采用线性决策树的暂态稳定规则提取-中国电机工程学报.PDF

第31 卷 第34 期 中 国 电 机 工 程 学 报 Vol.31 No.34 Dec.5, 2011 2011 年12 月5 日 Proceedings of the CSEE ©2011 Chin.Soc.for Elec.Eng. 61 文章编号：0258-8013 (2011) 34-0061-07 中图分类号：TM 71 文献标志码：A 学科分类号：470·40 采用线性决策树的暂态稳定规则提取 孙宏斌，王康，张伯明，赵峰 ( 电力系统及发电设备控制和仿真国家重点实验室(清华大学电机系) ，北京市 海淀区 100084) Rule Extraction in Transient Stability Study Using Linear Decision Trees SUN Hongbin, WANG Kang, ZHANG Boming, ZHAO Feng (State Key Lab of Control and Simulation of Power Systems and Generation Equipments (Dept. of Electrical Engineering, Tsinghua University), Haidian District, Beijing 100084, China) ABSTRACT: For the purpose of improving the performance 关键词：电力系统；安全稳定；线性决策树；支持样本；精 of automatic extracted fine-rule, a method of linear decision 细规则；线性分类器 tree based on support samples was proposed for rule extraction 0 引言 in this paper. Support samples, which are located in the vicinity of real stability boundary and used as input of decision tree, are 电力系统传统运行规则依赖于人工经验，且相 selected by distance method. Linear decision tree based on 对固定，难以满足电网发展提出的新要求。为了制 linear classifiers, which were generated by linear 定合理可行且能较快更新的运行规则，文献[1]提出 transformation, was proposed to obtain integrated attributes operation rules for power system security and stability study. 了电力系统精细规则的概念，通过知识发现技术制 Case study was carried out in one-machine infinite bus system 定电力系统运行规则，具有精细化、智能化的特点。 as well as IEEE 39-bus system. Results show that, rules 文献[2]阐述了“计算机归纳精细规则”在智能控制 generated by the proposed method are small in structure, have [3-5]