Evolutionary Optimization of a One-Class Classification System for Faults Recognition in Smart Grids

Enrico De Santis, Gianluca Distante, Fabio Massimo Frattale Mascioli, Alireza Sadeghian, Antonello Rizzi

2014

Abstract

The Computational Intelligence paradigm has proven to be a useful approach when facing problems related to Smart Grids (SG). The modern SG systems are equipped with Smart Sensors scattered in the real-world power distribution lines that are able to take a fine-grained picture of the actual power grid state gathering a huge amount of heterogeneous data. Modeling and predicting general faults instances by means of processing structured patterns of faults data coming from Smart Sensors is a very challenging task. This paper deals with the problem of faults modeling and recognition on MV feeders in the real-world Smart Grid system that feeds the city of Rome, Italy. The faults recognition problem is faced by means of a One-Class classifier based on a modified k-means algorithm trained through an evolutive approach. Due to the nature of the specific data-driven problem at hand, a custom weighted dissimilarity measure designed to cope with mixed data type like numerical data, Time Series and categorical data is adopted. For the latter a Semantic Distance (SD) is proposed, capable to grasp semantical information from clustered data. A genetic algorithm is in charge to optimize system’s performance. Tests were performed on data gathered over three years by ACEA Distribuzione S.p.A., the company that manages the power grid of Rome.

References

  1. Afzal, M. and Pothamsetty, V. (2012). Analytics for distributed smart grid sensing. In Innovative Smart Grid Technologies (ISGT), 2012 IEEE PES, pages 1-7.
  2. Barakbah, A. and Kiyoki, Y. (2009). A pillar algorithm for k-means optimization by distance maximization for initial centroid designation. pages 61-68.
  3. Cai, Y. and Chow, M.-Y. (2009). Exploratory analysis of massive data for distribution fault diagnosis in smart grids. In Power Energy Society General Meeting, 2009. PES 7809. IEEE, pages 1-6.
  4. Cheng, V., Li, C.-H., Kwok, J. T., and Li, C.-K. (2004). Dissimilarity learning for nominal data. Pattern Recognition, 37(7):1471 - 1477.
  5. Dan Pelleg, A. M. (2000). X-means: Extending k-means with efficient estimation of the number of clusters. In Proceedings of the Seventeenth International Conference on Machine Learning, pages 727-734, San Francisco. Morgan Kaufmann.
  6. Davies, D. L. and Bouldin, D. W. (1979). A cluster separation measure. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-1(2):224-227.
  7. De Santis, E., Rizzi, A., Livi, L., Sadeghian, A., and Frattale Mascioli, F. M. (2014). Fault recognition in smart grids by a one-class classification approach. In 2014 IEEE World Congress on Computational Intelligence. IEEE.
  8. De Santis, E., Rizzi, A., Sadeghian, A., and Frattale Mascioli, F. M. (2013). Genetic optimization of a fuzzy control system for energy flow management in microgrids. In 2013 Joint IFSA World Congress and NAFIPS Annual Meeting, pages 418-423. IEEE.
  9. Del Vescovo, G., Livi, L., Frattale Mascioli, F. M., and Rizzi, A. (2014). On the Problem of Modeling Structured Data with the MinSOD Representative. International Journal of Computer Theory and Engineering, 6(1):9-14.
  10. Energy Information Admin. (2013). International Energy Outlook 2011 - Energy Information Administration, note=http://www.eia.gov/forecasts/ieo/index.cfm.
  11. European Technology Plat. (2013). The SmartGrids European Technology Platform, note=http://www.smartgrids.eu/ETPSmartGrids.
  12. Guikema, S. D., Davidson, R. A., and Haibin, L. (2006). Statistical models of the effects of tree trimming on power system outages. IEEE Transactions on Power Delivery, 21(3):1549-1557.
  13. He, Z., Xu, X., and Deng, S. (2011). Attribute value weighting in k-modes clustering. Expert Systems with Applications, 38(12):15365 - 15369.
  14. Huang, Z. (1998). Extensions to the k-means algorithm for clustering large data sets with categorical values.
  15. Khan, S. S. and Madden, M. G. (2010). A survey of recent trends in one class classification. In Coyle, L. and Freyne, J., editors, Artificial Intelligence and Cognitive Science, volume 6206 of Lecture Notes in Computer Science, pages 188-197. Springer Berlin Heidelberg.
  16. Laszlo, M. and Mukherjee, S. (2006). A genetic algorithm using hyper-quadtrees for low-dimensional k-means clustering. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 28(4):533-543.
  17. Müller, M. (2007). Dynamic time warping. In Information Retrieval for Music and Motion, pages 69-84. Springer Berlin Heidelberg.
  18. Ng, M. K., Junjie, M., Joshua, L., Huang, Z., and He, Z. (2007). On the impact of dissimilarity measure in kmodes clustering algorithm. IEEE Transactions on Pattern Analysis and Machine Intelligence.
  19. Quang, L. and Bao, H. (2004). A conditional probability distribution-based dissimilarity measure for categorial data. In Dai, H., Srikant, R., and Zhang, C., editors, Advances in Knowledge Discovery and Data Mining, volume 3056 of Lecture Notes in Computer Science, pages 580-589. Springer Berlin Heidelberg.
  20. Raheja, D., Llinas, J., Nagi, R., and Romanowski, C. (2006). Data fusion/data mining-based architecture for condition-based maintenance. International Journal of Production Research, 44(14):2869-2887.
  21. Rizzi, A., Mascioli, F. M. F., Baldini, F., Mazzetti, C., and Bartnikas, R. (2009). Genetic optimization of a PD diagnostic system for cable accessories. IEEE Transactions on Power Delivery, 24(3):1728-1738.
  22. Shahid, N., Aleem, S., Naqvi, I., and Zaffar, N. (2012). Support vector machine based fault detection amp; classification in smart grids. In Globecom Workshops (GC Wkshps), 2012 IEEE, pages 1526-1531.
  23. Tibshirani, R., Walther, G., and Hastie, T. (2001). Estimating the number of clusters in a data set via the gap statistic. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 63(2):411-423.
  24. Venayagamoorthy, G. K. (2011). Dynamic, stochastic, computational, and scalable technologies for smart grids. IEEE Computational Intelligence Magazine, 6(3):22- 35.
Download


