Electricity Theft Detection in AMI Using Customers’ Consumption Patterns

TLDR

Advanced metering infrastructure enables load management and demand response but also creates new opportunities for energy theft. The study proposes a consumption‑pattern based detector that exploits the predictability of normal and malicious usage to identify theft. By short‑listing transformer‑metered areas with high theft risk and applying classification, clustering, and anomaly detection to low‑sampling consumption data, the algorithm robustly flags suspicious customers while tolerating benign usage changes. The method preserves customer privacy and, on a real dataset of 5,000 customers, achieves high detection performance.

Abstract

As one of the key components of the smart grid, advanced metering infrastructure brings many potential advantages such as load management and demand response. However, computerizing the metering system also introduces numerous new vectors for energy theft. In this paper, we present a novel consumption pattern-based energy theft detector, which leverages the predictability property of customers' normal and malicious consumption patterns. Using distribution transformer meters, areas with a high probability of energy theft are short listed, and by monitoring abnormalities in consumption patterns, suspicious customers are identified. Application of appropriate classification and clustering techniques, as well as concurrent use of transformer meters and anomaly detectors, make the algorithm robust against nonmalicious changes in usage pattern, and provide a high and adjustable performance with a low-sampling rate. Therefore, the proposed method does not invade customers' privacy. Extensive experiments on a real dataset of 5000 customers show a high performance for the proposed method.