Fault Prediction and Early-Detection in Large PV Power Plants Based on Self-Organizing Maps

In this paper, a novel and flexible solution for fault prediction based on data collected from Supervisory Control Data Acquisition (SCADA) system is presented. Generic fault/status offered by means of driven approach self-organizing map (SOM) the definition an original Key Performance Indicator (KPI). The model has been assessed park three photovoltaic (PV) plants with installed capacity up to 10 MW, more than sixty inverter modules different technology brands. results indicate that proposed method effective in predicting incipient generic faults average 7 days advance true positives rate 95%. easily deployable on-line monitoring anomalies new PV technologies, requiring only availability historical SCADA data, taxonomy electrical datasheet.