A New Method for Bad Data Identification of Oilfield System Based on Enhanced Gravitational Search-Fuzzy C-Means Algorithm

Abstract

Aiming at the shortcomings of current methods of bad data detection and identification in a power system, this article advances a new method to identify bad data of the power system based on the enhanced gravitation search-fuzzy c-mean algorithm (EGSA-FCM). By using the enhanced gravity search algorithm (EGSA), a better initial solution to search the measurement data uploaded by SCADA system is obtained. Then, the FCM algorithm was used to obtain the classification of benign data and bad data. Finally, through the COS clustering validity judgment index, the optimal clustering number is determined and the optimal clustering results and bad data were obtained. This method has already been applied to the IEEE 14-node power system and a regional power grid in Daqing, China. The results indicated that the proposed method is more accurate than the traditional ones and effectively avoid the occurrence of false detection and missed detection.