Fault Diagnosis Method Based on An Improved KNN Algorithm for PV strings

Rapid and accurate fault diagnosis under limited data has become one of the most important abilities of photovoltaic (PV) power generation systems. This study proposes an improved K-Nearest-Neighbor(KNN) method, which is based on the current at the maximum power point, voltage at the maximum power point and weather data. By using this method, short circuit, open circuit and shading of a PV string can be diagnosed quickly based on data obtained by inverters and weather monitor. Finally, a large number of data was obtained through a credible model whose data is proved to be consistent with the measured data greatly. Diagnosis result of the method was evaluated through these data.