Abstract: A method, performed by a first network node. The method is for handling Doppler shift pre-compensation. The first network node sends a first indication towards a first wireless device. The first indication indicates a start of a training phase. The first network node obtains, based on the sent first indication, a set of information from the first wireless device. The set of information indicates: i) a Doppler shift experienced by the first wireless device while moving along a pre-defined trajectory to which a static set of radio network nodes provide coverage, and ii) a set of features characterizing how the first wireless device experienced the Doppler shift. The first network node also initiates determining, using machine-learning, and based on the received set of information, a predictive model of Doppler shift pre-compensation. The training phase is of the predictive model.

Abstract: According to an aspect there is provided a method in a base station that is to operate in a full duplex communication mode. The method comprises sending respective device-to-device, D2D, announcement configurations to one or more first wireless devices that have data to transmit to the base station. A D2D announcement configuration configures a first wireless device to perform a respective D2D announcement. The method also comprises sending a D2D announcement monitoring configuration to one or more second wireless devices that the base station has data to transmit to. A D2D announcement monitoring configuration configures a second wireless device to monitor for a D2D announcement transmitted by one or more first wireless devices.