Design of a neural adaptive power system stabilizer using dynamic back-propagation method

A neural adaptive power system stabilizer (NAPSS) is described in this paper. The proposed structure consists of a neuro-identifier to track and identify the nonlinear plant in real-time, and a neuro-controller to damp the power plant oscillations. These two subnetworks are trained in an on-line mode utilizing the dynamic back-propagation method. The performance and effectiveness of the proposed controller are demonstrated by simulation studies for a variety of operating conditions and disturbances.

[1]  Mohamed Mobarak,et al.  Contrast of Power System Stabilizer Performance on Hydro and Thermal Units , 1980, IEEE Transactions on Power Apparatus and Systems.

[2]  Charles Concordia,et al.  Concepts of Synchronous Machine Stability as Affected by Excitation Control , 1969 .

[3]  T.F. Laskowski,et al.  Concepts of power system dynamic stability , 1975, IEEE Transactions on Power Apparatus and Systems.

[4]  Y. H. Ku,et al.  Electric Power System Dynamics , 1983 .

[5]  Kumpati S. Narendra,et al.  Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[6]  D.c. Lee,et al.  A Power System Stabilixer Using Speed and Electrical Power Inputs-Design and Field Experience , 1981, IEEE Transactions on Power Apparatus and Systems.

[7]  Kumpati S. Narendra,et al.  Gradient methods for the optimization of dynamical systems containing neural networks , 1991, IEEE Trans. Neural Networks.

[8]  B. Widrow,et al.  The truck backer-upper: an example of self-learning in neural networks , 1989, International 1989 Joint Conference on Neural Networks.