Efficient energy management strategy for photovoltaic-assisted electric vehicle charging infrastructure

The rapid growth of electric vehicles (EVs) and renewable energy combinations necessitates smart, storage-efficient charging infrastructure. This manuscript proposes a hybrid energy management framework, including Balancing Composite Motion Optimization and Human Urbanization Algorithm. The rationale in the proposed approach relies on the hypothesis that integrating scheduling optimization with predictive modeling can improve system performance and reduce operational costs. The Human Urbanization Algorithm is employed for optimal EV charging scheduling, while Balancing Composite Motion Optimization is used to predict EV arrival patterns for efficient resource allocation. The method is implemented in MATLAB and evaluated against Slime Mould Optimization, Side-Blotched Lizard Algorithm, and Chaos-Game Optimization. The proposed method achieves a maximum efficiency of 96% while reducing operational costs to 218 USD for photovoltaic systems and 254 USD for electric vehicle charging. These results demonstrate that the framework is efficient and scalable for optimizing energy use in systems, making it suitable for practical commercial deployment.