A Voting Approach of Ensemble Classifier for Detection of Power Quality in Islanded PV Microgrid

Abstract

In this research, an ensemble classifier using a voting method is proposed to categorize different Power Quality events (PQEs), switching, and fault transients in solar photovoltaic (PV) connected Microgrid (MG) network. For this analysis, an islanded MG network model is developed in the MATLAB-Simulink software framework to study the various power system disturbances (PQEs, switching transients, and Line to Ground (LG) fault). The voltage/current signals of various power disturbances are used for the extraction of features by applying a discrete wavelet transform technique. Then, the individual base classifiers (Bayesian Net, Naive Bayesian, and Logistic Regression) are trained by using the extracted features in the first stage. Subsequently, the voting method of Meta classification is applied to obtain the final predictions of class events in the second level, based on the predictions of base classifiers. The classification and statistical analysis are carried out under standard test conditions (STC) and real-time-varying solar irradiance of PV. The evaluation results of classification and statistical analysis clearly show that the proposed ensemble classifier offers improved classification accuracy with superior performance than individual base classifiers under STC and uncertain conditions of solar PV.