Automatic Learning Approaches for On-Line Transient Stability Preventive Control of the Hydro-Quebec System

Abstract This paper explores potential of the decision tree method for tacking the on-line transient stability strategy of the Hydro-Quebec power system. The specifics of this system are first described along with its very structure which makes transmission capacity strongly dependent on transient stability limits. Decision trees are then properly adjusted to this intricate real world problem, in particular by using composite attributes, decomposition of the problem into subproblems, and techniques able to reduce the number of dangerous (overoptimistic) diagnostics. Further, the resulting trees are compared with LIMSEL, i.e. the transient stability software presently used at Hydro-Quebec; they are found able to provide indeed an interesting alternative thanks to their intrinsic assets. Finally, limitations of decision trees are discussed and the interest to combine them with other, complementary automatic learning approaches is suggested. This latter issue is explored in a companion paper

[1]  Dagmar Niebur,et al.  Artificial Neural Networks for Power Systems - A Literature Survey , 1993 .

[2]  J.-C. Chow,et al.  Screening power system contingencies using a back-propagation trained multiperceptron , 1989, IEEE International Symposium on Circuits and Systems,.

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

[4]  J. Ross Quinlan,et al.  Learning Efficient Classification Procedures and Their Application to Chess End Games , 1983 .

[5]  Louis Wehenkel,et al.  Fuzzy Decision Tree Induction for Power System Security Assessment , 1995 .

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

[7]  Louis Wehenkel,et al.  Coupling of K-NN with decision trees for power system transient stability assessment , 1995, Proceedings of International Conference on Control Applications.

[8]  Louis Wehenkel,et al.  Decision tree based transient stability method a case study , 1994 .

[9]  Louis Wehenkel.  Machine-Learning Approaches to Power-System Security Assessment , 1997, IEEE Expert.

[10]  Lawrence Davis,et al.  Hybridizing the Genetic Algorithm and the K Nearest Neighbors Classification Algorithm , 1991, ICGA.

[11]  Louis Wehenkel,et al.  Automatic Learning Approaches for On-Line Transient Stability Preventive Control of the Hydro-Quebec System: Part II. A toolbox combining decision trees with neural nets and nearest neighbor classifiers otpimized by genetic algorithms , 1995 .

[12]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[13]  Louis Wehenkel,et al.  Machine learning, neural networks and statistical pattern recognition for voltage security: a comparative study , 1994 .

[14]  R.J. Marks,et al.  Preliminary results on using artificial neural networks for security assessment (of power systems) , 1989, Conference Papers Power Industry Computer Application Conference.