resource set for channel measurement associated with the first type of CSI report, and a second CSI-RS resource set for channel measurement associated with the second type of CSI report;
[0265] the first codebook configuration for the first type of CSI report, and the second codebook configuration for the second type of CSI report;
[0266] a first CSI report configuration for the first type of CSI report associated with performance monitoring of the ML based CSI, and a second CSI report configuration for the second type of CSI report associated with reporting the ML based CSI, wherein the second CSI report configuration is associated to the first CSI report configuration;
[0267] a report quantity indicating at least one precoding matrix indicator (PMI) report;
[0268] a frequency granularity;
[0269] an interference measurement resource;
[0270] a configuration of thresholds for a measurability determination for the CSI report;
[0271] a configuration for a CSI triggering window;
[0272] a configuration for a CSI measurement window; or
[0273] a configuration for a CSI reporting window.
[0274] Example 5 is a method of Example 4, wherein the second CSI report configuration is different from the first CSI report configuration, wherein the first CSI report configuration and the second CSI report configuration are for a bandwidth part (BWP) or a serving cell.
[0275] Example 6 is a method of Example 4, wherein the first and second CSI-RS resource sets comprise CSI-RS resources from a common antenna port or a plurality of different antenna ports, wherein the CSI-RS resources comprises multiple CSI-RS resource groups each including CSI-RS resources from different antenna ports, and wherein different CSI-RS resource groups are configured in different slots.
[0276] Example 7 is a method of any one of Examples 1 to 3, wherein the configuration comprises:
[0277] a first CSI report sub-configuration for the first type of CSI report for performance monitoring of ML based CSI; and
[0278] a second CSI report sub-configuration for the second type of CSI report indicating a model identifier (ID) for the ML based CSI.
[0279] Example 8 is a method of any one of Examples 1 to 7, wherein the first and the second codebook configurations comprise Type2 codebook, enhanced Type2 (eType2) codebook, or eType2-Doppler codebook, and wherein a first codebook for the first type of CSI report is for a ground-truth CSI report and a second codebook for the second type of CSI report is for ML based CSI report.
[0280] Example 9 is a method of Example 8, wherein a first parameter associated the first codebook has a higher resolution than a second parameter associated with the second codebook, wherein the first and second parameters include at least one of:
[0281] a number of reported beams;
[0282] a number of non-zero-coefficients for beam combining matrix;
[0283] a number of horizontal antenna ports;
[0284] a number of vertical antenna ports;
[0285] an oversampling factor in horizontal dimension;
[0286] an oversampling factor in vertical dimension;
[0287] an oversampling factor in frequency domain; or
[0288] a number of time instances for measuring CSI.
[0289] Example 10 is a method of any one of Examples 1 to 9, wherein the configuration indicates at least one of:
[0290] reporting the first type of CSI report for first future instances based on non-ML prediction and non-ML compression;
[0291] reporting the first type of CSI report for second future instances based on ML prediction and non-ML compression;
[0292] reporting the first type of CSI report for third future instances based on non-ML prediction and ML compression;
[0293] reporting the first type of CSI report for a first transmission occasion of the CSI-RS based ML compression; or
[0294] reporting the first type of CSI report for a second transmission occasion of the CSI-RS based non-ML compression.
[0295] Example 11 is a method of any one of Examples 1 to 10, wherein the first type of CSI report comprises at least one of:
[0296] a precoding matrix indicator (PMI) ;
[0297] a rank indicator (RI) and a PMI;
[0298] a PMI and a channel quality indicator (CQI) ; or
[0299] an RI, a PMI, and a CQI.
[0300] Example 12 is a method of Example 11, wherein the first CSI report configuration further indicates a frequency granularity for the first type of CSI report, the frequency granularity indicating whether the first type of CSI report is measured based on a wideband operation or a subband operation.
