A Novel Framework for Nontechnical Losses Detection in Electricity Companies

  • Matías Di Martino
  • Federico Decia
  • Juan Molinelli
  • Alicia Fernández
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 204)

Abstract

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.

Keywords

Electricity theft Support vector machine Optimum path forest Unbalance class problem Combining classifier UTE 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Alcetegaray, D., Kosut, J.: One class svm para la detección de fraudes en el uso de energía eléctrica. Trabajo Final Curso de Reconocimiento de Patrones, Dictado por el IIE- Facultad de Ingeniería- UdelaR (2008)Google Scholar
  2. 2.
    Barandela, R., Garcia, V.: Strategies for learning in class imbalance problems. Pattern Recognition, 849–851 (2003)Google Scholar
  3. 3.
    Batista, G., Pratti, R., Monard, M.: A study of the behavior of several methods for balancing machine learning training data. SIGKDD Explorations 6, 20–29 (2004)CrossRefGoogle Scholar
  4. 4.
    Brown, G., Kuncheva, L.: “Good” and “Bad” Diversity in Majority Vote Ensembles (2010)Google Scholar
  5. 5.
    Manning, C., Raghavan, P., Schutze, H.: An Introduction to Information Retrival, 1st edn. Cambridge University Press, Cambridge (2009)Google Scholar
  6. 6.
    Chang, C., Lin, C.: LIBSVM: a library for support vector machines (2001)Google Scholar
  7. 7.
    Chawla, N., Bowyer, K., Hall, L.: Smote: synthetic minority over-sampling technique. Journal of Artificial Intelligence Research (2002)Google Scholar
  8. 8.
    Chawla, N., Lazarevic, A., Hall, L.: Smoteboost: impoving prediction of the minority class in boosting. In: European Conf. of Principles and Practice of Knowledge Discovery in Databases (2003)Google Scholar
  9. 9.
    Chawla, N., Sylvester, J.: Exploiting diversity in ensembles: Improving the performance on unbalanced datasets. Departament of Computer Science and Engineering (2007)Google Scholar
  10. 10.
    Dash, M., Liu, H.: Feature selection for classification. Intelligent Data Analysis 1, 131–156 (1997)CrossRefGoogle Scholar
  11. 11.
    Di Martino, J., Decia, F., Molinelli, J., Fernámdez, A.: Improving electric fraud detection using class imbalance strategies. In: 1st International Conference in Pattern Recognition Aplications and Methods, vol. 2, pp. 135–141 (2012)Google Scholar
  12. 12.
    Dietterich, T.G.: Ensemble Methods in Machine Learning. In: Kittler, J., Roli, F. (eds.) MCS 2000. LNCS, vol. 1857, pp. 1–15. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  13. 13.
    Duin, R.: PRTools Version 3.0: A Matlab Toolbox for Pattern Recognition (2000)Google Scholar
  14. 14.
    Garcia, V., Sanchez, J., Mollineda, R.: On the suitability if numerical performance evaluation measures for class imbalance problems. In: 1st International Conference in Pattern Recognition Aplications and Methods, vol. 2, pp. 310–313 (2012)Google Scholar
  15. 15.
    Garcia, V., Sanchez, J., Mollineda, R., Alejo, R., Sotoca, J.: The class imbalance problem in pattern classification and learning (2007)Google Scholar
  16. 16.
    Guo, X., Zhou, G.: On the class imbalance problem. IIE - Computer Society 1, 192 (2008)Google Scholar
  17. 17.
    Jiang, R., Tagaris, H., Laschusz, A.: Wavelets based feature extraction and multiple cassifiers for electricity fraud detection (2000)Google Scholar
  18. 18.
    Kolez, A., Chowdhury, A., Alspector, J.: Data duplication: an imbalance problem? In: Proc. Proc. Intl. Conf. on Machine Learning, Workshop on Learning with Imbalanced Data Sets II (2003)Google Scholar
  19. 19.
    Kuncheva, L.: Combining Pattern Classifiers: Methods and Algorithms. Wiley-Interscience (2004)Google Scholar
  20. 20.
    Muniz, C., Vellasco, M., Tanscheit, R., Figueiredo, K.: Ifsa-eusflat 2009 a neuro-fuzzy system for fraud detection in electricity distribution (2009)Google Scholar
  21. 21.
    Nagi, J., Mohamad, M.: Nontechnical loss detection for metered customers in power utility using support vector machines. IEEE Transactions on Power Delivery 25(2) (2010)Google Scholar
  22. 22.
    Papa, J., Falcao, A.: Optimum-path forest: A novel and powerful framework for supervised graph-based pattern recognition techniques. Institute of Computing University of Campinas (2010)Google Scholar
  23. 23.
    Papa, J., Falcao, A., Suzuki, C.: LibOPF: a library for Opthimum Path Forets (2008)Google Scholar
  24. 24.
    Papa, J., Falcao, A., Miranda, P., Suzuki, C., Mascarenhas, N.: Design of robust pattern classifiers based on optimum-path forests. In: 8th International Symposium on Mathematical Morphology Rio de Janeiro Brazil, pp. 337–348 (October 2007)Google Scholar
  25. 25.
    Ramos, C., de Sousa, A.N., Papa, J., Falcao, A.: A new approach for nontechnical losses detection based on optimum-path forest. IEEE Transactions on Power Systems (2010)Google Scholar
  26. 26.
    Scholkopf, B., Smola, A.: Learning with Kernels, 2nd edn. The MIT Press, London (2002)Google Scholar
  27. 27.
    Vapnik, V.: Statistical Learning Theory. Wiley, New York (1998)MATHGoogle Scholar
  28. 28.
    Wang, S., Yao, X.: Theoretical study of the relationship between diversity and single-class measures for class imbalance learning (2009)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Matías Di Martino
    • 1
  • Federico Decia
    • 1
  • Juan Molinelli
    • 1
  • Alicia Fernández
    • 1
  1. 1.Instituto de Ingeniería EléctricaFacultad de Ingeniería Universidad de la RepúblicaMontevideoUruguay

Personalised recommendations