Modelling Ray Tracing Propagation Data Using Different Machine Learning Algorithms

In this paper, we apply different machine learning methods for the prediction of path loss in urban environment for cellular communications with unmanned aerial vehicles (UAVs). We generate the training set using a ray tracing technique assuming a flying base station at different heights within the city of Tripolis, Greece. We produce prediction models for the path loss using three different learners the k-Nearest Neighbors (kNN), the Support Vector Regression (SVR)and the Random Forest (RF). The obtained numerical results are compared with the original data from the test dataset using representative performance indicators and overall they exhibit good precision.