AN ENHANCED HYBRID P&O–ANFIS-BASED MPPT CONTROL STRATEGY FOR PV SYSTEMS UNDER DYNAMIC AND PARTIAL SHADING CONDITIONS

Abstract

Photovoltaic (PV) systems are widely used renewable energy sources; however, their efficiency is significantly affected by environmental factors such as temperature variations and partial shading conditions (PSC). Under PSC, conventional Maximum Power Point Tracking (MPPT) techniques such as Perturb and Observe (P&O) often fail to locate the global maximum power point (GMPP) and may get trapped at local maxima, resulting in reduced energy extraction. To overcome these challenges, this paper proposes a Hybrid P&O–Adaptive Neuro-Fuzzy Inference System (ANFIS)-based MPPT algorithm for PV systems operating under nonuniform irradiance conditions. In the proposed approach, the P&O algorithm provides a fast initial search of the operating region, while the ANFIS controller refines and adapts the tracking process using intelligent learning capabilities to achieve high accuracy and robustness. The hybrid method effectively combines the simplicity of P&O with the adaptive intelligence of ANFIS to enhance tracking speed, minimize steady-state oscillations, and prevent convergence to local peaks. MATLAB/Simulink simulations are performed on a PV array under dynamic shading scenarios, and the results demonstrate that the proposed hybrid MPPT achieves faster convergence, higher tracking efficiency, and better dynamic response compared to conventional P&O and standalone ANFIS techniques. The developed algorithm ensures optimal power extraction, improved system stability, and enhanced overall energy utilization, making it a suitable and efficient solution for real-time PV applications under partial shading conditions.