Advanced Optimization of Global Maximum Power Point Tracking under Partial Shading Conditions in Photovoltaic Arrays Using Deep Learning and Metaheuristic Algorithms for Enhanced Energy Efficiency

Partial shading conditions (PSC) significantly reduce the output efficiency of photovoltaic (PV) systems by introducing multiple local maxima in the power-voltage (P-V) curve, which can mislead conventional maximum power point tracking (MPPT) algorithms into converging on local rather than global peaks. As PV systems scale beyond individual modules and become more complex, the importance of robust Global Maximum Power Point Tracking (GMPPT) methods increases. This paper proposes a hybrid intelligent control approach combining Gravitational Search Algorithm (GSA) with a fuzzy neural control strategy to address the challenge of GMPPT under PSC. The proposed method dynamically and rapidly tracks the global maximum power point (GMPP) in real-time despite abrupt changes in irradiance and temperature. Simulation results confirm that the proposed approach outperforms conventional techniques in both accuracy and convergence speed, enhancing the overall energy harvesting efficiency of grid-connected PV arrays operating under partial shading.

کلیدواژه ها:

Photovoltaic Systems ، Maximum Power Point Tracking (MPPT) ، Model-Based Methods ، Gravitational Search Algorithm (GSA)