Optimized EV charging for Systems with Intelligent Transportation using Genetic Algorithms

Electric vehicle (EV) charging optimization in Intelligent Transportation Systems (ITS) is crucial for enhancing energy efficiency and reducing charging delays. However, existing methods struggle with load imbalance, inefficient energy distribution, and high computational complexity. To address these challenges, this study employs a Multi-Objective Genetic Algorithm (NSGA-II) for load balancing, optimizing charging station allocation and energy distribution. The proposed method efficiently manages charging demand, minimizes waiting time, and reduces grid stress. By integrating NSGA-II, the framework ensures fair energy distribution while considering multiple objectives such as cost, energy efficiency, and user convenience. Simulation results demonstrate that the proposed approach significantly improves charging efficiency, reduces peak loads, and enhances the overall performance of EV charging networks. The findings highlight the effectiveness of NSGA-II in balancing loads dynamically, leading to optimized charging schedules and improved grid stability in ITS.