Using Neural Networks for Channel Quality Prediction in Wireless 5G Networks

The article proposes a method for assigning a modulation coding scheme (MCS) by a base station (BS) scheduler on an unmanned aerial vehicle (UAV), based on predicting the value of the signal-to-interference-to-noise ratio (SINR) on the mobile user equipment (UE) at the next time slot from a sequence of known values of this ratio in the past. Prediction is performed using machine learning. For this, a neural network was built and applied to solve the problem of multi-parameter optimization using the stochastic gradient method. The trained neural network for the predicted SINR value allows the scheduler to select the modulation-code scheme correctly, thereby ensuring the level of data transmission quality in the radio channel necessary to provide the service. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.