电力系统自动化2024，Vol.48Issue(2)：71-81,11.DOI:10.7500/AEPS20230317003
基于时序生成对抗网络的居民用户非侵入式负荷分解
Non-intrusive Load Decomposition for Residential Users Based on Time-series Generative Adversarial Network
摘要
Abstract
The existing non-intrusive load decomposition algorithms often require a large number of electrical load data at equipment level to ensure the decomposition accuracy,but it is difficult to obtain these data due to the user's consideration of privacy and high installation cost.Therefore,a time-series generative adversarial network which can deeply explore the time-series characteristics of power load data and the correlation of electrical appliances is constructed.The dimensionality reduction network is used to reduce the dimensionality of the high-dimensional vector composed of the active power sequence of all electrical appliances to reduce the computational complexity,and the result is restored to the high-dimensional vector through the restoration network.Based on the non-intrusive decomposition method of electrical appliance operation status and deep learning,the load decomposition regression model of complex-state electrical appliances is built by using the convolutional neural network-bidirectional gated recurrent unit,and the load identification and classification model of simple-state electrical appliances is constructed by using the deep neural network.The effectiveness of the proposed method is verified by comparing other data generation methods and the load decomposition results obtained by changing the proportion of the generated data in typical public datasets.关键词
非侵入式负荷分解/对抗生成网络/降维网络/卷积神经网络-双向门控循环单元/深度神经网络Key words
non-intrusive load decomposition/generative adversarial network/dimensionality reduction network/convolutional neural network-bidirectional gated recurrent unit/deep neural network引用本文复制引用
罗平,朱振宇,樊星驰,孙博宇,张帆,吕强..基于时序生成对抗网络的居民用户非侵入式负荷分解[J].电力系统自动化,2024,48(2):71-81,11.基金项目
浙江省自然科学基金资助项目(LY20E070004) （LY20E070004）
国家自然科学基金资助项目(62073108) （62073108）
This work is supported by Zhejiang Provincial Natural Science Foundation of China(No.LY20E070004)and National Natural Science Foundation of China(No.62073108). （No.LY20E070004）
