Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 625243

Load forecasting using a multivariate meta-learning system


Matijaš, Marin; Suykens, Johan A.K.; Krajcar, Slavko
Load forecasting using a multivariate meta-learning system // Expert systems with applications, 40 (2013), 11; 4427-4437 doi:10.1016/j.eswa.2013.01.047 (međunarodna recenzija, članak, znanstveni)


CROSBI ID: 625243 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Load forecasting using a multivariate meta-learning system

Autori
Matijaš, Marin ; Suykens, Johan A.K. ; Krajcar, Slavko

Izvornik
Expert systems with applications (0957-4174) 40 (2013), 11; 4427-4437

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
electricity consumption prediction; energy expert systems; industrial applications; short-term electric load forecasting; meta-learning; power demand estimation

Sažetak
Although over a thousand scientific papers address the topic of load forecasting every year, only a few are dedicated to finding a general framework for load forecasting that improves the performance, without depending on the unique characteristics of a certain task such as geographical location. Meta-learning, a powerful approach for algorithm selection has so far been demonstrated only on univariate time-series forecasting. Multivariate time-series forecasting is known to have better performance in load forecasting. In this paper we propose a meta- learning system for multivariate time-series forecasting as a general framework for load forecasting model selection. We show that a meta- learning system built on 65 load forecasting tasks returns lower forecasting error than 10 well-known forecasting algorithms on 4 load forecasting tasks for a recurrent real-life simulation. We introduce new metafeatures of fickleness, traversity, granularity and highest ACF. The meta-learning framework is parallelized, component-based and easily extendable.

Izvorni jezik
Engleski

Znanstvena područja
Elektrotehnika, Računarstvo



POVEZANOST RADA


Projekti:
036-0361590-1591 - Razvoj alata za analizu tržišta električne energije (Krajcar, Slavko, MZOS ) ( POIROT)

Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb

Profili:

Avatar Url Marin Matijaš (autor)

Avatar Url Slavko Krajcar (autor)

Citiraj ovu publikaciju

Matijaš, Marin; Suykens, Johan A.K.; Krajcar, Slavko
Load forecasting using a multivariate meta-learning system // Expert systems with applications, 40 (2013), 11; 4427-4437 doi:10.1016/j.eswa.2013.01.047 (međunarodna recenzija, članak, znanstveni)
Matijaš, M., Suykens, J. & Krajcar, S. (2013) Load forecasting using a multivariate meta-learning system. Expert systems with applications, 40 (11), 4427-4437 doi:10.1016/j.eswa.2013.01.047.
@article{article, year = {2013}, pages = {4427-4437}, DOI = {10.1016/j.eswa.2013.01.047}, keywords = {electricity consumption prediction, energy expert systems, industrial applications, short-term electric load forecasting, meta-learning, power demand estimation}, journal = {Expert systems with applications}, doi = {10.1016/j.eswa.2013.01.047}, volume = {40}, number = {11}, issn = {0957-4174}, title = {Load forecasting using a multivariate meta-learning system}, keyword = {electricity consumption prediction, energy expert systems, industrial applications, short-term electric load forecasting, meta-learning, power demand estimation} }
@article{article, year = {2013}, pages = {4427-4437}, DOI = {10.1016/j.eswa.2013.01.047}, keywords = {electricity consumption prediction, energy expert systems, industrial applications, short-term electric load forecasting, meta-learning, power demand estimation}, journal = {Expert systems with applications}, doi = {10.1016/j.eswa.2013.01.047}, volume = {40}, number = {11}, issn = {0957-4174}, title = {Load forecasting using a multivariate meta-learning system}, keyword = {electricity consumption prediction, energy expert systems, industrial applications, short-term electric load forecasting, meta-learning, power demand estimation} }

Časopis indeksira:


  • Current Contents Connect (CCC)
  • Web of Science Core Collection (WoSCC)
    • Science Citation Index Expanded (SCI-EXP)
    • SCI-EXP, SSCI i/ili A&HCI
  • Scopus


Uključenost u ostale bibliografske baze podataka:


  • Cambridge/Computer and Information Abstracts
  • Research Alert
  • SCISEARCH
  • Scopus


Citati





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font