Reinforcement-Learning Based Handover Optimization for Cellular UAVs Connectivity

Abstract

The demand for services provided by Unmanned Aerial Vehicles (UAVs) is increasing pervasively across several sectors including potential public safety, economic, and delivery services. As the number of applications using UAVs grows rapidly, more and more powerful, quality of service, and power efficient computing units are necessary. Recently, cellular technology draws more attention to connectivity that can ensure reliable and flexible communications services for UAVs. In cellular technology, flying with a high speed and altitude is subject to several key challenges, such as frequent handovers (HOs), high interference levels, connectivity coverage holes, etc. Additional HOs may lead to “ping-pong” between the UAVs and the serving cells resulting in a decrease of the quality of service and energy consumption. In order to optimize the number of HOs, we develop in this paper a Q-learning-based algorithm. While existing works focus on adjusting the number of HOs in a static network topology, we take into account the impact of cells deployment for three different simulation scenarios (Rural, Semi-rural and Urban areas). We also consider the impact of the decision distance, where the drone has the choice to make a switching decision on the number of HOs. Our results show that a Q-learningbased algorithm allows to significantly reduce the average number of HOs compared to a baseline case where the drone always selects the cell with the highest received signal. Moreover, we also propose which hyper-parameters have the largest impact on the number of HOs in the three tested environments, i.e. Rural, Semi-rural, or Urban.