基于多模型融合的低压用户电能表运行误差在线监测方法研究  

Research on Online Monitoring Method of Low Voltage User Electric Energy Meter Operation Error Based on Multi-model Fusion

作　　者：杨婧 宋强 叶文波 付卿卿 YANG Jing;SONG Qiang;YE Wenbo;FU Qingqing(Guizhou Power Grid Co.,Ltd.,Guiyang 55000,Guizhou,China)

机构地区：[1]贵州电网有限责任公司,贵州贵阳550002

出　　处：《电力大数据》2024年第12期54-62,共9页Power Systems and Big Data

摘　　要：针对在运低压电能表异常检测准确率较低和运行误差偏差较大的实际问题,结合低压用户电能表只采集日冻结表码数据的实际情况,提出一种基于多模型融合的低压用户电能表运行误差在线监测方法。首先,基于离群点算法改进相关性分析模型,提升电能表异常识别能力;其次,通过岭回归估算台区可变损耗,改进运行误差分析模型,克服变量相关性和非线性因素对电能表运行误差值计算的不利影响;然后提出校验模型,深入挖掘用户日电量与台区线损间的关联关系;最后对所提模型进行融合综合评判,实现低压用户电能表误差的精准监测。采用某省真实数据进行算例分析,结果表明文中所提方法在低压用户电能表异常识别和误差监测等方面具有更高的准确性和鲁棒性。In order to address the practical issues of low anomaly detection accuracy and large operation error deviation of low-voltage electric energy meters in operation,combined with the actual situation that low-voltage user meters only collect daily frozen meter code data,this paper proposes an online monitoring method of low voltage user electric energy meter operation error based on multi-model fusion.Firstly,the correlation analysis model is improved based on the outlier detection algorithm to enhance the anomaly detection capability.Secondly,variable losses of distribution areas are estimated by ridge regression,and the operation error analysis model is improved to overcome the adverse effects of variable correlation and nonlinear factors on the calculation of the operation error values of the electric energy meters.Then,a review model is proposed to deeply explore the correlation between the user daily electricity consumption and the distribution area line loss.Finally,the proposed models are fused and comprehensively evaluated to achieve precise detection of abnormal low-voltage electricity meters.The case study,based on real data from a province,demonstrates that the method presented herein exhibits high accuracy and superior robustness in anomaly detection and error estimation.

关 键 词：运行误差 台区线损 损耗预测 相关性 校验模型 

分 类 号：TM933[电气工程—电力电子与电力传动]