{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T07:09:11Z","timestamp":1773385751753,"version":"3.50.1"},"reference-count":37,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["72331009"],"award-info":[{"award-number":["72331009"]}],"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":["72171206"],"award-info":[{"award-number":["72171206"]}],"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":["92270105"],"award-info":[{"award-number":["92270105"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Key Lab of Crowd Intelligence Empowered Low-Carbon Energy Network","award":["ZDSYS20220606100601002"],"award-info":[{"award-number":["ZDSYS20220606100601002"]}]},{"DOI":"10.13039\/501100012302","name":"Guangdong Power Grid Company","doi-asserted-by":"crossref","award":["GDKJXM20231024"],"award-info":[{"award-number":["GDKJXM20231024"]}],"id":[{"id":"10.13039\/501100012302","id-type":"DOI","asserted-by":"crossref"}]},{"name":"PolyU Direct","award":["P0047700"],"award-info":[{"award-number":["P0047700"]}]},{"name":"PolyU Direct","award":["P0043885"],"award-info":[{"award-number":["P0043885"]}]},{"name":"PolyU Direct","award":["P0051105"],"award-info":[{"award-number":["P0051105"]}]},{"name":"Shenzhen Natural Science Fund"},{"name":"Stable Support Plan Program","award":["GXWD20231128112434001"],"award-info":[{"award-number":["GXWD20231128112434001"]}]},{"name":"Shenzhen Institute of Artificial Intelligence and Robotics for Society"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Smart Grid"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tsg.2025.3593340","type":"journal-article","created":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:50:23Z","timestamp":1753732223000},"page":"4606-4619","source":"Crossref","is-referenced-by-count":2,"title":["Power Smoothing Control for Wind-Storage Integrated Systems With Hierarchical Safe Reinforcement Learning and Curriculum Learning"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8714-5012","authenticated-orcid":false,"given":"Shuyi","family":"Wang","sequence":"first","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong (Shenzhen), Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3133-3137","authenticated-orcid":false,"given":"Huan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Building Environment and Energy Engineering, The Hong Kong Polytechnic University, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8630-7868","authenticated-orcid":false,"given":"Ting","family":"Shu","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China"}]},{"given":"Zibin","family":"Pan","sequence":"additional","affiliation":[{"name":"Cyberspace Institute Advanced Technology, Guangzhou University, Guangzhou, China"}]},{"given":"Gaoqi","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering and Automation, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5446-2655","authenticated-orcid":false,"given":"Junhua","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Science and Engineering, The Chinese University of Hong Kong (Shenzhen), Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2021.102252"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1049\/enc2.12003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2016.01.059"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2020.110455"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.adapen.2024.100177"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2023.3287871"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2019.2929820"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.est.2022.106297"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2974037"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2022.10.094"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2020.105928"},{"key":"ref12","article-title":"Coordinated power smoothing control for wind storage integrated system with physics-informed deep reinforcement learning","author":"Wang","year":"2024","journal-title":"arXiv:2412.17838"},{"key":"ref13","first-page":"1","article-title":"Hierarchical deep reinforcement learning: Integrating temporal abstraction and intrinsic motivation","volume-title":"Proc. 30th Adv. Neural Inf. Process. Syst.","author":"Kulkarni"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.120500"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2020.3038072"},{"key":"ref16","article-title":"Accelerated primal-dual policy optimization for safe reinforcement learning","author":"Liang","year":"2018","journal-title":"arXiv:1802.06480"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2955437"},{"key":"ref18","first-page":"1","article-title":"A Lyapunov-based approach to safe reinforcement learning","volume-title":"Proc. 32nd Adv. Neural Inf. Process. Syst.","author":"Chow"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2022.3226106"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2962625"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2023.3277087"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2022.3142961"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyai.2022.100227"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/we.1891"},{"key":"ref25","first-page":"407","article-title":"A simple model for cluster efficiency","volume-title":"Proc. Eur. Wind Energy Assoc. Conf. Exhib.","author":"Katic"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2016.08.066"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2016.08.011"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"issue":"181","key":"ref29","first-page":"1","article-title":"Curriculum learning for reinforcement learning domains: A framework and survey","volume":"21","author":"Narvekar","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2011.2106494"},{"key":"ref31","article-title":"Prioritized experience replay","author":"Schaul","year":"2016","journal-title":"arXiv:1511.05952"},{"key":"ref32","article-title":"An overview of multi-task learning in deep neural networks","author":"Ruder","year":"2017","journal-title":"arXiv:1706.05098"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/753\/3\/032005"},{"key":"ref34","volume-title":"Wind mast data: Alternative energy development board","year":"2023"},{"key":"ref35","volume-title":"Technical Specifications for Active Power Regulation and Control of Wind Farm","year":"2017"},{"key":"ref36","volume-title":"Electric Sales, Revenue, and Average Price","year":"2024"},{"key":"ref37","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Haarnoja"}],"container-title":["IEEE Transactions on Smart Grid"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165411\/11214576\/11098726.pdf?arnumber=11098726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,24]],"date-time":"2025-10-24T04:41:27Z","timestamp":1761280887000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11098726\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":37,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tsg.2025.3593340","relation":{},"ISSN":["1949-3053","1949-3061"],"issn-type":[{"value":"1949-3053","type":"print"},{"value":"1949-3061","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}