{"authors":[{"id":"orcid_______::59337b3f45f05a9146822ce4568c2c39","fullName":"Mohamed Hassouna","name":"Mohamed","surname":"Hassouna","rank":1,"pid":{"id":{"scheme":"orcid","value":"0000-0001-9927-1625"},"provenance":null}},{"id":"orcid_______::6035ba9fe01f805665ecdaf7fdf2731b","fullName":"Clara Holzhüter","name":"Clara","surname":"Holzhüter","rank":2,"pid":{"id":{"scheme":"orcid","value":"0000-0001-8365-5544"},"provenance":null}},{"id":"orcid_______::1825d9789fd9328d8d4df04f155f431b","fullName":"Pawel Lytaev","name":"Pawel","surname":"Lytaev","rank":3,"pid":{"id":{"scheme":"orcid","value":"0009-0002-9791-0651"},"provenance":null}},{"id":null,"fullName":"Josephine Thomas","name":"Josephine","surname":"Thomas","rank":4,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0001-7166-9973"},"provenance":null}},{"id":null,"fullName":"Bernhard Sick","name":"Bernhard","surname":"Sick","rank":5,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0001-9467-656x"},"provenance":null}},{"id":null,"fullName":"Christoph Scholz","name":"Christoph","surname":"Scholz","rank":6,"pid":{"id":{"scheme":"orcid_pending","value":"0000-0002-8719-8261"},"provenance":null}}],"openAccessColor":"gold","publiclyFunded":false,"eoscIfGuidelines":null,"type":"publication","language":{"code":"eng","label":"English"},"countries":null,"subjects":[{"subject":{"scheme":"keyword","value":"Machine Learning"},"provenance":null},{"subject":{"scheme":"keyword","value":"FOS: Computer and information sciences"},"provenance":null},{"subject":{"scheme":"FOS","value":"0202 electrical engineering, electronic engineering, information engineering"},"provenance":null},{"subject":{"scheme":"FOS","value":"02 engineering and technology"},"provenance":null},{"subject":{"scheme":"keyword","value":"Machine Learning (cs.LG)"},"provenance":null}],"mainTitle":"Graph reinforcement learning for power grids: A comprehensive survey","subTitle":null,"descriptions":["The increasing share of renewable energy and distributed electricity generation requires the development of deep learning approaches to address the lack of flexibility inherent in traditional power grid methods. In this context, Graph Neural Networks are a promising solution due to their ability to learn from graph-structured data. Combined with Reinforcement Learning, they can be used as control approaches to determine remedial actions. This review analyses how Graph Reinforcement Learning can improve representation learning and decision-making in power grid applications, particularly transmission and distribution grids. We analyze the reviewed approaches in terms of the graph structure, the Graph Neural Network architecture, and the Reinforcement Learning approach. Although Graph Reinforcement Learning has demonstrated adaptability to unpredictable events and noisy data, its current stage is primarily proof-of-concept, and it is not yet deployable to real-world applications. We highlight the open challenges and limitations for real-world applications.","Accepted in Energy & AI, in-press"],"publicationDate":"2026-01-01","publisher":"Elsevier BV","embargoEndDate":"2024-07-01","sources":["Crossref"],"formats":null,"contributors":null,"coverages":null,"bestAccessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/"},"container":{"name":"Energy and