Identification of bad data of power system based improved GSA judgment

摘要

The power system security and stability of operation are determined by the accuracy of real-time data. A improvement judgment is made based on bad data detection using GSA (Gap Statistic Algorithm) data mining method, and is applied on bad data detection in power system. The Improvement judgment: elbow judgment was presented, which analyzes the relation between the error measures and the number of clusters k of the data set, then calculates the elbow angle at k and obtain the optimal number of clusters based on the least elbow angle. Combined the criterion with GSA, bad data detection could be implemented efficiently. Through simulation with real-time data from a power company, results show the detective method is accurate and rapid, and has the very good application prospects.