Application of an Artificial Immune System to Predict Electrical Energy Fraud and Theft

Mauricio Volkweis Astiazara, Dante Augusto Couto Barone


This paper describes the application of an Artificial Immune System (AIS) to a real world problem: how to predict electricity fraud and theft. The field of Artificial Immune Systems is a recent branch of Computational Intelligence and has several possible applications, like pattern recognition, fault and anomaly detection, data analysis, agent-based systems and others. Although its potential, AIS still is not applied as much other techniques such as Artificial Neural Nets are. Various works compare AIS with other techniques using toy problems. But how much efficient is AIS when applied to a real world problem? How to model and adapt AIS to a specific domain problem? And how would be its efficiency compared to traditional algorithms? On the other hand, many companies perform activities that can be improved by Computational Intelligence, like predicting fraud. Electrical energy fraud and theft cause large financial loss to energy companies and indirectly to the whole society. This work applies AIS to predict electrical energy fraud and theft, analyzes efficiency and compares against other classifier methods. Data sample used to training and validation was provided by an electrical energy company. The results obtained showed that AIS has the best performance.


  1. Aisweb (2009). Basic immune inspired algorithms. <>. The Online Home of Artificial Immune Systems.
  2. Alexandrino, J., Cavalcanti, G., and Filho, E. (2009). Hybrid intelligent system clonart applied to face recognition. In Neural Networks, 2009. IJCNN 2009. International Joint Conference on, pages 102 -107.
  3. ANEEL (2008). Nota técnica 342/2008- sre/aneel. < nren2008338 342.pdf>. Ageˆncia Nacional de Energia Elétrica, Superintendeˆncia de Regulac¸a˜o Econoˆmica.
  4. Brun, A., Pinto, J., Pinto, A., Sauer, L., and Colman, E. (2009). Fraud Detection in Electric Energy Using Differential Evolution. In Intelligent System Applications to Power Systems, 2009. ISAP 7809. 15th International Conference on, pages 1 -5.
  5. Burnet, M. (1959). The clonal selection theory of acquired immunity. The Abraham Flexner Lectures. Cambridge University Press.
  6. CEEE (2011). A ceee distribuic¸a˜o. < Component/Controller.aspx?CC=1755>. Companhia Estadual de Distribuic¸a˜o de Energia Elétrica.
  7. Dasgupta, D. (2006). Advances in artificial immune systems. Computational Intelligence Magazine, IEEE, 1(4):40 -49.
  8. Dasgupta, D. and NI N˜O, L. F. (2008). Immunological Computation: Theory and Applications. CRC Press, Florida, US.
  9. De Castro, L. N. and Timmis, J. (2002). Artificial Immune Systems: A New Computational Intelligence Approach. Springer, London, UK.
  10. Depuru, S., Wang, L., and Devabhaktuni, V. (2011). Support vector machine based data classification for detection of electricity theft. In Power Systems Conference and Exposition (PSCE), 2011 IEEE/PES, pages 1 -8.
  11. Depuru, S., Wang, L., Devabhaktuni, V., and Gudi, N. (2010). Measures and setbacks for controlling electricity theft. In North American Power Symposium (NAPS), 2010, pages 1 -8.
  12. Dick, A. (1995). Theft of electricity-how uk electricity companies detect and deter. In Security and Detection, 1995., European Convention on, pages 90 -95.
  13. Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., and Witten, I. H. (2009). The weka data mining software: an update. SIGKDD Explor. Newsl., 11:10- 18.
  14. Hilaire, V., Koukam, A., and Rodriguez, S. (2008). An adaptative agent architecture for holonic multi-agent systems. ACM Trans. Auton. Adapt. Syst., 3:2:1-2:24.
  15. Kessentini, M., Vaucher, S., and Sahraoui, H. (2010). Deviance from perfection is a better criterion than closeness to evil when identifying risky code. In Proceedings of the IEEE/ACM international conference on Automated software engineering, ASE 7810, pages 113-122, New York, NY, USA. ACM.
  16. Kodaz, H., Babaoglu, I., and Iscan, H. (2009). Thyroid disease diagnosis using artificial immune recognition system (airs). In Proceedings of the 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human, ICIS 7809, pages 756-761, New York, NY, USA. ACM.
  17. Kohavi, R. (1995). A study of cross-validation and bootstrap for accuracy estimation and model selection. In Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2, pages 1137- 1143, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc.
  18. Monedero, i., Biscarri, F., León, C., Biscarri, J., and Millán, R. (2006). MIDAS: Detection of Non-technical Losses in Electrical Consumption Using Neural Networks and Statistical Techniques. In Gavrilova, M., Gervasi, O., Kumar, V., Tan, C., Taniar, D., Laganà, A., Mun, Y., and Choo, H., editors, Computational Science and Its Applications - ICCSA 2006, volume 3984 of Lecture Notes in Computer Science, pages 725-734. Springer Berlin / Heidelberg.
  19. Nasir, A. N. M., Selamat, A., and Selamat, H. (2009). An artificial immune system for recommending relevant information through political weblog. In Proceedings of the 11th International Conference on Information Integration and Web-based Applications and Services, iiWAS 7809, pages 420-424, New York, NY, USA. ACM.
  20. Queiroga, R. and Vareja˜o, F. (2005). AI and GIS together on energy fraud detection. In North American Transmission and Distribution Conference and Expo.
  21. Rodionov, A. S., Choo, H., and Nechunaeva, K. A. (2011). Framework for biologically inspired graph optimization. In Proceedings of the 5th International Conference on Ubiquitous Information Management and Communication, ICUIMC 7811, pages 11:1-11:4, New York, NY, USA. ACM.
  22. Smith, T. B. (2004). Electricity theft: a comparative analysis. Energy Policy, 32(18):2067 - 2076.
  23. Yu, H. (2008). Optimizing task schedules using an artificial immune system approach. In Proceedings of the 10th annual conference on Genetic and evolutionary computation, GECCO 7808, pages 151-158, New York, NY, USA. ACM.
  24. Yu, Y. (2011). Anomaly intrusion detection based upon an artificial immunity model. In Proceedings of the 49th Annual Southeast Regional Conference, ACM-SE 7811, pages 121-125, New York, NY, USA. ACM.
  25. Zhang, X.-f., Liu, J., and Ding, Y.-s. (2009). An immune coevolutionary algorithm based approach for optimization control of gas turbine. In Proceedings of the first ACM/SIGEVO Summit on Genetic and Evolutionary Computation, GEC 7809, pages 751-756, New York, NY, USA. ACM.

Paper Citation

in Harvard Style

Volkweis Astiazara M. and Augusto Couto Barone D. (2012). Application of an Artificial Immune System to Predict Electrical Energy Fraud and Theft . In Proceedings of the 14th International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-8565-10-5, pages 265-271. DOI: 10.5220/0003993902650271

in Bibtex Style

author={Mauricio Volkweis Astiazara and Dante Augusto Couto Barone},
title={Application of an Artificial Immune System to Predict Electrical Energy Fraud and Theft},
booktitle={Proceedings of the 14th International Conference on Enterprise Information Systems - Volume 1: ICEIS,},

in EndNote Style

JO - Proceedings of the 14th International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - Application of an Artificial Immune System to Predict Electrical Energy Fraud and Theft
SN - 978-989-8565-10-5
AU - Volkweis Astiazara M.
AU - Augusto Couto Barone D.
PY - 2012
SP - 265
EP - 271
DO - 10.5220/0003993902650271