Parallel processing for channel state information reporting based on machine learning

Abstract

The present disclosure provides systems, apparatuses, apparatuses, and methods, including computer programs encoded on a storage medium, for parallel processing and processing delays for ML-based CSI reporting. The UE receives (404, 804), from a network entity (104), a configuration of an ML-based CSI report associated with the first CSI-RS. The UE (102) receives (407, 807) the first CSI-RS from the network entity (104), and transmits (412, 812) the ML-based CSI report to the network entity (104), the CSI report comprising a CSI based on a UE capability for handling an ML-based CSI report associated with the first CSI-RS.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of and priority to International Application No. PCT / CN2022 / 112193, filed on August 12, 2022, entitled “CSI Reports based on ML Techniques,” which is expressly incorporated herein by reference in its entirety. Technical Field

[0002] The present disclosure relates generally to wireless communications, and more particularly, to channel state information (CSI) reporting based on machine learning (ML) techniques. Background Art

[0003] The 3rd Generation Partnership Project (3GPP) specifies a radio interface called the fifth generation (5G) New Radio (NR) (5G NR). The architecture of the 5G NR wireless communication system includes a 5G core (5GC) network, a 5G radio access network (5G-RAN), user equipment (UE), etc. Compared with the previous generation cellular communication system, the 5G NR architecture seeks to provide increased data rates, reduced latency, and / or increased capacity.

[0004] Wireless communication systems generally provide various telecommunication services (e.g., telephone, video, data, messaging, broadcast, etc.) based on multiple access technologies (such as orthogonal frequency division multiple access (OFDMA) technologies) that support communication with multiple UEs. The improvement of mobile broadband continues the progress of such wireless communication technologies. For example, UEs and base stations can support more antenna configurations and multiple connections. However, one consequence is that channel state information (CSI) reports become larger and more complex. Summary of the invention

[0005] The following presents a simplified overview of one or more aspects in order to provide a basic understanding of such aspects. This overview is not an extensive review of all contemplated aspects. This overview neither identifies the key or important elements of all aspects, nor describes the scope of any or all aspects. Its sole purpose is to present some concepts of one or more aspects in a simplified form as a prelude to a more detailed description presented later.

[0006] A user equipment (UE) may receive one or more channel state information-reference signals (CSI-RS) from a network entity, such as a base station or a unit of a base station. The UE generates one or more channel state information (CSI) reports using the received CSI-RS. In some cases, the UE may generate one or more CSI reports based on at least one machine learning (ML) model. Thus, the UE may include a first UE capability for processing multiple CSI reports based on an ML model in parallel and / or a second UE capability for processing a first CSI report based on an ML model and a second CSI report not based on an ML model in parallel.

[0007] The UE may indicate the UE capability for parallel processing in a UE capability report transmitted to a network entity. However, the parallel processing capability of the UE is limited by the maximum number of CSI processing units (CPUs), such as when the UE performs ML-based CSI reporting processing based on a Type 2 CPU. "Type 2 CPU" as used herein refers to a CPU used for an ML-based CSI reporting process but not shared with / used for a non-ML-based CSI reporting process. A CPU shared with a non-ML-based CSI reporting process is referred to herein as a "Type 1 CPU". In order to comply with the limitation on the number of CPUs used for CSI reporting (e.g., the number of CPUs is less than or equal to the maximum number of CPUs associated with the UE capability), the UE may measure / report CSI for a high priority ML-based / non-ML-based CSI report, but report previously measured CSI (e.g., outdated CSI) for a low priority ML-based / non-ML-based CSI report.

[0008] According to some aspects, a UE receives a configuration for ML-based CSI reporting associated with a first CSI-RS from a network entity. The UE receives the first CSI-RS from the network entity and transmits an ML-based CSI report to the network entity, the CSI report including CSI based on UE capabilities for processing the ML-based CSI reporting associated with the first CSI-RS.

[0009] According to some aspects, a network entity transmits to a UE a configuration for ML-based CSI reporting associated with a first CSI-RS. The network entity transmits the first CSI-RS to the UE, and receives from the UE an ML-based CSI report including CSI based on UE capabilities for processing the ML-based CSI reporting associated with the first CSI-RS. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1A diagram showing a wireless communication system including multiple user equipments (UEs) and network entities communicating through one or more cells.

[0011] Figure 2 A diagram showing an example machine learning (ML) based channel state information (CSI) encoder compression at a UE and an example ML based CSI decoder decompression at a network entity.

[0012] Figure 3A A first timing diagram illustrating a first CSI processing unit (CPU) duration associated with periodic / semi-persistent CSI reporting.

[0013] Figure 3B A second timing diagram illustrating a second CPU duration associated with aperiodic CSI reporting.

[0014] Figure 4 is a signaling diagram illustrating the ML-based CSI processing procedure.

[0015] Figure 5 A timing diagram showing Type2 CPU occupancy.

[0016] FIG. 6A to FIG. 6B An example timing diagram showing CPU occupancy for ML-based periodic / semi-persistent CSI reporting.

[0017] FIG. 7A to FIG. 7B An example timing diagram showing CPU occupancy for ML-based aperiodic CSI reporting.

[0018] Figure 8 A signaling diagram showing CSI reporting based on minimum processing delay.

[0019] Fig. 9 is a flow chart of a method of performing wireless communication at a UE.

[0020] Fig.10 is a flow chart of a method of wireless communication at a network entity.

[0021] Fig.11 is a diagram illustrating an example of a hardware implementation of an example UE device.

[0022] Fig.12 is a diagram illustrating an example of a hardware implementation of one or more example network entities. DETAILED DESCRIPTION

[0023] Figure 1A diagram 100 of a wireless communication system associated with a plurality of cells 190 is shown. The wireless communication system includes a user equipment (UE) 102 and a base station / network entity 104. Some base stations may include a converged base station architecture, while other base stations may include a decomposed base station architecture. The converged base station architecture utilizes a radio protocol stack that is physically or logically integrated within a single radio access network (RAN) node. The decomposed base station architecture utilizes a protocol stack that is physically or logically distributed between two or more units (e.g., a radio unit (RU) 106, a distributed unit (DU) 108, a central unit (CU) 110). For example, the 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 in one or more other RAN nodes. The DU 108 may be implemented to communicate with one or more RUs 106. Any of the RU 106, DU 108, and CU 110 may be implemented as a virtual unit, such as a virtual radio unit (VRU), a virtual distributed unit (VDU), or a virtual central unit (VCU). A base station / network entity 104 (e.g., a converged base station or a disaggregated unit of a base station, such as RU 106 or DU 108) may be referred to as a transmission reception point (TRP).

[0024] The operation and / or network design of the base station 104 can be based on the aggregation characteristics of the base station functions. For example, a decomposed base station architecture is 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 as a cloud radio access network (C-RAN)). Decomposition may include distributing functions between two or more units located at various physical locations, and virtually distributing the functions of at least one unit, which enables flexibility in network design. Various units of a decomposed base station architecture or a decomposed RAN architecture may be configured to communicate with at least one other unit in wired or wireless communication. For example, a base station 104d / 104e and / or RU 106a-106d may communicate with UE 102a-102d and 102s via one or more radio frequency (RF) access links based on a Uu interface. In an example, multiple RUs 106 and / or base stations 104 may simultaneously serve UE 102, such as via intra-cell and / or inter-cell access links between UE 102 and RU 106 / base station 104.

[0025] RU 106, DU 108 and 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 information / signals via a wired transmission medium, such as via a fronthaul link 160 between a baseband unit (BBU) 112 of a base station 104d associated with a cell 190d. BBU 112 includes DU 108 and CU 110, which may also have a wired interface (e.g., a mid-range link) configured between DU 108 and CU 110 to transmit or receive information / signals between DU 108 and CU 110. In a further example, a wireless interface, which may include a receiver, transmitter, or transceiver (e.g., an RF transceiver), is configured to transmit and / or receive information / signals via a wireless transmission medium, such as information transmitted between RU 106a of cell 190a and base station 104e of cell 190e via cross-cell communication beams 136-138 of RU106a and base station 104e.

[0026] The RU 106 may be configured to implement lower layer functions. For example, the RU 106 is controlled by the DU 108 and may correspond to a logical node hosting RF processing functions or lower layer PHY functions, such as performing fast Fourier transform (FFT), inverse FFT (iFFT), digital beamforming, physical random access channel (PRACH) extraction and filtering, etc. The functions of the RU 106 may be based on functional partitioning, such as lower layer functional partitioning.

[0027] RU 106 can transmit or receive over-the-air (OTA) communications with one or more UEs 102. For example, RU 106b of cell 190b communicates with UE 102b of cell 190b via a first communication beam set 132 of RU 106b and a second communication beam set 134b of UE 102b, which can correspond to inter-cell communication beams or, in some examples, cross-cell communication beams. For example, UE 102b of cell 190b can communicate with RU 106a of cell 190a via a third communication beam set 134a of UE 102b and a fourth communication beam set 136 of RU 106a. DU 108 can control real-time and non-real-time features of control plane and user plane communications of RU 106.

