基于知识发现技术的电网安全分析新思路  

A New Method for Analysis of Power System Security Based on Knowledge Discovery

作　　者：王同文[1] 管霖[1] 张尧[1] 

机构地区：[1]华南理工大学电力学院,广州510640

出　　处：《南方电网技术》2008年第4期23-27,共5页Southern Power System Technology

摘　　要：提出了一种层次型结构的知识发现技术并应用于电网在线安全分析,此模型采用稳态潮流信息作为输入。离线训练环节中,首先应用特征裁减技术以保留尽可能多的与电网安全强关联的信息为前提,实现了原始高维输入空间的有效降维。随后,运用知识发现技术在降维后的特征空间中提取了规则形式的电网安全评估知识。在线引用知识推理即可根据事实运行潮流信息快速判断电网的安全状态和薄弱环节。This article presents a new method for on-line analysis of power system security. The method with hierarchical structure and based on knowledge discovery, uses steady state load flow information as input, During off-line learning process, kernel-feature subsets of the steady state quantities are obtained through feature reduction process, and the power system security-related information is preserved as much as possible. The rules about power gird security states and weak points are then extracted in the kernel feature spaces by using the knowledge discovery technique. With the rules and the steady state load flow quantities, the information about power system security state and weak points can be quickly obtained by the on-line reasoning process.

关 键 词：电网安全评估 知识发现 特征选择 模式发现 

分 类 号：TM712[电气工程—电力系统及自动化] TP182[自动化与计算机技术—控制理论与控制工程]