elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Datenschutz | Kontakt | English
Schriftgröße: [-] Text [+]

A Hybrid algorithm based on Bayesian Optimization and Interior Point OPTimizer for Optimal Operation of Energy Conversion Systems

Kyriakidis, Loukas und Mendez, Miguel Alfonso und Bähr, Martin (2023) A Hybrid algorithm based on Bayesian Optimization and Interior Point OPTimizer for Optimal Operation of Energy Conversion Systems. In: 36th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems, ECOS 2023, Seiten 1299-1310. 36TH INTERNATIONAL CONFERENCE ON EFFICIENCY, COST, OPTIMIZATION, SIMULATION AND ENVIRONMENTAL IMPACT OF ENERGY SYSTEMS, 2023-06-25 - 2023-06-30, Las Palmas de Gran Canaria, Spanien. doi: 10.52202/069564-0118. ISBN 978-171387492-8.

[img] PDF
1MB

Offizielle URL: https://www.proceedings.com/069564-0118.html

Kurzfassung

Optimization methods are essential to improve the operation of energy conversion systems including energy storage equipment and fluctuating renewable energy. Modern systems consist of many components, operating in a wide range of conditions and governed by nonlinear balance equations. Consequently, identifying their optimal operation (e.g. minimizing operational costs) requires solving challenging optimization problems, with the global optimum often hidden behind many local ones. In this work, we propose a hybrid method that advantageously combines Bayesian optimization (BO) and Interior Point OPTimizer (IPOPT). The BO is a global approach which exploits Gaussian process regression to build a surrogate model of the cost function to be optimized, while IPOPT is a local approach which uses quasi-Newton updates. The proposed BO-IPOPT combination allows leveraging the parameter space exploration of the BO with the quasi-Newton convergence of IPOPT once solution candidates are in the neighbourhood of an optimum. Using a challenging constrained test function, we test BO-IPOPT in accuracy, robustness and computational efficiency. Finally, we showcase the proposed hybrid method in the optimal operation of an industrial energy conversion system for renewable steam generation.

elib-URL des Eintrags:https://elib.dlr.de/199648/
Dokumentart:Konferenzbeitrag (Vortrag)
Titel:A Hybrid algorithm based on Bayesian Optimization and Interior Point OPTimizer for Optimal Operation of Energy Conversion Systems
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Kyriakidis, Loukasloukas.kyriakidis (at) dlr.dehttps://orcid.org/0009-0003-6634-8579148635987
Mendez, Miguel Alfonsomiguel.alfonso.mendez (at) vki.ac.beNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Bähr, MartinMartin.Baehr (at) dlr.dehttps://orcid.org/0000-0002-5420-5947NICHT SPEZIFIZIERT
Datum:2023
Erschienen in:36th International Conference on Efficiency, Cost, Optimization, Simulation and Environmental Impact of Energy Systems, ECOS 2023
Referierte Publikation:Ja
Open Access:Ja
Gold Open Access:Nein
In SCOPUS:Ja
In ISI Web of Science:Nein
DOI:10.52202/069564-0118
Seitenbereich:Seiten 1299-1310
ISBN:978-171387492-8
Status:veröffentlicht
Stichwörter:Nonlinear global optimization, Bayesian optimization, IPOPT, Hybrid method, Renewable steam generation
Veranstaltungstitel:36TH INTERNATIONAL CONFERENCE ON EFFICIENCY, COST, OPTIMIZATION, SIMULATION AND ENVIRONMENTAL IMPACT OF ENERGY SYSTEMS
Veranstaltungsort:Las Palmas de Gran Canaria, Spanien
Veranstaltungsart:internationale Konferenz
Veranstaltungsbeginn:25 Juni 2023
Veranstaltungsende:30 Juni 2023
Veranstalter :ECOS 2023
HGF - Forschungsbereich:Energie
HGF - Programm:Materialien und Technologien für die Energiewende
HGF - Programmthema:Thermische Hochtemperaturtechnologien
DLR - Schwerpunkt:Energie
DLR - Forschungsgebiet:E SP - Energiespeicher
DLR - Teilgebiet (Projekt, Vorhaben):E - Dekarbonisierte Industrieprozesse
Standort: Cottbus
Institute & Einrichtungen:Institut für CO2-arme Industrieprozesse
Hinterlegt von: Kyriakidis, Loukas
Hinterlegt am:13 Dez 2023 12:47
Letzte Änderung:24 Apr 2024 21:00

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
electronic library verwendet EPrints 3.3.12
Gestaltung Webseite und Datenbank: Copyright © Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.