Electricity theft detecting based on density-clustering method

Abstract

Nowadays, the problem of electricity theft and tampered smart meter data is causing widespread concern. Customer load profiles collected from smart meters can help detect abnormal electricity users and identify electricity theft. In this paper, a density-based electricity theft detection method is proposed to find out abnormal electricity patterns. Several malicious types are used to test the validation of the proposed method. Comparisons with k-means clustering, Gaussian mixture model (GMM) clustering and density-based spatial clustering of applications with noise (DBSCAN) are also con ducted. Numerical experiments show that the proposed method outperforms other methods in almost all the theft types.