{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:43:06Z","timestamp":1774366986035,"version":"3.50.1"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T00:00:00Z","timestamp":1656633600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shenzhen Science and Technology Program","award":["JCYJ20210324130811031"],"award-info":[{"award-number":["JCYJ20210324130811031"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2021A1515012450"],"award-info":[{"award-number":["2021A1515012450"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018913","name":"Tsinghua Shenzhen International Graduate School Interdisciplinary Research and Innovation Fund","doi-asserted-by":"publisher","award":["JC2021004"],"award-info":[{"award-number":["JC2021004"]}],"id":[{"id":"10.13039\/100018913","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Smart Grid"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1109\/tsg.2022.3162828","type":"journal-article","created":{"date-parts":[[2022,3,29]],"date-time":"2022-03-29T19:44:44Z","timestamp":1648583084000},"page":"2844-2858","source":"Crossref","is-referenced-by-count":68,"title":["An Improved Two-Stage Deep Reinforcement Learning Approach for Regulation Service Disaggregation in a Virtual Power Plant"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2363-1123","authenticated-orcid":false,"given":"Zhongkai","family":"Yi","sequence":"first","affiliation":[{"name":"Tsinghua–Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5149-5101","authenticated-orcid":false,"given":"Yinliang","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua–Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"given":"Xue","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba DAMO Academy, Alibaba Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2701-0009","authenticated-orcid":false,"given":"Wei","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Southeast University, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5465-9818","authenticated-orcid":false,"given":"Hongbin","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, State Key Laboratory of Power Systems, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7935-2567","authenticated-orcid":false,"given":"Qiuwei","family":"Wu","sequence":"additional","affiliation":[{"name":"Tsinghua–Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5405-3357","authenticated-orcid":false,"given":"Chenyu","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Southeast University, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2918058"},{"key":"ref2","volume-title":"PJM Manual 11: Energy & Ancillary Services Market Operations","year":"2021"},{"key":"ref3","volume-title":"California ISO: Pay for Performance Regulation Draft Final Proposal","year":"2012"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s41560-017-0075-y"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2890714"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2021.3062582"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2883753"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2016.2598186"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2017.07.021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2017.2741920"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCST.2020.3039492"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2012.2204074"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2424314"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1049\/iet-gtd.2019.0218"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2936142"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2823641"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3103917"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3041620"},{"key":"ref19","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"},{"key":"ref20","article-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2019","journal-title":"arXiv:1812.05905"},{"key":"ref21","first-page":"1","article-title":"Sharpness-aware minimization for efficiently improving generalization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Foret"},{"key":"ref22","first-page":"5905","article-title":"ASAM: Adaptive sharpness-aware minimization for scale-invariant learning of deep neural networks","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Kwon"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2021.3085885"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.11.057"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2614815"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2609422"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2016.2583435"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2020.3018913"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2015.2501458"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2017.2698414"},{"key":"ref31","volume-title":"Reinforcement Learning: An Introduction","author":"Sutton","year":"2018"},{"key":"ref32","first-page":"231","volume-title":"Stochastic Processes","author":"Ross","year":"1996"},{"key":"ref33","article-title":"Reinforcement learning for decision-making and control in power systems: Tutorial, review, and vision","author":"Chen","year":"2021","journal-title":"arXiv:2102.01168"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2570242"},{"key":"ref35","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref36","first-page":"1","article-title":"Prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Schaul"},{"key":"ref37","article-title":"Boosting soft actor-critic: Emphasizing recent experience without forgetting the past","author":"Wang","year":"2019","journal-title":"arXiv:1906.04009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2019.2925127"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIE.2013.2293692"},{"key":"ref40","volume-title":"Supplemental Materials of DER Parameters","author":"Yi","year":"2021"},{"key":"ref41","first-page":"1","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lillicrap"}],"container-title":["IEEE Transactions on Smart Grid"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165411\/9801905\/09744119.pdf?arnumber=9744119","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T00:00:58Z","timestamp":1705536058000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9744119\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7]]},"references-count":41,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tsg.2022.3162828","relation":{},"ISSN":["1949-3053","1949-3061"],"issn-type":[{"value":"1949-3053","type":"print"},{"value":"1949-3061","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7]]}}}