Abstract: A user equipment (UE) sends a simple message on a control channel to the base station (BS) that is using Machine Learning (ML) engine for random access (RA) procedures, the message being an indicator of a poor preamble detection performance of the BS upon UE observing repeated failure of random access attempts on the physical random access channel (PRACH). In response, the BS collects controlled preamble detection training data by selecting a plurality of trainer UEs and sending each UE a training random access configuration to use during a training cycle.

Abstract: A receiver of a Base Station (BS) uses a Machine Learning (ML) engine for random access preamble detection. The ML engine is trained from time to time wherein one of the triggers for retraining is a plurality of User Equipment (UE) sending a message to the base station, according to an aspect of this invention, that is indicative of poor preamble detection performance, upon which the BS collects controlled preamble detection dataset by selecting and engaging a group of so-called trainer-UEs. The retraining is performed by using both aforementioned controlled as well as normal preamble detection operations.

Abstract: The non-linear behavior of power amplifier is linearized using a pre-distorter that is adaptive to changes in the behavior of the power amplifier and uses an artificial neural network. According to embodiments presented here, the pre-distorter's artificial neural network is model-trained from time to time to learn the inverse of the transfer function of the power amplifier by using a second pre-distorter modeling system. The second modeling system determines the parameters of the inverse of the transfer function of the power amplifier using a least square method by using the (un-distorted) output signal samples of the power amplifier. Using the output of the second system as output to train the neural network enables the neural network to more successfully linearize the power amplifier's behavior. Furthermore, the trained artificial neural network as the pre-distorter can be implemented in hardware and presents a small form factor.