Swarm Intelligence Driven Route Optimization for Energy-Efficient Electric Vehicle Networks

In this work, we present a novel approach on the optimization of energy efficiency in Electric Vehicle (EV) networks using swarm intelligence algorithms namely Ant Colony Optimization (ACO) and Particle Swarm Optimization (PSO). With increasing congestion of urban traffic, EVs have to overcome the difficulties of reducing its energy consume in and around the crowded roads with less space to travel. In particular, the solution proposed poses the EVs as decentralized agents, capable of dynamically changing their route upon the local information, like the battery level, traffic pattern, etc., at real time. Building upon ant colony optimization for computing the shortest path and the way birds fly together, swarm intelligence constructs collaboration among EVs for the route optimization issue. By adapting routing decisions to the time and location of an individual vehicles, collective energy expenditure can be minimized, followed by traffic congestion and better overall efficiency of the network. It is dependent on Vehicle to Vehicle (V2V) communication support provided by IoT technology to communicate with each other and generate better decision making. Moreover, the development of the swarm algorithm, its integration into a simulation of urban environments, and the evaluation metrics in assessing the energy efficiency and scalability of the system are also covered in the paper. Simulation results show that the swarm intelligence model can provide remarkable energy saving and route optimizing performance than the traditional routing. With this work we provide a promising framework for the development of sustainable, energyefficient transportation systems, towards a sustainable city and towards a reduction of carbon emissions. Going forward, the model will be refined for real world applications and scale this model to larger networks.

Перевод пока недоступен