Unsupervised Classification for Non-Technical Loss Detection

Electricity theft has been a major issue for DSOs for years. However, despite efforts to detect it and the application of legal deterrents, the phenomenon insists. In this paper, unsupervised data mining NTL detection techniques are tested on a smart meter data set provided by the Greek DSO, HEDNO and a publically available smart meter data set. Frauds are simulated and the Twitter breakout detection library is used for extracting features which will be combined with typical features already found in literature. Then, unsupervised classifiers such as rule systems, multi-variate Gaussian distribution (MGD), local outlier factor (LOF), k-means, fuzzy c-means, DBSCAN and SOM are demonstrated. Finally, a number of metrics are calculated for each data set and classifier such as accuracy, detection rate, precision, false positive rate and F1score. In addition, the amount of stolen energy detected and detection delay are proposed as metrics for NTL detection system studies.

[1]  Josif V. Spirić,et al.  Fraud detection in registered electricity time series , 2015 .

[2]  A. N. de Souza,et al.  Detection and Identification of Abnormalities in Customer Consumptions in Power Distribution Systems , 2011, IEEE Transactions on Power Delivery.

[3]  Johan Driesen,et al.  Parameter identification of unknown radial grids for theft detection , 2012, 2012 3rd IEEE PES Innovative Smart Grid Technologies Europe (ISGT Europe).

[4]  Victor C. M. Leung,et al.  Electricity Theft Detection in AMI Using Customers’ Consumption Patterns , 2016, IEEE Transactions on Smart Grid.

[5]  J.O.P. Pinto,et al.  Fraud detection in high voltage electricity consumers using data mining , 2008, 2008 IEEE/PES Transmission and Distribution Conference and Exposition.

[6]  Pan Li,et al.  Privacy-Preserving Energy Theft Detection in Microgrids: A State Estimation Approach , 2016, IEEE Transactions on Power Systems.

[7]  Wil L. Kling,et al.  Theft detection and smart metering practices and expectations in the Netherlands , 2010, 2010 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT Europe).

[8]  Farrukh Nagi,et al.  Improving SVM-Based Nontechnical Loss Detection in Power Utility Using the Fuzzy Inference System , 2011, IEEE Transactions on Power Delivery.

[9]  C C O Ramos,et al.  A New Approach for Nontechnical Losses Detection Based on Optimum-Path Forest , 2011, IEEE Transactions on Power Systems.

[10]  Carlos León,et al.  Improving Knowledge-Based Systems with statistical techniques, text mining, and neural networks for non-technical loss detection , 2014, Knowl. Based Syst..

[11]  Stefan Axelsson,et al.  The base-rate fallacy and the difficulty of intrusion detection , 2000, TSEC.

[12]  Alvaro A. Cárdenas,et al.  Evaluating Electricity Theft Detectors in Smart Grid Networks , 2012, RAID.

[13]  Nikos D. Hatziargyriou,et al.  Review of non-technical loss detection methods , 2018 .

[14]  William H. Sanders,et al.  ARIMA-Based Modeling and Validation of Consumption Readings in Power Grids , 2015, CRITIS.

[15]  William H. Sanders,et al.  PCA-Based Method for Detecting Integrity Attacks on Advanced Metering Infrastructure , 2015, QEST.

[16]  David S. Matteson,et al.  Leveraging cloud data to mitigate user experience from ‘breaking bad’ , 2014, 2016 IEEE International Conference on Big Data (Big Data).

[17]  Neeraj Kumar,et al.  Decision Tree and SVM-Based Data Analytics for Theft Detection in Smart Grid , 2016, IEEE Transactions on Industrial Informatics.

[18]  Iñigo Monedero,et al.  Detection of frauds and other non-technical losses in a power utility using Pearson coefficient, Bayesian networks and decision trees , 2012 .