Dynamic Route Optimization Using Nature-Inspired Algorithms in IoV

Internet of Vehicles (IoV) has gained immense popularity with increasing research on fully integrated smart cities. The live data collectively gathered by various types of sensors or cameras installed on running vehicles, traffic lights, etc., forms an integral part of smart city ecosystem. Various emergency situations require vehicles to divert from their respective default routes to some more feasible and optimal routes. In this work, we implement two well-known algorithms Ant Colony Optimization and Particle Swarm Optimization to allow a coordinated dynamic route customization among the vehicles for an overall optimal traffic management. A centralized decision-making module is implemented by applying ACO and PSO on the data that continuously gathered from the vehicles in the live environment. The experimental setup consists of two well-known simulator software tools SUMO and NS2 that are accompanied by TraNS to provide mutual interactions between them. The results confirm an increase in the overall performance of the system with application of the optimization approaches.