Artificial Neural Network Based Electricity Theft Detection

Abstract

The theft of electricity is a matter of concern for the distribution utility today. The Aggregate Technical and Commercial (AT&C) loss of Maharashtra State Electricity Distribution Company is around 20.72% for the year 2020–21. The main cause of such a higher loss is pilferage or theft of electricity. As per statistics given by various distribution utilities, the theft incidences of three phase HT and LT consumers are under control. However, there is a rising trend in tampering of single phase meters. Various methods of theft detection of single phase meters are in existence, however, tampering of meter by inserting the resistive link in parallel with the meter cannot be detected using these conventional methods. In this paper, a novice technique of tamper detection using Artificial Neural Network is proposed. The proposed method is cost effective and feasible.