A Social Spider Optimisation Algorithm for 3D Unmanned Aerial Base Stations Placement

In recent years, the use of drones as aerial base stations (ABS) has attracted the attention of both scientific and industrial communities as a promising solution to enhance the network coverage. However, their deployment brings out many challenges and restrictions. In this work, we model a realistic, constrained scenario where unmanned aerial vehicles (UAVs) are used as ABSs along with traditional ground base stations (GBSs) to extend their coverage. We propose a scalable and efficient social spider optimization (SSO) algorithm that determines the placement of UAVs and their association with both user equipments (UEs) and GBSs. Extensive computational experiments were conducted to investigate the effect of the different SSO metaheuristic parameters and tune them to the best values. The efficiency of the proposed solution is then evaluated by comparing its results to two other schemes. Simulation results show that the proposed approach overcomes the two other strategies and presents an average gain of 18% and 31% compared to the them.