[0301] Example 13 is a method of any one of Examples 1 to 12, further comprising:
[0302] determining (903) , at the UE, whether a transmission occasion for the CSI-RS is measurable based on at least one of:
[0303] a measured reference signal received power (RSRP) being below a first threshold;
[0304] a measured signal-to-interference plus noise ratio (SINR) being below a second threshold;
[0305] a failure to receive the transmission occasion of the CSI-RS;
[0306] a delay offset between the transmission occasion of the CSI-RS and a reference downlink channel or signal is above a third threshold;
[0307] an offset between the transmission occasion of the CSI-RS and a first slot of the CSI report being below a minimum processing delay;
[0308] a number of CSI processing units (CPUs) exceeding a maximum number of CPUs;
[0309] channel estimation error being above a fourth threshold; or a minimum, a maximum, or an average value of RSRP or SINR for one or more antenna ports of the CSI-RS; and
[0310] transmitting, to the network entity, a measurable status for the first type of CSI report when the transmission occasion is measurable.
[0311] Example 14 is a method of any one of Examples 1 to 13, wherein the configuration further comprises:
[0312] a triggering window, wherein the triggering window is characterized by a first periodicity, a first duration, and a first slot offset for a first slot of the triggering window, and a reporting window for the transmitting the first type of CSI report, wherein the reporting window is characterized by a second periodicity, a second duration, and a second slot offset for a second slot of the reporting window; and
[0313] the method further comprises:
[0314] transmitting the first type of CSI report in response to receiving, from the network entity, a first downlink control information (DCI) within the triggering window, and ignoring a second DCI outside the triggering window; or
[0315] transmitting the first type of CSI report in response to receiving a valid DCI that triggers the first type of CSI report within the reporting window, and dropping the first type of CSI report in response to receiving an invalid DCI that triggers the first type of CSI report outside the reporting window.
[0316] Example 15 is a method of wireless communications by a network entity, the method comprising:
[0317] transmitting, to a user equipment (UE) , a configuration configuring a channel state information-reference signal (CSI-RS) resource set for channel measurement and indicating a first codebook configuration for a first type of CSI report having a higher CSI quantization resolution than that of a second codebook configuration for a second type of CSI report, the first and second type of CSI reports being associated with machine learning (ML) based CSI;
[0318] transmitting, to the UE, a CSI reference signal (CSI-RS) according to the CSI-RS resource set; and
[0319] receiving, from the UE, the first type of CSI report based on measurements of the CSI-RS.
[0320] Example 16 is a method of Examples 15, further comprising:
[0321] receiving, from the UE, UE capability information for supporting the first codebook configuration for the first type of CSI report and the second codebook configuration for the second type of CSI report.
[0322] Example 17 is a method of Examples 15 or 16, further comprising:
[0323] transmitting, to the UE, a triggering signal that triggers the first type of CSI report or associated measurements on the CSI-RS; and
[0324] receiving, from the UE, the second type of CSI report.
[0325] Example 18 is a method of any one of Examples 15 to 17, wherein the configuration further configures at least one of:
[0326] a first CSI-RS resource set for channel measurement associated with the first type of CSI report, and a second CSI-RS resource set for channel measurement associated with the second type of CSI report;
[0327] the first codebook configuration for the first type of CSI report, and the second codebook configuration for the second type of CSI report;
[0328] a first CSI report configuration for the first type of CSI report associated with performance monitoring of the ML based CSI, and a second CSI report configuration for the second type of CSI report associated with reporting the ML based CSI, wherein the second CSI report configuration is associated to the first CSI report configuration;
[0329] a report quantity indicating at least one precoding matrix indicator (PMI) report;
[0330] a frequency granularity;
[0331] an interference measurement resource;
[0332] a configuration of thresholds for a measurability determination for the CSI report;
[0333] a configuration for a CSI triggering window;
[0334] a configuration for a CSI measurement window; or
[0335] a configuration for a CSI reporting window.
[0336] Example 19 is a method of Example 18, wherein the second CSI report configuration is different from the first CSI report configuration, wherein the first CSI report configuration and the second CSI report configuration are for a bandwidth part (BWP) or a serving cell.
