A Review on Latest Trends in Non-Technical Loss Detection
Published in In the proceedings of Proceedings of the 1st Conference on Information Technology and Data Science, 2020
Recommended citation: Khawaja Ghori, Muhammad Awais, Akmal Khattak, Muhammad Imran, Rabeeh Abbasi, László Szathmáry, "A Review on Latest Trends in Non-Technical Loss Detection." In the proceedings of Proceedings of the 1st Conference on Information Technology and Data Science, 2020. https://konferencia.unideb.hu/en/program-1st-conference-information-technology-and-data-science
An increasing interest in digging out the consumption patterns in power and energy sector is observed globally. This includes electrical, gas and water supply industries. A reason behind analyzing the consumption patterns is the detection of fraudulent attempts which are made for the reduction of bill payments. In case of electricity, these attempts are made by reversing the meters, by-passing or slowing down the meters or inaccurate readings. The detection of theft attempts in power industry is termed as Non-Technical Loss (NTL) detection. With the increasing demand of electricity, the occurrences of NTL has been reported globally including India, Pakistan, Brazil and China etc. In this paper, we first describe an interesting characteristic of class imbalance that the dataset used in NTL detection exhibit. Then, we present a thorough review about the recent techniques used in the detection of NTL including machine learning classifiers, deep learning and hardware oriented techniques. Moreover, we introduce the synthesized and the real datasets that have been used in NTL detection. Lastly, we discuss the need for a relative comparison of classical machine learning and deep learning over a benchmark dataset for NTL detection.