Intelligent UAV Base Station Selection in Urban Environments: A Supervised Learning Approach
share
When Unmanned Aerial Vehicles (UAVs) connect into the cellular network, their wireless channel is negatively impacted by strong Line-of-Sight (LoS) interference from terrestrial Base Stations (BSs), as well as from antenna misalignment due to downtilted BS antennas. Moreover, due to their aerial positions, these UAVs are exposed to a large number of BSs with which they can associate for wireless service. Therefore, to maximise the performance of the UAV-BS wireless link, the UAVs need to be able to choose which BSs to connect to, based on the observed environmental conditions. In this regard, this paper proposes a supervised learning-based association scheme, using which a UAV can intelligently associate to the most appropriate BS. We train a Neural Network (NN) to identify the most suitable BS from several candidate BSs, based on the received signal powers from the BSs, known distances to the BSs, as well as the known locations of potential interferers. We then compare the performance of the NN-based association scheme against strongest-signal and closest-neighbour association schemes.
READ FULL TEXT