An opposition-based learning election algorithm for UAV placement in 3D space

Unmanned aerial vehicles (UAVs) are important tools to realize smart city applications due to their maneuver-ability and versatility. Recently, some machine learning methods were proposed for UAV placement and achieved encouraging results. However, the reported performances in literature are not ideal and there is room for more improvement in the field. As an element of research, this paper presents a novel opposition-based learning election algorithm (OBLEA) algorithm for UAV placement. With a test on ten benchmark placement scenarios, the proposed OBLEA algorithm is proven to generate better results than counterpart algorithms and is a competitive method for UAV placement.