AI","issnPrinted":"2666-5468","issnOnline":null,"issnLinking":null,"ep":null,"iss":null,"sp":"100671","vol":"23","edition":null,"conferencePlace":null,"conferenceDate":null},"documentationUrls":null,"codeRepositoryUrl":null,"programmingLanguage":null,"contactPeople":null,"contactGroups":null,"tools":null,"size":null,"version":null,"geoLocations":null,"id":"doi_dedup___::a20260a8865a8bef31ea57cb5716fb07","originalIds":["S2666546825002034","10.1016/j.egyai.2025.100671","50|doiboost____|cb9992eb79c188518bd3517776b11a66","50|datacite____::a20260a8865a8bef31ea57cb5716fb07","10.48550/arxiv.2407.04522","50|od________18::8de62ed2dc94e6e8ce8c592b300a9a32","oai:arXiv.org:2407.04522","50|od______2659::a9e65d2f49aeee173194d1eff1994004","oai:zenodo.org:13891957"],"pids":[{"scheme":"doi","value":"10.1016/j.egyai.2025.100671"},{"scheme":"doi","value":"10.48550/arxiv.2407.04522"},{"scheme":"arXiv","value":"2407.04522"}],"dateOfCollection":null,"lastUpdateTimeStamp":null,"indicators":{"citationImpact":{"citationCount":2.0,"influence":2.4375761E-9,"popularity":4.115475E-9,"impulse":2.0,"citationClass":"C5","influenceClass":"C5","impulseClass":"C5","popularityClass":"C4"}},"projects":[{"id":"corda_____he::9a3e6aafb94e5508d24fc838af2b828c","code":"101119527","acronym":"AI4REALNET","title":"AI for REAL-world NETwork operation","funder":"European Commission","pids":[{"scheme":"doi","value":"10.3030/101119527"}]}],"organizations":[{"legalName":"Fraunhofer Institute for Energy Economics and Energy System Technology","acronym":"Fraunhofer Institute for Energy Economics and Energy System Technology","id":"pending_org_::c78939c98b8ba8d9814dd8f1ca8ff6c5","pids":null},{"legalName":"Fraunhofer Society","acronym":"FHG","id":"openorgs____::76681f01bcfcc1ff3405bed86eea99b2","pids":[{"scheme":"RRID","value":"RRID:nlx_157956"},{"scheme":"PIC","value":"999659400"},{"scheme":"PIC","value":"999598290"},{"scheme":"PIC","value":"999984059"},{"scheme":"RRID","value":"RRID:SCR_011231"},{"scheme":"ISNI","value":"0000000092613939"},{"scheme":"FundRef","value":"501100003185"},{"scheme":"fundref","value":"501100003185"},{"scheme":"OrgReg","value":"DE1053"},{"scheme":"PIC","value":"999934589"},{"scheme":"OrgRef","value":"197440"},{"scheme":"GRID","value":"grid.4561.6"},{"scheme":"wikidata","value":"Q161057"},{"scheme":"ROR","value":"https://ror.org/05hkkdn48"},{"scheme":"mag_id","value":"4923324"},{"scheme":"Wikidata","value":"Q161057"}]},{"legalName":"B-com Institute of Research and Technology","acronym":"B-com Institute of Research and Technology","id":"openorgs____::209aa7fdd5b7347e0139e6436c0e0468","pids":[{"scheme":"GRID","value":"grid.481987.b"},{"scheme":"GRID","value":"grid.488851.8"},{"scheme":"PIC","value":"949729135"},{"scheme":"mag_id","value":"3018083178"},{"scheme":"ROR","value":"https://ror.org/03cejhk28"}]},{"legalName":"University of Kassel","acronym":"University of Kassel","id":"openorgs____::53cbdda3532612ce5a760a2130a1c798","pids":[{"scheme":"Wikidata","value":"Q833822"},{"scheme":"wikidata","value":"Q17058439"},{"scheme":"OrgRef","value":"18160530"},{"scheme":"ISNI","value":"0000000110891036"},{"scheme":"PIC","value":"999852624"},{"scheme":"FundRef","value":"501100012687"},{"scheme":"Wikidata","value":"Q17058439"},{"scheme":"mag_id","value":"106157433"},{"scheme":"GRID","value":"grid.5155.4"},{"scheme":"ROR","value":"https://ror.org/04zc7p361"},{"scheme":"wikidata","value":"Q833822"},{"scheme":"fundref","value":"501100012687"}]},{"legalName":"Fraunhofer Institute for Energy Economics and Energy System Technology","acronym":"IEE","id":"openorgs____::065dfd47a3450ac7ba9212692ee32037","pids":[{"scheme":"wikidata","value":"Q71250662"},{"scheme":"GRID","value":"grid.506250.4"},{"scheme":"ROR","value":"https://ror.org/05ptp9d64"},{"scheme":"ISNI","value":"0000000474706073"},{"scheme":"Wikidata","value":"Q71250662"}]}],"communities":[{"code":"eosc","label":"EOSC","provenance":null},{"code":"heosp","label":"Hessian