[0028] Any combination of RU 106, DU 108, and CU 110, or a separate reference thereto, may correspond to base station 104. Thus, base station 104 may include at least one of RU 106, DU 108, or CU 110. Base station 104 provides access to a core network for UE 102. Base station 104 may relay communications between UE 102 and a core network (not shown). Base station 104 may be associated with a macro cell of a high-power cellular base station and / or a small cell of a low-power cellular base station. For example, cell 190e may correspond to a macro cell, and cells 190a-190d may correspond to a small cell. Small cells include femto cells, pico cells, micro cells, and the like. A network including at least one macro cell and at least one small cell may be referred to as a "heterogeneous network."

[0029] Transmissions from the UE 102 to the base station 104 / RU 106 are referred to as uplink (UL) transmissions, while transmissions from the base station 104 / RU 106 to the UE 102 are referred to as downlink (DL) transmissions. Uplink transmissions may also be referred to as reverse link transmissions, while downlink transmissions may also be referred to as forward link transmissions. For example, the RU 106 d utilizes an antenna of the base station 104 d of the cell 190 d to transmit downlink / forward link communications to the UE 102 d, or receive uplink / reverse link communications from the UE 102 d, based on a Uu interface associated with an access link between the UE 102 d and the base station 104 d / RU 106 d.

[0030] The communication link between UE 102 and base station 104 / RU 106 can be based on multiple-input multiple-output (MIMO) antenna technology, including spatial multiplexing, beamforming and / or transmit diversity. The communication link can be associated with one or more carriers. UE 102 and base station 104 / RU 106 can utilize Y MHz (e.g., 5 MHz, 10 MHz, 15 MHz, 20 MHz, 100 MHz, 400 MHz, 800 MHz, 1600 MHz, 2000 MHz, etc.) spectrum bandwidth allocated per carrier in up to a total of Yx MHz carrier aggregation, where x component carriers (CCs) are used for communication in each direction of the uplink direction and the downlink direction. The carriers may be adjacent to each other along the spectrum, or may not be adjacent to each other. In an example, uplink carriers and downlink carriers may be allocated in an asymmetric manner, where more or fewer carriers are allocated for the uplink or downlink. The component carriers may include a primary component carrier and one or more secondary component carriers. The primary component carrier may be associated with a primary cell (PCell) and the secondary component carrier may be associated with a secondary cell (SCell).

[0031] Some UEs 102 (such as UEs 102a and 102s) may perform device-to-device (D2D) communication via a sidelink. For example, the sidelink communication / D2D link utilizes the spectrum of a wireless wide area network (WWAN) associated with uplink and downlink communications. Such sidelink / D2D communication may be performed via various wireless communication systems, such as a wireless fidelity (Wi-Fi) system, a Bluetooth system, a long term evolution (LTE) system, a new radio (NR) system, etc.

[0032] UE 102 and base station 104 / RU 106 may each include multiple antennas. Multiple antennas may correspond to antenna elements, antenna panels, and / or antenna arrays that may facilitate beamforming operations. For example, RU 106b transmits a downlink beamformed signal to UE 102b based on a first communication beam set 132 in one or more transmit directions of RU 106b. UE 102b may receive a downlink beamformed signal from RU 106b based on a second communication beam set 134b in one or more receive directions of UE 102b. In a further example, UE 102b may also transmit an uplink beamformed signal (e.g., a sounding reference signal (SRS)) to RU 106b based on a second communication beam set 134b in one or more transmit directions of UE 102b. RU 106b may receive an uplink beamformed signal from UE 102b in one or more receive directions of RU 106b. UE 102b may perform beam training to determine the best receive and transmit directions for beamformed signals.The transmit and receive directions of UE 102 and base station 104 / RU 106 may be the same, or may be different.

[0033] In a further example, beamformed signals may be transmitted between the first base station / RU 106a and the second base station 104e. For example, the base station 104e of the cell 190e may transmit beamformed signals to the RU 106a based on the communication beam 138 in one or more transmit directions of the base station 104e. The RU 106a may receive beamformed signals from the base station 104e of the cell 190e based on the RU communication beam 136 in one or more receive directions of the RU 106a. In a further example, the base station 104e transmits downlink beamformed signals to the UE 102e based on the communication beam 138 in one or more transmit directions of the base station 104e. The UE 102e may receive downlink beamformed signals from the base station 104e based on the UE communication beam 130 in one or more receive directions of the UE 102e. UE 102e may also transmit uplink beamformed signals to base station 104e based on UE communication beam 130 in one or more transmit directions of UE 102e, so that base station 104e may receive uplink beamformed signals from UE 102e in one or more receive directions of base station 104e.

[0034] The base station 104 may include and / or be referred to as a network entity. That is, a "network entity" may refer to a base station 104 or at least one unit of a base station 104, such as a RU 106, a DU 108, and / or a CU 110. The base station 104 may also include and / or be referred to as a next generation evolved Node B (ng-eNB), a next generation NB (gNB), an evolved NB (eNB), an access point, a base station transceiver, 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, a network device, or other related terms. The base station 104 or an entity at the base station 104 may be implemented as an IAB node, a relay node, a side link node, an aggregated (integrated) base station, or a decomposed base station including one or more of the RU 106, the DU 108, and / or the CU 110. An aggregated or decomposed base station set may be referred to as a next generation radio access network (NG-RAN). In some examples, UE 102a operates in dual connectivity (DC) with base station 104e and base station / RU 106a. In such a case, base station 104e may be the primary node and base station / RU 160a may be the secondary node.

[0035] The uplink / downlink signaling may also be communicated via a satellite positioning system (SPS) 114. In an example, the SPS 114 of the cell 190c may communicate with one or more UEs 102 (such as UE 102c) and one or more base stations 104 / RU 106 (such as RU 106c). The SPS 114 may correspond to one or more of a global navigation satellite system (GNSS), a global positioning system (GPS), a non-terrestrial network (NTN), or other satellite positioning / position systems. The SPS 114 may be associated with LTE signals, NR signals (e.g., based on round trip time (RTT) and / or multiple RTT), wireless local area network (WLAN) signals, terrestrial beacon systems (TBS), sensor-based information, NR enhanced cell ID (NR E-CID) technology, downlink departure angle (DL-AoD), downlink arrival time difference (DL-TDOA), uplink arrival time difference (UL-TDOA), uplink arrival angle (UL-AoA), and / or other systems, signals, or sensors.

[0036] Still refer to Figure 1 In certain aspects, any of the UEs 102 may include a UE-based channel state information (CSI) processing component 140, which is configured to: receive a configuration for a machine learning (ML) based CSI report associated with a first channel state information-reference signal (CSI-RS) from a network entity; receive the first CSI-RS from the network entity; and transmit the ML-based CSI report to the network entity based on the UE capability for processing the ML-based CSI report associated with the first CSI-RS.

[0037] In certain aspects, any of the base stations 104 or a network entity of the base station 104 may include a network-based CSI processing component 150, which is configured to: transmit a configuration for ML-based CSI reporting associated with a first CSI-RS to the UE; transmit the first CSI-RS to the UE; and receive an ML-based CSI report from the UE, the CSI report including CSI based on the UE capability for processing the ML-based CSI reporting associated with the first CSI-RS.

[0038] therefore, Figure 1 A wireless communication system is described that can be implemented in conjunction with aspects of one or more of the other figures described herein. In addition, although the following description may focus 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.

[0039] Figure 2 Diagram 200 illustrates an example ML-based CSI encoder compression at a UE 102 and an example ML-based CSI decoder decompression at a network entity 104. In a MIMO system, the network entity 104 may use CSI to select a digital precoder for the UE 102. The network entity 104 may configure CSI reporting 285 via RRC signaling (e.g., CSI-reportConfig), wherein the UE 102 uses channel measurement resources (CMRs) to measure CSI-RS 240 to estimate 250 a downlink channel. The network entity 104 may also configure (e.g., via CSI-reportConfig) interference measurement resources (IMRs) for the UE 102 to measure interference. Based on the CMRs and IMRs, the UE 102 may be able to identify the CSI, which may include a rank indicator (RI), a precoding matrix indicator (PMI), a channel quality indicator (CQI), and / or a layer indicator (LI). RI and PMI are used to determine the digital precoder (also known as the precoding matrix), CQI indicates the signal to interference plus noise (SINR), which is used to determine the transmitter's selection of the modulation and coding scheme (MCS). LI is used to identify the strongest layer, such as precoder selection for multi-user (MU)-MIMO pairing and phase tracking reference signal (PT-RS) with low rank transmission and precoder selection.

[0040] The UE 102 may indicate a CSI report 285 via a physical uplink control channel (PUCCH) / physical uplink shared channel (PUSCH) in two parts, where CSI Part 1 may include the RI and CQI of a first transport block (TB), and CSI Part 2 may include the PMI, LI, and CQI of a second TB. The payload size of CSI Part 2 may be based on CSI Part 1, and both parts may be transmitted to the network entity 104 using separate channel coding operations.

[0041] The network entity 104 may configure the time domain behavior (e.g., periodic, semi-persistent, or aperiodic reporting) for the CSI report 285 in CSI-reportConfig. The network entity 104 may activate or deactivate semi-persistent CSI reporting via a MAC control element (MAC CE). The network entity 104 may also trigger aperiodic CSI reporting via downlink control information (DCI). The UE 102 may report periodic CSI on PUCCH resources configured in CSI-reportConfig. The UE 102 may report semi-persistent CSI on PUCCH resources configured in CSI-reportConfig or on PUSCH resources triggered by DCI from the network entity 104. The UE 102 may report aperiodic CSI on PUSCH resources triggered by DCI from the network entity 104.

