Research Of Bad Data Identification And Correction In Power System

With the development of power system,the intelligence system and the degree of automation are constantly improving,which also makes the power system to be measured in the measured value of the trend of massive,and the bad data which will threaten the normal system run.Therefore,this paper proposes an improved gap statistic method to identify the bad data in the system.Redefine the amount of gap,and make a corresponding improvement in the part of the cluster to improve the accuracy of the identification algorithm.Then,the data collected at a certain point in time is taken as the object of study,and the method of particle swarm optimization neural network is proposed to correct the bad data.And realizes the real-time data of a second-tier city power company in northeast China.The results show that the method proposed in this paper can effectively realize the identification and correction of the data in the system,and the identification result is accurate and the modified parameters meet the actual working requirements of the city.Due to the large dispersion of data,the regularity is not obvious.Therefore,the method proposed in this paper is universal.