{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:47:35Z","timestamp":1775504855643,"version":"3.50.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,7,1]],"date-time":"2020-07-01T00:00:00Z","timestamp":1593561600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Smart Grid"],"published-print":{"date-parts":[[2020,7]]},"DOI":"10.1109\/tsg.2020.2976771","type":"journal-article","created":{"date-parts":[[2020,2,27]],"date-time":"2020-02-27T22:14:41Z","timestamp":1582841681000},"page":"3068-3082","source":"Crossref","is-referenced-by-count":215,"title":["Model-Free Real-Time Autonomous Control for a Residential Multi-Energy System Using Deep Reinforcement Learning"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9278-9218","authenticated-orcid":false,"given":"Yujian","family":"Ye","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0497-6089","authenticated-orcid":false,"given":"Dawei","family":"Qiu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4252-1897","authenticated-orcid":false,"given":"Xiaodong","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7421-3947","authenticated-orcid":false,"given":"Goran","family":"Strbac","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0017-0205","authenticated-orcid":false,"given":"Jonathan","family":"Ward","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"1","article-title":"Deep reinforcement learning solutions for energy microgrids management","author":"fran\u00e7ois-lavet","year":"2016","journal-title":"Proceedings of the 8th European Workshop on Reinforcement Learning (EWRL)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2879572"},{"key":"ref33","first-page":"1","article-title":"Optimizing home energy management and electric vehicle charging with reinforcement learning","author":"wu","year":"2018","journal-title":"Proc 16th Adapt Learn Agents (ALA)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2640184"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2629450"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2016.2517211"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICE.2019.8792636"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2018.2834219"},{"key":"ref35","first-page":"1","article-title":"Why deep neural networks for function approximation?","author":"liang","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)ICLR"},{"key":"ref34","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":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/en12010001"},{"key":"ref27","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1109\/CCNC.2015.7158054","article-title":"Reinforcement learning-based control of residential energy storage systems for electric bill minimization","author":"guan","year":"2015","journal-title":"Proc 12th Annu IEEE Consum Commun Netw Conf (CCNC)"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/PESGM.2018.8586321"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2010.2053053"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MPE.2016.2625218"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2933191"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPWRS.2019.2941134"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISGT-Asia.2018.8467877"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2396993"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2013.2263201"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-014-0169-8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2018.2855689"},{"key":"ref50","first-page":"1","article-title":"Prioritized experience replay","author":"schaul","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2013.2282039"},{"key":"ref58","year":"2019","journal-title":"GAMS\/SCENRED"},{"key":"ref57","year":"2019","journal-title":"Gurobi Optimizer Reference Manual"},{"key":"ref56","author":"abadi","year":"2015","journal-title":"TensorFlow Large-Scale Machine Learning on Heterogeneous Systems"},{"key":"ref55","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)ICLR"},{"key":"ref54","year":"2019","journal-title":"Fix Online V27 Gas Tariff"},{"key":"ref53","year":"2019","journal-title":"Feed-in Tariff (FiT) Rates"},{"key":"ref52","author":"hydro","year":"2019","journal-title":"Smart Meters and Time-of-Use Rates"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2012.2212729"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2012.03.015"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2876652"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-0237-4"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1137\/080734510"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2018.03.072"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2940005"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2936142"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2933502"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2019.2930299"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2019.01.145"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2015.07.028"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2012.2212032"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSG.2015.2504560"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2015.10.137"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.enconman.2017.04.074"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2014.03.038"},{"key":"ref49","first-page":"1","article-title":"Deterministic policy gradient algorithms","author":"silver","year":"2014","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2018.05.103"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2957289"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489210"},{"key":"ref48","author":"sutton","year":"2018","journal-title":"Reinforcement Learning An Introduction"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2019.07.019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062224"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.3390\/en12122291"},{"key":"ref44","first-page":"1008","article-title":"Actor–critic algorithms","author":"konda","year":"2000","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref43","first-page":"1","article-title":"Continuous control with deep reinforcement learning","author":"lillicrap","year":"2016","journal-title":"Proc 4th Int Conf Learn Represent (ICLR)"}],"container-title":["IEEE Transactions on Smart Grid"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165411\/9120396\/09016168.pdf?arnumber=9016168","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,27]],"date-time":"2023-09-27T19:15:48Z","timestamp":1695842148000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9016168\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7]]},"references-count":58,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tsg.2020.2976771","relation":{},"ISSN":["1949-3053","1949-3061"],"issn-type":[{"value":"1949-3053","type":"print"},{"value":"1949-3061","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7]]}}}