[0042] ML is an example technique that the UE 102 may implement to perform CSI compression 270a, where the first v columns of the eigenvector of the average channel for each subband may be used as input. As used herein, the terms "machine learning" and "artificial intelligence" may be used interchangeably with each other unless expressly stated otherwise.

[0043] Diagram 200 shows an example of ML-based CSI compression after UE 102 receives CSI-RS 240 from network entity 104. UE 102 may perform channel estimation 250 based on CSI-RS 240 and calculate 260a an eigenvector of the channel in each subband. The eigenvector may be input to a neural network for CSI encoder compression 270a. UE 102 transmits 280a a compressed CSI report 285 to network entity 104.

[0044] The network entity 104 performs CSI report detection 280b on the CSI report transmission 280a from the UE 102. The neural network at the network entity 104 decodes the compressed CSI report 285 via CSI decoder decompression 270b to recover the eigenvectors. The network entity 104 selects 260b a precoder for each subband based on the reported eigenvectors.

[0045] ML-based CSI compression techniques may refer to the following terms:

[0046] Data collection refers to the process by which a network node, management entity, or UE 102 collects data for ML model training, data analysis, and inference.

[0047] An ML model refers to a data-driven algorithm that applies ML techniques to generate an output set based on an input set.

[0048] ML model training refers to the process of training an ML model in a data-driven manner (e.g., by learning input / output relationships) to obtain the trained ML model for inference.

[0049] ML model inference refers to the process of using a trained ML model to generate an output set based on an input set.

[0050] ML model validation refers to a subprocess of ML model training for evaluating the quality of an ML model using a dataset different from the training dataset used for model training. The different data can be used to select model parameters that generalize data outside the dataset used for ML model training.

[0051] ML model testing refers to a subprocess of ML model training for evaluating the performance of a trained ML model using a dataset different from the training dataset used for ML model training and validation. Unlike ML model validation, testing does not assume subsequent adjustments to the ML model.

[0052] The UE-side ML model refers to an ML model whose inference is performed at the UE 102 .

[0053] The network-side ML model refers to an ML model whose inference is performed at the network / network entity 104 .

[0054] A one-sided ML model refers to a UE-side ML model or a network-side ML model.

[0055] A two-sided ML model refers to a paired ML model on which joint reasoning is performed, where the joint reasoning includes ML reasoning performed jointly across the UE 102 and the network entity 104 (e.g., a first portion of the reasoning is performed by the UE 102 and the remainder of the reasoning is performed by the network entity 104, or vice versa).

[0056] ML model delivery refers to the delivery of ML models over the air interface based on the parameters of the model structure known at the receiving end or a new model with parameters. The delivery technology can include the delivery of a complete ML model or a partial ML model.

[0057] Model download refers to the transfer of the ML model from the network entity 104 to the UE 102 .

[0058] Model upload refers to the transfer of the ML model from the UE 102 to the network entity 104 .

[0059] Federated learning / federated training refers to a machine learning technique that trains ML models across multiple distributed edge nodes (e.g., UEs, network entities, etc.), with each edge node performing local model training using local data samples. Federated learning / training can be based on multiple interactions with the ML model without exchanging local data samples.

[0060] Offline field data refers to data collected from the field and used for offline training of ML models.

[0061] Online field data refers to data collected from the field and used for online training of ML models.

[0062] Model monitoring refers to the process used to monitor the inference performance of ML models.

[0063] Supervised learning refers to the process of training a model based on inputs and corresponding labels.

[0064] Unsupervised learning refers to the process of training a model without the need for labeled data.

[0065] Semi-supervised learning refers to the process of training a model based on a mixture of labeled and unlabeled data.

[0066] Reinforcement learning (RL) is the process of training an ML model based on the inputs (aka states) and feedback signals (aka rewards) generated from the model’s outputs (aka actions) in the environment that the model interacts with.

[0067] Model activation refers to enabling an ML model for a specific feature.

[0068] Model deactivation refers to disabling an ML model for a specific feature.

[0069] Model switching refers to deactivating the currently active ML model and activating a different ML model for a specific function.

[0070] Figure 3A A first timing diagram 300 is shown of a first CSI processing unit (CPU) duration 311 associated with periodic / semi-persistent CSI reporting. Figure 3B A second timing diagram 350 is shown of a second CPU duration 313 associated with an aperiodic CSI report. The UE 102 may be configured with multiple CSI-reportConfig information elements (IEs) for multiple CSI measurements and reports. Thus, multiple CPUs may be used to process the received CSI-RS in parallel to create multiple CSI measurements and reports. The UE 102 may transmit UE capability information to the network entity 104 indicating the number of CPUs supported by the UE 102. If the CSI report requested by the network entity 104 has more parallel CSI processing at the UE 102 than the number of CPUs available at the UE 102 (i.e., indicated in the UE capability report), the UE 102 may report non-current information for a low priority CSI report. In some examples, the UE 102 may determine the priority of a particular CSI report based on a predefined protocol. For example, the CPU occupancy rules for periodic / semi-persistent CSI reports 307 and aperiodic CSI reports 309 may be based on a predefined protocol.

[0071] The first CPU duration 311 of the periodic / semi-persistent CSI report 307 corresponds to the CPU occupied starting from the first symbol of the earliest resource of the CMR 303 or IMR 305 used for measurement by the UE 102. For example, the UE 102 may perform one or more of CSI-RS measurement, CSI interference measurement (CSI-IM), synchronization signal block (SSB) measurement, etc. The first CPU duration 311 of the periodic / semi-persistent CSI report 307 continues through the last resource of the CMR 303 and IMR 305 used for measurement by the UE 102, and ends at the last symbol of the PUSCH / PUCCH used by the UE 102 to transmit the periodic / semi-persistent CSI report 307 to the network entity 104.

[0072] The second CPU duration 313 of the aperiodic CSI report 309 corresponds to the CPU occupied starting at the first symbol after receiving the physical downlink control channel (PDCCH) 301 that triggers the aperiodic CSI report 309. The second CPU duration 313 of the aperiodic CSI report 309 continues through the last resource of the CMR 303 and IMR 305 measured by the UE 102, and ends at the last symbol of the PUSCH used by the UE 102 to transmit the aperiodic CSI report 309 to the network entity 104. If the PDCCH 301 that triggers the aperiodic CSI report 309 corresponds to two PDCCH candidates in two corresponding search space sets, the PDCCH candidate that ends later in time is used to determine the second CPU duration 313 of the aperiodic CSI report 309.

[0073] If the PDCCH 301 triggers an initial semi-persistent CSI report on the PUSCH, the CPU duration of the initial semi-persistent CSI report may not be the same as the first CPU duration 311 of the periodic / semi-persistent CSI report 307. Instead, the CPU duration of the initial semi-persistent CSI report may correspond to the second CPU duration 313 of the aperiodic CSI report 309. That is, after the PDCCH 301, the CPU duration of the initial semi-persistent CSI report transmitted on the PUSCH starts at the first symbol after the PDCCH 301 and ends at the last symbol of the PUSCH carrying the initial semi-persistent CSI report. If the PDCCH 301 that triggers the initial semi-persistent CSI report corresponds to two PDCCH candidates in two corresponding search space sets, the PDCCH candidate that ends later in time is used to determine the CPU duration of the initial semi-persistent CSI report.

[0074] The CSI reporting by the UE 102 may be based on a minimum processing delay time. For example, the scheduling of periodic / semi-persistent CSI reporting 307 or aperiodic CSI reporting 309 may include minimum processing delays Z and Z'. The values ​​of Z and Z' for different types of CSI reports may be based on one or more predefined protocols. If the scheduling offset does not indicate a minimum processing delay Z and Z', the UE 102 may report the minimum processing delay associated with the non-current CSI, or ignore the triggering DCI if there is no other signal (e.g., data or hybrid automatic repeat request (HARQ)-acknowledgement (ACK) (HARQ-ACK)) to be transmitted on the PUSCH triggered by the DCI (e.g., PDCCH 301). If the CSI request field of the DCI is used to trigger one or more CSI reports from the UE 102 on the PUSCH, the first uplink symbol associated with the one or more CSI reports is used as no earlier than symbol Z. ref UE 102 may transmit one or more CSI reports to network entity 104 if the timing of the start of the nth CSI report is advanced by 0.1% or more. For example, if the first uplink symbol associated with the nth CSI report is not earlier than symbol Z′ ref (n), the UE 102 may transmit the nth triggered CSI report to the network entity 104.

[0075] Compared to non-ML based CSI, ML based CSI reporting may be implemented by the UE 102 based on different hardware (e.g., a neural processing unit (NPU)). ML based and non-ML based CSI reporting may not share a CPU. Therefore, techniques may be implemented to manage parallel processing of multiple ML based CSI reports and mixed ML based / non-ML based CSI reports. In addition, the complexity of ML based CSI reporting may be based on an ML model, which may be associated with a minimum processing delay for ML based CSI reporting. Therefore, a method for parallel processing of ML based CSI measurements and reports based on a CPU management framework and minimum processing delay is proposed.

