Photovoltaic systems: Analytic comparison of fuzzy logic and ML methods for applying maximum power tracking systems
Author Identifier (ORCID)
Ohirul Qays: https://orcid.org/0000-0003-1949-7160
Stefan Lachowicz: https://orcid.org/0000-0001-8262-2898
Farhana Yasmin: https://orcid.org/0000-0001-7377-0688
Abstract
Integration of artificial intelligence (AI) in solar power systems for maximum power point tracking (MPPT) is increasingly popular due to the limitations of traditional MPPT methods in locating the global maximum power point (GMPP) under partial shading conditions. Unlike conventional techniques, AI-based algorithms excel at identifying the GMPP even when multiple local maximum power points (MPPs) exist. Compared to traditional methods, AI-based MPPT techniques like reinforcement learning and fuzzy logic typically offer higher efficiency, reduced steady-state oscillation, and faster convergence but require significant resources and investment. This paper compares two AI-based MPPT methods-Fuzzy Logic and Reinforcement Learning using simulation. Each AI approached its strengths and weaknesses, complicating on optimal method selection. It provided a detailed efficiency comparison of these AI methods by implementing them in a solar power grid system under various environmental conditions.
Document Type
Conference Proceeding
Date of Publication
1-1-2025
Publication Title
International Conference on Robotics, Electrical and Signal Processing Techniques
Publisher
IEEE
School
School of Engineering
Copyright
subscription content
First Page
222
Last Page
227
Comments
Ahmed, M. U., Qays, O., Lachowicz, S., Thundiyil, N. T., Hossain, M. L., Amin, U., ... & Yasmin, F. (2025, January). Photovoltaic systems: Analytic comparison of fuzzy logic and ML methods for applying maximum power tracking systemss. In 2025 4th International Conference on Robotics, Electrical and Signal Processing Techniques (ICREST) (pp. 222-227). IEEE. https://doi.org/10.1109/ICREST63960.2025.10914370