Unsupervised learning procedure for NILM applications

被引：0
作者：
Jacobs, Gilles [1 ]
Henneaux, Pierre [1 ]
机构：
[1] Univ Libre Bruxelles, Ecole Polytech Bruxelles, Brussels, Belgium
来源：
20TH IEEE MEDITERRANEAN ELETROTECHNICAL CONFERENCE (IEEE MELECON 2020) | 2020年
关键词：
clustering; MILP; NILM; transient; learning;
D O I：
10.1109/melecon48756.2020.9140477
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
In a domestic context, NILM applications (Non-Intrusive Load Monitoring) allow users to know their electric consumption per appliance without having to install sensors for each appliance in their house. The aim of this paper is to present a new generic method allowing to discover the different appliances present in a house. Results obtained in this paper relies on supervised data obtained by sub-metering at the level of each appliance for 3 real domestic houses.
引用
收藏
页码：559 / 564
页数：6
相关论文
共 14 条
  • [1] [Anonymous], 2011, ENCARTES, DOI [DOI 10.1137/1.9781611972818.64, 10.1137/1.9781611972818.64]
  • [2] DETECTING CHANGES IN SIGNALS AND SYSTEMS - A SURVEY
    BASSEVILLE, M
    [J]. AUTOMATICA, 1988, 24 (03) : 309 - 326
  • [3] Non-intrusive load monitoring by using active and reactive power in additive Factorial Hidden Markov Models
    Bonfigli, Roberto
    Principi, Emanuele
    Fagiani, Marco
    Severini, Marco
    Squartini, Stefano
    Piazza, Francesco
    [J]. APPLIED ENERGY, 2017, 208 : 1590 - 1607
  • [4] Ester M., 1996, P 2 INT C KNOWL DISC, P226, DOI DOI 10.5555/3001460.3001507
  • [5] Goncalves H., 2012, P 1 INT WORKSH NONIN
  • [6] NONINTRUSIVE APPLIANCE LOAD MONITORING
    HART, GW
    [J]. PROCEEDINGS OF THE IEEE, 1992, 80 (12) : 1870 - 1891
  • [7] Jossen Quentin, UNSUPERVISED LEARNIN
  • [8] Kolter J.Z., 2012, Artificial Intelligence and Statistics, P1472
  • [9] Kolter J.Z., 2010, NIPS, P1
  • [10] Lofberg J., 2004, P IEEE INT S COMPUTE, V3
12