[0076] Figure 44 is a signaling diagram 400 illustrating an ML-based CSI report processing process. In some examples, the ML-based CSI report processing process may be implemented via hardware different from the non-ML-based CSI report processing process (e.g., via an NPU). The NPU may be dedicated to the ML-based CSI report processing process or shared with other applications (e.g., non-wireless communication based applications). In other examples, the ML-based CSI report processing process may be implemented via the same hardware as the non-ML-based CSI report processing process. Therefore, a second CPU framework may be introduced for the ML-based CSI report processing process. The Type 2 CPU used herein refers to a CPU used for an ML-based CSI report processing process, but not shared with a non-ML-based CSI report processing process / not used for a non-ML-based CSI report processing process. A CPU shared with a non-ML-based CSI report processing process may be referred to as a Type 1 CPU.

[0077] The UE 102 transmits 402 to the network entity 104 a UE capability report regarding ML-based / non-ML-based CSI reporting using a CPU framework. The UE capability report may further indicate whether the UE 102 supports ML-based CSI compression, the maximum number of Type 2 CPUs supported by the UE 102, etc. The network entity 104 may transmit 404 to the UE 102 a configuration of a CSI framework associated with multiple CSI reports. For example, the network entity 104 may transmit 404 the configuration for CSI reporting via RRC signaling (e.g., CSI-reportConfig). For semi-persistent and aperiodic CSI reporting, the network entity 104 may transmit 406 to the UE 102 a trigger indication, such as a MAC-CE or DCI that triggers the corresponding CSI reporting. The trigger indication may trigger multiple ML-based CSI reports or hybrid ML-based / non-ML-based CSI reporting from the UE 102. The network entity 104 may use MAC-CE to activate semi-persistent CSI reporting and use DCI to trigger aperiodic CSI reporting.

[0078] After receiving 406 the control signaling for triggering the CSI report, the UE 102 receives 407 one or more CSI-RSs from the network entity 104. The UE 102 may identify 408 the CPU occupancy state. For example, the UE 102 determines which ML-based / non-ML-based CSI report(s) the UE 102 may transmit 412 to the network entity 104 based on the updated CSI measurement according to the priority of the ML-based / non-ML-based CSI reports. The UE 102 performs 410 the updated CSI measurement to report the high-priority ML-based / non-ML-based CSI report to the network entity 104, but may use the previous (e.g., outdated) CSI measurement to report the low-priority ML-based / non-ML-based CSI report to the network entity 104. The UE 102 includes the updated CSI in the transmitted 412 CSI report of the high priority CSI report and includes the previously measured CSI in the transmitted 412 CSI report of the low priority CSI report, such as when the number of Type 1 CPUs or Type 2 CPUs exceeds the maximum number of Type 1 CPUs or the maximum number of Type 2 CPUs associated with the UE capabilities.

[0079] The UE capability report indicates at least one UE capability, such as whether the UE 102 supports ML-based CSI reporting processing, whether the ML-based CSI reporting processing can share the same CPU as the non-ML-based CSI reporting processing, the maximum number of Type 2 CPUs per component carrier (CC), per band, per band combination, or per UE, etc. In addition to the UE capability of the maximum number of Type 1 CPUs (e.g., simultaneousCSI-ReportsPerCC for the number of Type 1 CPUs per CC, and simultaneousCSI-ReportsAllCC for the number of Type 1 CPUs on all CCs), the UE 102 may also report 402 UE capability information of Type 2 CPUs. In an example, if the UE 102 supports ML-based CSI processing with zero Type 2 CPUs, the network entity 104 may assume that the ML-based CSI reporting processing can share the same CPU as the non-ML-based CSI reporting processing. In addition, if the NPU for the ML-based CSI reporting processing can be shared with other applications, the UE 102 may report the on / off duration of the Type 2 CPU. When a Type2 CPU is "off", the CPU may not be counted in the ML-based CSI reporting process. The on / off duration may be reported based on the maximum periodicity and the "on" duration of the Type2 CPU.

[0080] The network entity 104 may configure whether the ML-based CSI report may occupy the Type 2 CPU. When the ML-based CSI report does not occupy the Type 2 CPU, the ML-based CSI report may also occupy the Type 1 CPU. The network entity 104 may provide the CPU type indication of the CSI report to the UE 102 through RRC signaling (e.g., RRC parameters in CSI-reportConfig). The network entity 104 may provide the CPU type indication for the CSI report through MAC-CE. In an example, the network entity 104 may provide the CPU type indication for the semi-persistent CSI report through MAC-CE. In other examples, the network entity 104 may provide the CPU type indication based on a separate MAC-CE, wherein the MAC-CE may indicate at least one of a serving cell index, a bandwidth part (BWP) index, a CSI-reportConfig ID, or a CPU type indication for the indicated CSI-reportConfig.

[0081] The network entity 104 may similarly provide the CPU type indication of the CSI report to the UE 102 via the DCI. In an example associated with aperiodic CSI reporting, the network entity 104 may indicate the CPU type via the DCI for triggering the CSI report. A field indicating the CPU type may be included in the DCI. Alternatively, the network entity 104 may configure the CPU type corresponding to the CSI triggering state, and based on different values ​​of the CSI request field in the DCI, the network entity 104 may indicate the corresponding CPU type.

[0082] If the UE 102 reports ML-based CSI processing capabilities of a Type 2 CPU, the Type 2 CPU may be occupied based on similar rules / protocols as for a Type 1 CPU. For example, similar to Figure 3A , periodic or semi-persistent CSI reporting (e.g., excluding the initial semi-persistent CSI reporting on PUSCH after the PDCCH that triggers the CSI report) can occupy Type 2 CPU starting from the first symbol of the earliest resource among the CSI-RS resources, CSI-IM resources, or SSB resources used for channel measurement or interference measurement, where the latest CSI-RS / CSI-IM / SSB timing is no later than the corresponding CSI reference resource. Type 2 CPU can continue until the last symbol of the configured PUSCH / PUCCH carrying the CSI report. Similar to Figure 3B, aperiodic CSI reporting can occupy Type 2 CPU from the first symbol after the PDCCH that triggers the CSI report until the last symbol of the scheduled PUSCH carrying the CSI report. When PDCCH reception includes two PDCCH candidates from two separate search space sets, to determine the CPU occupation duration, the PDCCH candidate that ends later in time is used.

[0083] The initial semi-persistent CSI report on the PUSCH after the PDCCH that triggers the CSI report may occupy the Type 2 CPU from the first symbol after the PDCCH until the last symbol of the scheduled PUSCH carrying the CSI report. When the PDCCH reception includes two PDCCH candidates from two separate search space sets, the PDCCH candidate that ends later in time is used to determine the CPU occupancy duration. That is, the network entity 104 and the UE 102 may treat the Type 2 CPU as a subset of the Type 1 CPU. Therefore, if the Type 2 CPU is occupied, the Type 1 CPU is considered occupied. Therefore, the maximum number of Type 2 CPUs reported in the UE capability report is less than or equal to the maximum number of Type 1 CPUs reported in the UE capability report.

[0084] Figure 5 A timing diagram 500 is shown of Type 2 CPU occupancy. After indicating the channel to the UE 102, the UE 102 may utilize the NPU. Therefore, the UE 102 may assume that the Type 2 CPU is occupied after X symbols starting from the first / last symbol of the earliest / latest CMR 303 or IMR 305, until Y symbols before the first / last symbol of the PUSCH / PUCCH for CSI reporting 508. The values ​​of X and Y may be predefined or reported via UE capability messages. Figure 5 An example of the above-mentioned Type 2 CPU occupation rule / protocol is shown.

[0085] FIG. 6A to FIG. 6B Example timing diagrams 600 - 650 illustrate CPU occupancy for ML-based periodic / semi-persistent CSI reporting 307 . FIG. 7A to FIG. 7B Example timing diagrams 700-750 illustrate CPU occupancy for ML-based aperiodic CSI reporting 309. If the UE 102 supports ML-based CSI processing for Type 2 CPU, ML-based CSI reporting processing can also utilize Type 1 CPU because other CSI processing processes (e.g., decoding CSI-RS, RI, and CQI calculations) can be performed without neural network processing.

[0086] In an example, Type 1 CPU and Type 2 CPU may be occupied based on the same rules / protocols as for Type 1 CPU occupancy. In other examples, the network entity 104 and the UE 102 may determine that Type 1 CPU occupancy is based on a legacy protocol, while Type 2 CPU occupancy occurs after X symbols starting from the first symbol / last symbol of the earliest / latest one of the CMR 303 or IMR 305, until Y symbols before the first / last symbol of the PUSCH / PUCCH for CSI reports 307, 309. The values ​​of X and Y may be predefined or reported via a UE capability message.

