Development of Photovoltaic abnormal condition detection system using combined regression and Support Vector Machine

Abstract

It is essential to monitor and detect the abnormal conditions in Photovoltaic (PV) system as early as possible to maintain its productivity. This paper presents the development of a PV abnormal condition detection system by combining regression and Support Vector Machine (SVM) models. The regression model is used to estimate the expected power generation under the respective solar irradiance, which is used as the input for the SVM model. The SVM model is then used to identify the abnormal condition of a PV system. The proposed model does not require installing additional measurement devices and can be developed at low cost, because the data that is used as the input variable for the model is retrieved from the Power Conversion System (PCS). Furthermore, the accuracy of the detection system is improved by taking into consideration the daylight time and the interactions between the independent variables, as well as the implementation of the multi-stage k-fold cross-validation technique. The proposed detection system is validated by using actual data retrieved from a PV site, and the results show that it can successfully distinguish the normal condition, as well as identify the abnormal condition of a PV system by using the basic measurements.