| Omar Imamverdiyev, Burcu Ramazanli, Surkhay Fatullayev Enhancing Solar Photovoltaic Power Systems with AI-Based Maximum Power Point Tracking |
|---|
| Abstract. Photovoltaic (PV) power systems are increasingly deployed to meet sustainable energy needs but suffer efficiency losses under variable irradiance and temperature conditions. To address this, Maximum Power Point Tracking (MPPT) algorithms dynamically adjust the converter’s duty cycle to maximize power extraction. This study presents a comparative analysis of four advanced MPPT techniques, including Perturb and Observe (P&O), Fuzzy Logic Control (FLC), Particle Swarm Optimization (PSO), and Artificial Neural Networks (ANN), all implemented within a unified MATLAB/Simulink framework. Each algorithm is tested using real-world weather data that captures typical variations in solar irradiance and temperature and accelerated profiles that simulate rapid and abrupt changes in irradiance and photovoltaic cell temperature. Performance metrics include tracking accuracy, dynamic response, steady-state stability, total energy harvested, and overall efficiency. The findings illustrate the trade-offs among these approaches, highlighting their advantages and disadvantages regarding response time, overall efficiency, and energy output. This thorough examination offers comparative findings to identify the suitable MPPT strategy for particular environmental circumstances. |
| Keywords: Solar energy, Maximum Power Point, Photovoltaic panels, P&O, FLC, PSO, ANN |
 Download PDF |
| DOI: |
