Scheduling charging of hybrid-electric vehicles according to supply and demand based on particle swarm optimization, imperialist competitive and training-learning algorithms

If this load is imposed during peak load, undesirable effects occur in the distribution network including increase in losses and voltage drop. In this study, hybrid-electric vehicles connected to network and corresponding supply and demand programs are investigated; then, PSO, ICA and training-learning algorithms are used to schedule and optimize charging. Results show that in order to prevent generation of new load peak and decrease distance between peak and valley on load curve, training-learning algorithm outperforms other two algorithms. But in terms of convergence and decrease in performance cost, ICA outperforms the other two algorithms and convergence is obtained in smaller number of iterations.