The present technology is directed to providing a 3-D visualization of a Wi-Fi signal propagation pattern based on telemetry data. The present technology can receive telemetry data for a Wi-Fi access point located at a location of a building plan in a Wi-Fi visualization system, store the telemetry data with a timestamp, determine a change in a Wi-Fi coverage for the Wi-Fi access point based on the telemetry data, and present a visualization illustrating the change in the Wi-Fi coverage for the Wi-Fi access point. The present technology can further present an animation of the change in the Wi-Fi coverage for the Wi-Fi access point based on the stored telemetry data.

Machine learning method and systems for estimating a location of a target wireless device in an environment are disclosed. A machine learning method comprises: receiving a plurality of training received signal indictor data sets for discrete locations in the environment, each training received signal data set comprising received signal indicator values and corresponding wireless transmitter identifiers for wireless signals received by a test wireless device at a respective discrete location; generating feature vectors from the received signal indicator data sets; training a machine learning model using the feature vectors to obtain a trained machine learning model; receiving a target received signal data set from the target wireless device, the target received signal data set comprising signal indicator values and corresponding wireless transmitter identifiers for wireless signals received by the target wireless device; generating a target feature vector from the target received signal data set; and estimating a location of the target wireless device as a discrete location output by the trained machine learning model in response to the target feature vector.

Methods, systems, and devices for wireless communications are described. Some wireless devices may support a prediction capability for prediction-based control information. A first device may receive, from a second device, first control signaling that activates the predication capability of the first device to generate a set of one or more control parameters for communications. The second device may transmit second control signaling to the first device to indicate initial values of the control parameters and a channel condition model for the first device. The first device and the second device may generate a set of multiple values associated with the control parameters over a time period based on the initial values of the control parameters and the channel condition model. The first device and the second device may communicate during at least the time period according to the set of generated values associated with the control parameters.

A method for dynamic recovery from an unplanned network outage includes aggregating cell site data of multiple cell sites prior to the unplanned outage. The cell site data include subscriber activity data in site coverage areas of the multiple cell sites and data independent of the subscriber activity data. The method includes obtaining resource information of multiple resources available for recovering from the unplanned network outage and generating a predictive model for recovery from the unplanned network outage based on the cell site data and the resource information. The predictive model includes a priority ranking for recovering the multiple cell sites. The method further includes adjusting the predictive model based on live data indicative of a status of the multiple cell sites during the unplanned network outage. The method includes determining a priority ranking for the multiple cell sites and allocating the available resources for the multiple cell sites accordingly.

Deviations of signal strengths in a first frequency band from signal strengths in at least one second frequency band are predicted based on a trained machine-learning model (350′). At least one source signal strength map is obtained. The at least one source signal strength map describes signal strengths in the at least one second frequency band for a coverage area of the wireless communication network. Based on the at least one source signal strength map and the predicted deviations of signal strengths, at least one target signal strength map describing signal propagation in the first frequency band for the coverage area is determined.

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive, from a base station, configuration information specifying similarity data to be provided in a Layer 1 (L1) report. The UE may transmit, to the base station and based at least in part on receiving the configuration information, the L1 report. The L1 report indicates a measure of similarity between a current condition of the UE and a past condition of the UE associated with a past event associated with the UE. Numerous other aspects are described.

A processor-implemented method is presented. The method includes receiving an input sequence comprising a group of channel dynamics observations for a wireless communication channel. Each channel dynamics observation may correspond to a timing of a group of timings. The method also includes determining, via a recurrent neural network (RNN), a residual at each of the group of timings based on the group of channel dynamics observations. The method further includes updating Kalman filter (KF) parameters based on the residual and estimating, via the KF, a channel state based on the updated KF parameters.

Facilitating a transmission power dependent resource reservation protocol in advanced networks (e.g., 5G, 6G, and beyond) is provided herein. Operations of a method can comprise defining, by a system comprising a memory and a processor, a resource reservation procedure that associates respective amounts of reserved resources available for the mobile device based on a transmission power level of the mobile device. The method also can comprise selecting, by the system, an amount of reserved resources from the respective amounts of reserved resources available based on the transmission power level of the mobile device.

A system for an automated ML-based design of a wireless network. The system includes a processor of a design server node connected to at least one local, edge, or cloud server node over a network and a memory on which are stored machine-readable instructions that when executed by the processor, cause the processor to: acquire aerial 3-D mapping data of a target area from an unmanned aircraft system (UAS) flying over the target area; acquire surface 3-D mapping data from a ground robotic crawler; parse the 3-D mapping data to derive an at least one feature vector; provide the at least one feature vector to a machine learning (ML) module residing on the at least one local, edge, or cloud server node for generating a predictive model of a wireless network for some or all of the target area; receive outputs of the predictive model; and generate a wireless network design for the some or all of the target area based on the predictive outputs.

Certain aspects of the present disclosure provide techniques for providing a probabilistic feedback parameter. One example method for wireless communication may be performed by a first wireless node. The method generally includes generating a feedback message indicating a probabilistic estimate comprising a plurality of feedback parameter values and a plurality of value probabilities, wherein each value probability is associated with one feedback parameter value of the plurality of feedback parameter values, and transmitting the feedback message to a second wireless node.