基于数据驱动的台区户-变关系核查方法研究

Research on the method of transformer-meter relationship verification based on data-driven

经济的不断发展使得低压配电网的规模日趋庞大,但同时暴露了台区线损管理中的一些问题。台区的户-变隶属关系错误是导致台区线损异常的主要原因之一。为了弥补检修人员需要对所有用户逐户排查方法的缺陷,提出了一种基于数据驱动的台区户-变隶属关系核查的方法。模型利用台区供、用电的历史数据,以台区折算后日线损率最稳定为优化目标,采用长时间尺度下滚动优化的方式,最终给出疑似发生户-变隶属关系错误的用户。最后通过两个实际的案例进行分析,结果表明该模型能够给出疑似档案错误的用户集合,实现台区户-变隶属关系核查的高效化。

The continuous development of the economy has made the scale of the low⁃voltage distribution network increasingly large,but at the same time exposes some problems in the manage⁃ment of the line loss in the transformer areas.The fault of transform⁃er⁃meter relationship in transformer areas is one of the main causes of abnormal line loss.In order to make up for the shortcomings of maintenance personnel who need to check the methods of all users on a case⁃by⁃case basis,a data⁃driven method for verifying the trans⁃former⁃meter relationship of the district is proposed.The model us⁃es the historical data of power supply and power consumption in the transformer area,and optimizes the daily line loss rate of the trans⁃former area as the optimization target,and adopts the method of roll⁃ing optimization under the long⁃term scale,and finally gives the us⁃er who is suspected to have a transformer⁃meter relationship error.Finally,by using two actual case studies,the result shows that the model can give a set of users with suspected file errors,and realizes the efficiency of the transformer⁃meter relationship verification。