Cost-efficient energy management between electric vehicle charging stations and distribution systems using intelligent scheduling

The increasing integration of electric vehicles (EVs) into power distribution networks presents substantial challenges in energy management, struggling with accurate demand forecasting and failing to deliver efficient scheduling, leading to elevated operational costs and power losses. To address these issues, this research aims to develop an intelligent and cost-effective energy management framework that enables coordinated EV charging within distribution systems under dynamic demand conditions. The proposed framework combines a Supervised Attention Multi-Scale Temporal Convolutional Network (SAMSTCN) for accurate EV demand forecasting with an Opposition-based Fossa Optimization Algorithm (OFOA) for optimal charging/discharging scheduling, hence it is known as the SAMSTCN-OFOA approach. Simulation using MATLAB demonstrates that the proposed framework significantly enhances operational efficiency, cost-effectiveness, and power loss reduction, outperforming existing methods. Specifically, it achieves a cost reduction of 12.68 %, minimizes power loss to 11.51 kW, and also demonstrates a faster convergence time of 18.27 s compared to existing techniques. These findings underscore the framework's potential as a scalable and intelligent solution for cost-efficient energy management in smart grid environments.