[0087] In some implementations, the network entity 104 and the UE 102 may determine that the Type 1 CPU is occupied based on a legacy protocol, excluding the duration for which the Type 2 CPU is occupied, as shown in Figures 650 and 750. For example, the Type 1 CPU may start after the PDCCH 301 that triggers the aperiodic CSI report 309, or for the periodic / semi-persistent CSI report 307, after the first / last symbol of the earliest / latest one of the CMR 303 or IMR 305, but may be excluded during the Type 2 CPU occupation duration. As described above, the Type 2 CPU in Figures 650 and 750 may be occupied after X symbols from the first / last symbol of the earliest / latest one of the CMR 303 or IMR 305, until Y symbols before the first / last symbol of the PUSCH / PUCCH for the CSI report 307, 309. Again, the values ​​of X and Y may be predefined or reported via a UE capability message. In other examples, the network entity 104 and the UE 102 may determine that the Type 1 CPU is occupied, including the duration of the Type 2 CPU being occupied, based on a conventional protocol, as shown in diagrams 600 and 700 .

[0088] If the ML-based CSI reporting process is based on Type 2 CPU, then after determining / identifying the Type 2 CPU occupancy state, the UE 102 may process N CPU,2 High priority ML-based CSI reports, where N CPU,2 Corresponds to the maximum number of Type 2 CPUs reported by the UE in the UE capability report. For other (low) priority CSI reports, the UE 102 may report previously measured (eg, outdated) CSI to the network entity 104.

[0089] If the ML-based CSI reporting process is based on both Type 1 CPU and Type 2 CPU, after determining / identifying the Type 1 and Type 2 CPU occupancy states, the UE may process the higher priority min{N CPU,1 -n CPU,1 ,N CPU,2}ML-based CSI reports, where N CPU,1 corresponds to the maximum number of Type 1 CPUs reported by UE 102 in the UE Capability Report, and n CPU,1 The number of CPUs corresponding to other high priority non-ML based CSI reports. For other (low) priority CSI reports, UE 102 may report previously measured (e.g., outdated) CSI to network entity 104. In other examples, network entity 104 may avoid configuring or triggering CSI reports that utilize more Type 1 and Type 2 CPUs than the maximum number of Type 1 and Type 2 CPUs reported by UE 102 in the UE capability report.

[0090] Figure 8 A signaling diagram 800 is shown for CSI reporting based on minimum processing delay. The minimum processing delay for ML-based CSI reporting may depend on whether the UE 102 uses dedicated hardware to process the ML-based CSI reporting. Dedicated hardware such as an NPU may increase neural network processing speeds beyond processing speeds associated with other hardware. The minimum processing delay may also depend on the neural network architecture. If the network entity 104 schedules a scheduling offset that is smaller than the minimum processing delay, the UE 102 may determine to report previously measured (e.g., outdated) CSI to the network entity 104, or ignore the DCI if HARQ-ACK or data is not transmitted on the PUSCH triggered by the DCI.

[0091] The UE 102 transmits 802 a UE capability report to the network entity 104, the UE capability report indicating the UE capability in terms of minimum processing delay for ML-based CSI reporting. The network entity 104 transmits 804 a configuration for a CSI framework associated with ML-based CSI reporting. The network entity 104 may transmit 804 the configuration for ML-based CSI reporting via RRC signaling (e.g., via CSI-reportConfig). For semi-persistent and aperiodic CSI reporting, the network entity 104 may transmit 806 a MAC-CE or DCI that triggers corresponding ML-based CSI reporting. The network entity 104 may transmit 806 a MAC-CE to activate semi-persistent CSI reporting or transmit a DCI to trigger aperiodic CSI reporting.

[0092] After receiving 806 the control signaling for triggering CSI reporting, the UE 102 receives 807 one or more CSI-RS from the network entity 104. The UE 102 determines / identifies 808 a scheduling offset and delay to perform 810 CSI measurement to report ML-based CSI reporting. For example, the UE 102 may determine whether to perform ML-based CSI reporting processing based on a processing time of ML-based CSI reporting compared to the scheduling offset. If the scheduling offset satisfies the minimum processing delay for ML-based CSI reporting processing, the UE 102 transmits 812 the ML-based CSI report to the network entity 104.

[0093] The UE 102 may report minimum processing delays Z and Z' for CSI reporting, where Z and Z' may indicate when the CSI request field of the DCI triggers an ML-based CSI report on the PUSCH, such that if the first uplink symbol carrying the corresponding ML-based CSI-RS report based on the timing advance starts no earlier than symbol Z, and if the first uplink symbol carrying the nth ML-based CSI report based on the timing advance starts no earlier than symbol Z', then the UE 102 may transmit 812 the ML-based CSI report for the nth triggered report. The network entity 104 and the UE 102 may determine the minimum processing delays Z and Z' based on whether the UE 102 uses a Type 2 CPU for ML-based CSI reporting. In an example, two sets of Z and Z' may be predefined, where the first set is applied when the UE 102 does not use a Type 2 CPU, and the second set is applied when the UE 102 does use a Type 2 CPU for ML-based CSI reporting.

[0094] Since the minimum processing delay depends on the ML model, the UE 102 may report the supported Z and Z' for each ML model supported by the UE 102. The UE 102 may report more than one ML model supported by the UE 102. The network entity 104 may indicate the ML model to be used for ML-based CSI reporting via higher layer signaling (e.g., RRC signaling in CSI-reportConfig). The UE 102 applies the corresponding minimum processing delay to the ML-based CSI reporting processing at the UE 102.

[0095] Due to limitations of dedicated hardware for ML-based CSI reporting, the UE 102 may not be able to perform parallel processing for ML-based CSI reports. Therefore, the minimum processing delay may be based on the number of ML-based CSI reports used simultaneously for CSI reporting. The minimum processing delays Z and Z' for a single ML-based CSI report may be predefined or reported by the UE 102 via a UE capabilities message. For N ML-based CSI reports, the minimum processing delays may be µNZ and µNZ', where µ may be predefined, configured by higher layer signaling (e.g., RRC signaling in CSI-reportConfig) from the network entity 104, or reported in a UE capabilities message based on a range of (0,1). The UE 102 may also report whether the UE 102 supports parallel processing as a second UE capability.

[0096] For triggered ML-based CSI reporting, if the scheduling offset does not satisfy the minimum processing delay Z or Z', the UE 102 may ignore the DCI if HARQ-ACK or data is not transmitted on the PUSCH scheduled by the DCI. If the scheduling offset does not satisfy the minimum processing delay Z or Z', the UE 102 may report previously measured (e.g., outdated) CSI for all triggered CSI reports, or the UE 102 may report previously measured (e.g., outdated) CSI for triggered CSI reports that do not satisfy the minimum processing delay Z or Z'. The network entity 104 may avoid configuring or triggering ML-based CSI reporting with a scheduling offset that is smaller than the minimum processing delay for ML-based CSI reporting. Figures 9 and 10 Shown for implementation Figures 1 to 8 Specifically, Fig. 9 UE 102 is shown Figures 1 to 8 Implementation of one or more aspects. Fig.10 The network entity 104 is shown Figures 1 to 8 Implementation of one or more aspects.

[0097] Fig. 9 A flowchart 900 of a method for wireless communication at a UE is shown. Figure 1 to Figure 2 , Figure 4 , Figure 8 and Fig.11 The method may be performed by UE 102, UE device 1102, etc., which may include memory 1126', 1106', 1116 and may correspond to the entire UE 102 or the entire UE device 1102, or components of UE 102 or UE device 1102 (such as a wireless baseband processor 1126 and / or an application processor 1106).

[0098] The UE 102 transmits 902 a UE capability message to a network entity, the UE capability message indicating the UE capability for processing ML-based CSI reporting. Figure 4 , the UE 102 transmits 402 to the network entity 104 a UE capability message regarding ML-based / non-ML-based CSI reporting using a CPU framework. Figure 8 , the UE 102 transmits 802 to the network entity 104 a UE capability message regarding a minimum processing delay for ML-based CSI reporting.

[0099] UE 102 receives 904 from a network entity a configuration for ML-based CSI reporting associated with a first CSI-RS. Figure 4 , the UE 102 receives 404 from the network entity 104 a configuration for a CSI report (eg, ML-based / non-ML-based CSI report) associated with the CSI-RS 407. Figure 8 , the UE 102 receives 804 a configuration for ML-based CSI reporting associated with the CSI-RS 807 from the network entity 104 .

[0100] The UE 102 receives 906 from the network entity a trigger indication for at least one of: an ML-based CSI report, a plurality of ML-based CSI reports including an ML-based CSI report, or an ML-based CSI report and a non-ML-based CSI report. Figure 4 , the UE 102 receives 406 a trigger for multiple ML-based CSI reports or mixed ML-based / non-ML-based CSI reports from the network entity 104. Figure 8 , the UE 102 receives 806 a trigger for ML-based CSI reporting from the network entity 104.

[0101] UE 102 receives 907 a first CSI-RS from a network entity. Figure 4 , the UE 102 receives 407 the CSI-RS from the network entity 104, so that the UE 102 can identify 408 the CPU occupancy state and perform 410 CSI measurement to report the corresponding ML-based / non-ML-based CSI report. Figure 8 , the UE 102 receives 807 a CSI-RS from the network entity 104 so that the UE 102 can identify 808 a scheduling offset and delay and perform 810 a CSI measurement to report an ML-based CSI report.