[0337] Example 20 is a method of Example 18, wherein the first and second CSI-RS resource sets comprise CSI-RS resources from a common antenna port or a plurality of different antenna ports, wherein the CSI-RS resources comprises multiple CSI-RS resource groups each including CSI-RS resources from different antenna ports, and wherein different CSI-RS resource groups are configured in different slots.
[0338] Example 21 is a method of any one of Examples 15 to 17, wherein the configuration comprises:
[0339] a first CSI report sub-configuration for the first type of CSI report for performance monitoring of ML based CSI; and
[0340] a second CSI report sub-configuration for the second type of CSI report indicating a model identifier (ID) for the ML based CSI.
[0341] Example 22 is a method of any one of Examples 15 to 21, wherein the first and the second codebook configurations comprise Type2 codebook, enhanced Type2 (eType2) codebook, or eType2-Doppler codebook, and wherein a first codebook for the first type of CSI report is for a ground-truth CSI report and a second codebook for the second type of CSI report is for ML based CSI report.
[0342] Example 23 is a method of Example 22, wherein a first parameter associated the first codebook has a higher resolution than a second parameter associated with the second codebook, wherein the first and second parameters include at least one of:
[0343] a number of reported beams;
[0344] a number of non-zero-coefficients for beam combining matrix;
[0345] a number of horizontal antenna ports;
[0346] a number of vertical antenna ports;
[0347] an oversampling factor in horizontal dimension;
[0348] an oversampling factor in vertical dimension;
[0349] an oversampling factor in frequency domain; or
[0350] a number of time instances for measuring CSI.
[0351] Example 24 is a method of any one of Examples 15 to 23, wherein the configuration indicates at least one of:
[0352] reporting the first type of CSI report for first future instances based on non-ML prediction and non-ML compression;
[0353] reporting the first type of CSI report for second future instances based on ML prediction and non-ML compression;
[0354] reporting the first type of CSI report for third future instances based on non-ML prediction and ML compression;
[0355] reporting the first type of CSI report for a first transmission occasion of the CSI-RS based ML compression; or
[0356] reporting the first type of CSI report for a second transmission occasion of the CSI-RS based non-ML compression.
[0357] Example 25 is a method of any one of Examples 15 to 24, wherein the first type of CSI report comprises at least one of:
[0358] a precoding matrix indicator (PMI) ;
[0359] a rank indicator (RI) and a PMI;
[0360] a PMI and a channel quality indicator (CQI) ; or
[0361] an RI, a PMI, and a CQI.
[0362] Example 26 is a method of Example 25, wherein the first CSI report configuration further indicates a frequency granularity for the first type of CSI report, the frequency granularity indicating whether the first type of CSI report is measured based on a wideband operation or a subband operation.
[0363] Example 27 is a method of any one of Examples 15 to 26, wherein the configuration further comprises:
[0364] a triggering window, wherein the triggering window is characterized by a first periodicity, a first duration, and a first slot offset for a first slot of the triggering window, and a reporting window for the transmitting the first type of CSI report, wherein the reporting window is characterized by a second periodicity, a second duration, and a second slot offset for a second slot of the reporting window; and
[0365] the method further comprises:
[0366] receiving the first type of CSI report after transmitting, to the UE, a first downlink control information (DCI) within the triggering window; or
[0367] receiving the first type of CSI report after transmitting, to the UE, a DCI that triggers the first type of CSI report within the reporting window.
[0368] Example 28 is an apparatus comprising:
[0369] one or more radio frequency (RF) modems;
[0370] a processor coupled to the one or more RF modems; and
[0371] at least one memory storing executable instructions, the executable instructions to manipulate at least one of the processor or the one or more RF modems to perform the method of any of Examples 1 to 27.
