EGBCR-FANET: Enhanced genghis Khan shark optimizer based Bayesian-driven clustered routing model for FANETs

Unmanned Aerial Vehicle (UAV) technology has advanced rapidly, with broad use in both the military and commercial sectors. As a result, multi-UAV networks, also known as Flying Ad Hoc Networks (FANETs), have become a vital part of current communication systems. However, FANETs confront numerous challenges such as limited energy resources, high mobility, frequent topological changes, and inconsistent communication links. These difficulties influence network stability, limit data transmission efficiency, and shorten network longevity. Addressing these issues requires an adaptable routing strategy in FANETs. Cluster-based routing in UAVs is a great way to save energy, increase scalability, and improve network performance. This paper introduces a new clustering and routing framework for FANETs based on the Enhanced Genghis Khan Shark Optimizer (EGKSO). Unlike previous clustering approaches, the suggested solution dynamically selects the appropriate number of clusters while taking node coverage and network bandwidth into account. EGKSO is used to choose energy-efficient and stable cluster heads, resulting in balanced load distribution and a longer network lifetime. A dynamic cluster maintenance technique is proposed to ensure network stability and maintain efficient communication performance. In addition, a Bayesian-inspired next-hop selection model for adaptive routing is presented, allowing probabilistic decision-making to respond to network changes efficiently. This combination of swarm intelligence and probabilistic modeling improves communication reliability, reduces latency, and maximizes energy efficiency. The simulation results show that the suggested method outperforms existing clustering and routing protocols in terms of delivery ratio, energy consumption, latency, and clustering stability. The results demonstrate the efficacy of combining metaheuristic-based clustering with Bayesian-inspired routing, providing a resilient and scalable solution for FANETs in dynamic and resource-constrained contexts.