As advanced metering infrastructure (AMI) is deployed, the AMI data is used to detect an energy fraud. Along with context analysis of AMI data such as detection of an unreasonably low consumption AMI data mining is a primary solution for detecting abnormalities that cannot be detected using simple context analysis. Traditionally, abnormality detection based on AMI data mining compares a load profile with predefined normal prototypes. However, since a load profile can be normal in one condition and abnormal in another, the condition associated with the load profile should be considered as determining the normality. However, existing methods do not connect the normality of a prototype and a specific condition. In this study, the authors propose a mechanism that incorporates the conditional probability into determination of the normality of the prototype for comparison. The novelty of their study is its generating a two-dimensional space using similarity and conditional probability, so that several multi-dimensional classification methods can be applied. They compare the proposed mechanism with best-fit and average prototype-based abnormality detection methods. In conclusion, the proposed mechanism can distinguish fraud data with a higher precision than the traditional methods. They also explore the accuracy of the mechanism with various parameters.

References

1. 1)
  - 15. Han, J., Kamber, M.: ‘Data mining: concepts and techniques’ (Morgan Klishers, Waltham, MA, USA, 2001), pp. 299–302.
2. 2)
  - 9. Nizar, A.H., Dong, Z.Y., Jalaluddin, M., et al: ‘Load profiling method in detecting non-technical loss activities in a power utility’. Power and Energy Conf., 2006. PECon ‘06. IEEE Int., November 2006, pp. 82–87, 28–29.
3. 3)
  - 2. Dangar, B., Joshi, S.K.: ‘Electricity theft detection techniques for metered power consumer in GUVNL, GUJARAT, INDIA’. Power Systems Conf. (PSC), 2015 Clemson University, March 2015, pp. 1–6, 10–13.
4. 4)
  - 11. Schliep, K., Hechenbichler, K.: ‘Package KKNN’. Available at http://www.cran.r-project.org/web/packages/kknn/kknn.pdf.
5. 5)
  - 6. Räsänen, T., Voukantsis, D., Niska, H., et al: ‘Data-based method for creating electricity use load profiles using large amount of customer-specific hourly measured electricity use data’, Appl. Energy, 2010, 87, (11), pp. 3538–3545 (doi: 10.1016/j.apenergy.2010.05.015).
6. 6)
  - 5. Gerbec, G., Gašperič, S., Šmon, I., et al: ‘An approach to customers daily load profile determination’. Power Engineering Society Summer Meeting, IEEE, July 2002, vol. 1, pp. 587–591.
7. 7)
  - 13. Chen, J., Li, W., Lau, A., et al: ‘Automated load curve data cleansing in power systems’, IEEE Trans. Smart Grid, 2010, 1, (2), pp. 213–221 (doi: 10.1109/TSG.2010.2053052).
8. 8)
  - 12. Meyer, D.: ‘Support vector machines: the interface to LIBSVM in package e1071’. Available at http://www.cran.r-project.org/web/packages/e1071/ vignettes/svmdoc.pdf.
9. 9)
  - 4. Tsekouras, G.J., Hatziargyriou, N.D., Dialynas, E.N.: ‘Two-stage pattern recognition of load curves for classification of electricity customers’, IEEE Trans. Power Syst., 2007, 22, (3), pp. 1120–1128 (doi: 10.1109/TPWRS.2007.901287).
10. 10)
  - 3. Babu, T.V., Murthy, T.S., Sivaiah, B.: ‘Detecting unusual customer consumption profiles in power distribution systems – APSPDCL’. 2013 IEEE Int. Conf. on Computational Intelligence and Computing Research (ICCIC), December 2013, pp. 1–5, 26–28.
11. 11)
  - 8. Depuru, S.S.S.R., Wangn, L., Devabhaktuni, V., et al: ‘A hybrid neural network model and encoding technique for enhanced classification of energy consumption data’. Power and Energy Society Green Meeting, IEEE, July 2011, pp. 1–8.
12. 12)
  - 1. dos Angelos, E.W.S., Saavedra, O.R., Cortés, O.A.C., et al: ‘Detection and identification of abnormalities in customer consumptions in power distribution systems’, IEEE Trans. Power Deliv., 2011, 26, (4), pp. 2436–2442 (doi: 10.1109/TPWRD.2011.2161621).
13. 13)
  - 10. Everitt, B.S., Hothorn, T.: ‘A handbook of statistical analyses using R’ (Chapman & Hall/CRC, London, UK, 2013). Available at https://www.cran.r-project.org/web/packages/HSAUR/vignettes/.
14. 14)
  - 2. Nagi, J., Yap, K.S., Tiong, S.K., et al: ‘Non-technical loss detection for metered customers in power utility using support vector machines’, IEEE Trans. Power Deliv., 2010, 25, (2), pp. 1162–1171 (doi: 10.1109/TPWRD.2009.2030890).
15. 15)
  - 14. Guo, Z., Li, W., Lau, A., et al: ‘Detecting X-outliers in load curve data in power systems’, IEEE Trans. Power Syst., 2012, 27, (2), pp. 875–884 (doi: 10.1109/TPWRS.2011.2167022).

Conditional abnormality detection based on AMI data mining

References

Related content