Design and Simulation of a Micro-Inverter for Microgrid Applications Using a Recurrent Neural Network-Based Control Strategy
TL;DR
Simulation results demonstrate that the RNN-MPPT algorithm significantly improves the system’s ability to track the maximum power point accurately and rapidly, with improved output power stability under fluctuating irradiation.
Abstract
This study presents the design and simulation of a micro-inverter system for photovoltaic (PV) energy conversion in microgrid applications using a Recurrent Neural Network (RNN)-based Maximum Power Point Tracking (MPPT) control strategy. The objective is to enhance power conversion efficiency and system responsiveness under dynamic solar conditions. The proposed system integrates a boost converter, micro-inverter, LCL filter, and Phase Locked Loop (PLL) for grid synchronization. The RNN model is trained using variations of irradiance and PV electrical characteristics to determine the optimal duty cycle for controlling the converter. System modeling and simulations were conducted in MATLAB to assess performance. Simulation results demonstrate that the RNN-MPPT algorithm significantly improves the system’s ability to track the maximum power point accurately and rapidly, with improved output power stability under fluctuating irradiation. The boost converter and inverter responses confirm effective voltage regulation and reduced current ripple, while the overall system achieved high efficiency across different irradiance levels. These findings highlight the potential of AI-based control techniques in advancing renewable energy technologies and contribute to the development of intelligent energy management systems suitable for smart grid integration.