{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T08:45:21Z","timestamp":1786178721811,"version":"3.56.0"},"reference-count":268,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0201300"],"award-info":[{"award-number":["2021ZD0201300"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073148"],"award-info":[{"award-number":["62073148"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Key Project of National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62233006"],"award-info":[{"award-number":["62233006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Smart Grid Joint Key Project of National Natural Science Foundation of China and the State Grid Corporation of China","doi-asserted-by":"publisher","award":["U2066202"],"award-info":[{"award-number":["U2066202"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Major Program of National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61991400"],"award-info":[{"award-number":["61991400"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"2020 Science and Technology Major Project of Liaoning Province","award":["2020JH1\/10100008"],"award-info":[{"award-number":["2020JH1\/10100008"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/jproc.2023.3303358","type":"journal-article","created":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T17:51:06Z","timestamp":1693936266000},"page":"1055-1096","source":"Crossref","is-referenced-by-count":187,"title":["Deep Reinforcement Learning for Smart Grid Operations: Algorithms, Applications, and Prospects"],"prefix":"10.1109","volume":"111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8052-1233","authenticated-orcid":false,"given":"Yuanzheng","family":"Li","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Automation, Autonomous Intelligent Unmanned System Engineering Research Center, Key Laboratory of Image Processing and Intelligence Control, Ministry of Education of China, and the Hubei Key Laboratory of Brain-Inspired Intelligent Systems and the Belt and Road Joint Laboratory on Measurement and Control Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7112-7821","authenticated-orcid":false,"given":"Chaofan","family":"Yu","sequence":"additional","affiliation":[{"name":"China-EU Institute for Clean and Renewable Energy, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8994-1688","authenticated-orcid":false,"given":"Mohammad","family":"Shahidehpour","sequence":"additional","affiliation":[{"name":"Robert W. Galvin Center for Electricity Innovation, Illinois Institute of Technology, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4090-8497","authenticated-orcid":false,"given":"Tao","family":"Yang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4587-3588","authenticated-orcid":false,"given":"Zhigang","family":"Zeng","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Autonomous Intelligent Unmanned System Engineering Research Center, Key Laboratory of Image Processing and Intelligence Control, Ministry of Education of China, and the Hubei Key Laboratory of Brain-Inspired Intelligent Systems and the Belt and Road Joint Laboratory on Measurement and Control Technology, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianyou","family":"Chai","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Synthetical Automation for Process Industries, Northeastern University, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2022.3157162"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3015320"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3009323"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MELE.2020.3026444"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MPE.2017.2688599"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3089634"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3139754"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2988715"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-12490-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.enconman.2014.07.071"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3060483"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2022.3217579"},{"key":"ref13","volume-title":"Deep\n                        Reinforcement Learning Hands-On: Apply Modern RL Methods to Practical\n                        Problems of Chatbots, Robotics, Discrete Optimization, Web Automation, and\n                        More","author":"Lapan","year":"2020"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2019.2916583"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3073036"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2929141"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2743240"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-021-10061-9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3154718"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.17775\/CSEEJPES.2019.00920"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2019.09.008"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.35833\/MPCE.2020.000552"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2020.03.001"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2020.110618"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3078462"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.17775\/CSEEJPES.2018.00520"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2022.3192558"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3121870"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2020.2990096"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-4095-0"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1287\/opre.50.1.48.17791"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.3034800"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2017.2762739"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/9.580874"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TTE.2021.3074792"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561927"},{"key":"ref41","first-page":"2613","article-title":"Double Q-learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"23","author":"Hasselt"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2876279"},{"key":"ref44","first-page":"1995","article-title":"Dueling network architectures for deep reinforcement\n                        learning","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Wang"},{"key":"ref45","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning\n                        with function approximation","volume-title":"Proc. Adv.\n                        Neural Inf. Process. Syst.","volume":"12","author":"Sutton"},{"key":"ref46","first-page":"1008","article-title":"Actor-critic algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"12","author":"Konda"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1983.6313077"},{"key":"ref48","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement\n                        learning","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Mnih"},{"key":"ref49","first-page":"1889","article-title":"Trust region policy\n                    optimization","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Schulman"},{"key":"ref50","first-page":"267","article-title":"Approximately optimal approximate reinforcement\n                        learning","volume-title":"Proc. 19th Int. Conf. Mach.\n                        Learn.","author":"Kakade"},{"key":"ref51","first-page":"22","article-title":"Constrained policy\n                    optimization","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Achiam"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511804441"},{"key":"ref53","article-title":"Proximal policy optimization\n                        algorithms","author":"Schulman","year":"2017","journal-title":"arXiv:1707.06347"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-02886-1"},{"key":"ref55","article-title":"Emergence of locomotion behaviours in rich\n                        environments","author":"Heess","year":"2017","journal-title":"arXiv:1707.02286"},{"key":"ref56","article-title":"PPO dash: Improving generalization in deep\n                        reinforcement learning","author":"Booth","year":"2019","journal-title":"arXiv:1907.06704"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2020.05.003"},{"key":"ref58","first-page":"387","article-title":"Deterministic policy gradient\n                        algorithms","volume-title":"Proc. Int. Conf. Mach.