Extracting Features from an Electrical Signal of a Non-Intrusive Load Monitoring System

  • Marisa B. Figueiredo
  • Ana de Almeida
  • Bernardete Ribeiro
  • António Martins
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6283)


Improving energy efficiency by monitoring household electrical consumption is of significant importance with the present-day climate change concerns. A solution for the electrical consumption management problem is the use of a non-intrusive load monitoring system (NILM). This system captures the signals from the aggregate consumption, extracts the features from these signals and classifies the extracted features in order to identify the switched on appliances. An effective device identification (ID) requires a signature to be assigned for each appliance. Moreover, to specify an ID for each device, signal processing techniques are needed for extracting the relevant features. This paper describes a technique for the steady-states recognition in an electrical digital signal as the first stage for the implementation of an innovative NILM. Furthermore, the final goal is to develop an intelligent system for the identification of the appliances by automated learning. The proposed approach is based on the ratio value between rectangular areas defined by the signal samples. The computational experiments show the method effectiveness for the accurate steady-states identification in the electrical input signals.


Automated learning and identification feature extraction and classification non-intrusive load monitoring 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hart, G.W.: Nonintrusive appliance load monitoring. Proceedings of the IEEE, 1870–1891 (1992)Google Scholar
  2. 2.
    Sultanem, F.: Using appliance signatures for monitoring residential loads at meter panel level. IEEE Transactions on Power Delivery 6, 1380–1385 (1991)CrossRefGoogle Scholar
  3. 3.
    Drenker, S., Kader, A.: Nonintrusive monitoring of electric loads. IEEE Computer Applications in Power 12(4), 47–51 (1999)CrossRefGoogle Scholar
  4. 4.
    Cole, A., Albicki, A.: Data extraction for effective non-intrusive identification of residential power loads. In: Instrumentation and Measurement Technology Conference, vol. 2, pp. 812–815 (1998)Google Scholar
  5. 5.
    Berges, M., Goldman, E., Matthews, H.S., Soibelman, L.: Learning systems for electric consumption of buildings. In: ASCE International Workshop on Computing in Civil Engineering, Austin, Texas (2009)Google Scholar
  6. 6.
    Bijker, A.J., Xia, X., Zhang, J.: Active power residential non-intrusive appliance load monitoring system. In: IEEE AFRICON 2009 (2009)Google Scholar
  7. 7.
    ISA - Intelligent Sensing Anywhere, (last accessed April 15, 2010)
  8. 8.
    Matthews, H.S., Soibelman, L., Berges, M., Goldman, E.: Automatically disaggregating the total electrical load in residential buildings: a profile of the required solution. In: Intelligent Computing in Engineering (ICE’08) Proceedings, Plymouth (2008)Google Scholar
  9. 9.
    Cilibrasi, R., Vitányi, P.M.B.: Clustering by compression. IEEE Transactions on Information Theory 51, 1523–1545 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Marisa B. Figueiredo
    • 1
  • Ana de Almeida
    • 1
  • Bernardete Ribeiro
    • 1
  • António Martins
    • 2
  1. 1.CISUC - Center for Informatics and SystemsUniversity of Coimbra, Polo IICoimbraPortugal
  2. 2.ISA - Intelligent Sensing Anywhere, S.A.CoimbraPortugal

Personalised recommendations