Integration of Temporal Contextual Information for Robust Energy Disaggregation

Pascal A. Schirmer, Iosif Mporas

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

An extension of the baseline non-intrusive load monitoring approach using temporal contextual information is presented. It uses contextual information in order to capture time-varying power consumption patterns. The proposed methodology was evaluated using datasets of different sampling frequency, number, and types of appliances. The overall energy disaggregation accuracy was improved across all evaluated datasets with the maximum observed improvement in terms of absolute increase of accuracy being equal to 5.7%.

Original languageEnglish
Title of host publication2019 IEEE 38th International Performance Computing and Communications Conference, IPCCC 2019
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISBN (Electronic)9781728110257
DOIs
Publication statusPublished - Oct 2019
Event38th IEEE International Performance Computing and Communications Conference, IPCCC 2019 - London, United Kingdom
Duration: 29 Oct 201931 Oct 2019

Publication series

Name2019 IEEE 38th International Performance Computing and Communications Conference, IPCCC 2019

Conference

Conference38th IEEE International Performance Computing and Communications Conference, IPCCC 2019
Country/TerritoryUnited Kingdom
CityLondon
Period29/10/1931/10/19

Keywords

  • Energy Disaggregation
  • Feature Concatenation
  • Non-intrusive load monitoring
  • Temporal Information

Fingerprint

Dive into the research topics of 'Integration of Temporal Contextual Information for Robust Energy Disaggregation'. Together they form a unique fingerprint.

Cite this