\n                        Learn.","author":"Silver"},{"key":"ref59","first-page":"1587","article-title":"Addressing function approximation error in\n                        actor-critic methods","volume-title":"Proc. Int. Conf.\n                        Mach. Learn.","author":"Fujimoto"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3053092"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3107685"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3056768"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2021.3076020"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2020.2989522"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3094891"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.17775\/CSEEJPES.2020.02650"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3018635"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2983565"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3109111"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2992570"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2997956"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2998479"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2965578"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3068092"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3074915"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-0799-1"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.3001235"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2810897"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2018.04.087"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117474"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3074437"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3054763"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2986883"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.3000652"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.114772"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2962625"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3041620"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3052998"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2951769"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRD.2021.3107534"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.115900"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3005270"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3037066"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.116355"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2792441"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2014.2384031"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.3031324"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2022.123923"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2021.3112043"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2021.3049381"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3042007"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2996274"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3124465"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2021.3110294"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2021.3105529"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2930299"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3088290"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2020.2976909"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2022.3168577"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3155455"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/tsg.2023.3281782"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3002271"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3105232"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3015204"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3051032"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2955437"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2997896"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3111014"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2942593"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3098298"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2989382"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2021.121377"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1016\/j.enconman.2019.112199"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1049\/iet-rpg.2020.0370"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1016\/j.enconman.2020.113608"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.120540"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2020.106016"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.116623"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2976771"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117900"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1016\/j.enconman.2016.10.062"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2921431"},{"key":"ref133","doi-asserted-by":"crossref","DOI":"10.1016\/j.enconman.2019.112461","article-title":"A composite framework coupling multiple feature\n                        selection, compound prediction models and novel hybrid swarm optimizer-based\n                        synchronization optimization strategy for multi-step ahead short-term wind\n                        speed forecasting","volume":"205","author":"Fu","year":"2020","journal-title":"Energy Convers.\n                        Manage."},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2773458"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.23919\/ACC50511.2021.9483277"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2021.107471"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.17775\/CSEEJPES.2019.01840"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.116386"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3000784"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3019929"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1049\/rpg2.12310"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2022.108175"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.3390\/app8112185"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2020.105928"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2668983"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2894756"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/TTE.2020.2983247"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.2990179"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2019.2941134"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117982"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2021.3107535"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2021.3092961"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2021.3057090"},{"key":"ref154","article-title":"Scalable voltage control using structure-driven\n                        hierarchical deep reinforcement learning","author":"Mukherjee","year":"2021","journal-title":"arXiv:2102.00077"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3095179"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3084469"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3072251"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3166192"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2022.3155117"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2019.2958361"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3006080"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2020.3047137"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2881359"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.2999890"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2020.2964886"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3001095"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1049\/iet-gtd.2020.0884"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2021.06.081"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2022.3140702"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1002\/047122412X"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.17775\/CSEEJPES.2019.02510"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2936142"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2903756"