Abnormal Data Detection and Cleaning of Wind Turbines Based on Average Confidence Interval Method

Abstract

wind turbine SCADA (Supervisory control and data acquisition) data contains a considerable proportion reflecting abnormal operation. Accurately eliminating these abnormal data is the basis for subsequent wind turbine power prediction and generation performance evaluation. This paper proposes a method for cleaning abnormal operation data of wind turbines based on average confidence interval. First of all, all wind turbine operational data are allocated into different bins at a certain interval in the horizontal power direction, and the adaptive kernel density method is used to successively establish the probability density distribution of operation data in each horizontal power bin. Next, the distribution characteristics of abnormal data points are obtained by analyzing the shape of probability density curve. Finally, an average confidence interval method is used to eliminate abnormal data. With actual wind turbine SCADA data, the proposed method is proved to be effective.