[0102] The UE 102 transmits 912a an ML-based CSI report to a network entity based on the UE capability for processing the ML-based CSI report. Figure 4, the UE 102 transmits 412 an ML-based / non-ML-based CSI report to the network entity 104 based on the CPU occupancy status. Figure 8 , the UE 102 transmits 812 an ML-based CSI report to the network entity 104 based on the scheduling offset and delay.

[0103] The transmission 912a of the ML-based CSI report may further include the UE 102 transmitting 912b to the network entity 104 an indication of whether the CSI included in the ML-based CSI report is based on the first CSI-RS or a second CSI-RS different from the first CSI-RS. Figure 4 , the UE 102 may transmit 412 an ML-based / non-ML-based CSI report to the network entity 104 based on performing 410 a CSI measurement on the CSI-RS 407 or based on a previous CSI measurement of a previous CSI-RS of the CSI-RS 407. Figure 8 , the UE 102 may transmit 812 an ML-based CSI report to the network entity 104 based on performing 810 a CSI measurement on the CSI-RS 807 or based on a previous CSI measurement of a previous CSI-RS of the CSI-RS 807 . Fig. 9 A method from the UE side of a wireless communication link is described, while Fig.10 A method from the network side of a wireless communication link is described.

[0104] Fig.10 1000 is a flow chart of a method for wireless communication at a network entity. Figure 1 to Figure 2 , Figure 4 , Figure 8 and Fig.12 , the method may be performed by one or more network entities 104, which may correspond to a base station or a unit of a base station, such as RU 106, DU 108, CU 110, RU processor 1206, DU processor 1226, CU processor 1246, etc. One or more network entities 104 may include a memory 1206' / 1226' / 1246', which may correspond to the entirety of one or more network entities 104, or a component of one or more network entities 104, such as RU processor 1206, DU processor 1226, or CU processor 1246.

[0105] The network entity 104 receives 1002 a UE capability message from the UE, the UE capability message indicating a UE capability for processing an ML-based CSI report based on at least one of: a first capability for simultaneously processing a plurality of ML-based CSI reports including an ML-based CSI report, a second capability for simultaneously processing an ML-based CSI report and a non-ML-based CSI report, or a third capability for delaying processing the ML-based CSI report according to a threshold. For example, referring to Figure 4 , the network entity 104 receives 402 from the UE 102 a UE capability message regarding ML-based / non-ML-based CSI reporting using a CPU framework. Figure 8 , the network entity 104 receives 802 a UE capability message from the UE 102 regarding a minimum processing delay for ML-based CSI reporting.

[0106] The network entity 104 transmits 1004 to the UE a configuration for ML-based CSI reporting associated with the first CSI-RS. Figure 4 , the network entity 104 transmits 404 to the UE 102 a configuration for CSI reporting (eg, ML-based / non-ML-based CSI reporting) associated with the CSI-RS 407. Figure 8 , the network entity 104 transmits 804 to the UE 102 a configuration for ML-based CSI reporting associated with the CSI-RS 807 .

[0107] The network entity 104 transmits 1006 to the UE a trigger indication for at least one of: an ML-based CSI report, a plurality of ML-based CSI reports including an ML-based CSI report, or an ML-based CSI report and a non-ML-based CSI report. Figure 4 , the network entity 104 transmits 406 to the UE 102 a trigger for multiple ML-based CSI reports or mixed ML-based / non-ML-based CSI reports. Figure 8 , the network entity 104 transmits 806 to the UE 102 a trigger for ML-based CSI reporting.

[0108] The network entity 104 transmits 1007 a first CSI-RS to the UE. Figure 4 , the network entity 104 transmits 407 the CSI-RS to the UE 102, so that the UE 102 can identify 408 the CPU occupancy state and perform 410 CSI measurement to report the corresponding ML-based / non-ML-based CSI report. Figure 8, the network entity 104 transmits 807 a CSI-RS to the UE 102 so that the UE 102 can identify 808 the scheduling offset and delay and perform 810 CSI measurement to report an ML-based CSI report.

[0109] The network entity 104 receives 1012a an ML-based CSI report from the UE based on the UE capability for processing ML-based CSI reports. Figure 4 , the network entity 104 receives 412 an ML-based / non-ML-based CSI report from the UE 102 based on the CPU occupancy status. Figure 8 , the network entity 104 receives 812 an ML-based CSI report from the UE 102 based on the scheduling offset and delay.

[0110] The receiving 1012a of the ML-based CSI report may further include the network entity 104 receiving 1012b from the UE 102 an indication of whether the CSI included in the ML-based CSI report is based on the first CSI-RS or a second CSI-RS different from the first CSI-RS. Figure 4 , the network entity 104 may receive 412 an ML-based / non-ML-based CSI report from the UE 102 based on a CSI measurement performed 410 on the CSI-RS 407 by the UE 102 or based on a previous CSI measurement of the CSI-RS 407 by the UE 102. Figure 8 , the network entity 104 may receive 812 an ML-based CSI report from the UE 102 based on a CSI measurement performed 810 by the UE 102 on the CSI-RS 807 or based on a previous CSI measurement of the CSI-RS 807 by the UE 102. Fig.11 As described in , UE device 1102 may perform the method of flowchart 900. Fig.12 As described in , one or more network entities 104 may perform the method of flowchart 1000 .

[0111] Fig.111100 is a diagram illustrating an example of a hardware implementation of a UE device 1102. The UE device 1102 may be a UE 102, a component of a UE 102, or may implement a UE function. The UE device 1102 may include an application processor 1106, which may have an on-chip memory 1106'. In an example, the application processor 1106 may be coupled to a secure digital (SD) card 1108 and / or a display 1110. The application processor 1106 may also be coupled to a sensor module 1112, a power supply 1114, an additional memory module 1116, a camera 1118, and / or other related components. For example, the sensor module 1112 may control a barometric pressure sensor / altimeter, a motion sensor (such as an inertial management unit (IMU)), a gyroscope, an accelerometer, a light detection and ranging (LIDAR) device, a radio-aided detection and ranging (RADAR) device, a sound navigation and ranging (SONAR) device, a magnetometer, an audio device, and / or other technologies for positioning.

[0112] The UE device 1102 may further include a wireless baseband processor 1126, which may be referred to as a modem. The wireless baseband processor 1126 may have an on-chip memory 1126'. Together with and similar to the application processor 1106, the wireless baseband processor 1126 may also be coupled to a sensor module 1112, a power supply 1114, an additional memory module 1116, a camera 1118, and / or other related components. The wireless baseband processor 1126 may additionally be coupled to one or more subscriber identity modules (SIM) cards 1120 and / or one or more transceivers 1130 (e.g., wireless RF transceivers).

[0113] Within one or more transceivers 1130, the UE device 1102 may include a Bluetooth module 1132, a WLAN module 1134, an SPS module 1136 (e.g., a GNSS module), and / or a cellular module 1138. The Bluetooth module 1132, the WLAN module 1134, the SPS module 1136, and the cellular module 1138 may each include an on-chip transceiver (TRX), or in some cases, only a transmitter (TX) or only a receiver (RX). The Bluetooth module 1132, the WLAN module 1134, the SPS module 1136, and the cellular module 1138 may each include a dedicated antenna and / or utilize an antenna 1140 to communicate with one or more other nodes. For example, UE device 1102 can communicate with another UE (e.g., sidelink communication) and / or communicate with network entity 104 (e.g., uplink / downlink communication) via antenna 1140 through transceiver 1130, where network entity 104 can correspond to a base station or a unit of a base station, such as RU 106, DU 108, or CU 110.

[0114] The wireless baseband processor 1126 and the application processor 1106 may each include a computer-readable medium / memory 1126', 1106', respectively. The additional memory module 1116 may also be considered a computer-readable medium / memory. Each computer-readable medium / memory 1126', 1106', 1116 may be non-transitory. The wireless baseband processor 1126 and the application processor 1106 may each be responsible for general processing, including executing software stored on the computer-readable medium / memory 1126', 1106', 1116. The software, when executed by the wireless baseband processor 1126 / application processor 1106, enables the wireless baseband processor 1126 / application processor 1106 to perform various functions described herein. The computer-readable medium / memory may also be used to store data manipulated by the wireless baseband processor 1126 / application processor 1106 when executing the software. The wireless baseband processor 1126 / application processor 1106 may be a component of the UE 102. UE device 1102 may be a processor chip (eg, modem and / or applications) and include only the wireless baseband processor 1126 and / or the application processor 1106. In other examples, UE device 1102 may be the entire UE 102 and include additional modules of device 1102.

[0115] like Figure 1 Discussion and about Fig. 9 In an implementation, the UE-based CSI processing component 140 is configured to: receive a configuration for an ML-based CSI report associated with a first CSI-RS from a network entity; receive the first CSI-RS from the network entity; and transmit an ML-based CSI report to the network entity, the CSI report including CSI based on the UE capability for processing the ML-based CSI report associated with the first CSI-RS. The UE-based CSI processing component 140 can be within the application processor 1106 (e.g., at 140a), within the wireless baseband processor 1126 (e.g., at 140b), or within both the application processor 1106 and the wireless baseband processor 1126. The UE-based CSI processing components 140a-140b can be one or more hardware components explicitly configured to perform the process / algorithm, implemented by one or more processors configured to perform the process / algorithm, stored in a computer-readable medium for implementation by one or more processors, or a combination thereof.

