Anomaly detection and predictive maintenance for photovoltaic systems

Abstract

Abstract We present a learning approach designed to detect possible anomalies in photovoltaic (PV) systems in order to let an operator to plan predictive maintenance interventions. The anomaly detection algorithm presented is based on the comparison between the measured and the predicted values of the AC power production. The model designed to predict the AC power production is based on an Artificial Neural Network (ANN), that is capable of estimating the AC power production using solar irradiance and PV panel temperature measurements, and that is trained using a dataset previously gathered from the plant to be monitored. Live trend data coming from the PV system are then compared with the output of the model and the vector of residuals is analyzed to detect anomalies and generate daily predictive maintenance alerts; there residuals are aggregated over 1-day and processed to detect out-of-threshold samples and system degradation trends; these trends are extracted by computing the Triangular Moving Average (TMA) where the window size is automatically determined. The paper also reports experimental data results revealing that the model leads to a good anomaly detection rate, which is measured as a positive predictive detection rate greater than 90%. Moreover, the algorithm is able to recognize trends of system’s deviations from normal operation behavior and generate predictive maintenance alerts as a decision support system for operatives, with the aim of avoiding possible incoming failures.