Optimization of Cell Individual Offset for Handover of Flying Base Station

Abstract

Flying base stations (FlyBSs) mounted on unmanned aerial vehicles (UAVs) are widely used in mobile networks to improve a coverage and/or quality of service for users. To ensure a seamless mobility of the FlyBSs among the static base stations (SBSs), an efficient handover mechanism is required. In this paper, we develop a novel handover mechanism determining the serving SBS for the FlyBS in order to increase the sum capacity of the users served by the FlyBS. We propose to dynamically optimize the handover by adjusting the cell individual offset of the SBS via Q-learning. The results show that the Q-learning converges promptly and the proposed approach increases the users capacity (by up to 18%) and their satisfaction with required minimum capacity (by up to 20%) comparing to state-of-the-art algorithms.