Volume no :2, Issue no: 2, June (2015)

International Journal of Applied Mathematics and Machine Learning

FEATURE SELECTION BY KERNELIZED FUZZY ROUGH SETS FOR TRANSIENT STABILITY ASSESSMENT BASED ON GAUSSIAN PROCESS

Author's: Yang Li and Changjiang Wang
Pages: [159] - [175]
Received Date: April 6, 2015
Submitted by: Jianqiang Gao.
DOI: http://dx.doi.org/10.18642/ijamml_7100121484

Abstract

Feature selection of input features is the key issue for pattern recognition-based transient stability assessment (TSA) methods. Considering the possible real-time information provided by phasor measurement units, a group of system-level classification features are firstly extracted from the power system operation condition to construct the original feature set. Then kernelized fuzzy rough sets (KFRS) are used to select the near-optimal feature subset, and Gaussian process is finally employed to test the classification ability of the selected features. The effectiveness of the proposed method is validated by the simulation results on the New England 39-bus test system.

Keywords

transient stability assessment, feature selection, fuzzy rough sets, Gaussian process, phasor measurement unit.