000894319 001__ 894319
000894319 005__ 20240712112901.0
000894319 0247_ $$2doi$$a10.1016/j.ifacol.2020.12.1207
000894319 0247_ $$2ISSN$$a1474-6670
000894319 0247_ $$2ISSN$$a2405-8963
000894319 0247_ $$2ISSN$$a2405-8971
000894319 0247_ $$2ISSN$$a2589-3653
000894319 0247_ $$2Handle$$a2128/28412
000894319 0247_ $$2WOS$$aWOS:000652593000151
000894319 037__ $$aFZJ-2021-03179
000894319 082__ $$a600
000894319 1001_ $$0P:(DE-Juel1)180221$$aDoncevic, Danimir$$b0$$ufzj
000894319 1112_ $$a1st Virtual IFAC World Congress$$conline$$d2020-07-11 - 2020-07-17$$wGermany
000894319 245__ $$aDeterministic Global Nonlinear Model Predictive Control with Neural Networks Embedded
000894319 260__ $$aLaxenburg$$bIFAC$$c2020
000894319 300__ $$a5273 - 5278
000894319 3367_ $$2ORCID$$aCONFERENCE_PAPER
000894319 3367_ $$033$$2EndNote$$aConference Paper
000894319 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$mjournal
000894319 3367_ $$2BibTeX$$aINPROCEEDINGS
000894319 3367_ $$2DRIVER$$aconferenceObject
000894319 3367_ $$2DataCite$$aOutput Types/Conference Paper
000894319 3367_ $$0PUB:(DE-HGF)8$$2PUB:(DE-HGF)$$aContribution to a conference proceedings$$bcontrib$$mcontrib$$s1628086682_30450
000894319 520__ $$aNonlinear model predictive control requires the solution of nonlinear programs with potentially multiple local solutions. Here, deterministic global optimization can guarantee to find a global optimum. However, its application is currently severely limited by computational cost and requires further developments in problem formulation, optimization solvers, and computing architectures. In this work, we propose a reduced-space formulation for the global optimization of problems with recurrent neural networks (RNN) embedded, based on our recent work on feed-forward artificial neural networks embedded. The method reduces the dimensionality of the optimization problem significantly, lowering the computational cost. We implement the NMPC problem in our open-source solver MAiNGO and solve it using parallel computing on 40 cores. We demonstrate real-time capability for the illustrative van de Vusse CSTR case study. We further propose two alternatives to reduce computational time: i) reformulate the RNN model by exposing a selected state variable to the optimizer; ii) replace the RNN with a neural multi-model. In our numerical case studies each proposal results in a reduction of computational time by an order of magnitude.
000894319 536__ $$0G:(DE-HGF)POF4-1121$$a1121 - Digitalization and Systems Technology for Flexibility Solutions (POF4-112)$$cPOF4-112$$fPOF IV$$x0
000894319 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
000894319 7001_ $$0P:(DE-HGF)0$$aSchweidtmann, Artur M.$$b1
000894319 7001_ $$0P:(DE-HGF)0$$aVaupel, Yannic$$b2
000894319 7001_ $$0P:(DE-HGF)0$$aSchäfer, Pascal$$b3
000894319 7001_ $$0P:(DE-HGF)0$$aCaspari, Adrian$$b4
000894319 7001_ $$0P:(DE-Juel1)172025$$aMitsos, Alexander$$b5$$eCorresponding author$$ufzj
000894319 773__ $$0PERI:(DE-600)2839185-8$$a10.1016/j.ifacol.2020.12.1207$$gVol. 53, no. 2, p. 5273 - 5278$$n2$$p5273 - 5278$$tIFAC-PapersOnLine$$v53$$x2405-8963$$y2020
000894319 8564_ $$uhttps://juser.fz-juelich.de/record/894319/files/1-s2.0-S2405896320316037-main.pdf$$yOpenAccess
000894319 909CO $$ooai:juser.fz-juelich.de:894319$$pdnbdelivery$$pdriver$$pVDB$$popen_access$$popenaire
000894319 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)180221$$aForschungszentrum Jülich$$b0$$kFZJ
000894319 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-Juel1)180221$$aRWTH Aachen$$b0$$kRWTH
000894319 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b1$$kRWTH
000894319 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b2$$kRWTH
000894319 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b3$$kRWTH
000894319 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-HGF)0$$aRWTH Aachen$$b4$$kRWTH
000894319 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172025$$aForschungszentrum Jülich$$b5$$kFZJ
000894319 9101_ $$0I:(DE-588b)36225-6$$6P:(DE-Juel1)172025$$aRWTH Aachen$$b5$$kRWTH
000894319 9131_ $$0G:(DE-HGF)POF4-112$$1G:(DE-HGF)POF4-110$$2G:(DE-HGF)POF4-100$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-1121$$aDE-HGF$$bForschungsbereich Energie$$lEnergiesystemdesign (ESD)$$vDigitalisierung und Systemtechnik$$x0
000894319 9141_ $$y2021
000894319 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2020-08-27
000894319 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
000894319 915__ $$0LIC:(DE-HGF)CCBYNCND4$$2HGFVOC$$aCreative Commons Attribution-NonCommercial-NoDerivs CC BY-NC-ND 4.0
000894319 920__ $$lyes
000894319 9201_ $$0I:(DE-Juel1)IEK-10-20170217$$kIEK-10$$lModellierung von Energiesystemen$$x0
000894319 9801_ $$aFullTexts
000894319 980__ $$acontrib
000894319 980__ $$aVDB
000894319 980__ $$aUNRESTRICTED
000894319 980__ $$ajournal
000894319 980__ $$aI:(DE-Juel1)IEK-10-20170217
000894319 981__ $$aI:(DE-Juel1)ICE-1-20170217