@inproceedings{658fbf2eb4cf4e1b9755e3de03db436d,
title = "Revenue and Reliability Protection for Energy Suppliers From Energy Theft",
abstract = "Energy theft poses technical and social challenges for utilities and legitimate customers. In recent years, numerous machine learning (ML) concepts have been used to enhance power system operations in support of energy sector transitions towards digitization. The objective of the work is to identify suitable approaches to counteract various energy theft methods. In this collaborative work we have applied ML models with the market demand trends to find the most suitable approach(es) for identifying energy stealing. The work begins with some relevant results using ensemble ML models for energy theft detection. We then introduce the Naive Bayes model, which has been used for handling classification problems through supervised learning. This model is used to develop a methodology for identifying energy theft based on customers' consumption patterns. Results were compared using false-positive and detection rates for assessing their effectiveness.",
keywords = "Energy theft, machine learning, naive bayes",
author = "Dipu Sarkar and Ghosh, {Prasanta K.} and Gujjarlapudi, {Ch Sekhar}",
note = "Publisher Copyright: {\textcopyright} 2024 IEEE.; 12th IEEE International Conference on Smart Energy Grid Engineering, SEGE 2024 ; Conference date: 18-08-2024 Through 20-08-2024",
year = "2024",
doi = "10.1109/SEGE62220.2024.10739562",
language = "English (US)",
series = "2024 IEEE 12th International Conference on Smart Energy Grid Engineering, SEGE 2024",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "156--159",
booktitle = "2024 IEEE 12th International Conference on Smart Energy Grid Engineering, SEGE 2024",
}