{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T15:41:54Z","timestamp":1787758914350,"version":"build-2784847793"},"reference-count":47,"publisher":"AIP Publishing","issue":"11","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62473001"],"award-info":[{"award-number":["62473001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003995","name":"Natural Science Foundation of Anhui Province","doi-asserted-by":"publisher","award":["2208085MF174"],"award-info":[{"award-number":["2208085MF174"]}],"id":[{"id":"10.13039\/501100003995","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,1]]},"abstract":"<jats:p>Power flow calculation plays a significant role in the operation and planning of modern power systems. Traditional numerical calculation methods have good interpretability but high time complexity. They are unable to cope with increasing amounts of data in power systems; therefore, many machine learning based methods have been proposed for more efficient power flow calculation. Despite the good performance of these methods in terms of computation speed, they often overlook the importance of transmission lines and do not fully consider the physical mechanisms in the power systems, thereby weakening the prediction accuracy of power flow. Given the importance of the transmission lines as well as to comprehensively consider their mutual influence, we shift our focus from bus adjacency relationships to transmission line adjacency relationships and propose a physics-informed line graph neural network framework. This framework propagates information between buses and transmission lines by introducing the concepts of the incidence matrix and the line graph matrix. Based on the mechanics of the power flow equations, we further design a loss function by integrating physical information to ensure that the output results of the model satisfy the laws of physics and have better interpretability. Experimental results on different power grid datasets and different scenarios demonstrate the accuracy of our proposed model.<\/jats:p>","DOI":"10.1063\/5.0235301","type":"journal-article","created":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T16:23:09Z","timestamp":1731082989000},"update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":8,"title":["Physics-informed line graph neural network for power flow calculation"],"prefix":"10.1063","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7094-669X","authenticated-orcid":false,"given":"Hai-Feng","family":"Zhang","sequence":"first","affiliation":[{"name":"The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, School of Mathematical Science, Anhui University 1 , Hefei 230601,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5679-9299","authenticated-orcid":false,"given":"Xin-Long","family":"Lu","sequence":"additional","affiliation":[{"name":"The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Institutes of Physical Science and Information Technology, Anhui University 2 , Hefei 230601,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0863-242X","authenticated-orcid":false,"given":"Xiao","family":"Ding","sequence":"additional","affiliation":[{"name":"The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, School of Mathematical Science, Anhui University 1 , Hefei 230601,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3134-9294","authenticated-orcid":false,"given":"Xiao-Ming","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Institutes of Physical Science and Information Technology, Anhui University 2 , Hefei 230601,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"317","published-online":{"date-parts":[[2024,11,8]]},"reference":[{"key":"2024110816230196300_c1","doi-asserted-by":"publisher","first-page":"12159","DOI":"10.1073\/pnas.1309151110","article-title":"Transdisciplinary electric power grid science","volume":"110","year":"2013","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"2024110816230196300_c2","doi-asserted-by":"publisher","first-page":"013139","DOI":"10.1063\/5.0175372","article-title":"Predicting dynamic stability from static features in power grid models using machine learning","volume":"34","year":"2024","journal-title":"Chaos"},{"key":"2024110816230196300_c3","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1109\/tcsii.2017.2705758","article-title":"Robustness of interdependent power grids and communication networks: A complex network perspective","volume":"65","year":"2017","journal-title":"IEEE Trans. Circuits Syst. II: Express Br."},{"key":"2024110816230196300_c4","doi-asserted-by":"publisher","first-page":"258301","DOI":"10.1103\/PhysRevLett.120.258301","article-title":"Emergent failures and cascades in power grids: A statistical physics perspective","volume":"120","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"2024110816230196300_c5","doi-asserted-by":"publisher","first-page":"012311","DOI":"10.1103\/PhysRevE.102.012311","article-title":"State estimation of power flows for smart grids via belief propagation","volume":"102","year":"2020","journal-title":"Phys. Rev. E"},{"key":"2024110816230196300_c6","doi-asserted-by":"publisher","first-page":"113121","DOI":"10.1063\/5.0011187","article-title":"Effects of demand control on the complex dynamics of electric power system blackouts","volume":"30","year":"2020","journal-title":"Chaos"},{"key":"2024110816230196300_c7","doi-asserted-by":"publisher","first-page":"103103","DOI":"10.1063\/5.0160915","article-title":"Toward dynamic stability assessment of power grid topologies using graph neural networks","volume":"33","year":"2023","journal-title":"Chaos"},{"key":"2024110816230196300_c8","doi-asserted-by":"publisher","first-page":"1866","DOI":"10.1109\/TPAS.1968.292150","article-title":"Optimal power flow solutions","volume":"PAS-87","year":"1968","journal-title":"IEEE Trans. Power Appar. Syst."},{"key":"2024110816230196300_c9","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1109\/TPWRS.2015.2395452","article-title":"On the existence and linear approximation of the power flow solution in power distribution networks","volume":"31","year":"2015","journal-title":"IEEE Trans. Power Syst."},{"key":"2024110816230196300_c10","doi-asserted-by":"publisher","first-page":"043003","DOI":"10.1103\/PRXEnergy.2.043003","article-title":"Physics-informed machine learning for power grid frequency modeling","volume":"2","year":"2023","journal-title":"PRX Energy"},{"key":"2024110816230196300_c11","doi-asserted-by":"publisher","first-page":"013127","DOI":"10.1063\/5.0180204","article-title":"Predicting Braess\u2019s paradox of power grids using graph neural networks","volume":"34","year":"2024","journal-title":"Chaos"},{"key":"2024110816230196300_c12"},{"key":"2024110816230196300_c13"},{"key":"2024110816230196300_c14"},{"key":"2024110816230196300_c15","doi-asserted-by":"publisher","first-page":"013181","DOI":"10.1103\/PhysRevResearch.6.013181","article-title":"Inferring attracting basins of power system with machine learning","volume":"6","year":"2024","journal-title":"Phys. Rev. Res."},{"key":"2024110816230196300_c16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tim.2023.3293555","article-title":"Deep learning for power quality event detection and classification based on measured grid data","volume":"72","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"2024110816230196300_c17","doi-asserted-by":"publisher","first-page":"2459","DOI":"10.1109\/TSTE.2021.3100846","article-title":"Scheduling thermostatically controlled loads to provide regulation capacity based on a learning-based optimal power flow model","volume":"12","year":"2021","journal-title":"IEEE Trans. Sustain. Energy"},{"key":"2024110816230196300_c18","doi-asserted-by":"publisher","first-page":"033005","DOI":"10.1103\/PRXEnergy.1.033005","article-title":"Defending smart electrical power grids against cyberattacks with deep Q-learning","volume":"1","year":"2022","journal-title":"PRX Energy"},{"key":"2024110816230196300_c19","doi-asserted-by":"publisher","first-page":"2475","DOI":"10.1109\/TPWRS.2020.2975455","article-title":"Linearizing power flow model: A hybrid physical model-driven and data-driven approach","volume":"35","year":"2020","journal-title":"IEEE Trans. Power Syst."},{"key":"2024110816230196300_c20","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1109\/TPWRS.2020.3001919","article-title":"Data-driven optimal power flow: A physics-informed machine learning approach","volume":"36","year":"2021","journal-title":"IEEE Trans. Power Syst."},{"key":"2024110816230196300_c21"},{"key":"2024110816230196300_c22","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","year":"2008","journal-title":"IEEE Trans. Neural Netw."},{"key":"2024110816230196300_c23"},{"key":"2024110816230196300_c24","doi-asserted-by":"publisher","first-page":"2234","DOI":"10.1109\/TPWRS.2022.3187218","article-title":"Leveraging power grid topology in machine learning assisted optimal power flow","volume":"38","year":"2022","journal-title":"IEEE Trans. Power Syst."},{"key":"2024110816230196300_c25","doi-asserted-by":"publisher","first-page":"3632","DOI":"10.1109\/tpwrs.2022.3205043","article-title":"Cascading failure analysis based on a physics-informed graph neural network","volume":"38","year":"2023","journal-title":"IEEE Trans. Power Syst."},{"key":"2024110816230196300_c26","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1109\/JSYST.2022.3201041","article-title":"DeepOPF: A feasibility-optimized deep neural network approach for AC optimal power flow problems","volume":"17","year":"2023","journal-title":"IEEE Syst. J."},{"key":"2024110816230196300_c27","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1016\/j.ejor.2020.01.034","article-title":"A survey on conic relaxations of optimal power flow problem","volume":"287","year":"2020","journal-title":"Eur. J. Oper. Res."},{"key":"2024110816230196300_c28","doi-asserted-by":"publisher","first-page":"666","DOI":"10.1109\/TPWRS.2021.3097066","article-title":"An exact sequential linear programming algorithm for the optimal power flow problem","volume":"37","year":"2021","journal-title":"IEEE Trans. Power Syst."