Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Journal of Chongqing University of Technology(Natural Science)》 2017-08
Add to Favorite Get Latest Update

Research on Abnormal Behavior of Power Consumption Based on BP Neural Network with PCA

TIAN Ye;ZHANG Cheng;MAO Xinru;LIU Ji;College of Computer Science,Chongqing University;State Grid Corporation;  
According to the problems of resource wasting,low efficiency and difficult detection encountered in the traditional way of detecting user's abnormal power consumption,the algorithm for large-scale data mining was designed and realized combined with data mining technology,and an effective anomaly feature extraction model was established. It determines the abnormal indicators using the statistic-based feature extraction method,and reduces the dimension of the characteristic data using the principal component analysis method to achieve the analysis,identification and processing for abnormal power consumption. Then,the back-propagation neural network was established to detectthe abnormal behavior from the power consumption information. The test result shows that this method can effectively extract the characteristics of power consumption behavior,and can be effectively used in the detection of electricity-using anomaly.
【Fund】: 国家自然科学基金资助项目(61502060)
【CateGory Index】: TP183;TP311.13
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved