{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:58:47Z","timestamp":1774022327719,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T00:00:00Z","timestamp":1638662400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T00:00:00Z","timestamp":1638662400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,12,5]],"date-time":"2021-12-05T00:00:00Z","timestamp":1638662400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["ECCS 1917275"],"award-info":[{"award-number":["ECCS 1917275"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,12,5]]},"DOI":"10.1109\/ssci50451.2021.9659545","type":"proceedings-article","created":{"date-parts":[[2022,1,24]],"date-time":"2022-01-24T21:09:51Z","timestamp":1643058591000},"page":"1-8","source":"Crossref","is-referenced-by-count":10,"title":["Online Microgrid Energy Management Based on Safe Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Hepeng","family":"Li","sequence":"first","affiliation":[]},{"given":"Zhenhua","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Lusi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Haibo","family":"He","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2798039"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2859821"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2017.06.007"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.3390\/en12122291"},{"key":"ref14","author":"lei","year":"2020","journal-title":"Dynamic energy dispatch in isolated microgrids based on deep reinforcement learning"},{"key":"ref15","first-page":"1","article-title":"Online scheduling of a residential microgrid via monte-carlo tree search and a learned model","author":"shuai","year":"2020","journal-title":"IEEE Transactions on Smart Grid"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2018.2829021"},{"key":"ref17","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume":"12","author":"sutton","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"22","article-title":"Constrained policy optimization","author":"achiam","year":"0","journal-title":"Proceedings of the 34th International Conference on Machine Learning - Volume 70 ser ICML'17"},{"key":"ref19","first-page":"1889","article-title":"Trust region policy optimization","volume":"37","author":"schulman","year":"2015","journal-title":"ser Proceedings of Machine Learning Research"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2016.2569525"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2013.2294187"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/app10144833"},{"key":"ref5","first-page":"1","article-title":"Optimal schedule for networked microgrids under deregulated power market environment using model predictive control","author":"garcia-torres","year":"2020","journal-title":"IEEE Transactions on Smart Grid"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2016.2577040"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2462294"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2012.2233770"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2514358"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2012.2231440"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/PES.2006.1709447"},{"key":"ref22","author":"brockman","year":"2016","journal-title":"OpenAI Gym"},{"key":"ref21","author":"abadi","year":"2015","journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems"},{"key":"ref24","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref23","author":"lillicrap","year":"2019","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/61.107303"}],"event":{"name":"2021 IEEE Symposium Series on Computational Intelligence (SSCI)","location":"Orlando, FL, USA","start":{"date-parts":[[2021,12,5]]},"end":{"date-parts":[[2021,12,7]]}},"container-title":["2021 IEEE Symposium Series on Computational Intelligence (SSCI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9659537\/9659538\/09659545.pdf?arnumber=9659545","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T16:56:42Z","timestamp":1652201802000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9659545\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,5]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/ssci50451.2021.9659545","relation":{},"subject":[],"published":{"date-parts":[[2021,12,5]]}}}