Adaptive conventional power system stabilizer based on artificial neural network

Author

Kothari, M.L. ; Segal, Ravi ; Ghodki, Bhushan K.

Author_Institution

Dept. of Electr. Eng., IIT, Delhi, India

Volume

2

fYear

1996

fDate

8-11 Jan 1996

Firstpage

1072

Abstract

This paper deals with an artificial neural network (ANN) based adaptive conventional power system stabilizer (PSS). The ANN comprises an input layer, a hidden layer and an output layer. The input vector to the ANN comprises real power (P) and reactive power (Q), while the output vector comprises optimum PSS parameters. A systematic approach for generating training set covering a wide range of operating conditions is presented. The ANN has been trained using a back-propagation training algorithm. Investigations reveal that the dynamic performance of ANN based adaptive conventional PSS is quite insensitive to wide variations in loading conditions

Keywords

backpropagation; neural nets; power engineering computing; power system stability; reactive power; ANN; PSS; adaptive conventional power system stabilizer; artificial neural network; back-propagation training algorithm; dynamic performance; hidden layer; input layer; input vector; output layer; reactive power; real power; training set generation; Adaptive systems; Artificial neural networks; Nonlinear dynamical systems; Out of order; Power generation; Power system modeling; Power systems; State-space methods; Transfer functions; Voltage;

fLanguage

English

Publisher

ieee

Conference_Titel

Power Electronics, Drives and Energy Systems for Industrial Growth, 1996., Proceedings of the 1996 International Conference on

Conference_Location

New Delhi

Print_ISBN

0-7803-2795-0

Type

conf

DOI

10.1109/PEDES.1996.536419

Filename

536419