An Optimized Intelligent Transport System to Control Traffic in Internet of Vehicles

K. Renuka and Dr.R. Muralidharan

Lot of research scholars are pulled towards the Internet of Vehicles (IoV), next to arrival of intelligent or independent cars. IoV being a fragment of the Internet of Things (IoT) too, is primarily meant for communications of vehicle. Incessant alterations of topology in vehicle communications are a critical issue in IoV which can have an impact on the shortest routing path and modification in network scalability. Ergo, a progressivel y more challenging issue is the configuration of efficient and trustworthy intercommunication routes among vehicle nodes grounded on traffic intensity conditions. Meant for these difficulties, the traffic intensity in every path of the map is computed utilizing the former growth of the fuzzy approach. Ultimate route path is selected on the basis of traffic intensity which employed ant colony optimization algorithm. But then the count of paths and the number of vehicles thought out for the measurement of traffic intensity needs enhancement. Thus an innovative algorithm that is swarm-based is proposed in this research work that alleviates topology by employing a Fuzzy Neural Network (FNN) algorithm based on Enhanced Ant Colony Optimization (EACO) in two different phases for packet route optimization. For the purpose of efficient structure for traffic control, both of these algorithms collectively indicated as EACOFNN IoV by the support of IoV technology and the transmission range accommodation concerning the local traffic intensity. The outcomes of NS-2 simulations reveal that the latest protocol is better than Ad hoc Ondemand Distance Vector (AODV) routing and ACO systems on the basis of assessing routing functioning based on throughput, average waiting time, average travel time, packet delivery, average end-to-end delay and drop ratio,.

Volume 12 | 03-Special Issue

Pages: 420-431

DOI: 10.5373/JARDCS/V12SP3/20201277