Paper Citation


in Harvard Style

De Santis E., Distante G., Mascioli F., Sadeghian A. and Rizzi A. (2014). Evolutionary Optimization of a One-Class Classification System for Faults Recognition in Smart Grids . In Proceedings of the International Conference on Evolutionary Computation Theory and Applications - Volume 1: ECTA, (IJCCI 2014) ISBN 978-989-758-052-9, pages 95-103. DOI: 10.5220/0005124800950103


in Bibtex Style

@conference{ecta14,
author={Enrico De Santis and Gianluca Distante and Fabio Massimo Frattale Mascioli and Alireza Sadeghian and Antonello Rizzi},
title={Evolutionary Optimization of a One-Class Classification System for Faults Recognition in Smart Grids},
booktitle={Proceedings of the International Conference on Evolutionary Computation Theory and Applications - Volume 1: ECTA, (IJCCI 2014)},
year={2014},
pages={95-103},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005124800950103},
isbn={978-989-758-052-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Evolutionary Computation Theory and Applications - Volume 1: ECTA, (IJCCI 2014)
TI - Evolutionary Optimization of a One-Class Classification System for Faults Recognition in Smart Grids
SN - 978-989-758-052-9
AU - De Santis E.
AU - Distante G.
AU - Mascioli F.
AU - Sadeghian A.
AU - Rizzi A.
PY - 2014
SP - 95
EP - 103
DO - 10.5220/0005124800950103