Mohammed Alnaftchi, Shaymaa MustafaIbrahim, Abdullahi2022-08-052022-08-052022Alnaftchi, S. M. M., Ibrahim, A. (2022). Design of electricity theft detection system based on supervised learning. In 2022 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), IEEE.9781665468350https://hdl.handle.net/20.500.12939/2767Power grids are critical assets, not limited to the theft, disrupting or defective meters and the arrangement of false meter readings of the infrastructure faced with non-technical losses (NTLs). In emergent markets, NTL is a main concern and up to 10% of the total distribution of electricity. NTL's estimated annual global cost to utilities is around 100 billion USD. Therefore, it is crucial for utilities and authorities to reduce NTL to increase revenue, profit and reliability of the grid. The result of electricity theft, broken electronic meters or billing errors is non-technological losses (NTD) in grids. In this paper, we present a novel frame work called ETD (Electricity Theft Detection), which comprises of an intelligent algorithms such as ETD and SVM, RF, XGBoost and Neural Network classifiers to detect fraudulent consumer from the normal consumer based upon the consumer's consumption pattern. simulation result shows that the proposed system is efficient in identifying the suspects with high accuracy.eninfo:eu-repo/semantics/closedAccessSupervised LearningTheft of ElectricityUser BehaviorConference Object2-s2.0-85133976069N/A