[0116] Fig.121200 is a diagram illustrating an example of a hardware implementation of one or more network entities 104. One or more network entities 104 may be a base station, a component of a base station, or may implement base station functionality. One or more network entities 104 may include or may correspond to at least one of a RU 106, a DU 108, or a CU 110. The CU 110 may include a CU processor 1246, which may have an on-chip memory 1246'. In some aspects, the CU 110 may further include an additional memory module 1256 and / or a communication interface 1248, both of which may be coupled to the CU processor 1246. The CU 110 may communicate with the DU 108 via a mid-range link 162, such as an F1 interface between the communication interface 1248 of the CU 110 and the communication interface 1228 of the DU 108.

[0117] The DU 108 may include a DU processor 1226, which may have an on-chip memory 1226'. In some aspects, the DU 108 may further include an additional memory module 1236 and / or a communication interface 1228, both of which may be coupled to the DU processor 1226. The DU 108 may communicate with the RU 106 via a fronthaul link 160 between the communication interface 1228 of the DU 108 and the communication interface 1208 of the RU 106.

[0118] The RU 106 may include a RU processor 1206, which may have an on-chip memory 1206'. In some aspects, the RU 106 may further include an additional memory module 1216, a communication interface 1208, and one or more transceivers 1230, all of which may be coupled to the RU processor 1206. The RU 106 may further include an antenna 1240, which may be coupled to the one or more transceivers 1230, such that the RU 106 may communicate with the UE 102 via the antenna 1240 through the one or more transceivers 1230.

[0119] On-chip memory 1206 ', 1226 ', 1246 'and additional memory modules 1216, 1236, 1256 can each be considered as a computer-readable medium / memory. Each computer-readable medium / memory can be non-temporary. Each of the processors 1206, 1226, 1246 is responsible for general processing, including executing software stored on the computer-readable medium / memory. The software, when executed by the corresponding processor 1206, 1226, 1246, enables the processor 1206, 1226, 1246 to perform various functions described herein. The computer-readable medium / memory can also be used to store data manipulated by the processor 1206, 1226, 1246 when executing the software. In an example, the network-based CSI processing component 150 may be located at any of the one or more network entities 104, such as at the CU 110; at both the CU 110 and the DU 108; at each of the CU 110, DU 108, and RU 106; at both the DU 108 and the RU 106; or at the RU 106.

[0120] like Figure 1 Discussion and about Fig.10 In one embodiment, the network-based CSI processing component 150 is configured to: transmit to the UE a configuration for an ML-based CSI report associated with a first CSI-RS; transmit to the UE the first CSI-RS; and receive from the UE an ML-based CSI report, the CSI report including CSI based on the UE capability for processing the ML-based CSI report associated with the first CSI-RS. The network-based CSI processing component 150 may be located within one or more processors of one or more network entities 104, such as within a RU processor 1206 (e.g., at 150a), a DU processor 1226 (e.g., at 150b), and / or a CU processor 1246 (e.g., at 150c). The network-based CSI processing components 150a-150c may be one or more hardware components explicitly configured to perform the process / algorithm, implemented by one or more processors 1206, 1226, 1246 configured to perform the process / algorithm, stored in a computer-readable medium for implementation by one or more processors 1206, 1226, 1246, or a combination thereof.

[0121] The specific order or hierarchy of the boxes in the process and flow chart disclosed herein is an illustration of an example method. Therefore, the specific order or hierarchy of the boxes in the process and flow chart can be rearranged. Some boxes can also be merged or deleted. The attached method claims present the elements of each box in the example order, and are not limited to the specific order or hierarchy presented in the claims, process and flow chart.

[0122] The detailed description set forth herein describes various configurations in conjunction with the accompanying drawings, but does not represent the only configuration in which the concepts described herein can be practiced. The detailed description includes specific details for providing a comprehensive explanation of the various concepts. However, these concepts can be practiced without using these specific details. In some cases, well-known structures and components are shown in block diagram form in order to avoid blurring such concepts.

[0123] Various aspects of wireless communication systems (such as telecommunication systems) are presented with reference to various apparatus and methods. These apparatus and methods are described in the detailed description that follows and are illustrated in the accompanying drawings by various blocks, components, circuits, processes, call flows, systems, algorithms, etc. (collectively, "elements"). These elements may be implemented using electronic hardware, computer software, or a combination thereof. Whether such elements are implemented as hardware or software depends on the specific application and design constraints imposed on the overall system.

[0124] Elements, or any part of elements or any combination of elements can be implemented as a "processing system" including 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 (SoCs), baseband processors, field programmable gate arrays (FPGAs), programmable logic devices (PLDs), state machines, gating logic, discrete hardware circuits, and other similar hardware configured to perform various functions described throughout this disclosure. One or more processors in a processing system can execute software, which can be referred to as software, firmware, middleware, microcode, hardware description language, or other. Software should be broadly interpreted as meaning instructions, instruction sets, codes, code segments, program codes, programs, subroutines, software components, applications, software applications, software packages, routines, subroutines, objects, executables, execution threads, processes, functions, or any combination thereof.

[0125] If the functions described herein are implemented in software, the functions may be stored on a computer-readable medium (such as a non-transitory computer-readable storage medium) or encoded as one or more instructions or codes on the computer-readable medium. Computer-readable media include computer storage media and may include random access memory (RAM), read-only memory (ROM), electrically erasable programmable ROM (EEPROM), optical disk storage devices, magnetic disk storage devices, other magnetic storage devices, combinations of these types of computer-readable media, or any other medium that can be used to store computer-executable code in the form of computer-accessible instructions or data structures. The storage medium can be any available medium that is accessible to a computer.

[0126] The aspects, implementations, and / or use cases described herein may be implemented across many different platform types, devices, systems, shapes, sizes, and packaging arrangements. For example, the aspects, implementations, and / or use cases may be generated via integrated chip implementations and other non-module component-based devices such as end-user devices, vehicles, communication devices, computing devices, industrial equipment, retail / procurement devices, medical devices, AI-enabled devices, ML-enabled devices, and the like. 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 aggregated, distributed, or original equipment manufacturer (OEM) devices or systems incorporating one or more of the techniques described herein.

[0127] Devices incorporating the various aspects and features described herein may also include additional components and features for implementing and practicing the various aspects and features claimed and described. For example, the transmission and reception of wireless signals necessarily include many components for analog and digital purposes, such as hardware components, antennas, RF chains, power amplifiers, modulators, buffers, processors, interleavers, adders / summers, etc. The 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., in various configurations.

[0128] The description herein is provided to enable those skilled in the art to practice the various aspects described herein. Various modifications to these aspects will be apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects. Therefore, the claims are not limited to the various aspects described herein, but should be interpreted in view of the full scope of the disclosure consistent with the language of the claims.

[0129] Unless explicitly stated, references to singular elements do not mean "one and only one", but rather "one or more". Terms such as "if", "when ..." and "at ..." do not imply an immediate temporal relationship or reaction. That is, these phrases (such as "when ...") do not imply an immediate action in response to the occurrence of an action or during the occurrence of an action, but simply mean that if a certain condition is met, a certain action will occur, but no specific or immediate time constraints are required for the occurrence of the action. Unless explicitly 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 multiple A, multiple B, and / or multiple C, or may include only A, only B, or only C. A set should be interpreted as a set of elements in which the number of elements is one or more.

[0130] The structural equivalents and functional equivalents of the elements of various aspects described in the entire disclosure known or later learned by those of ordinary skill in the art are expressly incorporated herein by reference and are covered by the claims. The words "module", "mechanism", "element", "device", etc. may not be substitutes for the word "component". Therefore, unless the claim element is clearly stated using the phrase "component for...", any claim element shall not be interpreted as a means plus function. As used herein, the phrase "based on" should not be interpreted as a reference to a closed information set, one or more conditions, one or more factors, etc. In other words, unless clearly stated differently, the phrase "based on A" (where "A" can be information, conditions, factors, etc.) should be interpreted as "at least based on A".

[0131] The following examples are merely illustrative and may be combined with other examples or teachings described herein without limitation.

[0132] Example 1 is a method for performing wireless communications at a UE, comprising: receiving a configuration for an ML-based CSI report associated with a first CSI-RS from a network entity; receiving the first CSI-RS from the network entity; and transmitting the ML-based CSI report to the network entity, the CSI report including CSI based on UE capabilities for processing the ML-based CSI report associated with the first CSI-RS.

[0133] Example 2 may be combined with Example 1, and the UE capability for processing the ML-based CSI report includes a first capability for simultaneously processing a plurality of ML-based CSI reports including the ML-based CSI report.

[0134] Example 3 may be combined with any one of Examples 1 to 2, and include the UE capability for processing the ML-based CSI report including a second capability for simultaneously processing the ML-based CSI report and a non-ML-based CSI report.

[0135] Example 4 may be combined with any one of Examples 1 to 3, and include the UE capability for processing the ML-based CSI report including a third capability for processing the ML-based CSI report with a processing delay according to a threshold.

[0136] Example 5 may be combined with any one of Examples 1 to 4, and further comprises transmitting, to the network entity, a UE capability message indicating the UE capability for processing the ML-based CSI report.

