Maximizing VANET performance in cluster head selection using Intelligent Fuzzy Bald Eagle optimization

Vehicular Ad-hoc Network (VANET) is a type of wireless network that allows communication among vehicles and roadside units to develop advanced intelligent transportation systems. The success of VANETs depends on the stability of wireless communication, among vehicles, which is challenging to achieve due to high vehicle speed, rapidly changing topology, and unstable communication links. Moreover, the instability of the network caused by the mobile nature of vehicles in VANET reduces the performance of the network. Clustering in VANETs is a crucial technique that organizes the network and forms the basis of the routing protocol. Clustering algorithms are designed for VANETs to work efficiently and require several phases that must be integrated into the process before a clustering decision can be made. Therefore, this paper presents a novel Intelligent Fuzzy Bald Eagle (IFBE) optimization to enhance the performance of VANETs by optimizing the cluster head selection (CHS) process. The experimental results prove that the IFBE approach outperforms other existing mechanisms in terms of energy consumption, end-to-end delay, and packet delivery ratio. The proposed mechanism utilizes an intelligent fuzzy system to optimize the CHS process. The fuzzy system uses a set of rules and membership functions to evaluate the candidate nodes' suitability for being cluster heads. The Bald Eagle Search (BES) optimization meta-heuristic algorithm is used to find the optimal values for the fuzzy system's membership functions. The proposed mechanism was evaluated using the MATLAB simulator. Finally, the experimental result proved that the IFBE approach achieved minimum delay and energy consumption of 13.58 ms, and 15.5 J, and higher clustering efficiency and packet delivery rate of 94.15% and 97.65% respectively, which show that it performs better than other existing approaches.