Non-intrusive load monitoring method based on multi-scale convolution and Informer hybrid model

被引：0
|
作者：
Han L. [1 ]
Gao F. [1 ]
Zhao Z. [1 ]
Guo S. [1 ]
Li X. [1 ]
Zhang D. [1 ]
Wu X. [1 ,2 ]
机构：
[1] School of Electrical Engineering, Guangxi University, Nanning
[2] School of Computer，Electronics and Information, Guangxi University, Nanning
来源：
Dianli Zidonghua Shebei/Electric Power Automation Equipment | 2024年 / 44卷 / 03期
基金：
中国国家自然科学基金;
关键词：
correction of decomposition value; data segmentation optimization; Informer network; multi-scale convolution; non-intrusive load monitoring;
D O I：
10.16081/j.epae.202306017
中图分类号：
学科分类号：
摘要：
Aiming at the problems of low load decomposition accuracy and poor model generalization performance existing in the current non-intrusive load monitoring methods，a non-intrusive load monitoring method combining multi-scale convolution and Informer network is proposed. The data segmentation optimization method is adopted to segment the power signal，a multi-scale convolution kernel is used to obtain the feature sequences of different time scales and adaptively extract multi-dimensional power features，thus a feature matrix is formed. The long-term dependence relation of feature sequences in high-dimensional space is captured based on the probability sparse self-attention mechanism in Informer network，thus the prediction accuracy is improved. The decomposition value correction method is used to eliminate the“spurious”activation states in the power decomposition values for further improving the decomposition accuracy. The feasibility of the proposed method is verified by the example results. © 2024 Electric Power Automation Equipment Press. All rights reserved.
引用
收藏
页码：134 / 141
页数：7
相关论文
共 23 条
  • [1] PENG Chunhua, ZHANG Jinke, CHEN Lu, Et al., Source-load-storage coordinated optimal scheduling of microgrid considering differential demand response［J］, Electric Power Automation Equipment, 40, 3, pp. 1-7, (2020)
  • [2] DENG Xiaoping, ZHANG Guiqing, WEI Qinglai, Et al., A survey on the non-intrusive load monitoring［J］, Acta Automatica Sinica, 48, 3, pp. 644-663, (2022)
  • [3] NILM applications：literature review of learning approaches，recent developments and challenges［J］, Energy and Buildings, 261, (2022)
  • [4] KUMAR M，, JOSHUA C P C，, Et al., Energy management using non-intrusive load monitoring techniques-state-of-the-art and future research directions［J］, Sustainable Cities and Society, 62, (2020)
  • [5] ZHOU Yongjun, WU Yuanxiang, DONG Zhihua, Et al., Non-intrusive load monitoring based on motif mining and harmonic function based semi-supervised learning［J］, Electric Power Automation Equipment, 42, 7, pp. 3-10, (2022)
  • [6] CAI Yu, DONG Shufeng, XU Hang, Et al., Real-time disaggregation algorithm of nonintrusive load based on usage influencing factor［J］, Electric Power Automation Equipment, 41, 12, pp. 193-199, (2021)
  • [7] BAJIC I V., Load disaggregation based on aided linear integer programming［J］, IEEE Transactions on Circuits and Systems Ⅱ：Express Briefs, 64, 7, pp. 792-796, (2017)
  • [8] TSAI M S., Development of an improved time-frequency analysis-based nonintrusive load monitor for load demand identification［J］, IEEE Transactions on Instrumentation and Measurement, 63, 6, pp. 1470-1483, (2014)
  • [9] ZHAO Wenqing, ZHANG Shiman, LI Gang, Non-intrusive load decomposition of residential users based on cluster and association analysis［J］, Electric Power Automation Equipment, 40, 6, pp. 8-19, (2020)
  • [10] PENG W X，, Et al., Non-intrusive load monitoring using factorial hidden Markov model based on adaptive density peak clustering［J］, Energy and Buildings, 244, (2021)
123