A Novel Feature Selection Method for the Dynamic Security Assessment of Power Systems Based on Multi-Layer Perceptrons

Peyman Beyranvand, Cavit Fatih Kucuktezcan, Zehra Cataltepe, Veysel Murat Istemihan Genc
  • Peyman Beyranvand
    Istanbul Technical University, Turkey
  • Cavit Fatih Kucuktezcan
    Bahcesehir University, Turkey
  • Zehra Cataltepe
    Istanbul Technical University, Computer Engineering Department, Turkey


In this study, the effect of feature selection methods on the performance of multi-layer perceptrons used for the dynamic security assessment of electric power systems is investigated. The existence of many measurable parameters (features) characterizing the power system security status complicates the use of multi-layer perceptron both in terms of prediction accuracy and training time. In this paper, the dynamic security of a power system subject to a number of critical contingencies is assessed as the critical clearing time of any credible fault is predicted by a multi-layer perceptron. In addition to the study of two different feature selection methods, which are Minimum Redundancy Maximum Relevance (mRMR), and Regressional ReliefF (RReliefF), a novel multi-layer perceptron based feature selection method is proposed to be applied in the prediction of security indices. The performance of the feature selection methods on the dynamic security assessment is investigated on a 16-generator, 68-bus test system.


dynamic security assessment; feature selection; neural networks

Full Text:

Submitted: 2017-10-18 18:16:37
Published: 2018-03-29 15:53:50
Search for citations in Google Scholar
Related articles: Google Scholar


Y. V. Makarov, P. Du, S. Lu, T. B. Nguyen, X. Guo, J. W. Burns, J. F. Gronquist and M. A. Pai, "PMU-Based wide-area security assessment: concept, method, and implementation," IEEE T. Smart Grid, vol. 3, no. 3, pp. 1325-1332, 2012.

P. Sauer, K. L. Tomsovic and V. Vittal, "Dynamic Security Assessment," in The Electric Power Engineering Handbook, 2nd ed., Vol. 5, Chapter 15, London: Taylor and Francis, 2007.

H. W. Dommel and N. Sato, "Fast Transient Stability Solutions," IEEE T. Power Ap. Syst., vol. 91, no. 4, pp. 1643-1650, 1972.

A. A. Fouad and V. Vittal, Power System Transient Stability Analysis Using the Transient Energy Function Method. NJ: Prentice Hall, 1992.

M. P. Anderson and A. Bose, "A Probabilistic Approach to Power System Stability Analysis Power Engineering Review," IEEE T. Power Syst., vol. 3, no. 8, pp. 25-26, 1983.

C. F. Kucuktezcan and V. M. I. Genc, "Dynamic security assessment of a power system based on Probabilistic Neural Networks," in Proc. IEEE PES Innovative Smart Grid Technologies Conference Europe, Gotenburg, Sweden, 2010, pp. 1-6.

E. M. Voumvoulakis, A. E. Gavoyiannis and N. D. Hatziargyriou, "Application of Machine Learning on Power System Dynamic Security Assessment," in Proc. IEEE International Conference on Intelligent Systems Applications to Power Systems, Kaohsiung, Taiwan, 2007, pp. 1-6.

A. Hoballah and I. Erlich, "Real-time operation of deregulated electricity market: An integrated approach to dynamic stability assurance," in Proc. IEEE International Energy Conference and Exhibition, Manama, Bahrain, 2010, pp. 262-267.

J. Shang, J. Zhang, W. Zhao and J. Liu, "ANN based dynamic voltage security assessment for a practical power system," in Proc. IEEE International Power Engineering Conference, Singapore, 2007, pp. 794-798.

A. Al-Masri, M. Z. A. A.Kadir, H. Hizam, J. Jasni and N. Mariun, "Transient security assessment for power system stability: A review on artificial intelligence approach," in Proc. IEEE Student Conference on Research and Development, Malaysia, 2009, pp. 371-375.

K. S. Swarup, and K. V. Prasad Reddy, "Neural network based pattern recognition for power system security assessment," in Proc. IEEE International Conference on Intelligent Sensing and Information Processing, Piscataway, New Jersey, USA, 2005, pp. 234-239.

N. Srilatha, G. Yesuratnam and M. S. Deepthi, "RBF Neural Network approach for security assessment and enhancement," in Proc. IEEE PES T&D Conference and Exposition, Chicago, Illinois, USA, 2014, pp. 1-5.

C. F. Kucuktezcan and V. M. I. Genc, "A comparison between ANN based methods of critical clearing time estimation," in Proc. IEEE 8th International Electrical and Electronics Engineering, Bursa, Turkey, 2013. pp. 132-136.

S. P. Teeuwsen, I. Erlich and M. A. El-Sharkawi, "Robust oscillatory stability assessment for large interconnected power systems," in Proc. IEEE PES General Meeting, Denver, Colorado, USA, 2004, pp. 1871-1876.

H. Sawhney and B. Jeyasurya, "A feed-forward artificial neural network with enhanced feature selection for power system transient stability assessment," Ele. Pow. Sys. Res., vol. 76, no. 12, pp. 1047-1054, 2006.

K. R. Niazi, C. M. Arora and S. L. Surana, "Power system security evaluation using ANN: feature selection using divergence," Ele. Pow. Sys. Res., vol. 69, no. 2, pp. 161-167, 2004.

C. Jensen, M. El-Sharkawi and R. J. Marks, "Power system security assessment using neural networks: feature selection using Fisher discrimination," IEEE T. Power Syst., vol. 16, no. 4, pp. 757-763, 2001.

H. Peng, F. Long and C. Ding, "Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy," IEEE T. Pattern Anal., vol. 27, no. 8, pp. 1226-1238, 2005.

M. Robnik-Ĺ ikonja, and I. Kononenko, "An adaptation of Relief for attribute estimation in regression," in Proc. IEEE International Conf. on Machine Learning, Nashville, Tennessee, USA, 1997, pp. 296-304.

J. N. Fidalgo and J. Lopes, "ANN sensitivity analysis for identification of relevant features in security assessment," in Proc. IEEE Power Tech Proceedings, Porto, Portugal, 2001, pp. 1-6.

G. Rogers, Power System Oscillations. Norwell, MA: Kluwer, 2000.

DSATools™ Dynamic Security Assessment Software, by Powertech Labs Inc. (2014) [Online]. Available: http://www.dsatools.com

Abstract views:


Copyright (c) 2018 International Journal of Intelligent Systems and Applications in Engineering

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
© AtScience 2013-2018     -     AtScience is a registered trademark property of AtScience.