基于聚类分析的电力系统暂态稳定故障筛选

POWER SYSTEM TRANSIENT STABILITY CONTINGENCY SCREENING BASED ON CLUSTERING ANALYSIS

提出了一种基于聚类分析的电力系统暂态稳定故障筛选方法。该方法建立在模糊C-均值(FCM)算法和矢量量化(VQ)方法的基础上,结合了两种聚类分析方法的优点,通过选择故障后系统的能量裕度作为特征变量之一,有效提高了故障筛选的准确性。采用新英格兰10机39节点系统和IEEE50机145节点系统进行的测试证明了该方法的有效性。

A power system transient stability contingency screening method is put forward. Based on fuzzy C-means （FCM） and vector quantization （VQ） method, this method integrates the advantages of two clustering analysis methods. By choosing the energy margin of post-fault system as one of contingency features, the contingency screening accuracy is improved efficiently. Case studies on New England 10-machine 39-bus system and IEEE 50-machine 145-bus system show that the proposed method is effective.