Design of an MPPT Algorithm Based on Neural Networks and Fuzzy Logic for Different Photovoltaic Panel Technologies

The growing demand for electrical energy driven by global consumption, such as China's 600 TWh in 2023 has reinforced the importance of clean and sustainable sources. The performance of photovoltaic (PV) systems is significantly influenced by panel manufacturing technologies and external environmental conditions, including dust, water droplets, animal waste, and especially partial shading, which can reduce power output. This paper proposes a Maximum Power Point Tracking (MPPT) algorithm based on Fuzzy Logic Control (FLC) and Artificial Neural Networks (ANN), aimed at enhancing the energy extraction efficiency from PV systems under variable and non-stable environmental conditions. A DC-DC boost converter is used to regulate the energy transfer between the PV panel and the load, with its duty cycle dynamically adjusted by the proposed algorithms. The hybrid FL&ANN model is trained using real-world data from different photovoltaic technologies, including HIT, Amorphous Silicon (a-Si), Tandem (a-Si/μc-Si), and Copper Indium Gallium Selenide (CIGS). Simulations are carried out in MATLAB/Simulink under varying irradiance and temperature scenarios. The results demonstrate that the hybrid FL&ANN controller outperforms original FLC in terms of response time and tracking accuracy. Additionally, this approach proves highly effective in electro mobility applications, where PV panels are continuously exposed to dynamic environmental conditions such as partial shading during vehicle movement. The proposed method offers a viable and efficient solution to optimize solar energy usage in modern, mobility-focused energy systems.