A Multi-Objective Optimization Approach for Electric Vehicle Charging Scheduling

The fast growth of electric vehicles (EVs) has led to considerable challenges in grid stability and user charging costs due to uncoordinated charging. To tackle these challenges, this paper presents an EV charging scheduling approach grounded in a multi-objective optimization framework, which integrates road network structures to enhance alignment with real-world application scenarios. First, Monte Carlo simulation is employed to model the distribution of energy demands at various nodes in the road network, revealing the potential impact of uncoordinated charging on grid load. Then, an enhanced Multi-Objective Particle Swarm Optimization technique is proposed, featuring dynamic adjustment of inertia weights to enhance both global search capability and local convergence performance. Finally, the proposed approach is used to solve the scheduling problem, aiming to minimize the grid peak-to-average ratio and electricity costs. Numerical simulations and case studies demonstrate that this method effectively reduces charging costs, balances grid load, improves charging efficiency, and increases user satisfaction.