lnu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Production Planning of Cascaded Hydropower Stations using Approximate Dynamic Programming
Linnaeus University, Faculty of Technology, Department of Physics and Electrical Engineering.ORCID iD: 0000-0002-2028-9847
Linnaeus University, Faculty of Technology, Department of Physics and Electrical Engineering.ORCID iD: 0000-0003-3111-4820
2023 (English)In: IFAC-PapersOnLine: 22nd IFAC World Congress, Yokohama, Japan, July 9-14, 2023 / [ed] Ishii H., Ebihara Y., Imura J., Yamakita M., Elsevier, 2023, Vol. 56(2), no 2, p. 10069-10076Conference paper, Published paper (Refereed)
Abstract [en]

We formulate the day-ahead bidding problem for a hydropower producer having several hydropower plants residing in a river basin. We present a novel approach inspired by Dynamic programming with approximations in value and policy space by neural networks. This allows for more accurate modeling of the problem by avoiding linear approximations of the production function and bidding. Stochastic programming is a method frequently used in literature to solve the hydropower production planning problem. Stochastic programming is used on linearized systems and under assumptions of known distributions of the involved stochastic processes. We test the proposed algorithm on a simplified system, suitable for Stochastic Programming and compare the obtained policy with the results from Stochastic Programming. The results show that the algorithm obtains a policy similar to that of Stochastic Programming.

Place, publisher, year, edition, pages
Elsevier, 2023. Vol. 56(2), no 2, p. 10069-10076
Series
IFAC-PapersOnLine, E-ISSN 2405-8963 ; 56(2)
Keywords [en]
Analysis and control in deregulated power systems, Approximate dynamic programming, Hydropower production planning, Neural networks
National Category
Control Engineering
Research subject
Physics, Electrotechnology
Identifiers
URN: urn:nbn:se:lnu:diva-129978DOI: 10.1016/j.ifacol.2023.10.876Scopus ID: 2-s2.0-85183624066ISBN: 9781713872344 (print)OAI: oai:DiVA.org:lnu-129978DiVA, id: diva2:1865857
Conference
22nd IFAC World Congress, Yokohama, Japan, July 9-14, 2023
Available from: 2024-06-05 Created: 2024-06-05 Last updated: 2024-06-28Bibliographically approved

Open Access in DiVA

fulltext(840 kB)23 downloads
File information
File name FULLTEXT01.pdfFile size 840 kBChecksum SHA-512
35ee07060d908f98f8e934b9d227a4bf784818f2745e467884c9a811240286f80ef78375fa71b9e466867f0f24c2cc1a48f4a43689fe93ef237af01947405784
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Marcial, AlexanderPerninge, Magnus

Search in DiVA

By author/editor
Marcial, AlexanderPerninge, Magnus
By organisation
Department of Physics and Electrical Engineering
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar
Total: 23 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 32 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf