Fault Detection and Diagnosis in Grid-Connected PV Systems Under Irradiance Variations

Photovoltaic energy holds great promise. However, the energy output of photovoltaic systems is closely linked to solar irradiance. Monitoring irradiance variability is crucial for ensuring the stable operation and improved generation of these systems. Within the field of fault detection and diagnosis, researchers hold different perspectives on the impact of irradiance variability. To gain a deeper understanding of the dynamic model of photovoltaic systems under various operating conditions, this paper introduces the influence of irradiance variability and proposes an efficient fault detection and diagnosis method based on machine learning and deep learning techniques. This method accurately identifies the healthy and faulty operating states of photovoltaic systems and exhibits inspiring results in simulated data studies. The significance of this research lies in the incorporation of irradiance variability into photovoltaic system monitoring, as well as the realization of efficient fault detection and diagnosis through the utilization of machine learning and deep learning techniques. As a result, the stability and reliability of photovoltaic systems are enhanced, thereby fully harnessing the potential of photovoltaic energy as a renewable energy source.