A novel unsupervised feature‐based approach for electricity theft detection using robust PCA and outlier removal clustering algorithm

Abstract

This paper presents a novel data‐oriented unsupervised machine learning‐based theft detection approach for efficiently identifying the fraudster consumers. It accomplishes the above‐mentioned objective by exploiting the intelligence of the robust principal component analysis (ROBPCA) algorithm in conjunction with the outlier removal clustering (ORC) algorithm. To avoid the irregularities in acquired consumers’ data from a power utility, the statistical features are extracted from each consumer's consumption patterns using an anomalous time series extension. Based on the extracted features, the consumers with most similar features are initially grouped into two categories using the ROBPCA algorithm. In order to evade any overlapping between the two newly formed groups, the ORC algorithm is utilized to categorize the consumers distinctly as “suspicious” and “non‐suspicious”. Finally, a very selective onsite inspection is proposed, thus, saving the considerable time, resources, and overall cost of the utilities. The effectiveness of the proposed theft detection method is validated by comparing its performance with nine most widely used outlier detection methods on the basis of seven of the most prominent performance metrics. The accuracy and detection rate of the proposed technique are found as 94.34% and 92.52%, respectively, which is significantly higher than that of other studied conventional methods.

A combined unsupervised learning approach for electricity theft detection and loss estimation

“…Otherwise, the load sample may be a fraudulent sample, and the bigger differences between the mean index values and the lower bounds, the more likely an electricity thief is. Therefore, we define the following Equations ( 5), (6), and (7) to calculate the differences.…”

“…To address these issues, the power utilities usually send technical staffs to check ammeters termly, which is extremely time-consuming, expensive, and inefficient and can only detect the electricity theft behaviour of destroying ammeters [5][6][7]. With the application of smart meters and advanced metering infrastructure (AMI) [8], other electricity theft behaviours including bypassing and non-invasive interference ammeters can be effectively prevented.…”

Boruta-XGBoost Electricity Theft Detection Based on Features of Electric Energy Parameters

“…In recent years, many related types of research have introduced machine learning and other artificial intelligence methods, which can be classified into unsupervised learning and supervised learning. The unsupervised learning method is used to analyze the user's load curve by applying cluster analysis and outlier detection based on similarity or dissimilarity measures [3], [4], [5], [6]. The supervised learning method is used to pre-label datasets (i.e.…”

Electric theft detection in advanced metering infrastructure using Jaya optimized combined Kernel‐Tree boosting classifier—A novel sequentially executed supervised machine learning approach

“…In addition, data-oriented algorithms have been developed as an effective automated tool for screening aberrant energy consumption patterns and identifying possible electrical fraud activities. These data-oriented theft detection methods can be broadly categorized into four categories, statistical-based [14][15][16][17], game-theory-based [18,19], expert system [20,21] and ML-based [22][23][24][25].…”