电力需求侧管理2025，Vol.27Issue(1)：52-58,7.DOI:10.3969/j.issn.1009-1831.2025.01.009
基于ADASYN和图像分析的非侵入式负荷辨识方法研究
Research on non-intrusive load identification method based on ADASYN and image analysis
摘要
Abstract
In order to popularize the load identification technology of smart meters and solve the problem of low identification accuracy of traditional non-intrusive load identification algorithm on unbalanced sampled data,a non-intrusive load identification method based on adaptive synthetic(ADASYN)and image analysis is proposed.1D power data is converted into 2D MTF feature images by markov transi-tion field(MTF)coding,which is used as the input of image recognition network.Based on the deep information mining capability of dense connectivity network(DenseNet),2D images are input into DenseNet121 network to extract feature information and realize the identifica-tion of load types.Based on ADASYN algorithm,the unbalanced data set is oversampled to eliminate the model learning bias caused by the unbalanced data distribution.The results show that ADASYN algorithm can solve the non-intrusive load monitoring data imbalance problem well,and its identification accuracy and F1 score are increased by 0.247 and 0.267,respectively.At the same time,MTF images have clear and easily distinguishable feature information.Combined with the powerful deep feature capture capability of DenseNet121 net-work,the identification accuracy and F1 score can both reach 0.952,which effectively improves the identification accuracy of non-intru-sive load types on unbalanced sampled data.关键词
智能电能表/非侵入式负荷/自适应合成采样/马尔可夫变迁场/密集连接网络/负荷辨识Key words
intelligent energy meter/non-intrusive load/adaptive synthetic/markov transition field/dense connectivity network/load identi-fication分类
能源科技引用本文复制引用
顾水福,周磊,李洁,李亚飞,李圆琪,朱超群..基于ADASYN和图像分析的非侵入式负荷辨识方法研究[J].电力需求侧管理,2025,27(1):52-58,7.基金项目
国网江苏省电力有限公司科技项目(J2022093) （J2022093）
