Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Bayesian neural networks for one-hour ahead wind power forecasting
KTH, Skolan för datavetenskap och kommunikation (CSC), Beräkningsvetenskap och beräkningsteknik (CST).ORCID-id: 0000-0001-6553-823X
2017 (Engelska)Ingår i: 2017 6th International Conference on Renewable Energy Research and Applications, ICRERA 2017, Institute of Electrical and Electronics Engineers (IEEE), 2017, Vol. 2017, s. 591-596Konferensbidrag, Publicerat paper (Refereegranskat)
Abstract [en]

The greatest concern facing renewable energy sources like wind is the uncertainty in production volumes as their generation ability is inherently dependent on weather conditions. When providing forecasts for newly commissioned wind farms there is a limited amount of historical power production data, while the number of potential features from different weather forecast providers is vast. Bayesian regularization is therefore seen as a possible technique for reducing model overfitting problems that may arise. This work investigates Bayesian Neural Networks for one-hour ahead forecasting of wind power generation. Initial results show that Bayesian Neural Networks display equivalent predictive performance to Neural Networks trained by Maximum Likelihood. Further results show that Bayesian Neural Networks become superior after removing irrelevant features using Automatic Relevance Determination(ARD).

Ort, förlag, år, upplaga, sidor
Institute of Electrical and Electronics Engineers (IEEE), 2017. Vol. 2017, s. 591-596
Serie
International Conference on Renewable Energy Research and Applications
Nyckelord [en]
Ahead, Automatic relevance determination, Bayesian, Forecasting, Neural networks, One-hour, Wind power
Nationell ämneskategori
Kommunikationssystem
Identifikatorer
URN: urn:nbn:se:kth:diva-224241DOI: 10.1109/DISTRA.2017.8191129ISI: 000426708600096Scopus ID: 2-s2.0-85042722249ISBN: 9781538620953 (tryckt)OAI: oai:DiVA.org:kth-224241DiVA, id: diva2:1190694
Konferens
6th IEEE International Conference on Renewable Energy Research and Applications, ICRERA 2017, 5 November 2017 through 8 November 2017, San Diego, United States
Anmärkning

QC 20180315

Tillgänglig från: 2018-03-15 Skapad: 2018-03-15 Senast uppdaterad: 2018-03-23Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Personposter BETA

Herman, Pawel

Sök vidare i DiVA

Av författaren/redaktören
Herman, Pawel
Av organisationen
Beräkningsvetenskap och beräkningsteknik (CST)
Kommunikationssystem

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 58 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • harvard1
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf