000124057 001__ 124057 000124057 005__ 20240731103320.0 000124057 0247_ $$2doi$$a10.1016/j.engappai.2022.105567 000124057 0248_ $$2sideral$$a132647 000124057 037__ $$aART-2023-132647 000124057 041__ $$aeng 000124057 100__ $$aLopez Garcia, Tania B. 000124057 245__ $$aPower flow analysis via typed graph neural networks 000124057 260__ $$c2023 000124057 5060_ $$aAccess copy available to the general public$$fUnrestricted 000124057 5203_ $$aPower flow analyses are essential for the correct operation of power grids, however, electricity systems are becoming increasingly complex to analyze with the conventional numerical methods. The present work proposes a typed graph neural network based approach to solve the power flow problem. The neural networks are trained on benchmark power grid cases which are modified by varying the injections (load and generation), branch characteristics and topology. The solution to the power flow analysis is found when all voltage values are known. The proposed system infers the voltage magnitude and phase and is trained so that the obtained values minimize the violation of the physical laws that govern the system, this way the training is achieved in an unsupervised manner. The proposed solver has linear time complexity and is able to generalize to grids with considerably different conditions, including size, from the grids available during training. Though the training is unsupervised and does not suppose any ground truth data, the solutions obtained are found to have a close correlation with the conventional Newton–Raphson method. The results are additionally validated by finding the root mean square deviation from the Newton–Raphson method, and the faster, though less accurate, DC approximation method. 000124057 536__ $$9info:eu-repo/grantAgreement/ES/MICINN/PID2019-104711RB-100 000124057 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc-nd$$uhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/ 000124057 590__ $$a7.5$$b2023 000124057 592__ $$a1.749$$b2023 000124057 591__ $$aAUTOMATION & CONTROL SYSTEMS$$b6 / 84 = 0.071$$c2023$$dQ1$$eT1 000124057 593__ $$aArtificial Intelligence$$c2023$$dQ1 000124057 591__ $$aENGINEERING, MULTIDISCIPLINARY$$b5 / 179 = 0.028$$c2023$$dQ1$$eT1 000124057 593__ $$aElectrical and Electronic Engineering$$c2023$$dQ1 000124057 591__ $$aENGINEERING, ELECTRICAL & ELECTRONIC$$b25 / 352 = 0.071$$c2023$$dQ1$$eT1 000124057 593__ $$aControl and Systems Engineering$$c2023$$dQ1 000124057 591__ $$aCOMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE$$b24 / 197 = 0.122$$c2023$$dQ1$$eT1 000124057 594__ $$a9.6$$b2023 000124057 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion 000124057 700__ $$0(orcid)0000-0002-4770-0069$$aDomínguez Navarro, José A.$$uUniversidad de Zaragoza 000124057 7102_ $$15009$$2535$$aUniversidad de Zaragoza$$bDpto. Ingeniería Eléctrica$$cÁrea Ingeniería Eléctrica 000124057 773__ $$g117, Pat A (2023), 105567 [11 pp]$$pEng. appl. artif. intell.$$tENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE$$x0952-1976 000124057 8564_ $$s1027358$$uhttps://zaguan.unizar.es/record/124057/files/texto_completo.pdf$$yVersión publicada 000124057 8564_ $$s2899412$$uhttps://zaguan.unizar.es/record/124057/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada 000124057 909CO $$ooai:zaguan.unizar.es:124057$$particulos$$pdriver 000124057 951__ $$a2024-07-31-09:42:40 000124057 980__ $$aARTICLE