Knowledge Distillation for Scalable Nonintrusive Load Monitoring

被引:2
|
作者
Tanoni, Giulia [1 ]
Stankovic, Lina [2 ]
Stankovic, Vladimir [2 ]
Squartini, Stefano [1 ]
Principi, Emanuele [1 ]
机构
[1] Univ Politecn Marche, Dept Informat Engn, I-60131 Ancona, Italy
[2] Univ Strathclyde, Dept Elect & Elect Engn, Glasgow City G1 1XQ, Scotland
关键词
Deep learning (DL); knowledge distillation (KD); multilabel appliance classification; nonintrusive load monitoring (NILM); weak supervision; CLASSIFICATION;
D O I
10.1109/TII.2023.3328436
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Smart meters allow the grid to interface with individual buildings and extract detailed consumption information using nonintrusive load monitoring (NILM) algorithms applied to the acquired data. Deep neural networks, which represent the state of the art for NILM, are affected by scalability issues since they require high computational and memory resources, and by reduced performance when training and target domains mismatched. This article proposes a knowledge distillation approach for NILM, in particular for multilabel appliance classification, to reduce model complexity and improve generalization on unseen data domains. The approach uses weak supervision to reduce labeling effort, which is useful in practical scenarios. Experiments, conducted on U.K.-DALE and REFIT datasets, demonstrated that a low-complexity network can be obtained for deployment on edge devices while maintaining high performance on unseen data domains. The proposed approach outperformed benchmark methods in unseen target domains achieving a F-1-score 0.14 higher than a benchmark model 78 times more complex.
引用
收藏
页码:4710 / 4721
页数:12
相关论文
共 50 条
  • [31] A New Power Signature for Nonintrusive Appliance Load Monitoring
    Huang, T. D.
    Wang, Wen-Sheng
    Lian, Kuo-Lung
    IEEE TRANSACTIONS ON SMART GRID, 2015, 6 (04) : 1994 - 1995
  • [32] A Novel Search Scheme for Nonintrusive Load Monitoring Systems
    Lai, Yi-Sheng
    Chen, Yung-Chi
    Tsao, Shiao-Li
    Tsai, Tzung-Cheng
    2012 IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL TECHNOLOGY (ICIT), 2012, : 102 - 107
  • [33] Enhancing Nonintrusive Load Monitoring With Targeted Adaptive Networks
    Zhao, Maojiang
    Chen, Song
    Xiong, Zuqiang
    Bai, Zhemin
    Yang, Yu
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2025, 74
  • [34] Nonintrusive Industrial Load Monitoring Considering Load Power Characteristics and Timing Correlation
    Zhang, Yi
    Chen, Jintao
    Li, Chuandong
    Zhang, Liangyu
    Sun, Shouquan
    IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2025, 74
  • [35] Nonintrusive Load Monitoring of Variable Speed Drive Cooling Systems
    Lindahl, Peter A.
    Ali, Muhammad Tauha
    Armstrong, Peter
    Aboulian, Andre
    Donnal, John
    Norford, Les
    Leeb, Steven B.
    IEEE ACCESS, 2020, 8 : 211451 - 211463
  • [36] A Review of Nonintrusive Load Monitoring and Its Application in Commercial Building
    Liu, Yan
    Chen, Mei
    2014 IEEE 4TH ANNUAL INTERNATIONAL CONFERENCE ON CYBER TECHNOLOGY IN AUTOMATION, CONTROL, AND INTELLIGENT SYSTEMS (CYBER), 2014, : 623 - 629
  • [37] Detecting Users' Behaviors based on Nonintrusive Load Monitoring Technologies
    Chen, Yung-Chi
    Chu, Chun-Mei
    Tsao, Shiao-Li
    Tsai, Tzung-Cheng
    2013 10TH IEEE INTERNATIONAL CONFERENCE ON NETWORKING, SENSING AND CONTROL (ICNSC), 2013, : 804 - 809
  • [38] Nonintrusive Load Monitoring Using Wavelet Design and Machine Learning
    Gillis, Jessie M.
    Alshareef, Sami M.
    Morsi, Walid G.
    IEEE TRANSACTIONS ON SMART GRID, 2016, 7 (01) : 320 - 328
  • [39] Nonintrusive Load Monitoring of Electrical Devices in Health Smart Homes
    Rahimi, Saba
    Chan, Adrian D. C.
    Goubran, Rafik A.
    2012 IEEE INTERNATIONAL INSTRUMENTATION AND MEASUREMENT TECHNOLOGY CONFERENCE (I2MTC), 2012, : 2313 - 2316
  • [40] An Efficient and Accurate Nonintrusive Load Monitoring Scheme for Power Consumption
    He, Jialing
    Zhang, Zijian
    Zhu, Liehuang
    Zhu, Zhesi
    Liu, Jiamou
    Gai, Keke
    IEEE INTERNET OF THINGS JOURNAL, 2019, 6 (05) : 9054 - 9063