基于改进最大相关最小冗余判据的暂态稳定评估特选择.pdfVIP

第33 卷 第34 期 中 国 电 机 工 程 学 报 Vol.33 No.34 Dec.5, 2013 2013 年12 月5 日 Proceedings of the CSEE ©2013 Chin.Soc.for Elec.Eng. 179 0258-8013 (2013) 34-0179-08 TM 71 A 470 40 文章编号： 中图分类号： 文献标志码： 学科分类号： ⋅ 基于改进最大相关最小冗余判据的 暂态稳定评估特征选择 李扬，顾雪平 (华北电力大学电气与电子工程学院，河北省 保定市 071003) Feature Selection for Transient Stability Assessment Based on Improved Maximal Relevance and Minimal Redundancy Criterion LI Yang, GU Xueping (School of Electrical and Electronic Engineering, North China Electric Power University, Baoding 071003, Hebei Province, China) ABSTRACT: A new feature selection method based on an 进的mRMR 应用于特征选择。通过增量搜索算法得到一组 improved maximal relevance and minimal redundancy (mRMR) 嵌套的候选特征子集，并使用支持向量机分类器验证各候选 criterion was proposed for power system transient stability 特征子集的分类性能，选择得到具有最大分类正确率的特征 assessment. First, the standard mRMR was improved by 子集。基于新英格兰39 节点系统和IEEE 50 机测试系统的 introducing a weight coefficient in the evaluation criteria to 算例结果验证了所提特征选择方法的有效性。 refine the measurement of the features correlation and 关键词：暂态稳定评估；特征选择；最大相关最小冗余；支 redundancy. Then, the possible real-time information provided 持向量机；相量测量单元 by phasor measurement unit (PMU) considered, a group of system-level classification features were extracted from the 0 引言 power system operation parameters to build the original feature 电力系统暂态稳定评估(transient stability set, and the improved mRMR was employed to evaluate the assessment ，T