电测与仪表2024，Vol.61Issue(1)：125-130,156,7.DOI:10.19753/j.issn1001-1390.2024.01.019
基于改进卷积神经网络的非侵入负荷辨识方法研究
Non-intrusive load identification method based on improved convolutional neural network
摘要
Abstract
Non-intrusive load monitoring is one of the important technologies of the ubiquitous power IoT on the customer side,which not only helps the power company to strengthen load management,but also can guide users to rationally ar-range the use of the load.In order to achieve the demand side with household power users as the main body,it provides important technical support for responding to and satisfying the demand of residents for precise and lean electricity service.In this paper,for the problem of low resolution of low-frequency sampling signals in non-intrusive load identifiication and easy overlap of load characteristics,two confluent transient current waveforms and time-domain characteristics are pro-posed for convolutional neural networks that cannot effectively identify loads with similar waveform characteristics.One of the improved methods is to integrate the root mean square(RMS)of the transient current value into the current waveform image,and the other is to superimpose the threshold judgment on the basis of the identification result of the convolutional neural network to improve the recognition accuracy of the similar waveform feature load.Through the measured data and reference energy disaggregation data set(REDD)test,the feasibility and effectiveness of the proposed method are veri-fied.关键词
非侵入式负荷监测/负荷辨识/低频采样/CNNKey words
non-intrusive load monitoring/load identification/low frequency sampling/CNN分类
信息技术与安全科学引用本文复制引用
李莉,黄友金,熊炜,汪敏,阳东升..基于改进卷积神经网络的非侵入负荷辨识方法研究[J].电测与仪表,2024,61(1):125-130,156,7.基金项目
国家自然科学基金资助项目(51667007) （51667007）
贵州省科技计划项目(黔科合基础[2019]1058、黔科合基础[2019]1128) （黔科合基础[2019]1058、黔科合基础[2019]1128）
