000148610 001__ 148610 000148610 005__ 20260217205523.0 000148610 0247_ $$2doi$$a10.1109/TPWRS.2024.3394371 000148610 0248_ $$2sideral$$a141954 000148610 037__ $$aART-2024-141954 000148610 041__ $$aeng 000148610 100__ $$aLopez-Garcia, Tania B. 000148610 245__ $$aOptimal Power Flow With Physics-Informed Typed Graph Neural Networks 000148610 260__ $$c2024 000148610 5060_ $$aAccess copy available to the general public$$fUnrestricted 000148610 5203_ $$aThis work describes a new way to solve the optimal power flow problem applying typed graph neural networks. Typed graph neural networks allow the representation of different elements of transmission systems with different types of nodes, thus adding accuracy and interpretability to the solutions obtained, in comparison to results obtained with conventional feed-forward neural network models. The proposed graph neural network architecture is trained without the need of training data, through a physics informed loss function which incorporates not only the optimization objective, but also operational constraints of the physical system. Results are comparable with those obtained with the interior point method, and it is shown that the calculation time is greatly reduced. 000148610 536__ $$9info:eu-repo/grantAgreement/ES/MICINN/PID2019-104711RB-100 000148610 540__ $$9info:eu-repo/semantics/openAccess$$aby$$uhttps://creativecommons.org/licenses/by/4.0/deed.es 000148610 590__ $$a7.2$$b2024 000148610 592__ $$a3.629$$b2024 000148610 591__ $$aENGINEERING, ELECTRICAL & ELECTRONIC$$b39 / 368 = 0.106$$c2024$$dQ1$$eT1 000148610 593__ $$aEnergy Engineering and Power Technology$$c2024$$dQ1 000148610 593__ $$aElectrical and Electronic Engineering$$c2024$$dQ1 000148610 594__ $$a15.9$$b2024 000148610 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion 000148610 700__ $$0(orcid)0000-0002-4770-0069$$aDomínguez-Navarro, José Antonio$$uUniversidad de Zaragoza 000148610 7102_ $$15009$$2535$$aUniversidad de Zaragoza$$bDpto. Ingeniería Eléctrica$$cÁrea Ingeniería Eléctrica 000148610 773__ $$g40, 1 (2024), 381-393$$pIEEE trans. power syst.$$tIEEE TRANSACTIONS ON POWER SYSTEMS$$x0885-8950 000148610 8564_ $$s3075196$$uhttps://zaguan.unizar.es/record/148610/files/texto_completo.pdf$$yVersión publicada 000148610 8564_ $$s3509408$$uhttps://zaguan.unizar.es/record/148610/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada 000148610 909CO $$ooai:zaguan.unizar.es:148610$$particulos$$pdriver 000148610 951__ $$a2026-02-17-20:29:19 000148610 980__ $$aARTICLE