Abstract
•Developed a clustering-based approach for anomaly detection in photovoltaic systems.•Real data from a photovoltaic system is used to evaluate the performances of the developed approach.•The results show the superior performance of the proposed approach over other five binary clustering schemes.
One of the greatest challenges in a photovoltaic solar power generation is to keep the designed photovoltaic systems working with the desired operating efficiency. Towards this goal, fault detection in photovoltaic plants is essential to guarantee their reliability, safety, and to maximize operating profitability and avoid expensive maintenance. In this context, a model-based anomaly detection approach is proposed for monitoring the DC side of photovoltaic systems and temporary shading. First, a model based on the one-diode model is constructed to mimic the characteristics of the monitored photovoltaic array. Then, a one-class Support Vector Machine (1SVM) procedure is applied to residuals from the simulation model for fault detection. The choice of 1SVM approach to quantify the dissimilarity between normal and abnormal features is motivated by its good capability to handle nonlinear features and do not make assumptions on the underlying data distribution. Experimental results over real data from a 9.54 kWp grid-connected plant in Algiers, show the superior detection efficiency of the proposed approach compared with other binary clustering schemes (i.e., K-means, Birch, mean-shift, expectation–maximization, and agglomerative clustering).