基于数据关联性挖掘的电力系统暂态稳定态势感知研究

Research on power system transient stability situation awareness based on data correlation mining

电力系统暂态稳定态势感知对电网安全运行具有十分重要的意义,提出一种基于数据关联性挖掘的电力系统暂态稳定态势感知的方法。首先,构建多维系统暂态稳定特征集合,对系统当前暂态稳定性进行评估;然后,针对数据集构建维度高、数据挖掘难度大的问题,提出将系统划分为受端区域与送端区域,根据两区域间联络线上的潮流数据与系统暂态稳定特征构建挖掘数据库降低数据集维度;最后,根据挖掘结果提供的显式映射关系,分析重载线路潮流预警区间,通过提取、识别重载线路潮流的变化趋势来映射系统暂态稳定裕度变化情况。通过10机-39节点模型对所提方法进行了验证,结果表明所提方法能通过联络线上的潮流断面进行系统多维暂态稳定性特征表征,并指导系统运行状态调整,提高系统暂态稳定裕度。

The transient stability situation awareness of power system plays an important role in the safe operation of power grid.A method of transient stability situation awareness of power system based on data association relationship mining is proposed.Firstly,multi-dimensional system transient stability characteristics were constructed to evaluate the current transient stability of the system.In addition,in view of the high dimension of data set construction and the difficulty of data mining,the system was proposed to be divided into receiver region and sender region,and a mining database was constructed according to the power flow data on the contact line between the two regions and the system transient stability characteristics to reduce the dimension of the data set.Finally,according to the explicit mapping relationship provided by the mining results,the early-warning interval of heavy load line power flow is analyzed,and the change of transient stability margin of the system is mapped by extracting and identifying the change trend of heavy load line power flow.The results show that the proposed method can characterize the multi-dimensional transient stability of the system through the power flow section on the contact line,guide the adjustment of the system operating state,and improve the transient stability margin of the system.