用电采集系统停上电事件的数据质量辨识技术  

Identification technology of power-off event data quality in electricity acquisition system

作　　者：王建雄 罗心仪 闫林 唐海国 马瑞[2] WANG Jianxiong;LUO Xinyi;YAN Lin;TANG Haiguo;MA Rui(State Grid Xiangtan Power,Changsha 410007,China;School of Electrical Engineering,Changsha University of Science and Technology,Changsha 410114,China)

机构地区：[1]国网湘潭供电公司,湖南湘潭411100 [2]长沙理工大学电气与信息工程学院,湖南长沙410114

出　　处：《电力科学与技术学报》2021年第5期187-194,共8页Journal of Electric Power Science And Technology

基　　金：国家自然科学基金(51277015);国网湖南省电力公司科技项目(5216A5160031)。

摘　　要：为解决智能配电网抢修服务平台中数据质量缺陷对预警抢修精准度产生负面影响的问题,提出一种针对用电信息采集系统停上电信息的数据质量处理方法。首先使用回归方法对数据整体异常率进行辨识,其次依据完整性、唯一性、一致性、准确性各项辨识指标对停上电数据缺陷进行辨识与处理,最后分析最新数据与历史数据之间的显著关系,辅助实现数据时效性辨识。该方法对源数据的质量进行辨识与处理,为后期平台建设中信息集成和故障研判的开发运行提供可靠的数据支撑。The data quality defects in the emergency repair service platform of intelligent distribution network have negative impacts on the accuracy of early warning and emergency repair.Under the background,a data quality processing method for power-off information of power consumption information acquisition system is proposed.Firstly,the regression method is utilized to identify the overall anomaly rate of the data.Secondly,the defects of the shutdown and power on data are identified and processed according to the identification indicators of integrity,uniqueness,consistency and accuracy.Finally,the significant relationship between the latest data and historical data is analyzed to help identify data timeliness.This method identifies and processes the quality of source data,and provides reliable data support for the development and operation of information integration and fault diagnosis in the later platform construction.

关 键 词：智能配网 数据质量 异常检测 停上电数据 用电采集系统 

分 类 号：TM732[电气工程—电力系统及自动化]