Fault detection in photovoltaic power converter using machine learning algorithm

Abstract

Nowadays, Artificial intelligence applications have increased importance in renewable energies, such as photovoltaic systems, especially in data analysis and fault detection. Therefore, in this paper, a standalone solar photovoltaic system based on multicellular converter with flying capacitor fault detection using machine learning algorithms. Two control strategies; sliding mode and exact linearization controls are used in this paper in order to determine the more robustness and increased accuracy control. Simulation results with MATLAB using K-Nearest Neighbors (KNN) algorithm show that sliding mode control present high accuracy and improved robustness compared with exact linearization control.