Machine Learning Algorithm for Efficient Power Theft Detection using Smart Meter Data

  • Authors

    • Jeyaranjani J
    • Devaraj D
    https://doi.org/10.14419/ijet.v7i3.34.19585
  • Smart Grid, AMI, Smart Meter, Electricity Theft, Machine Learning Algorithm, k-means ANN

  • Abstract

    Electricity theft is one of the major problems of electric utilities. The dishonest electric power users produce financial loss to the utility companies. It is not possible to inspect the manually. The electricity consumption energy data obtained from the Smart Meter installed at customer premise have the information that is used for identifying the anomaly customers. This paper proposes an approach to identify the suspect customers using the customer power usage pattern. Machine learning algorithm is used for this purpose. The trustworthiness of customers is verified and is selected for theft program. This analysis is carried out by tweaking the actual Smart Meter data to create fraudulent data. The ANN classification model is developed using supervised learning algorithm that helps to discriminate the customers profile based on their genuine activity and fraudulent activity in electricity power usage. Simulation result shows that the proposed system is efficient in identifying the suspects with high accuracy.

     

     

  • References

    1. [1] Patrick Glauner et al. “Large-scale detection of non-technical losses in imbalanced data setsâ€. In: Innovative Smart Grid Technologies Conference (ISGT), 2016 IEEE Power & Energy Society. IEEE. 2016, pp. 1–5

      [2] [2]S.S.S.R. Depuru, L. Wang, and V. Devabhaktuni, “Electricity theft: overview,issues, prevention and a smart meter based approach to control theft,†Energy Policy, vol. 39, pp. 1007–1015, Feb. 2011.

      [3] Blue Yonder GmbH Maximilian Christ. How to add a custom feature. tsfresh. May 28, 2017. url: http : / / tsfresh . readthedocs . io / en/latest/text/how_to_add_custom_feature.html

      [4] Patrick Glauner et al. “The Challenge of Non-Technical Loss DetectionUsing Artificial Intelligence: A Surveyâ€. In: International Journal of Computational Intelligence Systems 10.1 (2017), pp. 760–775

      [5] S. McLaughlin , B. Holbert, A. Fawaz, R. Berthier, and S. Zonouz , “A multi-sensor energy theft detection framework for advanced metering infrastructures,†IEEE J. Sel. Areas Commun., vol. 31, no. 7, pp. 1319–1330, Jul. 2013.

      [6] J. I. Guerrero , C. Leon, I. Monedero, F. Biscarri, and J. Biscarri , “Improving knowledge-based systems with statistical techniques, text mining, and neural networks for non-technical loss detection.†Knowl.-Based Syst. , vol. 71, pp. 376–388, 2014.

      [7] P. Jokar, N. Arianpoo, V.C.M. Leung, "Electricity theft detection in AMI using customers’ consumption patterns", IEEE Trans. Smart Grid, vol. 7, no. 1, pp. 216-226, 2016.

      [8] Srihari Mandava, Vanishree J, Ramesh V, “Automation of Power Theft Detection Using PNN Classifier†International Journal of Artificial Intelligence and Mechatronics, Volume 3, Issue 4, ISSN 2320 – 512.

      [9] J. R. Filho, E. M. Gontijo, A. C. Delaiba, E. Mazina, J. E. Cabral, and J. O. P. Pinto, "Fraud Identification in Electricity Company Customers Using Decision Trees" in Proc. of 2004 IEEE International Conference on Systems, Man and Cybernetics, Vol. 4, pp. 3730-3734, Oct. 2004.

      [10] Technique for identifying abnormal energy usage pattern, in Proc. IEEE North American Power Symposium (NAPS), 2012, pp. 1-6

      [11] Sanujit Sahoo, Daniel Nikovski, Toru Muso, and Kaoru Tsuru. Electricity theft detection using smart meter data. In Innovative Smart Grid Technologies Conference (ISGT), 2015 IEEE Power & Energy Society, pages 1–5. IEEE, 2015.

      [12] Vladimir N Vapnik. An overview of statistical learning theory. IEEE transactions on neural networks, 10(5):988–999, 1999

      [13] Soma Shekara Sreenadh Reddy Depuru, Lingfeng Wang, Vijay Devabhaktuni, and Robert C Green. High performance computing for detection of electricity theft. International Journal of Electrical Power & Energy Systems, 47:21–30, 2013

      [14] Jawad Nagi, Keem Siah Yap, Sieh Kiong Tiong, Syed Khaleel Ahmed, and Farrukh Nagi. Improving svm-based nontechnical loss detection in power utility using the fuzzy inference system. IEEE Transactions on power delivery, 26(2):1284–1285, 2011

      [15] Breno C Costa, Bruno LA Alberto, Andre M Portela, ´ W Maduro, and Esdras O Eler. Fraud detection in electric power distribution networks using an annbased knowledge-discovery process. International Journal of Artificial Intelligence & Applications, 4(6):17, 2013.

      [16] AH Nizar, ZY Dong, and Y Wang. Power utility nontechnical loss analysis with extreme learning machine method. IEEE Transactions on Power Systems, 23(3):946–955, 2008.

      [17] Cyro Muniz, Marley Maria Bernardes Rebuzzi Vellasco, Ricardo Tanscheit, and Karla Figueiredo. A neuro-fuzzy system for fraud detection in electricity distribution. In IFSA/EUSFLAT Conf., pages 1096– 1101. Citeseer, 2009.

      [18] Cyro Muniz, Karla Figueiredo, Marley Vellasco, Gustavo Chavez, and Marco Pacheco. Irregularity detection on low tension electric installations by neural network ensembles. In 2009 International Joint Conference on Neural Networks, pages 2176–2182. IEEE, 2009.

      [19] Jawad Nagi, Keem Siah Yap, Sieh Kiong Tiong, Syed Khaleel Ahmed, and Malik Mohamad. Nontechnical loss detection for metered customers in power utility using support vector machines. IEEE transactions on Power Delivery, 25(2):1162–1171, 2010.

  • Downloads

  • How to Cite

    J, J., & D, D. (2018). Machine Learning Algorithm for Efficient Power Theft Detection using Smart Meter Data. International Journal of Engineering & Technology, 7(3.34), 900-904. https://doi.org/10.14419/ijet.v7i3.34.19585

    Received date: 2018-09-12

    Accepted date: 2018-09-12