[0137] Example 6 can be combined with any one of Examples 1 to 5, and further includes receiving a trigger indication of at least one of the following from the network entity: the ML-based CSI report, the multiple ML-based CSI reports including the ML-based CSI report, or the ML-based CSI report and the non-ML-based CSI report.

[0138] Example 7 can be combined with any one of Examples 1 to 6, and includes when the UE has the UE capability for processing the ML-based CSI report associated with the first CSI-RS, the CSI included in the ML-based CSI report is based on the first CSI-RS.

[0139] Example 8 can be combined with any one of Examples 1 to 6, and includes when the UE does not have the UE capability for processing the ML-based CSI report associated with the first CSI-RS, the CSI included in the ML-based CSI report is based on a second CSI-RS different from the first CSI-RS; and the method further includes receiving the second CSI-RS from the network entity before receiving the first CSI-RS.

[0140] Example 9 can be combined with Example 8, and includes that the ML-based CSI report of the CSI based on the second CSI-RS is a first CSI report, the UE processes the first CSI report simultaneously with a second CSI report having a higher priority than the first CSI report, wherein the priority of the second CSI report is higher than the first CSI report, and the UE is capable of simultaneously processing the first CSI report based on the second CSI-RS and the second CSI report based on the first CSI-RS, but is not capable of simultaneously processing the first CSI report based on the first CSI-RS and the second CSI report.

[0141] Example 10 may be combined with any one of Examples 1 to 9, and include that transmitting the ML-based CSI report includes: transmitting to the network entity an indication of whether the CSI included in the ML-based CSI report is based on the first CSI-RS or the second CSI-RS.

[0142] Example 11 is a method for wireless communication at a network entity, comprising: transmitting a configuration for an ML-based CSI report associated with a first CSI-RS to a UE; transmitting the first CSI-RS to the UE; and receiving the ML-based CSI report from the UE, the CSI report including CSI based on UE capabilities for processing the ML-based CSI report associated with the first CSI-RS.

[0143] Example 12 can be combined with Example 11, and further includes receiving a UE capability message from the UE, the UE capability message indicating that the UE capability for processing the ML-based CSI report includes at least one of the following: a first capability for simultaneously processing multiple ML-based CSI reports including the ML-based CSI report, a second capability for simultaneously processing the ML-based CSI report and a non-ML-based CSI report, or a third capability for delaying processing the ML-based CSI report according to a threshold processing.

[0144] Example 13 can be combined with any one of Examples 11 to 12, and further includes transmitting a trigger indication of at least one of the following to the UE: the ML-based CSI report, the multiple ML-based CSI reports including the ML-based CSI report, or the ML-based CSI report and the non-ML-based CSI report.

[0145] Example 14 may be combined with any one of Examples 11 to 13, and includes when the UE has the UE capability for processing the ML-based CSI report associated with the first CSI-RS, the CSI included in the ML-based CSI report being based on the first CSI-RS.

[0146] Example 15 can be combined with any one of Examples 11 to 13, and includes when the UE does not have the UE capability for processing the ML-based CSI report associated with the first CSI-RS, the CSI included in the ML-based CSI report is based on a second CSI-RS different from the first CSI-RS; and the method further includes transmitting the second CSI-RS to the UE before transmitting the first CSI-RS.

[0147] Example 16 can be combined with Example 15, and includes that the ML-based CSI report of the CSI based on the second CSI-RS is a first CSI report, the UE processes the first CSI report simultaneously with a second CSI report having a higher priority than the first CSI report, and the UE is capable of simultaneously processing the first CSI report based on the second CSI-RS and the second CSI report based on the first CSI-RS, but is not capable of simultaneously processing the first CSI report based on the first CSI-RS and the second CSI report.

[0148] Example 17 may be combined with any one of Examples 11 to 16, and includes receiving the ML-based CSI report including: receiving, from the UE, an indication of whether the CSI included in the ML-based CSI report is based on the first CSI-RS or the second CSI-RS.

[0149] Example 18 is a device for wireless communication implementing the method as described in any one of Examples 1 to 17.

[0150] Example 19 is an apparatus for wireless communication including means for implementing the method as described in any of Examples 1 to 17.

[0151] Example 20 is a non-transitory computer-readable medium storing a computer executable code, which, when executed by at least one processor, causes the at least one processor to implement a method as described in any one of Examples 1 to 17.

Claims

1. A method of wireless communication at a user equipment (UE) (102), comprising: receiving (404, 804) from a network entity (104) a configuration for machine learning (ML) based channel state information (CSI) reporting associated with a first channel state information-reference signal (CSI-RS); receiving (407, 807) the first CSI-RS from the network entity (104); as well as The ML-based CSI report is transmitted (412, 812) to the network entity (104), the ML-based CSI report comprising CSI based on UE capabilities for processing the ML-based CSI report associated with the first CSI-RS.

2. The method of claim 1, wherein the UE capability for processing the ML-based CSI report comprises a first capability for simultaneously processing (410) a plurality of ML-based CSI reports including the ML-based CSI report.

3. The method according to any one of claims 1 to 2, wherein the UE capability for processing the ML-based CSI report comprises a second capability for simultaneously processing (410) the ML-based CSI report and a non-ML-based CSI report.

4. The method of any one of claims 1 to 3, wherein the UE capabilities for processing the ML-based CSI report include a third capability for processing (810) the ML-based CSI report according to a threshold processing delay (808).

5. The method according to any one of claims 1 to 4, further comprising: A UE capability message is transmitted (402, 802) to the network entity (104), the UE capability message indicating the UE capability for processing the ML-based CSI report.

6. The method according to any one of claims 1 to 5, further comprising: Receiving (406, 806) from the network entity (104) a trigger indication of at least one of: The ML-based CSI report, the plurality of ML-based CSI reports comprising the ML-based CSI report, or The ML-based CSI report and the non-ML-based CSI report.

7. The method of any one of claims 1 to 6, wherein when the UE (102) has the UE capability for processing the ML-based CSI report associated with the first CSI-RS (407, 807), the CSI included in the ML-based CSI report is based on the first CSI-RS (407, 807).

8. The method according to any one of claims 1 to 6, wherein when the UE (102) does not have the UE capability for processing the ML-based CSI report associated with the first CSI-RS (407, 807), the CSI included in the ML-based CSI report is based on a second CSI-RS different from the first CSI-RS (407, 807); and The method further includes receiving the second CSI-RS from the network entity (104) before receiving (407, 807) the first CSI-RS.

9. The method of claim 8, wherein the ML-based CSI report including the CSI based on the second CSI-RS is a first CSI report, the UE (102) processes the first CSI report simultaneously with a second CSI report having a higher priority than the first CSI report, and the UE (102) is capable of simultaneously processing the first CSI report based on the second CSI-RS and the second CSI report based on the first CSI-RS (407, 807), but is not capable of simultaneously processing the first CSI report based on the first CSI-RS (407, 807) and the second CSI report.

10. The method of any one of claims 1 to 9, wherein transmitting (412, 812) the ML-based CSI report comprises: An indication of whether the CSI included in the ML-based CSI report is based on the first CSI-RS (407, 807) or the second CSI-RS is transmitted (412, 812) to the network entity (104).

11. A method for wireless communication at a network entity (104), comprising: transmitting (404, 804) to a user equipment (UE) (102) a configuration for machine learning (ML) based channel state information (CSI) reporting associated with a first channel state information-reference signal (CSI-RS); transmitting (407, 807) the first CSI-RS to the UE (102); as well as The ML-based CSI report is received (412, 812) from the UE (102), the ML-based CSI report comprising CSI based on UE capabilities for processing the ML-based CSI report associated with the first CSI-RS.

12. The method of claim 11, further comprising: Receiving (402, 802) a UE capability message from the UE (102), the UE capability message indicating that the UE capability for processing the ML-based CSI report includes at least one of the following: a first capability for simultaneously processing a plurality of ML-based CSI reports including said ML-based CSI report, a second capability for simultaneously processing the ML-based CSI reports and non-ML-based CSI reports, or A third capability for processing the ML-based CSI report according to a threshold processing delay.

13. The method of any one of claims 11 to 12, wherein when the UE (102) has the UE capability for processing the ML-based CSI report associated with the first CSI-RS (407, 807), the CSI included in the ML-based CSI report is based on the first CSI-RS (407, 807).

14. The method of any one of claims 11 to 12, wherein when the UE (102) does not have the UE capability for processing the ML-based CSI report associated with the first CSI-RS (407, 807), the CSI included in the ML-based CSI report is based on a second CSI-RS different from the first CSI-RS (407, 807); and The method further comprises transmitting the second CSI-RS to the UE (102) before transmitting (407, 807) the first CSI-RS.

15. The method of any one of claims 11 to 14, wherein receiving (412, 812) the ML-based CSI report comprises: An indication is received (412, 812) from the UE (102) as to whether the CSI included in the ML-based CSI report is based on the first CSI-RS (407, 807) or the second CSI-RS.

16. An apparatus for wireless communication, comprising a memory, a transceiver and a processor, the processor being coupled to the memory and the transceiver, the apparatus being configured to implement the method according to any one of claims 1 to 15.

Images