论文信息 - Prediction of the Transient Stability Boundary Using the Lasso

Prediction of the Transient Stability Boundary Using the Lasso

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.

[1] Xueping Gu,et al. Neural-Network Security-Boundary Constrained Optimal Power Flow , 2011, IEEE Transactions on Power Systems.

[2] Louis Wehenkel,et al. Automatic Learning Techniques in Power Systems , 1997 .

[3] R. Tibshirani. Regression Shrinkage and Selection via the Lasso , 1996 .

[4] R. Tibshirani,et al. PATHWISE COORDINATE OPTIMIZATION , 2007, 0708.1485.

[5] H. Zou. The Adaptive Lasso and Its Oracle Properties , 2006 .

[6] B. Jayasekara,et al. Derivation of an Accurate Polynomial Representation of the Transient Stability Boundary , 2006, IEEE Transactions on Power Systems.

[7] Udaya Annakkage,et al. Accurate prediction of damping in large interconnected power systems with the aid of regression analysis , 2009, 2009 IEEE Power & Energy Society General Meeting.

[8] M.A. El-Sharkawi,et al. Support vector machines for transient stability analysis of large-scale power systems , 2004, IEEE Transactions on Power Systems.

[9] D. Ruppert. The Elements of Statistical Learning: Data Mining, Inference, and Prediction , 2004 .

[10] Zygmunt Hasiewicz,et al. On Nonparametric Identification of Wiener Systems , 2007, IEEE Transactions on Signal Processing.