《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (10): 3300-3306.DOI: 10.11772/j.issn.1001-9081.2021081512

• 前沿与综合应用 • 上一篇    

基于上采样金字塔结构的卷积神经网络的非侵入负荷辨识算法

杜宇, 严萌, 武昕   

  1. 华北电力大学 电气与电子工程学院,北京 102206
  • 收稿日期:2021-08-25 修回日期:2021-11-08 接受日期:2021-11-19 发布日期:2022-01-07 出版日期:2022-10-10
  • 通讯作者: 武昕
  • 作者简介:第一联系人:杜宇(1992—),男,河北保定人,硕士研究生,主要研究方向:智能用电与电力系统信息处理、大数据智能分析
    严萌(1997—),女,河北唐山人,硕士研究生,主要研究方向:非侵入式负荷监测、智能信息处理
    武昕(1986—),女,北京人,副教授,博士,主要研究方向:物联网、智能感知、能源互联网智能信息处理。wuxin07@ncepu.edu.cn
  • 基金资助:
    中央高校基本科研业务费专项资金资助项目(2020MS002)

Non-intrusive load identification algorithm based on convolutional neural network with upsampling pyramid structure

Yu DU, Meng YAN, Xin WU   

  1. School of Electrical and Electronic Engineering,North China Electric Power University,Beijing 102206,China
  • Received:2021-08-25 Revised:2021-11-08 Accepted:2021-11-19 Online:2022-01-07 Published:2022-10-10
  • Contact: Xin WU
  • About author:DU Yu, born in 1992, M. S. candidate. His research interests include intelligent power consumption and power system information processing, big data intelligent analysis.
    YAN Meng, born in 1997, M. S. candidate. Her research interests include non-intrusive load monitoring, intelligent information processing.
    WU Xin, born in 1986, Ph. D. , associate professor. Her research interests include internet of things, intelligent sensing, energy internet intelligent information processing.
  • Supported by:
    Fundamental Research Funds for Central Universities(2020MS002)

摘要:

非侵入式负荷监测(NILM)技术为需求侧管理提供了技术支撑,而非侵入负荷辨识是负荷监测过程中的关键环节。在负荷数据采样过程中无法实现长期的实时高频采集,得到的负荷数据还存在缺乏时序性的问题;同时,卷积神经网络(CNN)存在对低级信号特征表现不足的缺陷。针对以上两个问题,提出了一种基于上采样金字塔结构的CNN非侵入负荷辨识算法。所提算法直接面向采集到的负荷电流信号,利用上采样网络扩展数据在时间维度上的相关信息弥补数据的时序性,并通过双向金字塔一维卷积提取负荷信号的高级与低级特征,以对负荷特征进行全面利用,从而实现对未知负荷信号进行识别的目的。实验结果表明,基于上采样金字塔结构的CNN非侵入负荷辨识算法的识别准确率能够达到95.21%,且具有良好的泛化能力,可有效实现负荷辨识。

关键词: 非侵入负荷辨识, 需求侧管理, 数据上采样, 双向金字塔结构, 卷积神经网络, 自动特征提取

Abstract:

Non-Intrusive Load Monitoring (NILM) technology provides technical support for demand side management, and non-intrusive load identification is the key link in the process of load monitoring. The long-term sampling process of load data cannot be carried out in real time and high frequency, and the time sequence of the obtained load data is lost. At the same time, the defect of insufficient representation of low-level signal features occurs in Convolution Neural Network (CNN). In view of the above two problems, a CNN based non-intrusive load identification algorithm with upsampling pyramid structure was proposed. In the proposed algorithm, with direct orientation to the collected load current signals, the time sequence of the data was compensated by the relevant information in the time dimension of the upsampling network expanded data, and the high-level and low-level features of load signals were extracted by the bidirectional pyramid one-dimensional convolution, so that the load characteristics were fully utilized. As a result, the purpose of identifying unknown load signals can be achieved. Experimental results show that the recognition accuracy of non-intrusive load identification algorithm based on CNN with upsampling pyramid structure can reach 95.21%, indicating that the proposed algorithm has a good generalization ability, and can effectively realize load identification.

Key words: non-intrusive load identification, demand side management, data upsampling, bidirectional pyramid structure, Convolution Neural Network (CNN), automatic feature extraction

中图分类号: