摘要
随着科学技术的不断进步,不法分子窃电手段日趋专业化多样化,而传统的防窃电技术实时性及可行性较低。研究对运行中智能电能表用电信息的数据采集及特征提取,分析异常用电数据,应用机器学习的方法对特征值进行学习,并推导出用电异常的判断阈值,采用关联规则数据挖掘方法对独立检测的结果进行融合,从而实现窃电数据的挖掘。最后验证了模型建立的准确性,并推导出用电异常案例的甄别方法。
Because of the technology development, the means for stealing electricity becomes more specialized and diversified. The traditional anti-theft technology is less real-time and less feasible. This paper studied the intelligent diagnosis and characteristics extract method of electricity energy meter during online operation, analyzed the abnormal electricity consumption data, used machine learning abnormality judgment thresholds based on features, and used association rule data mining methods to fuse independent de-tection results, realizing the mining of power theft data. At last, this paper verified the accuracy of the model establishment, and deduced the screening method of power consumption abnormal cases.
作者
段晓萌
王爽
赵婷
丁徐楠
Duan Xiaomeng;Wang Shuang;Zhao Ting;Ding Xunan(China Electric Power Research Institute,Beijing 100192,China;State Grid Zhejiang Electric Power Co.,Ltd.,Hangzhou 310007,China)
出处
《电子技术应用》
2020年第10期47-50,共4页
Application of Electronic Technique
基金
国家电网公司科技项目(5442PD180022)。
