A Hybrid ANN-P&O MPPT Strategy for Enhancing Solar Photovoltaic Output Under Partial Shading Conditions

Enhancing the efficiency of solar photovoltaic (PV) systems under fluctuating environmental conditions relies on the precise identification and tracking of the highest power point associated with existing solar irradiation levels. This study introduces a hybrid Maximum Power Point Tracking (MPPT) method that combines an Artificial Neural Network (ANN) with the Perturb and Observe (P&O) technique to optimize PV system output under partial shading conditions (PSC). The proposed hybrid model is evaluated against traditional P&O, Incremental Conductance (InC), and standalone ANN-based MPPT approaches using MATLAB/Simulink simulations under both standard test conditions (STC) and two distinct PSC scenarios. The hybrid ANN-P&O method achieves tracking efficiencies of 96.98% and 97% under PSC1 and PSC2 respectively, surpassing P&O by up to 6.8% and InC by 5.8% in power extraction. It also demonstrates faster convergence and reduced steady-state oscillations when compared to the other methods. Overall, the findings highlight the hybrid approach as a highly competent and enduring solution for maximizing PV output under dynamic shading conditions.