Machine learning-based statistical testing hypothesis for fault detection in photovoltaic systems

•A Gaussian process regression (GPR)-based generalized likelihood ratio test (GLRT) is developed.•GPR-based GLRT is proposed to enhance PV system monitoring.•The detection performance is studied using several PV system faults through simulated and real data.•The good detection, false alarm, and computation time are used for evaluation. In this paper, we consider a machine learning approach merged with statistical testing hypothesis for enhanced fault detection performance in photovoltaic (PV) systems. The developed method makes use of a machine learning based Gaussian process regression (GPR) technique as a modeling framework, while a generalized likelihood ratio test (GLRT) chart is applied to detect PV system faults. The developed GPR-based GLRT approach is assessed using simulated and real PV data through monitoring the key PV system variables (current, voltage, and power). The computation time, missed detection rate (MDR), and false alarm rate (FAR) are computed to evaluate the fault detection performance of the proposed approach.