},{"key":"2024110816230196300_c29","doi-asserted-by":"publisher","first-page":"650","DOI":"10.1109\/TCSI.2016.2529281","article-title":"Convex relaxations of optimal power flow problems: An illustrative example","volume":"63","year":"2016","journal-title":"IEEE Trans. Circuits Syst. I: Regul. Pap."},{"key":"2024110816230196300_c30","doi-asserted-by":"publisher","first-page":"1459","DOI":"10.1109\/TPWRS.2018.2874072","article-title":"Convex relaxations and approximations of chance-constrained AC-OPF problems","volume":"34","year":"2019","journal-title":"IEEE Trans. Power Syst."},{"key":"2024110816230196300_c31","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1016\/j.ijepes.2007.12.003","article-title":"Semidefinite programming for optimal power flow problems","volume":"30","year":"2008","journal-title":"Int. J. Electr. Power Energy Syst."},{"key":"2024110816230196300_c32","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.1109\/TPWRS.2008.926439","article-title":"Optimal power flow using an extended conic quadratic formulation","volume":"23","year":"2008","journal-title":"IEEE Trans. Power Syst."},{"key":"2024110816230196300_c33","doi-asserted-by":"publisher","first-page":"2235","DOI":"10.1109\/TSG.2019.2950115","article-title":"Fast calculation of probabilistic power flow: A model-based deep learning approach","volume":"11","year":"2019","journal-title":"IEEE Trans. Smart Grid"},{"key":"2024110816230196300_c34","doi-asserted-by":"publisher","first-page":"6376","DOI":"10.1109\/TSG.2019.2903767","article-title":"Joint chance constraints in AC optimal power flow: Improving bounds through learning","volume":"10","year":"2019","journal-title":"IEEE Trans. Smart Grid"},{"key":"2024110816230196300_c35","doi-asserted-by":"publisher","first-page":"209","DOI":"10.17775\/cseejpes.2020.02700","article-title":"Deep learning in power systems research: A review","volume":"7","year":"2020","journal-title":"CSEE J. Power Energy Syst."},{"key":"2024110816230196300_c36"},{"key":"2024110816230196300_c37","doi-asserted-by":"publisher","first-page":"106547","DOI":"10.1016\/j.epsr.2020.106547","article-title":"Neural networks for power flow: Graph neural solver","volume":"189","year":"2020","journal-title":"Electr. Power Syst. Res."},{"key":"2024110816230196300_c38"},{"key":"2024110816230196300_c39"},{"key":"2024110816230196300_c40","doi-asserted-by":"publisher","first-page":"2082","DOI":"10.1109\/TPWRS.2020.3029557","article-title":"Physics-guided deep neural networks for power flow analysis","volume":"36","year":"2020","journal-title":"IEEE Trans. Power Syst."},{"key":"2024110816230196300_c41","doi-asserted-by":"publisher","first-page":"5660","DOI":"10.1109\/TPWRS.2022.3230555","article-title":"Topology-aware graph neural networks for learning feasible and adaptive AC-OPF solutions","volume":"38","year":"2023","journal-title":"IEEE Trans. Power Syst."},{"key":"2024110816230196300_c42","doi-asserted-by":"publisher","first-page":"2450142","DOI":"10.1142\/S0218127424501426","article-title":"Node centrality based on edge dynamics in a chaotic network","volume":"34","year":"2024","journal-title":"Int. J. Bifurc. Chaos"},{"key":"2024110816230196300_c43","doi-asserted-by":"publisher","first-page":"109958","DOI":"10.1016\/j.ress.2024.109958","article-title":"Dual nature of cyber-physical power systems and the mitigation strategies","volume":"244","year":"2024","journal-title":"Reliab. Eng. Syst. Saf."},{"key":"2024110816230196300_c44"},{"key":"2024110816230196300_c45"},{"key":"2024110816230196300_c46","doi-asserted-by":"publisher","first-page":"1098","DOI":"10.35833\/MPCE.2020.000885","article-title":"Deep reinforcement learning based real-time AC optimal power flow considering uncertainties","volume":"10","year":"2022","journal-title":"J. Mod. Power Syst. Clean Energy"},{"key":"2024110816230196300_c47","doi-asserted-by":"publisher","first-page":"108412","DOI":"10.1016\/j.epsr.2022.108412","article-title":"Physics-informed neural networks for AC optimal power flow","volume":"212","year":"2022","journal-title":"Electr. Power Syst. Res."}],"container-title":["Chaos: An Interdisciplinary Journal of Nonlinear Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/aip\/cha\/article-pdf\/doi\/10.1063\/5.0235301\/20241171\/113123_1_5.0235301.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/aip\/cha\/article-pdf\/doi\/10.1063\/5.0235301\/20241171\/113123_1_5.0235301.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T16:23:10Z","timestamp":1731082990000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/cha\/article\/34\/11\/113123\/3319453\/Physics-informed-line-graph-neural-network-for"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"references-count":47,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2024,11,1]]}},"URL":"https:\/\/doi.org\/10.1063\/5.0235301","relation":{},"ISSN":["1054-1500","1089-7682"],"issn-type":[{"value":"1054-1500","type":"print"},{"value":"1089-7682","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,11]]},"published":{"date-parts":[[2024,11,1]]},"article-number":"113123"}}