Household electricity demand forecasting - Benchmarking state-of-the-art methods

Andreas Veit; Christoph Goebel; Rohit Tidke; Christoph Doblander; Hans Arno Jacobsen

doi:10.1145/2602044.2602082

Household electricity demand forecasting - Benchmarking state-of-the-art methods

Andreas Veit, Christoph Goebel, Rohit Tidke, Christoph Doblander, Hans Arno Jacobsen

Technische Universität München

Publikation: Beitrag in Buch/Bericht/Konferenzband › Konferenzbeitrag › Begutachtung

55 Zitate (Scopus)

Abstract

We benchmark state-of-the-art methods for forecasting electricity demand on the household level. Our evaluation is based on two data sets containing the power usage on the individual appliance level. Our results indicate that without further refinement the considered advanced state-of-the-art forecasting methods rarely beat corresponding persistence forecasts. Therefore, we also provide an exploration of promising directions for future research.

Originalsprache	Englisch
Titel	e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems
Herausgeber (Verlag)	Association for Computing Machinery
Seiten	233-234
Seitenumfang	2
ISBN (Print)	9781450328197
DOIs	https://doi.org/10.1145/2602044.2602082
Publikationsstatus	Veröffentlicht - 2014
Veranstaltung	5th ACM International Conference on Future Energy Systems, e-Energy 2014 - Cambridge, Großbritannien/Vereinigtes Königreich Dauer: 11 Juni 2014 → 13 Juni 2014

Publikationsreihe

Name	e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems

Konferenz

Konferenz	5th ACM International Conference on Future Energy Systems, e-Energy 2014
Land/Gebiet	Großbritannien/Vereinigtes Königreich
Ort	Cambridge
Zeitraum	11/06/14 → 13/06/14

UN SDGs

Dieser Output leistet einen Beitrag zu folgendem(n) Ziel(en) für nachhaltige Entwicklung

Zugriff auf Dokument

10.1145/2602044.2602082

Andere Dateien und Links

Verknüpfung zur Publikation in Scopus

Dieses zitieren

Veit, A., Goebel, C., Tidke, R., Doblander, C., & Jacobsen, H. A. (2014). Household electricity demand forecasting - Benchmarking state-of-the-art methods. in e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems (S. 233-234). (e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems). Association for Computing Machinery. https://doi.org/10.1145/2602044.2602082

Veit, Andreas ; Goebel, Christoph ; Tidke, Rohit et al. / Household electricity demand forecasting - Benchmarking state-of-the-art methods. e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems. Association for Computing Machinery, 2014. S. 233-234 (e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems).

@inproceedings{ea0c8a6bfcb5425ba4f7dadd40134301,

title = "Household electricity demand forecasting - Benchmarking state-of-the-art methods",

abstract = "We benchmark state-of-the-art methods for forecasting electricity demand on the household level. Our evaluation is based on two data sets containing the power usage on the individual appliance level. Our results indicate that without further refinement the considered advanced state-of-the-art forecasting methods rarely beat corresponding persistence forecasts. Therefore, we also provide an exploration of promising directions for future research.",

keywords = "load forecasting, smart grid, smart home",

author = "Andreas Veit and Christoph Goebel and Rohit Tidke and Christoph Doblander and Jacobsen, {Hans Arno}",

year = "2014",

doi = "10.1145/2602044.2602082",

language = "English",

isbn = "9781450328197",

series = "e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems",

publisher = "Association for Computing Machinery",

pages = "233--234",

booktitle = "e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems",

note = "5th ACM International Conference on Future Energy Systems, e-Energy 2014 ; Conference date: 11-06-2014 Through 13-06-2014",

}

Veit, A, Goebel, C, Tidke, R, Doblander, C & Jacobsen, HA 2014, Household electricity demand forecasting - Benchmarking state-of-the-art methods. in e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems. e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems, Association for Computing Machinery, S. 233-234, 5th ACM International Conference on Future Energy Systems, e-Energy 2014, Cambridge, Großbritannien/Vereinigtes Königreich, 11/06/14. https://doi.org/10.1145/2602044.2602082

Household electricity demand forecasting - Benchmarking state-of-the-art methods. / Veit, Andreas; Goebel, Christoph; Tidke, Rohit et al.
e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems. Association for Computing Machinery, 2014. S. 233-234 (e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems).

Publikation: Beitrag in Buch/Bericht/Konferenzband › Konferenzbeitrag › Begutachtung

TY - GEN

T1 - Household electricity demand forecasting - Benchmarking state-of-the-art methods

AU - Veit, Andreas

AU - Goebel, Christoph

AU - Tidke, Rohit

AU - Doblander, Christoph

AU - Jacobsen, Hans Arno

PY - 2014

Y1 - 2014

N2 - We benchmark state-of-the-art methods for forecasting electricity demand on the household level. Our evaluation is based on two data sets containing the power usage on the individual appliance level. Our results indicate that without further refinement the considered advanced state-of-the-art forecasting methods rarely beat corresponding persistence forecasts. Therefore, we also provide an exploration of promising directions for future research.

AB - We benchmark state-of-the-art methods for forecasting electricity demand on the household level. Our evaluation is based on two data sets containing the power usage on the individual appliance level. Our results indicate that without further refinement the considered advanced state-of-the-art forecasting methods rarely beat corresponding persistence forecasts. Therefore, we also provide an exploration of promising directions for future research.

KW - load forecasting

KW - smart grid

KW - smart home

UR - http://www.scopus.com/inward/record.url?scp=84907007789&partnerID=8YFLogxK

U2 - 10.1145/2602044.2602082

DO - 10.1145/2602044.2602082

M3 - Conference contribution

AN - SCOPUS:84907007789

SN - 9781450328197

T3 - e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems

SP - 233

EP - 234

BT - e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems

PB - Association for Computing Machinery

T2 - 5th ACM International Conference on Future Energy Systems, e-Energy 2014

Y2 - 11 June 2014 through 13 June 2014

ER -

Veit A, Goebel C, Tidke R, Doblander C, Jacobsen HA. Household electricity demand forecasting - Benchmarking state-of-the-art methods. in e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems. Association for Computing Machinery. 2014. S. 233-234. (e-Energy 2014 - Proceedings of the 5th ACM International Conference on Future Energy Systems). doi: 10.1145/2602044.2602082

Household electricity demand forecasting - Benchmarking state-of-the-art methods

Abstract

Publikationsreihe

Konferenz

UN SDGs

Zugriff auf Dokument

Andere Dateien und Links

Fingerprint

Dieses zitieren