基于模式发现的电力系统稳定评估和规则提取.pdfVIP

第 27 卷 第 19 期 中 国 电 机 工 程 学 报 Vol.27 No.19 Jul. 2007 2007 年 7 月 Proceedings of the CSEE ©2007 Chin.Soc.for Elec.Eng. 0258-8013 (2007) 19-0025-07 TM714 A 470 40 文章编号： 中图分类号： 文献标识码： 学科分类号： ⋅ 基于模式发现的电力系统稳定评估和规则提取 王同文，管 霖 (华南理工大学电力学院，广东省 广州市 510640) Power System Stability Assessment and Rule Extraction Based on Pattern Discovery WANG Tong-wen, GUAN Lin (College of Electric Power, South China University of Technology, Guangzhou 510640, Guangdong Province, China) ABSTRACT: A novel heuristic stability assessment scheme 使电力系统越来越接近其稳定极限运行，导致近年 was proposed based on the objective of identifying power 来国内外电网稳定破坏和重大事故频繁发生[1-2] 。在 system stability weak-point according to SCADA data. 实际电网运行监控中，一方面SCADA系统采集到的 Residual analysis and recursive partitioning algorithm were 运行数据日益丰富和完善，数量庞大且不断更新。 applied to discover the significant patterns in the operational 另一方面则缺少有效的技术从这些海量数据中快 data that compose feature space. With patterns as samples, a 速筛选出反映稳定水平及其边界的关键信息，并协 decision tree based rule extraction method was proposed to generate production rules for stability classification. According 助运行人员实现稳定水平和薄弱环节的初步判别。 to application and tests of the proposed scheme in the New 基于样本的数据挖掘和知识工程相关技术是目前 England 10-machine power system, the rules obtained show 针对上述需求最有前景的理论和方法[3] 。 good classification and generalization ability and through fast 目前相关方向的研究非常薄弱。多数暂态稳定 rule reasoning, fault locations with low stability level can be