In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may receive at least two reference signals from a base station. The apparatus may determine CSI associated with at least one of the at least two reference signals. The apparatus may determine at least one parameter based on the CSI. The apparatus may transmit, to the base station, the at least one parameter and the CSI to enable a predicted CSI to be determined based on the at least one parameter and the CSI. The apparatus may receive data or control information from the base station based on predictive CSI determined by the base station using the transmitted at least one parameter and CSI.

Certain aspects of the present disclosure provide techniques and apparatus for calibrating radio frequency (RF) circuits using machine learning. One example method generally includes calibrating a first subset of RF circuit calibration parameters. Values are predicted for a second subset of RF circuit calibration parameters based on a machine learning model and the first subset of RF circuit calibration parameters. The second subset of RF circuit calibration parameters may be distinct from the first subset of RF circuit calibration parameters. At least the first subset of RF circuit calibration parameters is verified, and after the verifying, at least the first subset of RF circuit calibration parameters are written to a memory associated with the RF circuit.

Methods and apparatus are described for enhanced node communication within a wireless node network having nodes and a server. The method begins with a first node associating with a second node, and the first node capturing relevant node information. When the first node is in a first connectivity mode, the relevant node information is transmitted to the server via the second node operating as an intermediary for indirect communication with the server. When the first node is in a second connectivity mode, the first node transmits the relevant node information to the server without using the second node as the intermediary or bridge to the server. Each of the first node and second node may be wireless transceiver-based nodes and respectively implemented as integrated circuits.

In one embodiment, a method includes sending SRS received from a plurality of UEs associated with the base station to a DU associated with the base station, receiving information regarding a subset of the plurality of UEs selected for downlink data transmissions for an RBG, multi-user data to be transmitted to UEs in the subset, and identities of selected beams among a plurality of pre-determined beams to be associated with the UEs in the subset from the DU, where each of the plurality of pre-determined beams corresponds to a DFT vector, computing a precoding matrix for the RBG based on IDFT vectors corresponding to the selected beams, preparing pre-coded multi-user data by applying the precoding matrix to the multi-user data, and transmitting the pre-coded multi-user data to the UEs in the subset for the RBG using MIMO technologies.

A user equipment (UE), such as a mobile phone, may support multiple power classes. Power classes can define maximum output power levels for uplink transmissions. A base station of a radio access network (RAN) can, based on metrics reported by the UE, dynamically instruct the UE to switch to using a different power class. For example, the base station may instruct the UE to switch from using a first power class with a higher maximum output power to using a second power class with a lower maximum output power, in order to preserve battery life of the UE in situations in which the second power class provides sufficient output power for uplink transmissions to reach the base station.

A method and network node for determining a Radio Frequency (RF) propagation model for a coverage area from an image view of the coverage area. The method selects a coverage area for a transmission point of a transmitter and obtains an image view of the selected coverage area. The method further recognizes, from a plurality of morphology types, a morphology type for the selected coverage area from the obtained image view using a machine learning model; and determines a RF propagation model for the selected coverage area based on the recognized morphology type.

A robust predictive model. A plurality of different predictive models for a target feature are run, and a comparative analysis provided for each predictive model that meet minimum performance criteria for the target feature. One of the predictive models is selected, either manually or automatically, based on predefined criteria. For semi-automatic selection, a static or dynamic survey is generated for obtaining user preferences for parameters associated with the target feature. The survey results will be used to generate a model that illustrates parameter trade-offs, which will be used to finalize the optimal predictive model for the user.

One or more processors control processing of radio frequency (RF) signals using a machine-learning network. The one or more processors receive as input, to a radio communications apparatus, a first representation of an RF signal, which is processed using one or more radio stages, providing a second representation of the RF signal. Observations about, and metrics of, the second representation of the RF signal are obtained. Past observations and metrics are accessed from storage. Using the observations, metrics and past observations and metrics, parameters of a machine-learning network, which implements policies to process RF signals, are adjusted by controlling the radio stages. In response to the adjustments, actions performed by one or more controllers of the radio stages are updated. A representation of a subsequent input RF signal is processed using the radio stages that are controlled based on actions including the updated one or more actions.

Aspects of the subject disclosure may include, for example, obtaining channel cross correlation data relating to multiple user equipment (UEs) being served in a cell, wherein the channel cross correlation data comprises a correlation coefficient associated with a first UE of the multiple UEs and a second UE of the multiple UEs, identifying that the first UE is experiencing decreasing throughput, responsive to the identifying that the first UE is experiencing decreasing throughput, determining whether the correlation coefficient associated with the first UE and the second UE satisfies a correlation threshold, and, based on a first determination that the correlation coefficient does not satisfy the correlation threshold, adjusting a downlink (DL) transmit power allocation for transmissions directed to the first UE. Other embodiments are disclosed.

Systems and methods for localizing individuals in a region using wireless signals in accordance with embodiments are illustrated. One embodiment includes a method for localizing individuals in a region between wireless devices of a system. The method receives wireless signal strength data for signals transmitted along signal paths between several wireless playback devices transmitting on a wireless channel during synchronous playback of media content by the several wireless playback devices and determines a first signal strength for each of several portions of the wireless channel. The method calculates, for each signal path between each of the several wireless playback devices, a difference in the determined first signal strength from a second signal strength for each of the several subcarriers, and determines, based on the calculated differences, a state for a set of one or more individuals in the region.