Data Mining Based Partitioning of Dynamic Voltage Control Areas and Contingency Clustering

摘要: Partitioning of dynamic voltage control areas (DVCAs) and contingency clustering have attracted increasing attentions in power system planning. In this paper, we propose a data mining based method to recognize behavior patterns buses contingencies from offline simulation, so as identify DVCAs group contingencies. The ability index (VCAI) is defined firstly evaluate the effect bus with VAR injection subject contingency. By traversing all influencing factors VCAI, including contingency, controlling bus, observed pool VCAI obtained. Behavior are then extracted pool, respectively. Similarity metric for pattern affinity propagation algorithm adopted cluster contingencies, form clusters, Silhouette coefficient analysis applied determine proper scheme. proposed approach tested on modified NE 39-bus validate its effectiveness.