Optimization and dimensioning of stand-alone systems: enhancing MPPT efficiency through DLGA integration

Abstract

This paper explores optimizing and sizing stand-alone solar power systems using an intelligent maximum power point tracking (MPPT) method, enhanced by artificial neural networks (ANN). The study focuses on both system sizing and energy optimization, integrating genetic algorithms (GA) with deep learning (DL) to optimize the architecture of the ANN for improved performance in predicting solar energy output. The hybrid method, deep learning genetic algorithms (DLGA), efficiently reduces computational complexity and enhances flexibility through parameter tuning, significantly improving the performance of multi-layer perceptron networks. Additionally, a precise sizing methodology based on solar irradiance data was implemented to ensure the system is neither oversized nor undersized. The system's performance was tested and validated using MATLAB/Simulink simulations, which demonstrated superior predictive accuracy, faster convergence, and optimized energy capture. This combined approach of intelligent MPPT and accurate sizing presents a highly effective solution for improving the efficiency and reliability of stand-alone solar energy systems under varying environmental conditions.