Time series distance-based methods for non-intrusive load monitoring in residential buildings - Archive ouverte HAL Access content directly
Journal Articles Energy and Buildings Year : 2015

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.
No file

Dates and versions

hal-01208468 , version 1 (02-10-2015)

Identifiers

  • HAL Id : hal-01208468 , version 1

Cite

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, 2015, 96 (109–117). ⟨hal-01208468⟩
152 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More