Fault Identification of Photovoltaic Array Based on Machine Learning Classifiers

Fault identification in Photovoltaic (PV) array is a contemporary research topic motivated by the higher penetration levels of PV systems recent electrical grids. Therefore, this work aims to define an optimal Machine learning (ML) structure automatic detection and diagnosis algorithm for common faults, namely, permanent (Arc Fault, Line-to-Line, Maximum Power Point Tracking unit failure, Open-Circuit faults), temporary (Shading) under wide range climate datasets, fault impedances, shading scenarios. To achieve best-fit ML structure, three distinct classifiers are compared, Decision Tree (DT) based on different splitting criteria, K-Nearest Neighbors (KNN) metrics distance weighting functions, Support Vector (SVM) Kernel functions multi-classification approaches. Also, Bayesian Optimization adopted assign hyperparameters classifiers. investigate performance reported, both simulation experimental case studies carried out presented.