An Algorithmic Approach to Detect Anomalies in VANET Environments

Vehicular Ad Hoc Networks (VANETs) evolved from Mobile Ad Hoc Networks (MANETs) and have significantly enhanced the performance of the transportation sector. Their ability to ensure traffic safety and prevent accidents has led to widespread adoption. However, VANETs face challenges such as self-organization, rapid topology changes, and frequent link disruptions, necessitating effective strategies to address these issues. To tackle these concerns, a hybrid model called HFWOA-VANET, integrating the Whale Optimization Algorithm and Firefly Optimization Algorithm, has been developed. This model leverages the strengths of both meta-heuristic methods to optimize VANET performance. It primarily focuses on analyzing Quality of Service (QoS) criteria for each vehicle, thereby improving service delivery within the VANET framework. The proposed model's efficacy is thoroughly validated by conducting evaluations on the NS2 platform and meticulously scrutinizing the results. Detailed comparative analysis against existing technologies confirms the superiority of the proposed model in performance metrics.