Open Science Portal","provenance":null}],"collectedFrom":[{"key":"openaire____::9e3be59865b2c1c335d32dae2fe7b254","value":"Datacite"},{"key":"opendoar____::358aee4cc897452c00244351e4d91f69","value":"ZENODO"},{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"},{"key":"opendoar____::6f4922f45568161a8cdf4ad2299f6d23","value":"arXiv.org e-Print Archive"}],"instances":[{"pids":[{"scheme":"doi","value":"10.1016/j.egyai.2025.100671"}],"license":"CC BY","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":"gold"},"type":"Article","urls":["https://doi.org/10.1016/j.egyai.2025.100671"],"publicationDate":"2026-01-01","refereed":"peerReviewed","hostedBy":{"key":"doajarticles::f09d699aa6f3ef8f2b95b8988d38996e","value":"Energy and AI"},"collectedFrom":{"key":"openaire____::081b82f96300b6a6e3d282bad31cb6e2","value":"Crossref"}},{"pids":[{"scheme":"doi","value":"10.48550/arxiv.2407.04522"}],"license":"CC BY","type":"Article","urls":["https://dx.doi.org/10.48550/arxiv.2407.04522"],"publicationDate":"2024-01-01","refereed":"nonPeerReviewed","hostedBy":{"key":"openaire____::55045bd2a65019fd8e6741a755395c8c","value":"Unknown Repository"},"collectedFrom":{"key":"openaire____::9e3be59865b2c1c335d32dae2fe7b254","value":"Datacite"}},{"pids":[{"scheme":"arXiv","value":"2407.04522"}],"alternateIdentifiers":[{"scheme":"doi","value":"10.1016/j.egyai.2025.100671"}],"accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Preprint","urls":["http://arxiv.org/abs/2407.04522"],"publicationDate":"2024-07-05","refereed":"nonPeerReviewed","hostedBy":{"key":"opendoar____::6f4922f45568161a8cdf4ad2299f6d23","value":"arXiv.org e-Print Archive"},"collectedFrom":{"key":"opendoar____::6f4922f45568161a8cdf4ad2299f6d23","value":"arXiv.org e-Print Archive"}},{"alternateIdentifiers":[{"scheme":"oai","value":"oai:zenodo.org:13891957"},{"scheme":"doi","value":"10.48550/arxiv.2407.04522"}],"license":"CC BY","accessRight":{"code":"c_abf2","label":"OPEN","scheme":"http://vocabularies.coar-repositories.org/documentation/access_rights/","openAccessRoute":null},"type":"Journal","urls":["http://dx.doi.org/10.48550/ARXIV.2407.04522","https://zenodo.org/records/13891957"],"publicationDate":"2024-07-05","refereed":"nonPeerReviewed","hostedBy":{"key":"opendoar____::358aee4cc897452c00244351e4d91f69","value":"ZENODO"},"collectedFrom":{"key":"opendoar____::358aee4cc897452c00244351e4d91f69","value":"ZENODO"}}],"links":[{"header":{"relationType":"resultProject","relationClass":"isProducedBy","relatedIdentifier":"corda_____he::9a3e6aafb94e5508d24fc838af2b828c","relatedRecordType":"project","relationProvenance":"sysimport:crosswalk:repository","trust":"0.9"},"collectedfrom":[{"dsId":"openaire____::3f264f93cf3b0cfc4ede188a6300455c","dsName":"CORDA - COmmon Research DAta Warehouse - Horizon Europe"}],"projectTitle":"AI for REAL-world NETwork operation","code":"101119527","funding":{"funder":{"id":"ec__________::EC","shortname":"EC","name":"European Commission","jurisdiction":{"code":"EU","label":"European Union"},"pid":null},"level0":{"id":"ec__________::EC::HE","description":"Horizon Europe Framework Programme","name":"HE"},"level1":{"id":"ec__________::EC::HE::HORIZON-RIA","description":"HORIZON  Research and Innovation Actions","name":"HORIZON-RIA"},"level2":{"id":null,"description":null,"name":null}},"startDate":"2023-10-01","endDate":"2027-03-31"}],"otherTitles":null,"inDiamondJournal":false,"green":true,"isGreen":true,"isInDiamondJournal":false}