Abstract: Aspects described herein relate to using machine learning (ML) models for performing channel state information (CSI) encoding or decoding, CSI-reference signal (RS) optimization, channel estimation, etc. The ML models can be trained by a user equipment (UE), separately by the UE and a network node (e.g., base station), or jointly by the UE and network node.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may generate multiple channel state information (CSI) reports that are linked together for coherent joint transmission (CJT) with multiple transmit receive points (TRPs). The UE may transmit the multiple CSI reports that are linked. Numerous other aspects are described.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a network node may determine a reference location associated with an image corresponding to a target area, wherein the target area is offset from the reference location. The network node may transmit a radio frequency signal, wherein the radio frequency signal is beamformed based at least in part on the reference location to provide the radio frequency signal to the target area. Numerous other aspects are described.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive from a network entity, a control message triggering the UE to provide a time-domain aperiodic channel state information (A-CSI) report for indicating time-domain channel state information (CSI) associated with CSI reference signal (CSI-RS) resources within an observation window, where a beginning of the observation window is based on when the control message is received. The UE may perform performing measurements of channel state information reference signals (CSI-RSs) received via the CSI-RS resources that occur within the observation window. The UE may then transmit, to the network entity based on the control message, the time-domain A-CSI report indicating measured time-domain CSI associated with the observation window, where the measured time-domain CSI is based on the measurements.

Abstract: A base station may select at least one of one or more 2D beams for at least one first SSB of a plurality of SSBs or one or more 3D beams for at least one second SSB of the plurality of SSBs. A UE may identify a beam type of at least one of one or more 2D beams for at least one first SSB of a plurality of SSBs or one or more 3D beams for at least one second SSB of the plurality of SSBs. The base station may transmit, to the UE, at least one of the at least one first SSB via the one or more 2D beams or the at least one second SSB via the one or more 3D beams.

Abstract: Methods, systems, and devices for wireless communications are described. The method may include a first network node receiving a configuration message for a report by the first network node of parameters for a temporal domain precoder. The configuration message may indicate a range of Doppler frequencies, a resolution associated with the range of Doppler frequencies, or a quantity of the parameters to be reported. The first network node may estimate a communications channel and select one or more bins within the range of Doppler frequencies based on the channel estimation. For each selected bin, the first network node may determine a corresponding discrete Fourier transform (DFT) vector and transmit a report indicating the corresponding DFT vector.

Abstract: Certain aspects of the present disclosure provide techniques for channel estimation based on transmission spatial information. An example method of wireless communication by a user equipment includes receiving an indication of transmission spatial information associated with a network entity; receiving a reference signal from the network entity based on the transmission spatial information; and transmitting, to the network entity, channel state information (CSI) based on the received reference signal and the transmission spatial information.

Abstract: A method of wireless communication by a base station includes receiving a channel state information (CSI) payload at a neural network CSI decoder. The method also includes decoding the CSI payload to generate a quantity (N) of precoding vectors for N transmission layers. The method further includes orthogonalizing the N precoding vectors to generate N orthogonal precoding vectors. The method still further includes transmitting, to a user equipment (UE), downlink data that is precoded in accordance with the N orthogonal precoding vectors.

Abstract: Methods, systems, and devices for wireless communication are described. A user equipment (UE) may transmit a sounding reference signal (SRS) in multiple slots. A network entity may determine precoding weights in three domains based on the SRS and output reference signals that are precoded based on the precoding weights. The network entity may output control signaling that indicates reference signal resource grouping information that the UE is to use for channel estimations. The reference signal resource grouping information may specify whether the ports in one group are precoded with identical or different spatial, frequency, and time domain weights. A UE may receive the precoded reference signals and the grouping information and report estimated channel metrics and an indication of selected ports per group to the network entity. The network entity may determine precoding in three domains for subsequent downlink communications.

Abstract: Aspects of the disclosure relate to a method of, and apparatus for, wireless communication by a user equipment (UE). The method includes receiving a set of reference signals and transmitting, based at least in part on the set of reference signals: a set of Doppler frequency values and a set of weight values that correspond to the set of Doppler frequency values. In another example, a method of, and apparatus for, wireless communication by a base station (BS) is disclosed. The method includes transmitting, to the UE, a signal that has been precoded based at least in part on the set of Doppler frequency values, and the corresponding set of weight values. Other aspects, embodiments, and features are also claimed and described.

Abstract: A method and a system for automatic machine learning-based prediction of new energy power with cloud-edge collaboration are disclosed. The method includes: obtaining, in response to a power prediction demand for a target new energy station, future numerical weather prediction data of the target new energy station in a future period and historical output power of a historical period corresponding to the future period; selecting, based on missing of the future numerical weather prediction data and a data amount of the historical output power, a target power prediction model corresponding to the target new energy station; and adjusting the target power prediction model according to the target working mode, and predicting, by the adjusted target power prediction model, a target output power of the target new energy station in the future period, based on the future numerical weather prediction data and the historical output power.

Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive configuration information that specifies one or more parameters associated with generating, by the UE, a time domain covariance matrix specific to the UE. The UE may receive a channel state information (CSI) reference signal (CSI-RS). The UE may transmit, based at least in part on the CSI-RS and the one or more parameters, a CSI report, the CSI report including data representing the time domain covariance matrix. Numerous other aspects are described.

Abstract: Aspects described herein relate to encoding, based on an estimated channel matrix of a reference signal received from a base station, channel state information (CSI) using a machine learning (ML)-based CSI encoder, transmitting, to the base station, an output of the ML-based CSI encoder and assistance information related to the estimated channel matrix, and receiving, from the base station, a scheduling grant for a downlink channel having at least one parameter that is based on the output of the ML-based CSI encoder and the assistance information. Other aspects relate to receiving the CSI encoder output and assistance information, and transmitting the scheduling grant.

Abstract: Methods, systems, and devices for wireless communication are described to support reducing a time domain selectivity of a downlink channel with multiple signal paths. A base station may spatially precode multiple channel state information reference signals (CSI-RSs) and transmit the spatially precoded CSI-RSs to a user equipment (UE), where at least one spatially precoded CSI-RS may correspond to each signal path. Based on the spatially precoded CSI-RSs, the UE may determine a mean or average Doppler shift for each signal path. The UE may transmit, to the base station, signaling indicative of the respective average Doppler shifts for each signal path. Based on the indication of the Doppler shifts, the base station may spatially and temporally precode one or more downlink transmissions to the UE, which may reduce the time domain selectivity of the downlink channel.

Abstract: Certain aspects of the present disclosure provide techniques for reporting channel state information (CSI). According to certain aspects, a method for wireless communications by a user equipment (UE) generally includes generating channel state information (CSI) comprising a (at least one) fractional rank indication (RI) value for a set of candidate ranks, a first indication of a first layer or first singular vector, and a second indication of a second layer or second singular vector and transmitting the CSI to a network entity.

Abstract: Methods, systems, and devices for wireless communication are described. A first wireless device may transmit one or more signals to a second wireless device using an antenna panel including antenna elements that are arranged in a hexagonal configuration. The signals may be transmitted using one or more directional beams for multiple-input multiple-output communications with the second wireless device, the directional beams generated based on the antenna elements in the hexagonal configuration. The first wireless device may receive a signal from the second wireless device, and in some cases, the first wireless device may transmit one or more reference signals via the one or more directional beams, the reference signals associated with a set of two or more antenna elements of the antenna panel of the first wireless device. The second wireless device may perform measurements of the reference signals and transmit a measurement report to the first wireless device.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive, from a base station, a first indication that the UE is within a distance threshold (e.g., in the near field) of multiple-in multiple-out (MIMO) communications from the base station. The UE may communicate with the base station via signaling including a second indication of antenna panel information of at least one of the UE or the base station, the communication based on the UE being within the distance threshold. The UE may receive, from the base station, a first beamformed signal on one or more first beams within the distance threshold, and the CE may receive, from the base station, one or more second beamformed signals on a second beam within the distance threshold, the second beam based on a channel response matrix that is estimated from the second indication and the first beamformed signal.

Abstract: A method and a system for automatic machine learning-based prediction of new energy power with cloud-edge collaboration are disclosed. The method includes: obtaining, in response to a power prediction demand for a target new energy station, future numerical weather prediction data of the target new energy station in a future period and historical output power of a historical period corresponding to the future period; selecting, based on missing of the future numerical weather prediction data and a data amount of the historical output power, a target power prediction model corresponding to the target new energy station; and adjusting the target power prediction model according to the target working mode, and predicting, by the adjusted target power prediction model, a target output power of the target new energy station in the future period, based on the future numerical weather prediction data and the historical output power.

Abstract: A method of wireless communication by a user equipment (UE), includes estimating a downlink channel to generate a channel estimate. The method also includes obtaining multiple precoding matrices, by a channel state information (CSI) module including a neural network encoder decoder pair, based on the channel estimate and multiple different multiple input multiple output (MIMO) ranks. The method further includes determining a best rank indicator based on the precoding matrices and spectral efficiency estimates for the different MIMO ranks. The method still further includes reporting, to a base station, the best rank indicator, a channel quality index (CQI), and CSI encoder output.

Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive, from a base station, a channel state information (CSI) configuration indicating a first feedback reporting periodicity for a dominant, or strong, spatial layer and a second feedback reporting periodicity for a non-dominant, or weak, spatial layer. The UE may transmit a first CSI report for at least the dominant spatial layer according to the first feedback reporting periodicity. The UE may transmit a second CSI report for the non-dominant spatial layer according to the second feedback reporting periodicity. In some cases, for aperiodic reporting, the UE may be triggered by downlink control information to report CSI for the dominant spatial layer. In some cases, the CSI configuration may indicate different codebooks for the dominant and non-dominant spatial layers.