基于伪异常点辨识的关口电能表计量数据异常研究  

Abnormal Measurement Data of Gateway Energy Meter Based on Pseudo Outlier Identification

作　　者：孙一浩 肖先勇[1] 张文海 卢宏 胡文曦 SUN Yihao;XIAO Xianyong;ZHANG Wenhai;LU Hong;HU Wenxi(College of Electrical Engineering,Sichuan University,Chengdu 610065,Sichuan Province,China)

机构地区：[1]四川大学电气工程学院,四川省成都市610065

出　　处：《电网技术》2021年第11期4568-4576,共9页Power System Technology

摘　　要：关口电能表计量数据是贸易结算的根据,其数据质量的好坏对贸易结算的公平、公正性产生较大影响。针对现有计量数据异常辨识方法忽略了关口表异常状态与负荷动态行为之间差异性的缺陷,该文提出一种基于伪异常点辨识的关口电能表计量数据异常辨识方法。该方法考虑到用户动态用电行为具有潜在规律性,结合时间序列分解和自相关分析挖掘其内在周期性,并考虑负荷曲线的动态变化特点,采用用电相似度判据消除时间偏移影响,进而实现伪异常点准确辨识。基于西南某省电网关口表实测数据对该文方法有效性进行验证,结果表明该文方法能够有效辨识伪异常点,可满足工程实践需要。The metering data of the gateway energy meter is the basis of trade settlements, and its data quality has a great impact on the fairness and impartiality of trade settlements.Aiming at the ignorance of the difference between the abnormal states of the gateway energy meter and the dynamic behavior of the loads in the existing measurement data anomaly identification methods, this paper proposes a method for identifying the abnormality of the metering data of the gateway energy meter based on the identification of pseudo-outliers.This method considers the potential regularity of users’ dynamic electricity consumption behaviors and combines the time series decomposition and auto-correlation analysis to explore its inherent periodicity. And in view of the dynamic change characteristics of the load curve, the power similarity criterion is used to eliminate the influence of time offsets. In turn, the accurate identification of pseudo-outliers is realized.The validity of the proposed method is verified based on the measured data of the gateway energy meter of a power grid in Southwest China. The results show that the proposed method can effectively identify the pseudo-outliers and meet the needs of engineering practice.

关 键 词：关口电能表 数据异常 用户行为 伪异常点 

分 类 号：TM721[电气工程—电力系统及自动化]