{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T21:38:18Z","timestamp":1771018698992,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFA1004600"],"award-info":[{"award-number":["2022YFA1004600"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125304"],"award-info":[{"award-number":["62125304"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62192751"],"award-info":[{"award-number":["62192751"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073182"],"award-info":[{"award-number":["62073182"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"111 International Collaboration Project","award":["BP2018006"],"award-info":[{"award-number":["BP2018006"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Automat. Sci. Eng."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tase.2025.3638318","type":"journal-article","created":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T18:26:22Z","timestamp":1764613582000},"page":"3916-3933","source":"Crossref","is-referenced-by-count":0,"title":["Consensus-Based Distributed Reinforcement Learning With Primal\u2013Dual Update for Networked Microgrids On-Line Coordination"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3423-3792","authenticated-orcid":false,"given":"Gaochen","family":"Cui","sequence":"first","affiliation":[{"name":"CFINS, Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4683-7215","authenticated-orcid":false,"given":"Qing-Shan","family":"Jia","sequence":"additional","affiliation":[{"name":"CFINS, Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8826-0362","authenticated-orcid":false,"given":"Xiaohong","family":"Guan","sequence":"additional","affiliation":[{"name":"CFINS, Department of Automation, BNRist, Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiaozhu","family":"Zhai","sequence":"additional","affiliation":[{"name":"MOEKLINNS Laboratory, Systems Engineering Institute, Xi’an Jiaotong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6954-5947","authenticated-orcid":false,"given":"Xianping","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Mathematics, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Guo","sequence":"additional","affiliation":[{"name":"China Southern Power Grid Electric Power Research Institute, Gaungzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2569604"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3154718"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3010570"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2021.3123660"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3126761"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3154151"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1201\/9781315140223"},{"key":"ref8","first-page":"7553","article-title":"Constrained reinforcement learning has zero duality gap","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paternain"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysconle.2010.08.013"},{"key":"ref10","first-page":"5872","article-title":"Fully decentralized multi-agent reinforcement learning with networked agents","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2020.3004171"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.13140\/RG.2.2.18893.74727"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2019.09.008"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2010.2080328"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2016.2645761"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2017.2780804"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.2976044"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2012.2236368"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2014.2322622"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.enconman.2016.01.011"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10957-014-0561-3"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2808272"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3137842"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2023.3240106"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2721923"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1063\/1.5077032"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1063\/1.5043187"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.2987292"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.35833\/MPCE.2020.000522"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2933502"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.35833\/MPCE.2020.000557"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2801880"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.115256"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3092220"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2024.3378915"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3151607"},{"key":"ref37","article-title":"Safe reinforcement learning for multi-energy management systems with known constraint functions","volume":"12","author":"Ceusters","year":"2022","journal-title":"Energy AI"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2023.3243170"},{"key":"ref39","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2023.120759","article-title":"Secure energy management of multi-energy microgrid: A physical-informed safe reinforcement learning approach","volume":"335","author":"Wang","year":"2023","journal-title":"Appl. Energy"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3292388"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3034827"},{"key":"ref42","first-page":"36524","article-title":"Scalable primal-dual actor-critic method for safe multi-agent RL with general utilities","volume-title":"Proc.  37th Int. Conf. Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2025.3534639"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1137\/16M1084316"},{"key":"ref45","first-page":"1","article-title":"High-dimensional continuous control using generalized advantage estimation","volume-title":"Proc. 4th Int. Conf. Learn. Represent.","author":"Schulman"},{"key":"ref46","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-2696-8"},{"key":"ref48","volume":"48","author":"Borkar","year":"2009","journal-title":"Stochastic Approximation: A Dynamical Systems Viewpoint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2892841"},{"key":"ref50","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. 33rd Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref51","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.120495","article-title":"Reinforcement learning algorithms: A brief survey","volume":"231","author":"Shakya","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TSIPN.2018.2866342"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2016.2564339"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1002\/9781118032701"},{"issue":"7","key":"ref55","doi-asserted-by":"crossref","first-page":"1192","DOI":"10.1016\/j.epsr.2007.10.002","article-title":"Maximum savings approach for location and sizing of capacitors in distribution systems","volume":"78","author":"Khodr","year":"2008","journal-title":"Electric Power Syst. Res."},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3250269"}],"container-title":["IEEE Transactions on Automation Science and Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8856\/11323516\/11271756.pdf?arnumber=11271756","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,13]],"date-time":"2026-02-13T20:53:05Z","timestamp":1771015985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11271756\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tase.2025.3638318","relation":{},"ISSN":["1545-5955","1558-3783"],"issn-type":[{"value":"1545-5955","type":"print"},{"value":"1558-3783","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}