On-line supervised learning for dynamic security classification using probabilistic neural networks

This paper addresses the problem of dynamic security classification of electric power systems using multiclass pattern recognition. In particular, on-line supervised learning using probabilistic neural networks is applied. The various patterns are recognized by calculating probabilities of belonging to each class. These probabilities are used in a subsequent decision-making stage to achieve classification. The learning of each class can be performed in parallel. Results regarding performance of the proposed pattern recognition tested on the dynamic security of an actual island power system are presented and discussed.

[1]  Donald F. Specht,et al.  Probabilistic neural networks , 1990, Neural Networks.

[2]  George K. Papakonstantinou,et al.  Mixture density estimation based on Maximum Likelihood and test statistics , 1999 .

[3]  Hans G. C. Tråvén,et al.  A neural network approach to statistical pattern classification by 'semiparametric' estimation of probability density functions , 1991, IEEE Trans. Neural Networks.

[4]  Christian Rehtanz,et al.  Electric Power System's Stability Assessment and Online-Provision of Control Actions Using Self-Organizing Maps , 2001, IWANN.

[5]  Bruno Meyer,et al.  New trends and requirements for dynamic security assessment , 1997 .

[6]  M. P. Dave,et al.  ANN for transmission system static security assessment , 2002 .

[7]  Louis Wehenkel,et al.  Automatic Learning Techniques in Power Systems , 1997 .

[8]  N. D. Hatziargyriou,et al.  On-Line Preventive Dynamic Security of Isolated Power Systems Using Decision Trees , 2002, IEEE Power Engineering Review.

[9]  Nikos A. Vlassis,et al.  A kurtosis-based dynamic approach to Gaussian mixture modeling , 1999, IEEE Trans. Syst. Man Cybern. Part A.

[10]  Roy L. Streit,et al.  Maximum likelihood training of probabilistic neural networks , 1994, IEEE Trans. Neural Networks.

[11]  R. Grondin,et al.  Time-varying contingency screening for dynamic security assessment using intelligent-systems techniques , 2001, PICA 2001. Innovative Computing for Power - Electric Energy Meets the Market. 22nd IEEE Power Engineering Society. International Conference on Power Industry Computer Applications (Cat. No.01CH37195).

[12]  Mohamed A. El-Sharkawi,et al.  Large scale dynamic security screening and ranking using neural networks , 1997 .

[13]  A. E. Gavoyiannis,et al.  On-line dynamic security classification using probavliistic neural networks , 2001 .

[14]  Bruno O. Shubert,et al.  Random variables and stochastic processes , 1979 .

[15]  Richard S. Sutton,et al.  Online Learning with Random Representations , 1993, ICML.

[16]  Mohamed A. El-Sharkawi,et al.  Neural networks and support vector machines applied to power systems transient stability analysis , 2001 .

[17]  Dejan J. Sobajic,et al.  Artificial Neural-Net Based Dynamic Security Assessment for Electric Power Systems , 1989, IEEE Power Engineering Review.

[18]  A. Valette,et al.  An intelligent system for advanced dynamic security assessment , 2002, Proceedings. International Conference on Power System Technology.

[19]  R. V. Mises,et al.  Mathematical Theory of Probability and Statistics , 1966 .

[20]  N. D. Hatziargyriou,et al.  Dynamic security evaluation functions in the more care project , 2002 .

[21]  João Peças Lopes,et al.  Artificial intelligence techniques applied to dynamic security assessment of isolated systems with high wind power penetration , 2000 .

[22]  John G. Proakis,et al.  Probability, random variables and stochastic processes , 1985, IEEE Trans. Acoust. Speech Signal Process..

[23]  A. E. Gavoyiannis,et al.  Combined support vector classifiers using fuzzy clustering for dynamic security assessment , 2001, 2001 Power Engineering Society Summer Meeting. Conference Proceedings (Cat. No.01CH37262).

[24]  Hua Li,et al.  Development of BCU classifiers for on-line dynamic contingency screening of electric power systems , 1999 .

[25]  V. Brandwajn,et al.  Severity indices for contingency screening in dynamic security assessment , 1997 .

[26]  George K. Papakonstantinou,et al.  Mixture Density Estimation Based on Maximum Likelihood and Sequential Test Statistics , 1999, Neural Processing Letters.

[27]  Louis Wehenkel,et al.  Decision tree approach to power systems security assessment , 1993 .