Artificial Intelligence for Energy Theft Detection in Distribution Networks

Mileta Žarković () and Goran Dobrić
Additional contact information
Mileta Žarković: School of Electrical Engineering, University of Belgrade, Bulevar kralja Aleksandra 73, 11020 Belgrade, Serbia
Goran Dobrić: School of Electrical Engineering, University of Belgrade, Bulevar kralja Aleksandra 73, 11020 Belgrade, Serbia

Energies, 2024, vol. 17, issue 7, 1-17

Abstract: The digitization of distribution power systems has revolutionized the way data are collected and analyzed. In this paper, the critical task of harnessing this information to identify irregularities and anomalies in electricity consumption is tackled. The focus is on detecting non-technical losses (NTLs) and energy theft within distribution networks. A comprehensive overview of the methodologies employed to uncover NTLs and energy theft is presented, leveraging measurements of electricity consumption. The most common scenarios and prevalent cases of anomalies and theft among consumers are identified. Additionally, statistical indicators tailored to specific anomalies are proposed. In this research paper, the practical implementation of numerous artificial intelligence (AI) algorithms, including the artificial neural network (ANN), ANFIS, autoencoder neural network, and K-mean clustering, is highlighted. These algorithms play a central role in our research, and our primary objective is to showcase their effectiveness in identifying NTLs. Real-world data sourced directly from distribution networks are utilized. Additionally, we carefully assess how well statistical methods work and compare them to AI techniques by testing them with real data. The artificial neural network (ANN) accurately identifies various consumer types, exhibiting a frequency error of 7.62%. In contrast, the K-means algorithm shows a slightly higher frequency error of 9.26%, while the adaptive neuro-fuzzy inference system (ANFIS) fails to detect the initial anomaly type, resulting in a frequency error of 11.11%. Our research suggests that AI can make finding irregularities in electricity consumption even more effective. This approach, especially when using data from smart meters, can help us discover problems and safeguard distribution networks.

Keywords: machine learning; energy theft detection; non-technical loss (NTL); autoencoder; artificial neural networks; ANFIS (search for similar items in EconPapers)
JEL-codes: Q Q0 Q4 Q40 Q41 Q42 Q43 Q47 Q48 Q49 (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1996-1073/17/7/1580/pdf (application/pdf)
https://www.mdpi.com/1996-1073/17/7/1580/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jeners:v:17:y:2024:i:7:p:1580-:d:1364055

Access Statistics for this article

Energies is currently edited by Ms. Agatha Cao

More articles in Energies from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().