Machine Learning Approaches for Radio Propagation Modeling in Urban Vehicular Channels

The use of vehicular communications is anticipated to improve safety in road traffic. The traditional radio channel models that describe the effects of radio wave propagation in dynamic vehicular environments have their own limitations. In this paper, machine learning (ML) techniques are applied for radio channel modeling in urban vehicular environments. A large data set of path loss (PL) and root-mean-square Delay spread (RMS-DS) is computed using ray-tracing for a Line-of-Sight (LOS) straight road and a Non-Line-of-Sight (NLOS) intersection road scenario. Fourteen input features are used to train three ML models for vehicular channel prediction. The models considered in this work include Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), and Random Forest (RF). The results show that RF gives better performance than MLP and CNN models in the prediction of PL and RMS-DS in urban vehicular channels.