PV Wind Battery Based DC Microgrid with Neural Network MPPT

Abstract

This Research presents a novel approach to enhancing the performance and efficiency of a PV-wind-battery-based DC microgrid through the integration of a neural network maximum power point tracking (MPPT) system. The proposed system aims to optimize energy harvesting from photovoltaic (PV) panels and wind turbines while efficiently managing energy storage in batteries. By employing neural network algorithms, the MPPT system adapts to varying environmental conditions and load demands, thereby maximizing energy extraction and system stability. Two important RE (Renewable Energy) power sources—photovoltaic cells and wind energy systems—are examined in this technical study under a range of meteorological conditions. Initially, a state-of-the-art intelligent controller system was developed to help monitor the peak power point. For RES, an MPPT (maximum power point tracking) controller is necessary since weather patterns are unpredictable. The purpose of this work is to provide novel ways for power generation using solar and wind energy that are based on MPPT and IDNN (enhanced deep neural network). The integration of a hybrid PV/WES system into microgrids, or MGs, has the potential to lower THD values and enhance power quality. The simulation findings validated that the suggested IDNN system outperforms the current approach in various operating scenarios, as seen by decreased mean square error (MSE) rates, total harmonic distortion (THD), and computational complexity.