LAUSR

Electricity theft has emerged as one of the major reasons of Non-Technical Losses (NTLs) in the power distribution systems and has become a global issue. Therefore, power utilities are concerned about resolving the issue of electricity theft. In this regard, the data collected by Advanced Metering Infrastructure (AMI) can be used to devise data-driven machine learning-based Electricity Theft Detection (ETD) methods. In this paper, a novel data-driven ETD method is proposed that firstly labels the electricity consumers as fair or malicious based on three analyses: intra-consumer, inter-consumer, and temperature-electricity consumption relation. After assigning labels to the data, significant features are extraction from data by introducing a new feature extractor that is based on Reconstruction Independent Component Analysis (RICA) and sparse auto-encoder. Finally, classification is performed using two newly proposed enhanced classifiers, named as Differential Evolution (DE) Random Undersampling Boosting (DE-RUSBoost) and Jaya-RUSBoost. The performance of RUSBoost is enhanced using two nature-inspired swarm intelligence-based optimization algorithms, namely DE and Jaya optimization. The performance evaluation of the proposed classifiers is performed by conducting comprehensive simulations on real-world data taken from the UMass* smart homes electricity consumption dataset and the State Grid Corporation of China (SGCC) electricity theft dataset. DE-RUSBoost achieves an Area Under the Curve (AUC) of 0.89 and Jaya-RUSBoost achieves AUC of 0.95. The proposed classifiers have superior performance compared to two state-of-the-art benchmarks, i.e., Wide And Deep Convolution Neural Network (WADCNN) and grid search-based RUSBoost.