Vehicular Ad Hoc Networks (VANETs) enables real-time communication between vehicles. VANETs address issues like Urban traffic congestion and frequent accidents that pose challenges to commuters leading to delays, inefficiencies, and safety hazards. However, the effectiveness of VANET could be hampered via high node mobility and sparse vehicle distribution, necessitating novel and efficient optimization approaches. This study introduces the Crayfish Optimization Algorithm (COA) for Vehicular Ad Hoc Networks (COANET), designed to intelligently optimize clusters within the VANET framework. To evaluate the efficacy of COA, comprehensive experiments were conducted, benchmarking the results against two state-of-the-art algorithms: Intelligent cluster optimization algorithm. based on whale optimization algorithm for VANETs (WOACNET) and An Intelligent Harris Hawks Optimization Based Cluster Optimization Scheme for VANETs (HHO). The comparison is focused on key performance metrics, including cluster stability, communication efficiency, and resource utilization. The findings demonstrate that the developed method outperforms both well-established methods WOACNET and HHO by 10%. The proposed method optimized clusters exhibit increased stability, reduced communication latency, and improved overall system performance. These results highlight the potential of COANET as a promising optimization tool for improving the effectiveness and functionality of VANETs as part of the larger framework of Intelligent Transportation System.

Index Terms- Crayfish Optimization Algorithm, Vehicular Ad Hoc Networks, Crayfish Optimization Algorithm for VANETs, Whale Optimization Algorithm for Clustering in VANETs, Harris Hawk Optimization.