Clustering-based novelty detection for identification of non-technical losses

Abstract

The reduction of non-technical losses is a significant part of the total potential benefits resulting from implementations of the smart grid concept. This paper proposes a data-based method to detect sources of theft and other commercial losses. Prototypes of typical consumption behavior are extracted through clustering of data collected from smart meters. A distance-based novelty detection framework classifies new data samples as malign if their distance to the typical consumption prototypes is significant. The proposed method works on the space of four different indicators of irregular consumption, enabling the easy interpretation of results. A use case based on real data is presented to evaluate the method. The threat model considers sixteen different possible types of changes in consumption pattern that result from non-technical losses, including attacks and defects present since the first day of metering. The proposed clustering-based novelty detection method for identification of non-technical losses, using the Gustafson-Kessel fuzzy clustering algorithm, achieves a true positive rate of 63.6% and false positive rate of 24.3%, outperforming other state-of-the-art unsupervised learning methods.