Optimal tuning of power system stabilizer parameters using Population-Based Incremental Learning

Author

Folly, K.A.

Author_Institution

Univ. of Cape Town, Cape Town

fYear

2005

fDate

27-30 June 2005

Firstpage

1

Lastpage

5

Abstract

This paper uses a simplified version of GAs called Population-Based Incremental Learning (PBIL) to optimally tune the parameters of the power system stabilizers (PSSs) for a multi- machine system. The technique combines aspects of GAs and competitive learning-based artificial neural network. The issue of optimally tuning the parameters of the PSS is converted into an optimization problem that is solved via the PBIL algorithm. Simulation results are presented to show the effectiveness of the PBIL based PSSs.

Keywords

learning (artificial intelligence); neural nets; power engineering computing; power system stability; competitive learning-based artificial neural network; multimachine system; population-based incremental learning; power system stabilizer; Artificial neural networks; Control systems; Genetic algorithms; Genetic mutations; Nuclear power generation; Power system modeling; Power system simulation; Power system stability; Power systems; Tuning; Genetic Algorithms; Low-frequency oscillations; Parameter optimization; Population-based incremental learning; Power system Stabilizer;

fLanguage

English

Publisher

ieee

Conference_Titel

Power Tech, 2005 IEEE Russia

Conference_Location

St. Petersburg

Print_ISBN

978-5-93208-034-4

Electronic_ISBN

978-5-93208-034-4

Type

conf

DOI

10.1109/PTC.2005.4524679

Filename

4524679