Title :
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
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;
Journal_Title :
Power Systems, IEEE Transactions on
DOI :
10.1109/TPWRS.2012.2197763
