Expected output calculation based on inverse distance weighting and its application in anomaly detection of distributed photovoltaic power stations

摘要

With the increasing installed capacity of distributed photovoltaic generation, the anomaly detection is of great significance for the safe operation of distributed photovoltaic stations. Due to the lack of weather station, meteorological data based assessment and fault diagnosis methods are not applicable. To solve the problem, this paper proposes an expected output calculation and anomaly detection method based on inverse distance weighting. Output characteristics of different distributed stations in certain area are first analyzed, which show correlation with each other, the expected output calculation method of distributed stations is then proposed based on the inverse distance weighting algorithm. Robustness analysis is conducted to study the performance of inverse distance weighting method under different conditions. The parameters optimization of inverse distance weighting method is analyzed for its utilization in distributed photovoltaic generation. Three time series indexes: spatial performance ratio, similarity coefficient, and feature distance are selected as the anomaly detection indicators. Finally, an experimental study on the anomaly detection approach is conducted to prove its feasibility. (C) 2020 Elsevier Ltd. All rights reserved.