Detection of electricity theft based on Minimal Gated Memory network combined adaptive synthesis sampling and decision tree

Abstract

Advanced metering infrastructure is the foundation for recording and analyzing the massive, high-frequency electricity consumption data. With the increasing number of electricity theft issues caused by tampering with smart meters, it is necessary to detect electricity theft anomalies. For effective electricity theft inspection, an electricity theft detection method based on Minimal Gated Memory（MGM） network combined Adaptive Synthesis (ADASYN) sampling and Decision Tree (DT) is proposed in this paper. The proposed method considers that the number of electricity theft consumers is far less than that of honest consumers, and the electricity theft detection is a problem of data imbalance. From the perspective of data, ADASYN sampling method is selected to process the sample data of electricity theft consumers. In order to detect electricity theft effectively, the DT is further introduced for feature selection, and combined with the newly proposed MGM network to distinguish honest consumers and electricity theft consumers. Six forms of electricity theft attacks are introduced in this research. Based on real data from smart meters in Ireland, two experiments are designed to demonstrate the effectiveness of the proposed method. The results show that our proposed method perform the best in Precision, Recall, F1-score and Area Under the Curve (AUC) when detecting electricity theft. The method proposed in this research can provide a new idea and approach for the detection of electricity theft and maintain the electricity supply quality and safety of smart grid.