Artificial neural network based identification of dynamic equivalents

Abstract This paper presents techniques for identifying coherent generators using artificial neural networks. The proposed method is used to identify three types of equivalents, parochial, local and global. Identification is based on the adaptive pattern recognition concept and four features which are considered to be central to the phenomenon of coherency. An algorithm based on an algebraic characterization of global equivalents using an inertially weighted synchronizing torque matrix is proposed. The method is applied to the well-known 39-bus New England system, taken as a test example.

[1]  Yoh-Han Pao,et al.  Learning control with neural networks , 1989, Proceedings, 1989 International Conference on Robotics and Automation.

[2]  Joe H. Chow,et al.  Area decomposition for electromechanical models of power systems , 1980, Autom..

[3]  A.H. El-Abiad,et al.  Dynamic equivalents using operating data and stochastic modeling , 1976, IEEE Transactions on Power Apparatus and Systems.

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

[5]  Albert Chang,et al.  Power System Dynamic Equivalents , 1970 .

[6]  O. T. Tan,et al.  Neural-net based real-time control of capacitors installed on distribution systems , 1990 .

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

[8]  Fred C. Schweppe,et al.  Distance Measures and Coherency Recognition for Transient Stability Equivalents , 1973 .

[9]  Robin Podmore,et al.  Identification of Coherent Generators for Dynamic Equivalents , 1978, IEEE Transactions on Power Apparatus and Systems.

[10]  E. M. Gulachenski,et al.  Testing of the Modal Dynamic Equivalents Technique , 1978, IEEE Transactions on Power Apparatus and Systems.

[11]  Mark W. White,et al.  Neural network applications for data interpretation and diagnostic analysis , 1989 .

[12]  Felix F. Wu,et al.  COHERENCY IDENTIFICATION FOR POWER SYSTEM DYNAMIC EQUIVALENTS. , 1978 .

[13]  J. M. Undrill,et al.  Construction of Power System lectromechanical Equivalents by Modal Analysis , 1971 .

[14]  Yoh-Han Pao,et al.  Unsupervised/supervised learning concept for 24-hour load forecasting , 1993 .

[15]  Takashi Hiyama,et al.  Identification of coherent generators using frequency response , 1981 .

[16]  B. Spalding,et al.  Coherency recognition for transient stability studies using singular points , 1977, IEEE Transactions on Power Apparatus and Systems.

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

[18]  R. Bruce Shipley,et al.  A Study of Stability Equivalents , 1969 .

[19]  H. Rudnick,et al.  Power-system dynamic equivalents:coherency recognition via the rate of change of kinetic energy , 1981 .

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

[21]  Robert J. Thomas,et al.  Coherency identification for large electric power systems , 1982 .

[22]  Robert J. Marks,et al.  Electric load forecasting using an artificial neural network , 1991 .

[23]  Yao-nan Yu,et al.  Estimation of External Dynamic Equivalents of a Thirteen-Machine System , 1981, IEEE Transactions on Power Apparatus and Systems.