Improved Beluga Whale Optimizer-Based Cluster Head Selection in FANET

Important issues have arisen for the reliability of communications in FANETs as of the high-speed mobility of unmanned aerial vehicles (UAVs). One of the more recent Meta-heuristic (MH) methods, makes use of the Beluga Whale optimizer (BWO) to optimize network parameters in FANET. However, BWO may get stuck in local optima and converge too quickly because of its lack of diversity. This paper provides two steps to improve the original BWO procedure. Opposition-based learning (OBL), also known as OBWO's first stage, helps to speed up the search procedure and improve the learning procedure so that a higher quality generation of candidate keys for the basic BWO can be selected. In addition, a powerful cluster maintenance algorithm for continually updating UAV clusters is proposed. The simulation findings show that the projected OBWO scheme outperforms state-of-the-art clustering techniques by a wide margin in terms of packet delivery ratio, network lifetime to cluster head altering ratio, and energy usage.