Mod Tanh‐Activated Physical Neural Network MPPT Control Algorithm for Varying Irradiance Conditions

• Published in: Energy science & engineering Vol. 13; no. 6; pp. 2606 - 2619
• Main Authors: Nguyen‐Vinh, Khuong, Rangaraju, Surender, Jasinski, Michal
• Format: Journal Article
• Language: English
• Published: London John Wiley & Sons, Inc 01.06.2025; Wiley
• Subjects: Algorithms; Alternative energy sources; beta‐distributed point estimation technique (BDPET); Control algorithms; Control theory; Controllers; Cost control; Efficiency; Energy consumption; Feedback control; Fuzzy logic; Harmonic distortion; Irradiance; maximum power point tracking (MPPT); Maximum power tracking; Mismatch (electrical); Mod tanh neural network (MAPNN); Neural networks; Optimization; Optimization algorithms; photovoltaic (PV); Photovoltaics; Proportional integral derivative; puzzle optimization algorithm (POA); Renewable resources; Solar energy; Solar photovoltaic systems
• ISSN: 2050-0505; 2050-0505
• DOI: 10.1002/ese3.70062

ABSTRACT The increasing adoption of solar photovoltaic systems necessitates efficient maximum power point tracking (MPPT) algorithms to ensure optimal performance. This study proposes a Mod tanh‐activated physical neural network (MAPNN)‐based MPPT control algorithm, which addresses inefficiencies in existing models caused by spectral mismatch and improper converter control. The proposed method incorporates beta‐distributed point estimation technique for mismatch factor correction and a Buck‐Boost converter with a feedback control using the Chinese Remainder Theorem – Puzzle Optimization Algorithm‐tuned PID controller. Simulations demonstrate an efficiency improvement of 98.42%, with a 4.54 dB reduction in total harmonic distortion and faster convergence compared to traditional methods such as ANN and LSTM. This system significantly enhances MPPT performance under dynamic irradiance conditions. The proposed MPPT controller (CRT‐POA‐PID) is implemented to enhance power efficiency in the PV system. The beta‐distributed point estimation technique is used for mismatch factor correction, improving performance. Simulations show a 98.42% efficiency improvement, a 4.54 dB reduction in total harmonic distortion, and faster convergence compared to ANN and LSTM.