Extremely randomised trees machine learning model for electricity theft detection

Abstract

Electricity ranks among the world’s most plundered commodities. The fraudulent act of acquiring electrical power without paying for it is termed electricity theft. Electricity theft is captured in power distribution systems as non-technical losses (NTL), representing a major loss in revenue for power utility companies. Electricity theft has far-reaching financial consequences owing to unrealised revenue, and this has a knock-on effect on both developed and developing countries because electricity represents a major part of a country’s GDP and facilitates other industries. AMI-based smart energy meters (SM) gather large amounts of electricity consumption (EC) data that power utilities can utilise to monitor and detect fraudulent customers. This EC data is fed to a machine learning (ML) based electricity theft detection model to learn the behaviour of fraudulent customers. However, existing ML-based electricity theft detection (ETD) models do not produce the best outcomes because of; consecutive missing values in EC datasets, data class imbalance problems, inappropriate hyperparameter tuning of ML models, etc. This research introduces an ETD model using an extremely randomised trees classifier to detect electricity theft in smart grids efficiently. SMOTE Tomek sampling is used to deal with the data class imbalance, and the grid search optimisation technique is employed to optimise the hyperparameters of the proposed model. The proposed model shows its capacity to detect electricity theft by obtaining 98%, 95.06%, 98%, 97%, 98%, and 99.65% accuracy, Matthew’s correlation coefficient, detection rate, Precision, F1-score, and area under the curve receiver operating characteristic, respectively.