Receding-Horizon Control of Constrained Switched Systems with Neural Networks as Parametric Function Approximators
dc.date.accessioned | 2023-01-04T10:42:56Z | |
dc.date.available | 2023-01-04T10:42:56Z | |
dc.date.issued | 2022-11-21 | |
dc.identifier | doi:10.17170/kobra-202301047295 | |
dc.identifier.uri | http://hdl.handle.net/123456789/14328 | |
dc.description.sponsorship | Gefördert im Rahmen des Projekts DEAL | |
dc.language.iso | eng | |
dc.rights | Namensnennung 4.0 International | * |
dc.rights.uri | http://creativecommons.org/licenses/by/4.0/ | * |
dc.subject | Model approximation | eng |
dc.subject | Neural networks | eng |
dc.subject | Optimization | eng |
dc.subject | Online control | eng |
dc.subject | Reinforcement learning | eng |
dc.subject | Stability | eng |
dc.subject.ddc | 600 | |
dc.title | Receding-Horizon Control of Constrained Switched Systems with Neural Networks as Parametric Function Approximators | eng |
dc.type | Aufsatz | |
dcterms.abstract | This work studies receding-horizon control of discrete-time switched linear systems subject to polytopic constraints for the continuous states and inputs. The objective is to approximate the optimal receding-horizon control strategy for cases in which the online computation is intractable due to the necessity of solving mixed-integer quadratic programs in each discrete time instant. The proposed approach builds upon an approximated optimal finite-horizon control law in closed-loop form with guaranteed constraint satisfaction. The paper derives the properties of recursive feasibility and asymptotic stability for the proposed approach. A numerical example is provided for illustration and evaluation of the approach. | eng |
dcterms.accessRights | open access | |
dcterms.creator | Markolf, Lukas | |
dcterms.creator | Stursberg, Olaf | |
dcterms.extent | 16 Seiten | |
dc.relation.doi | doi:10.1007/s42979-022-01442-0 | |
dc.subject.swd | Modellprädiktive Regelung | ger |
dc.subject.swd | Neuronales Netz | ger |
dc.subject.swd | Optimierung | ger |
dc.subject.swd | Approximation | ger |
dc.subject.swd | Modell | ger |
dc.type.version | publishedVersion | |
dcterms.source.identifier | eissn:2661-8907 | |
dcterms.source.issue | issue 1 | |
dcterms.source.journal | SN Computer Science | eng |
dcterms.source.volume | Volume 4 | |
kup.iskup | false | |
dcterms.source.articlenumber | 62 |
Dateien zu dieser Ressource
Das Dokument erscheint in:
-
Artikel [1106]