基于电力营销大数据技术的反窃电检查应用分析  

Application Analysis of Anti-stealing Electricity Inspection Based on Power Marketing Big Data Technology

作　　者：崔亚洲 曹敬立 王玉君 佟鑫 陈丽晔 李明 CUI Ya-zhou;CAO Jing-li;WANG Yu-jun;TONG Xin;CHEN Li-ye;LI Ming(State Grid Jibei Electric Power Co.,Ltd.,Chengde Power Supply Company,Chengde 067000 China;State Grid Jibei Electric Power Co.,Ltd.,Marketing Department,Beijing 100045 China)

机构地区：[1]国网冀北电力有限公司承德供电公司,河北承德067000 [2]国网冀北电力有限营销部,北京100045

出　　处：《自动化技术与应用》2024年第5期131-134,162,共5页Techniques of Automation and Applications

摘　　要：由于目前方法存在精度低和性能差的问题,提出基于电力营销大数据技术的反窃电检查应用分析方法。该方法采用因子分析模型对电力营销大数据进行降维处理,并利用缺失数据填补算法对降维处理后的缺失电力营销数据进行填补,对线损波动率、电流差异曲线和台区线损三者之间存在的关联进行分析,以此判断是否存在窃电行为,完成反窃电检查。实验结果表明,所提方法可准确检测到窃电行为发生的时间和次数,F-Measure值高,表明所提方法的检测精度高、性能好。The current method has the problems of low accuracy and poor performance.An application analysis method of anti electricity theft inspection based on power marketing big data technology is proposed.This method uses the factor analysis model to reduce the dimension of power marketing big data,and uses the missing data filling algorithm to fill the missing power marketing data after dimension reduction,and analyzes the relationship between line loss fluctuation rate,current difference curve and station line loss.In order to judge whether there is electricity theft and complete the anti electricity theft inspection.The experimental results show that the proposed method can accurately detect the time and times of electricity theft,and the F-Measure value is high,which shows that the proposed method has high detection accuracy and good performance.

关 键 词：因子分析模型 数据降维 缺失数据填补算法 反窃电检查 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]