Power system security assessment using neural networks: feature selection using Fisher discrimination

Author

Jensen, Craig A. ; El-Sharkawi, Mohamed A. ; Marks, Robert J., II

Author_Institution

Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA

Volume

16

Issue

4

fYear

2001

fDate

11/1/2001 12:00:00 AM

Firstpage

757

Lastpage

763

Abstract

One of the most important considerations in applying neural networks to power system security assessment is the proper selection of training features. Modern interconnected power systems often consist of thousands of pieces of equipment each of which may have an effect on the security of the system. Neural networks have shown great promise for their ability to quickly and accurately predict the system security when trained with data collected from a small subset of system variables. This paper investigates the use of Fisher´s linear discriminant function, coupled with feature selection techniques as a means for selecting neural network training features for power system security assessment. A case study is performed on the IEEE 50-generator system to illustrate the effectiveness of the proposed techniques

Keywords

learning (artificial intelligence); neural nets; power system analysis computing; power system interconnection; power system security; Fisher discrimination; Fisher linear discriminant function; IEEE 50-generator system; interconnected power systems; neural network training; neural networks; power system security assessment; training features selection; Data security; Feature extraction; Helium; Integrated circuit interconnections; Intelligent networks; Intelligent systems; Neural networks; Power system interconnection; Power system security; Propagation losses;

fLanguage

English

Journal_Title

Power Systems, IEEE Transactions on

Publisher

ieee

ISSN

0885-8950

Type

jour

DOI

10.1109/59.962423

Filename

962423