基于概率不安全指标的实时故障筛选策略  

Strategies of real time contingency screening based on probabilistic insecurity index

作　　者：刘怀东[1] 马林[1] 王曦冉[2] 崔晓君[1] 吴贺[1] 

机构地区：[1]天津大学电气与自动化工程学院,天津300072 [2]国网浙江省电力公司经济技术研究院,浙江杭州310007

出　　处：《电力系统保护与控制》2015年第16期16-21,共6页Power System Protection and Control

摘　　要：为了解决电力系统面临的故障筛选问题,提出了一种改进的故障筛选策略。利用动态安全域的分析方法,结合实用概率不安全指标作为对故障筛选排序的依据,将致命性故障与非致命性故障分别建模,以故障可能造成的损失作为目标函数进行排序。分析多种故障分类下系统面临的不同情况,综合考虑全局概率分布,通过权值控制反映系统安全性指标,通过目标函数反映经济性指标,采用离线计算在线应用的方式得到故障综合筛选情况。采用IEEE10机39节点系统算例进行验证性排序,结果符合事实依据,该方法鲁棒性好,对实际故障隐患的处理指导性强。In order to solve the problem of contingency screening that power system faces, an improved contingency screening strategy is proposed. This paper uses the analysis method of dynamic security domain, and practical probabilistic insecurity index is a basis for contingency screening and ranking. Building models depend on fatal contingency or not, then it takes the loss that may be caused by the failure as the objective function to rank. This method analyses different circumstances under a variety of fault classification that the system faces and considers the overall probability distribution, reflects system security by weight control and economy index by objective function. Then it uses the method of off-line calculation and online application to get the results of contingency screening. Tests on the New England 10-generator 39-bus test system show that the results accord with the factual basis, and it has good robustness and strong guidance for the processing of actual hidden faults.

关 键 词：电力系统 概率不安全指标 BP神经网络 损失模型 故障筛选 

分 类 号：TM73[电气工程—电力系统及自动化]