A Novel Framework for Nontechnical Losses Detection in Electricity Companies

Nontechnical losses represent a very high cost to power supply companies, who aims to improve fraud detection in order to reduce this losses. The great number of clients and the diversity of different types of fraud makes this a very complex task. In this paper we present a combined strategy based on measures and methods adequate to deal with class imbalance problems. We also describe the features proposed, the selection process and results. Analysis over consumers historical kWh load profile data from Uruguayan Electricity Utility (UTE) shows that using combination and balancing techniques improves automatic detection performance.

[1]  Fabio Roli,et al.  Multiple Classifier Systems, 9th International Workshop, MCS 2010, Cairo, Egypt, April 7-9, 2010. Proceedings , 2010, MCS.

[2]  Rong Jiang,et al.  Wavelet based feature extraction and multiple classifiers for electricity fraud detection , 2002, IEEE/PES Transmission and Distribution Conference and Exhibition.

[3]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[4]  Nitesh V. Chawla,et al.  SMOTEBoost: Improving Prediction of the Minority Class in Boosting , 2003, PKDD.

[5]  Ludmila I. Kuncheva,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2004 .

[6]  João Paulo Papa,et al.  Design of robust pattern classifiers based on optimum-path forests , 2007, ISMM.

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

[8]  Thomas G. Dietterich.  Multiple Classifier Systems , 2000, Lecture Notes in Computer Science.

[9]  José Martínez Sotoca,et al.  Combined Effects of Class Imbalance and Class Overlap on Instance-Based Classification , 2006, IDEAL.

[10]  Ricardo Tanscheit,et al.  A Neuro-fuzzy System for Fraud Detection in Electricity Distribution , 2009, IFSA/EUSFLAT Conf..

[11]  Joshua Alspector,et al.  Data duplication: an imbalance problem ? , 2003 .

[12]  Sieh Kiong Tiong,et al.  Nontechnical Loss Detection for Metered Customers in Power Utility Using Support Vector Machines , 2010, IEEE Transactions on Power Delivery.

[13]  Huan Liu,et al.  Feature Selection for Classification , 1997, Intell. Data Anal..

[14]  Gustavo E. A. P. A. Batista,et al.  A study of the behavior of several methods for balancing machine learning training data , 2004, SKDD.

[15]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[16]  Xin Yao,et al.  Theoretical Study of the Relationship between Diversity and Single-Class Measures for Class Imbalance Learning , 2009, 2009 IEEE International Conference on Data Mining Workshops.

[17]  Gongping Yang,et al.  On the Class Imbalance Problem , 2008, 2008 Fourth International Conference on Natural Computation.

[18]  Alicia Fernández,et al.  Improving Electric Fraud Detection using Class Imbalance Strategies , 2012, ICPRAM.

[19]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[20]  Nitesh V. Chawla,et al.  Exploiting Diversity in Ensembles: Improving the Performance on Unbalanced Datasets , 2007, MCS.

[21]  Alexander J. Smola,et al.  Learning with kernels , 1998 .

[22]  Gavin Brown,et al.  "Good" and "Bad" Diversity in Majority Vote Ensembles , 2010, MCS.

[23]  Subhash C. Bagui,et al.  Combining Pattern Classifiers: Methods and Algorithms , 2005, Technometrics.

[24]  José Salvador Sánchez,et al.  Strategies for learning in class imbalance problems , 2003, Pattern Recognit..

[25]  José Salvador Sánchez,et al.  On the Suitability of Numerical Performance Measures for Class Imbalance Problems , 2012, ICPRAM.