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.35833\/MPCE.2020.000502"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyr.2021.11.216"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2022.3156426"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2020.2999536"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3076296"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2021.107625"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3116275"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2022.3145102"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-021-06020-8"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.08.106"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2022.3142969"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2018.03.033"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3055517"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/TIA.2020.2984614"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.17775\/cseejpes.2021.04330"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117754"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2020.3025832"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2021.3109954"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3027728"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3009419"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2021.121926"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2016.2616861"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2709784"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2979051"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2021.3058514"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/TTE.2022.3165804"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.17775\/CSEEJPES.2020.03290"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/ICBDA49040.2020.9099946"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.116940"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.119123"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/POWERCON53785.2021.9697585"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/401"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2022.3171534"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3103917"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.116722"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/iThings-GreenCom-CPSCom-SmartData-Cybermatics50389.2020.00071"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3204796"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2687865"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2005.857490"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3091616"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/SmartGridComm51999.2021.9631991"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3038769"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2022.108265"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3149764"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.116015"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.3390\/app11073101"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC48107.2020.9148342"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3175917"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2933020"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2818167"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3049222"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2000263"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1109\/TC.2021.3130402"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3035451"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3007167"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3128488"},{"key":"ref230","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3095506"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3124848"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.2968631"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.17775\/cseejpes.2020.05540"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2021.107410"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/MCOMSTD.0001.2000081"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3181329"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1109\/TGCN.2021.3073979"},{"issue":"42","key":"ref238","first-page":"1437","article-title":"A comprehensive survey on safe reinforcement\n                        learning","volume":"16","author":"Garc\u00eda","year":"2015","journal-title":"J. Mach. Learn. Res."},{"issue":"9","key":"ref239","first-page":"1","article-title":"Safe reinforcement learning: A\n                    survey","volume":"49","author":"Wang","year":"2023","journal-title":"Acta Automatica Sinica"},{"key":"ref240","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3162828"},{"key":"ref241","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3164080"},{"key":"ref242","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3233709"},{"key":"ref243","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2933191"},{"key":"ref244","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i7.20737"},{"key":"ref245","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2023.3243170"},{"key":"ref246","doi-asserted-by":"publisher","DOI":"10.1109\/tpwrs.2023.3257259"},{"key":"ref247","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3250269"},{"key":"ref248","first-page":"36599","article-title":"When to trust your simulator: Dynamics-aware hybrid\n                        offline-and-online reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Niu"},{"key":"ref249","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2022.3150023"},{"key":"ref250","doi-asserted-by":"publisher","DOI":"10.1109\/tpwrs.2022.3220799"},{"key":"ref251","doi-asserted-by":"publisher","DOI":"10.1109\/CDC45484.2021.9683573"},{"key":"ref252","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2021.3111139"},{"key":"ref253","doi-asserted-by":"publisher","DOI":"10.1109\/tsg.2023.3263243"},{"key":"ref254","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2955857"},{"key":"ref255","doi-asserted-by":"publisher","DOI":"10.23919\/ACC45564.2020.9147846"},{"key":"ref256","first-page":"21024","article-title":"Robust deep reinforcement learning against\n                        adversarial perturbations on state observations","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"33","author":"Zhang"},{"key":"ref257","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014213"},{"key":"ref258","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3093300"},{"key":"ref259","first-page":"3046","article-title":"Reinforcement learning under model\n                        mismatch","volume-title":"Proc. Adv. Neural Inf. Process.\n                        Syst.","volume":"30","author":"Roy"},{"key":"ref260","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.120291"},{"key":"ref261","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3232630"},{"key":"ref262","first-page":"11702","article-title":"Bridging offline reinforcement learning and imitation\n                        learning: A tale of pessimism","volume-title":"Proc. Adv.\n                        Neural Inf. Process. Syst.","volume":"34","author":"Rashidinejad"},{"key":"ref263","first-page":"18353","article-title":"BAIL: Best-action imitation learning for batch deep\n                        reinforcement learning","volume-title":"Proc. Adv. Neural\n                        Inf. Process. Syst.","volume":"33","author":"Chen"},{"key":"ref264","doi-asserted-by":"publisher","DOI":"10.1109\/IV51971.2022.9827073"},{"key":"ref265","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5587"},{"key":"ref266","doi-asserted-by":"publisher","DOI":"10.1109\/SmartGridComm51999.2021.9632292"},{"key":"ref267","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3025015"},{"key":"ref268","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5\/10251702\/10241311.pdf?arnumber=10241311","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,21]],"date-time":"2024-07-21T04:19:07Z","timestamp":1721535547000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10241311\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":268,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2023.3303358","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}