{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T17:08:05Z","timestamp":1784135285593,"version":"3.55.0"},"reference-count":54,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,11,1]],"date-time":"2021-11-01T00:00:00Z","timestamp":1635724800000},"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":["51877037"],"award-info":[{"award-number":["51877037"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Smart Grid"],"published-print":{"date-parts":[[2021,11]]},"DOI":"10.1109\/tsg.2021.3103917","type":"journal-article","created":{"date-parts":[[2021,8,10]],"date-time":"2021-08-10T20:11:07Z","timestamp":1628626267000},"page":"5185-5200","source":"Crossref","is-referenced-by-count":148,"title":["A Scalable Privacy-Preserving Multi-Agent Deep Reinforcement Learning Approach for Large-Scale Peer-to-Peer Transactive Energy Trading"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9278-9218","authenticated-orcid":false,"given":"Yujian","family":"Ye","sequence":"first","affiliation":[{"name":"School of Electrical Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2250-6024","authenticated-orcid":false,"given":"Yi","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6622-3579","authenticated-orcid":false,"given":"Huiyu","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0995-4989","authenticated-orcid":false,"given":"Xiao-Ping","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Computer Engineering, University of Birmingham, Birmingham, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Goran","family":"Strbac","sequence":"additional","affiliation":[{"name":"Department of Electrical and Electronic Engineering, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.39.10.1953"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2879572"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.115473"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2019.01.140"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1343\/1\/012058"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-335-6.50027-1"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2014.2358197"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2017.2702009"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1049\/iet-gtd.2018.6223"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2437795"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.3007167"},{"key":"ref29","author":"hernandez-leal","year":"2017","journal-title":"A Survey of Learning in Multiagent Environments Dealing With Non-Stationarity"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2020.106761"},{"key":"ref1","author":"shakoor","year":"2017","journal-title":"Roadmap for Flexibility Services to 2030 A Report to the Committee on Climate Change"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-0237-4"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"mnih","year":"2015","journal-title":"Nature"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.tej.2020.106879"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2976771"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2019.07.019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.scs.2018.11.021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3302505.3310069"},{"key":"ref50","year":"2020","journal-title":"Time of Use Pricing"},{"key":"ref51","year":"2020","journal-title":"Solar Rebates and Feed-in Tariffs"},{"key":"ref54","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc 33rd Conf Neural Inf Process Syst (NIPS)"},{"key":"ref53","first-page":"3751","article-title":"Learned optimizers that scale and generalize","author":"wichrowska","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn (ICML)"},{"key":"ref52","year":"2021","journal-title":"IEEE DataPort Dataset"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2020.3026611"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.3036915"},{"key":"ref40","first-page":"1","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.116131"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2487422"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2878445"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2929498"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2020.2986337"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2020.106204"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2017.2649558"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/PESGM.2017.8274546"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2833959"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41560-017-0075-y"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2019.01.091"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2877236"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2834472"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2932109"},{"key":"ref49","year":"2017","journal-title":"Rainfall and Temperature Forecast and Observations—Verification 2016-05 to 2017-04"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3007196"},{"key":"ref46","first-page":"7254","article-title":"Learning attentional communication for multi-agent cooperation","author":"jiang","year":"2018","journal-title":"Proc 32nd Int Conf Adv Neural Inf Process Syst (NIPS)"},{"key":"ref45","first-page":"2961","article-title":"Actor-attention-critic for multi-agent reinforcement learning","author":"iqbal","year":"2019","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1080\/14786451.2015.1100196"},{"key":"ref47","first-page":"1861","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"haarnoja","year":"2018","journal-title":"Proc Int Conf Mach Learn Res"},{"key":"ref42","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2957289"},{"key":"ref44","first-page":"6379","article-title":"Multi-agent actor-critic for mixed cooperative-competitive environments","author":"lowe","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NIPS)"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2977374"}],"container-title":["IEEE Transactions on Smart Grid"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165411\/9582816\/09509579.pdf?arnumber=9509579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T21:18:04Z","timestamp":1705353484000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9509579\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11]]},"references-count":54,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tsg.2021.3103917","relation":{},"ISSN":["1949-3053","1949-3061"],"issn-type":[{"value":"1949-3053","type":"print"},{"value":"1949-3061","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11]]}}}