摘要
针对常见的窃电现象及方法,分析了窃电方法的本质特征;利用鱼骨图表示特征参量的方法建立了多维度电参量的相关特征参量集合,并构建了多维度电参量的窃电本质特征模型来揭示窃电方法、本质特征和特征参量三者的关联关系;提出了基于大数据的防窃电模型与方法,包括数据预处理、大数据的防窃电结构化模型;最后通过用电信息系统采集的数据验证了本文结构化防窃电模型与方法的有效性。本文研究成果可为解决大数据条件下窃电行为监控问题提供有效的途径和方法。
The multidimensional essential characteristics of common methods of electricity theft are first analyzed.Their characteristic parameters are represented by means of fishbone diagrams,and the relevant electrical characteristic parameter sets are established. Subsequently,a model of the essential characteristics based on multidimensional electrical parameters is built; this can reveal the relationship between electricity theft methods,their essential characteristics and characteristic parameters. An electricity anti-theft model and method based on big data technology is proposed,including data preprocessing and an electricity anti-theft structural model. Finally,the validity of the proposed structured electricity anti-theft model and method is verified by experiments based on data on site.This work provides an effective way to solve the problem of electricity theft and its monitoring under big data conditions.
作者
吴迪
王学伟
窦健
张海龙
章宏伟
WU Di;WANG XueWei;DOU Jian;ZHANG HaiLong;ZHANG HongWei(College of Information Science and Technology,Beijing University of Chemical Technology,Beijing 100029;China Electric Power Research Institute,Beijing 100085,China)
出处
《北京化工大学学报（自然科学版）》
CAS
CSCD
北大核心
2018年第6期79-86,共8页
Journal of Beijing University of Chemical Technology(Natural Science Edition)
基金
国家自然科学基金(51577006)
关键词
大数据
防窃电
结构化模型
big data
electricity anti-theft
structural model
