Feature selection by separability assessment of input spaces for transient stability classification based on neural networks

Abstract Power system transient-stability assessment based on neural networks can usually be treated as a two-pattern classification problem separating the stable class from the unstable class. In such a classification problem, the feature extraction and selection is the first important task to be carried out. A new approach of feature selection is presented using a new separability measure in this paper. Through finding the ‘inconsistent cases’ in a sample set, a separability index of input spaces is defined. Using the defined separability index as criterion, the breadth-first searching technique is employed to find the minimal or optimal subsets of the initial feature set. The numerical results based on extensive data obtained for the 10-unit 39-bus New England power system demonstrate the effectiveness of the proposed approach in extracting the ‘best combination’ of features for improving the quality of transient-stability classification.

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

[2]  Ka Wing Chan,et al.  Transient stability screening using artificial neural networks within a dynamic security assessment system , 1996 .

[3]  Adly Girgis,et al.  Input feature selection for real-time transient stability assessment for artificial neural network (ANN) using ANN sensitivity analysis , 1999, Proceedings of the 21st International Conference on Power Industry Computer Applications. Connecting Utilities. PICA 99. To the Millennium and Beyond (Cat. No.99CH36351).

[4]  Shiu Kit Tso,et al.  Deriving a transient stability index by neural networks for power-system security assessment , 1998 .

[5]  A. A. Fouad,et al.  Application of artificial neural networks in power system security and vulnerability assessment , 1994 .

[6]  K. L. Lo,et al.  An ANN-based multilevel classification approach using decomposed input space for transient stability assessment , 1998 .

[7]  Mayank Dave,et al.  INPUT-FEATURES BASED COMPARATIVE STUDY OF INTELLIGENT TRANSIENT STABILITY ASSESSMENT , 1997 .

[8]  Mu-Chun Su,et al.  Application of a novel fuzzy neural network to real-time transient stability swings prediction based on synchronized phasor measurements , 1999 .

[9]  Ibrahim El-Amin,et al.  Transient stability assessment using artificial neural networks , 1997 .

[10]  M. Damborg,et al.  Towards static-security assessment of a large-scale power system using neural networks , 1992 .

[11]  K. L. Lo,et al.  Fast real power contingency ranking using a counterpropagation network , 1998 .

[12]  M. Pai.  Energy function analysis for power system stability , 1989 .

[13]  M.A. El-Sharkawi,et al.  Comparative study of feature extraction techniques for neural network classifier [power system simulation] , 1996, Proceedings of International Conference on Intelligent System Application to Power Systems.

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

[15]  E. Hobson,et al.  Effectiveness of artificial neural networks for first swing stability determination of practical systems , 1994 .

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

[17]  Anjan Bose,et al.  On-line power system security analysis , 1992, Proc. IEEE.