Methods, systems, and apparatus, including computer programs encoded on computer-storage media, for processing communications signals using a machine-learning network are disclosed. In some implementations, pilot and data information are generated for a data signal. The data signal is generated using a modulator for orthogonal frequency-division multiplexing (OFDM) systems. The data signal is transmitted through a communications channel to obtain modified pilot and data information. The modified pilot and data information are processed using a machine-learning network. A prediction corresponding to the data signal transmitted through the communications channel is obtained from the machine-learning network. The prediction is compared to a set of ground truths and updates, based on a corresponding error term, are applied to the machine-learning network.

A system includes a method for detecting a signal interference in a communication signal of a wireless communication system. An identified source of the signal interference is determined according to an interference profile of a plurality of interference profiles associated with an interference profile library having information that approximates characteristics of the signal interference. The signal interference of the communication signal is mitigated according to an interference parameter associated with the identified source by filtering the communication signal according to the interference parameter.

A system includes a method for detecting a signal interference in a communication signal of a wireless communication system. An identified source of the signal interference is determined according to an interference profile of a plurality of interference profiles associated with an interference profile library having information that approximates characteristics of the signal interference. The signal interference of the communication signal is mitigated according to an interference parameter associated with the identified source by filtering the communication signal according to the interference parameter.

A base station (UE) is configured to perform a computer-implemented method for antenna fault detection and correction. The computer-implemented method includes acquiring one or more sounding reference signals (SRSs) received from at least one gNB antenna; detecting an antenna failure based on the one or more SRSs; estimating a noise power based on the antenna failure and a history of received SRSs; detecting a missing SRS based on the noise power and the history of received SRSs; and handling the missing SRS. Handling the missing SRS is based on performing at least one of: replacing an SRS measurement with a predicted SRS value for the missing SRS when the predicted SRS is available; or avoiding use of the missing SRS in a sequential SRS prediction when the predicted SRS is unavailable.

Methods, apparatus and systems for wireless communication are described. One example method includes estimating, based on channel quality information for a first communication channel during a first time interval, a predicted quality of a second communication channel during a second time interval that is a latency interval after the first time interval and using the predicted quality for processing transmissions on the second communication channel during the second time interval.

Methods, apparatus and systems for wireless communication are described. One example method includes estimating, based on channel quality information for a first communication channel during a first time interval, a predicted quality of a second communication channel during a second time interval that is a latency interval after the first time interval and using the predicted quality for processing transmissions on the second communication channel during the second time interval.

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive a configuration associated with artificial noise assisted physical layer security for at least one of an uplink channel or a sidelink channel. The UE may receive an indication of a power allocation parameter associated with a power allocation between a data signal and an artificial noise signal. The UE may transmit, via the uplink channel or the sidelink channel, at least one of the data signal or the artificial noise signal with the power allocation between the data signal and the artificial noise signal based at least in part on the power allocation parameter. Numerous other aspects are described.

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive a configuration associated with artificial noise assisted physical layer security for at least one of an uplink channel or a sidelink channel. The UE may receive an indication of a power allocation parameter associated with a power allocation between a data signal and an artificial noise signal. The UE may transmit, via the uplink channel or the sidelink channel, at least one of the data signal or the artificial noise signal with the power allocation between the data signal and the artificial noise signal based at least in part on the power allocation parameter. Numerous other aspects are described.

A client device is configured to communicate with an access point over a wireless network, exchanging data with the access point over a selected communication channel. The client device stores an identifier of the selected communication channel. After the wireless connection to the access point has ended, the client device initiates a process to reconnect to the access point over the selected communication channel using the stored identifier.

In one embodiment, a supervisory service for a wireless network obtains frequency-time Doppler profile information for an endpoint node attached to a first access point in the wireless network. The supervisory service uses the frequency-time Doppler profile information for the endpoint node as input to a machine learning model. The machine learning model is trained to output an action for the endpoint node with respect to the wireless network. The supervisory service causes the action for the endpoint node with respect to the wireless network to be performed.