Neural-net based calculation of voltage dips at maximum angular swing in direct transient stability analysis

Abstract In heavily stressed power systems, post-fault transient voltage dips can lead to undesired tripping of industrial drives and large induction motors. The lowest transient voltage dips occur when fault clearing times are less than critical ones. In this paper, we propose a new iterative analytical methodology to obtain more accurate estimates of voltage dips at maximum angular swing in direct transient stability analysis. We also propose and demonstrate the possibility of storing the results of these computations into the associative memory (AM) system, which exhibits remarkable generalization capabilities. Feature-based models stored in the AM cab utilized for fast and accurate prediction of the location, duration and the amount of worst voltage dips, thereby avoiding the need and cost for lengthy time-domain simulations. Numerical results obtained using the example of the New England power system are presented to illustrate our approach.

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

[2]  Tharam S. Dillon.  Artificial neural network applications to power systems and their relationship to symbolic methods , 1991 .

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

[4]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[5]  D. J. Sobajic,et al.  Real-time security monitoring of electric power systems using parallel associative memories , 1990, IEEE International Symposium on Circuits and Systems.

[6]  M. Pavella,et al.  Direct methods for studying dynamics of large-scale electric power systems - A survey , 1985, Autom..

[7]  Felix F. Wu,et al.  Dynamic security regions of power systems , 1982 .

[8]  Hiroyuki Mori,et al.  An artificial neural-net based technique for power system dynamic stability with the Kohonen model , 1991 .

[9]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[10]  Vijay Vittal,et al.  Transient stability analysis of stressed power systems using the energy function method , 1988 .

[11]  Dejan J. Sobajic,et al.  Combined use of unsupervised and supervised learning for dynamic security assessment , 1991 .

[12]  Dejan J. Sobajic,et al.  Neural-net based unstable machine identification using individual energy functions , 1991 .

[13]  R J. Thomas,et al.  ON-LINE SECURITY SCREENING USING AN ARTIFICIAL NEURAL NETWORK , 1990 .

[14]  A. S. Debs.  Voltage dip at maximum angular swing in the context of direct stability analysis , 1990 .

[15]  Dejan J. Sobajic,et al.  Current Status of Artificial Neural Network Applications to Power Systems in the United States (電力・エネルギ-分野におけるニュ-ラルネットワ-ク応用 ) , 1991 .

[16]  V. Vittal,et al.  Direct Transient Stability Assessment with Excitation Control , 1989, IEEE Power Engineering Review.