Ensemble Learning for 5G Flying Base Station Path Loss Modelling

Abstract

The usage of unmanned aerial vehicles (UAVs) as flying base stations (FBSs) for expanding coverage and assisting the terrestrial cellular networks constitutes a promising technology for 5G and beyond. The wide range of a flying base station's movement may stretch the boundaries of path loss at the receiver's site and induce the occurrence of extreme values. Thus, using machine learning techniques may help in accurate path loss modeling for this case. In this paper, we use a combination of the techniques of ensemble learning and oversampling to provide a satisfactory path loss model for FBSs. The datasets used have been obtained through Ray Tracing simulations.