Claims
1.A method of wireless communications by a user equipment (UE) (102) , the method comprising:receiving (304) , from a network entity (104) , a configuration configuring a channel state information (CSI) reference signal (CSI-RS) resource set for channel measurement and indicating a first codebook configuration for a first type of CSI report having a higher CSI quantization resolution than that of a second codebook configuration for a second type of CSI report, the first and second type of CSI reports being associated with machine learning (ML) based CSI;receiving (308) , from the network entity (104) , a CSI-RS according to the CSI-RS resource set; andtransmitting (310) , to the network entity (104) , the first type of CSI report based on measurements of the CSI-RS.2.The method of claims 1, further comprising:transmitting (302) , to the network entity (104) , UE capability information for supporting the first codebook configuration for the first type of CSI report and the second codebook configuration for the second type of CSI report.3.The method of claim 1 or 2, wherein the configuration further configures at least one of:a first CSI-RS resource set for channel measurement associated with the first type of CSI report, and a second CSI-RS resource set for channel measurement associated with the second type of CSI report;the first codebook configuration for the first type of CSI report, and the second codebook configuration for the second type of CSI report;a first CSI report configuration for the first type of CSI report associated with performance monitoring of the ML based CSI, and a second CSI report configuration for the second type of CSI report associated with reporting the ML based CSI, wherein the second CSI report configuration is associated to the first CSI report configuration;a report quantity indicating at least one precoding matrix indicator (PMI) report;a frequency granularity;an interference measurement resource;a configuration of thresholds for a measurability determination for the CSI report;a configuration for a CSI triggering window;a configuration for a CSI measurement window; ora configuration for a CSI reporting window.4.The method of claim 3, wherein the second CSI report configuration is different from the first CSI report configuration, wherein the first CSI report configuration and the second CSI report configuration are for a bandwidth part (BWP) or a serving cell.5.The method of claim 3, wherein the first and second CSI-RS resource sets comprise CSI-RS resources from a common antenna port or a plurality of different antenna ports, wherein the CSI-RS resources comprises multiple CSI-RS resource groups each including CSI-RS resources from different antenna ports, and wherein different CSI-RS resource groups are configured in different slots.6.The method of any one of claims 1 to 2, wherein the configuration comprises:a first CSI report sub-configuration for the first type of CSI report for performance monitoring of ML based CSI; anda second CSI report sub-configuration for the second type of CSI report indicating a model identifier (ID) for the ML based CSI.7.The method of any one of claims 1 to 6, wherein the first and the second codebook configurations comprise Type2 codebook, enhanced Type2 (eType2) codebook, or eType2-Doppler codebook, and wherein a first codebook for the first type of CSI report is for a ground-truth CSI report and a second codebook for the second type of CSI report is for ML based CSI report.8.The method of claim 7, wherein a first parameter associated the first codebook has a higher resolution than a second parameter associated with the second codebook, wherein the first and second parameters include at least one of:a number of reported beams;a number of non-zero-coefficients for beam combining matrix;a number of horizontal antenna ports;a number of vertical antenna ports;an oversampling factor in horizontal dimension;an oversampling factor in vertical dimension;an oversampling factor in frequency domain; ora number of time instances for measuring CSI.9.The method of any one of claims 1 to 8, wherein the configuration indicates at least one of:reporting the first type of CSI report for first future instances based on non-ML prediction and non-ML compression;reporting the first type of CSI report for second future instances based on ML prediction and non-ML compression;reporting the first type of CSI report for third future instances based on non-ML prediction and ML compression;reporting the first type of CSI report for a first transmission occasion of the CSI-RS based ML compression; orreporting the first type of CSI report for a second transmission occasion of the CSI-RS based non-ML compression.10.The method of any one of claims 1 to 9, wherein the first type of CSI report comprises at least one of:a precoding matrix indicator (PMI) ;a rank indicator (RI) and a PMI;a PMI and a channel quality indicator (CQI) ; oran RI, a PMI, and a CQI.11.The method of any one of claims 1 to 10, further comprising:determining (903) , at the UE (102) , whether a transmission occasion for the CSI-RS is measurable based on at least one of:a measured reference signal received power (RSRP) being below a first threshold;a measured signal-to-interference plus noise ratio (SINR) being below a second threshold;a failure to receive the transmission occasion of the CSI-RS;a delay offset between the transmission occasion of the CSI-RS and a reference downlink channel or signal is above a third threshold;an offset between the transmission occasion of the CSI-RS and a first slot of the CSI report being below a minimum processing delay;a number of CSI processing units (CPUs) exceeding a maximum number of CPUs;channel estimation error being above a fourth threshold; ora minimum, a maximum, or an average value of RSRP or SINR for one or more antenna ports of the CSI-RS; andtransmitting (905) , to the network entity (104) , a measurable status for the first type of CSI report when the transmission occasion is measurable.12.The method of any one of claims 1 to 11, wherein the configuration further comprises:a triggering window, wherein the triggering window is characterized by a first periodicity, a first duration, and a first slot offset for a first slot of the triggering window, anda reporting window for the transmitting (310) the first type of CSI report, wherein the reporting window is characterized by a second periodicity, a second duration, and a second slot offset for a second slot of the reporting window; andthe method further comprises:transmitting (310) the first type of CSI report in response to receiving, from the network entity (104) , a first downlink control information (DCI) within the triggering window, and ignoring a second DCI outside the triggering window; ortransmitting (310) the first type of CSI report in response to receiving a valid DCI that triggers the first type of CSI report within the reporting window, and dropping the first type of CSI report in response to receiving an invalid DCI that triggers the first type of CSI report outside the reporting window.13.A method of wireless communications by a network entity (104) , the method comprising:transmitting (304) , to a user equipment (UE) (102) , a configuration configuring a channel state information (CSI) reference signal (CSI-RS) resource set for channel measurement and indicating a first codebook configuration for a first type of CSI report having a higher CSI quantization resolution than that of a second codebook configuration for a second type of CSI report, the first and second type of CSI reports being associated with machine learning (ML) based CSI;transmitting (308) , to the UE (102) , a CSI-RS according to the CSI-RS resource set; andreceiving (310) , from the UE (102) , the first type of CSI report based on measurements of the CSI-RS.14.The method of claim 13, wherein the configuration further configures at least one of:a first CSI-RS resource set for channel measurement associated with the first type of CSI report, and a second CSI-RS resource set for channel measurement associated with the second type of CSI report;the first codebook configuration for the first type of CSI report, and the second codebook configuration for the second type of CSI report;a first CSI report configuration for the first type of CSI report associated with performance monitoring of the ML based CSI, and a second CSI report configuration for the second type of CSI report associated with reporting the ML based CSI, wherein the second CSI report configuration is associated to the first CSI report configuration;a report quantity indicating at least one precoding matrix indicator (PMI) report;a frequency granularity;an interference measurement resource;a configuration of thresholds for a measurability determination for the CSI report;a configuration for a CSI triggering window;a configuration for a CSI measurement window; ora configuration for a CSI reporting window.15.The method of claim 13, wherein the configuration comprises:a first CSI report sub-configuration for the first type of CSI report for performance monitoring of ML based CSI; anda second CSI report sub-configuration for the second type of CSI report indicating a model identifier (ID) for the ML based CSI.16.The method of any one of claims 13 to 15, wherein the first and the second codebook configurations comprise Type2 codebook, enhanced Type2 (eType2) codebook, or eType2-Doppler codebook, and wherein a first codebook for the first type of CSI report is for a ground-truth CSI report and a second codebook for the second type of CSI report is for ML based CSI report.17.An apparatus comprising:one or more radio frequency (RF) modems;a processor coupled to the one or more RF modems; andat least one memory storing executable instructions, the executable instructions to manipulate at least one of the processor or the one or more RF modems to perform the method of any of claims 1 to 16.
Citation Information
Patent Citations
CSI feedback in cellular systems
US20240097764A1