Combined genetic algorithms and neural-network approach for power-system transient stability evaluation

Citation
M. Moechtar et al., Combined genetic algorithms and neural-network approach for power-system transient stability evaluation, EUR T EL P, 9(2), 1999, pp. 115-122
Citations number
15
Language
INGLESE
art.tipo
Article
Categorie Soggetti
Eletrical & Eletronics Engineeing
Journal title
EUROPEAN TRANSACTIONS ON ELECTRICAL POWER
ISSN journal
1430-144X → ACNP
Volume
9
Issue
2
Year of publication
1999
Pages
115 - 122
Database
ISI
SICI code
1430-144X(199903/04)9:2<115:CGAANA>2.0.ZU;2-9
Abstract
As the electric power system grows in size and complexity with a large numb er of interconnections, the assessment of the transient stability of power systems became an extremely intricate and highly non-linear problem. Its so lution needs either numerical methods involving bulk computations or specif ic dedicated methods to analyse dynamic non-linens systems. Either method m ostly assesses, particularly in the post-fault condition, rite critical cle aring time (CCT). This parameter constitutes very complex functional relati onships between the pre-fault condition, type, and location of fault beside the clearance sequence. The available methods for evaluating such paramete r had been previously reviewed. New approaches using the locally-tuned radi al basis function (RBF) network, an artificial neural network (ANN) paradig m have been recently proposed The goal of this this paper is to develop met hods that can combine both neural networks and genetic algorithms (GA) into a common framework, and apply them to prediction problems. in the paper th e application of generic algorithms in selecting the input patterns for the RBF network is proposed. Description of this combined approach and the res ults of its application to two power systems, one for four-machine six-bus system and the other-for an existing system of North Sumatra, Indonesia, ar e also given in the paper The attainable results show that the performance of the RBF net work cart be maintained and improved in spite of less featur es in the input patterns.