Skip to Main content Skip to Navigation
Journal articles

Time series distance-based methods for non-intrusive load monitoring in residential buildings

Abstract : Non-Intrusive Load Monitoring (Nilm) deals with the disaggregation of in- dividual appliances from the total load at the smart meter level. This work proposes a generic methodology using temporal sequence classification algo- rithms. It is based on a low sampling rate unlike other approaches in this domain. An innovative time series distance-based approach in the temporal classification domain is compared with a standard Nilm application based on the Hidden Markov Model algorithm (Hmm). The method is validated over a data-set of 100 houses for a duration of one year (with a 10 minutes sampling rate). A qualitative analysis of the database is also conducted, allowing to segment it into four major clusters based on discussed features.
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01208468
Contributor : Ahlame Douzal <>
Submitted on : Friday, October 2, 2015 - 3:57:43 PM
Last modification on : Friday, October 25, 2019 - 2:01:41 AM

Identifiers

  • HAL Id : hal-01208468, version 1

Collections

CNRS | LIG | UGA | G2ELAB

Citation

Kaustav Basu, Vincent Debusschere, Ahlame Douzal-Chouakria, Seddik Bacha. Time series distance-based methods for non-intrusive load monitoring in residential buildings. Energy and Buildings, Elsevier, 2015, 96 (109–117). ⟨hal-01208468⟩

Share

Metrics

Record views

393