Prediction of the Transient Stability Boundary Using the Lasso

Author

Jiaqing Lv ; Pawlak, M. ; Annakkage, U.D.

Author_Institution

Electr. & Comput. Eng. Dept., Univ. of Manitoba, Winnipeg, MB, Canada

Volume

28

Issue

1

fYear

2013

fDate

Feb. 2013

Firstpage

281

Lastpage

288

Abstract

This paper utilizes a class of modern machine learning methods for estimating a transient stability boundary that is viewed as a function of power system variables. The simultaneous variable selection and estimation approach is employed yielding a substantially reduced complexity transient stability boundary model. The model is easily interpretable and yet possesses a stronger prediction power than techniques known in the power engineering literature so far. The accuracy of our methods is demonstrated using a 470-bus system.

Keywords

learning (artificial intelligence); power engineering computing; power system transient stability; 470-bus system; Lasso; machine learning methods; power engineering literature; prediction power; substantially reduced complexity transient stability boundary model; variable selection; Algorithm design and analysis; Power system stability; Prediction algorithms; Stability criteria; Transient analysis; Lasso algorithms; machine learning; shrinkage methods; transient stability boundary;

fLanguage

English

Journal_Title

Power Systems, IEEE Transactions on

Publisher

ieee

ISSN

0885-8950

Type

jour

DOI

10.1109/TPWRS.2012.2197763

Filename

6214585