摘要
传统异常用电行为识别方法浪费大量人力与物力,且准确率较低、效果不佳,本文在大数据背景下,提出一种基于相似性搜索的商业园区异常用电行为自动识别方法。通过分析相似性搜索方法获得用户用电时间序列,采用趋势性指标、变化性指标、波动性指标以及其他指标分析商业园区异常用电行为,引用主分量分析与因子分析方法提取异常用电行为特征,凭借误差矩阵自动规整化数据,设定欧氏距离阈值实现商业园区异常用电行为自动识别。实验结果表明方法可降低计算难度,高效识别出异常用电数据,保证商业园区正常用电。
The traditional method of abnormal electricity use behavior identification usually wastes a lot of manpower and material resources,and has low accuracy and poor effect.In the context of big data,this paper proposes an identification method of abnormal electricity use behavior in business park based on similarity search.By analyzing the similarity search method,the time series of electricity consumption is obtained.The trend index,variability index,volatility index and other indicators are used to analyze the abnormal electricity consumption behavior of the business park.The principal component analysis and factor analysis are used to extract the characteristics of abnormal electricity consumption behavior.The data is automatically normalized by the error matrix,and the Euclidean distance threshold is set to realize the abnormal electricity consumption of the business park automatic behavior recognition.The experimental results show that the method can reduce the difficulty of calculation,identify the abnormal power data efficiently,and ensure the normal power consumption of the business park.
作者
邓博雅
高志平
张平康
房洪甲
刘双峰
DENG Bo-ya;GAO Zhi-ping;ZHANG Ping-kang;FANG Hong-jia;LIU Shuang-feng(NARI Group Corporation(State Grid Electric Power Research Institute),Nanjing 210000 China;Nanjing Nanrui Information Communication Technology Co.,Ltd.,Nanjing 210000 China;State Grid Xinjiang Electric Power Co.,Ltd.,Economic and Technical Research Institute,Wulumuqi 830000 China)
出处
《自动化技术与应用》
2023年第3期63-66,共4页
Techniques of Automation and Applications
关键词
相似性搜索
异常用电行为
电负荷识别
similarity search
abnormal electricity usage behavior
electricity load identification
