Effective Cluster Head based Routing using Neuro-Fuzzy Algorithm in Vehicular Ad Hoc Networks (VANETs)

Our project focuses on enhancing communication and cluster management within Vehicular Ad-Hoc Networks (VANETs), which are integral to modern transportation systems. To achieve this, we propose a comprehensive framework that integrates zone-based clustering, cluster head (CH) selection, Neuro-Fuzzy prediction for CH validation, and routing using Dijkstra’s algorithm. The simulation of our project is performed in MATLAB to test for the proper working of the model. Considering the impact of varying parameters such as the number of vehicles, velocity, and connectivity of the vehicles on network performance we developed an effective cluster head selection process for cluster-based routing in Vehicular Ad Hoc Networks (VANETs) using Neuro-Fuzzy technique. Performance metrics such as Packet Delivery Ratio (PDR), End-to End Delay, and CH Formation Delay are employed to assess the effectiveness of our framework and increase the efficiency of CH selection and validation processes. Through careful analysis of these efficiency measures, our project aims to deepen our understanding of communication optimization and CH management in VANETs. We believe that the insights gained will significantly contribute to the development of more efficient and reliable vehicular networks. Ultimately, our initiative tries to advance Intelligent Transportation Systems (ITS), enhanced road safety and traffic efficiency. In summary, our project strives to provide valuable insights and practical solutions for optimizing communication efficiency and cluster management within VANETs. By understanding and using these insights, we aim to drive advancements in Intelligent Transportation Systems (ITS), ultimately leading to improved road safety and traffic efficiency for future generations.