{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T04:18:26Z","timestamp":1773202706727,"version":"3.50.1"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030954697","type":"print"},{"value":"9783030954703","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-95470-3_2","type":"book-chapter","created":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T10:07:13Z","timestamp":1643710033000},"page":"15-30","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Deep Reinforcement Learning for\u00a0Optimal Energy Management of\u00a0Multi-energy Smart Grids"],"prefix":"10.1007","author":[{"given":"Dhekra","family":"Bousnina","sequence":"first","affiliation":[]},{"given":"Gilles","family":"Guerassimoff","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,2]]},"reference":[{"key":"2_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/978-3-030-64583-0_17","volume-title":"Machine Learning, Optimization, and Data Science","author":"D Bousnina","year":"2020","unstructured":"Bousnina, D., de Oliveira, W., Pflaum, P.: A stochastic optimization model for frequency control and energy management in a microgrid. In: Nicosia, G., et al. (eds.) LOD 2020. LNCS, vol. 12565, pp. 177\u2013189. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-64583-0_17"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"de Bruin, T., Kober, J., Tuyls, K., Babu\u0161ka, R.: Improved deep reinforcement learning for robotics through distribution-based experience retention. In: 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 3947\u20133952. IEEE (2016)","DOI":"10.1109\/IROS.2016.7759581"},{"key":"2_CR3","doi-asserted-by":"publisher","first-page":"113820","DOI":"10.1016\/j.eswa.2020.113820","volume":"164","author":"S Carta","year":"2021","unstructured":"Carta, S., Ferreira, A., Podda, A.S., Recupero, D.R., Sanna, A.: Multi-DQN: An ensemble of deep q-learning agents for stock market forecasting. Expert Syst. Appl. 164, 113820 (2021)","journal-title":"Expert Syst. Appl."},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"van den Ende, M., Lukszo, Z., Herder, P.M.: Smart thermal grid. In: 2015 IEEE 12th International Conference on Networking, Sensing and Control, pp. 432\u2013437. IEEE (2015)","DOI":"10.1109\/ICNSC.2015.7116076"},{"issue":"4","key":"2_CR5","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1109\/SURV.2011.101911.00087","volume":"14","author":"X Fang","year":"2011","unstructured":"Fang, X., Misra, S., Xue, G., Yang, D.: Smart grid-the new and improved power grid: a survey. IEEE Commun. Surv. Tutorials 14(4), 944\u2013980 (2011)","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"2_CR6","unstructured":"Fran\u00e7ois-Lavet, V.: Contributions to deep reinforcement learning and its applications in smartgrids. Ph.D. thesis, Universit\u00e9 de Li\u00e8ge, Li\u00e8ge, Belgique (2017)"},{"key":"2_CR7","doi-asserted-by":"crossref","unstructured":"Fran\u00e7ois-Lavet, V., Henderson, P., Islam, R., Bellemare, M.G., Pineau, J.: An introduction to deep reinforcement learning. arXiv preprint arXiv:1811.12560 (2018)","DOI":"10.1561\/9781680835397"},{"key":"2_CR8","unstructured":"Fran\u00e7ois-Lavet, V., Taralla, D., Ernst, D., Fonteneau, R.: Deep reinforcement learning solutions for energy microgrids management. In: European Workshop on Reinforcement Learning (EWRL 2016) (2016)"},{"key":"2_CR9","unstructured":"Gao, G., Li, J., Wen, Y.: Energy-efficient thermal comfort control in smart buildings via deep reinforcement learning. arXiv preprint arXiv:1901.04693 (2019)"},{"issue":"3","key":"2_CR10","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1016\/0005-1098(89)90002-2","volume":"25","author":"CE Garcia","year":"1989","unstructured":"Garcia, C.E., Prett, D.M., Morari, M.: Model predictive control: theory and practice-a survey. Automatica 25(3), 335\u2013348 (1989)","journal-title":"Automatica"},{"key":"2_CR11","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1016\/j.egypro.2018.11.028","volume":"155","author":"R Gelleschus","year":"2018","unstructured":"Gelleschus, R., B\u00f6ttiger, M., Stange, P., Bocklisch, T.: Comparison of optimization solvers in the model predictive control of a PV-battery-heat pump system. Energ. Procedia 155, 524\u2013535 (2018)","journal-title":"Energ. Procedia"},{"issue":"12","key":"2_CR12","doi-asserted-by":"publisher","first-page":"2291","DOI":"10.3390\/en12122291","volume":"12","author":"Y Ji","year":"2019","unstructured":"Ji, Y., Wang, J., Xu, J., Fang, X., Zhang, H.: Real-time energy management of a microgrid using deep reinforcement learning. Energies 12(12), 2291 (2019)","journal-title":"Energies"},{"key":"2_CR13","unstructured":"Knight, W.: Google just gave control over data center cooling to an AI (2018)"},{"key":"2_CR14","unstructured":"Konda, V.R., Tsitsiklis, J.N.: Actor-critic algorithms. In: Advances in Neural Information Processing Systems, pp. 1008\u20131014 (2000)"},{"issue":"19","key":"2_CR15","doi-asserted-by":"publisher","first-page":"5027","DOI":"10.3390\/en13195027","volume":"13","author":"Y Kuang","year":"2020","unstructured":"Kuang, Y., Wang, X., Zhao, H., Huang, Y., Chen, X., Wang, X.: Agent-based energy sharing mechanism using deep deterministic policy gradient algorithm. Energies 13(19), 5027 (2020)","journal-title":"Energies"},{"key":"2_CR16","unstructured":"Liaw, R., Krishnan, S., Garg, A., Crankshaw, D., Gonzalez, J.E., Goldberg, K.: Composing meta-policies for autonomous driving using hierarchical deep reinforcement learning. arXiv preprint arXiv:1711.01503 (2017)"},{"key":"2_CR17","unstructured":"Lillicrap, T.P., et al.: Continuous control with deep reinforcement learning. arXiv preprint arXiv:1509.02971 (2015)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Lin, S., Yu, H., Chen, H.: On-line optimization of microgrid operating cost based on deep reinforcement learning. In: IOP Conference Series: Earth and Environmental Science, vol. 701, p. 012084. IOP Publishing (2021)","DOI":"10.1088\/1755-1315\/701\/1\/012084"},{"key":"2_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2020.117794","volume":"202","author":"H Liu","year":"2020","unstructured":"Liu, H., Yu, C., Wu, H., Duan, Z., Yan, G.: A new hybrid ensemble deep reinforcement learning model for wind speed short term forecasting. Energy 202, 117794 (2020)","journal-title":"Energy"},{"key":"2_CR20","doi-asserted-by":"publisher","first-page":"112963","DOI":"10.1016\/j.eswa.2019.112963","volume":"141","author":"M Lopez-Martin","year":"2020","unstructured":"Lopez-Martin, M., Carro, B., Sanchez-Esguevillas, A.: Application of deep reinforcement learning to intrusion detection for supervised problems. Expert Syst. Appl. 141, 112963 (2020)","journal-title":"Expert Syst. Appl."},{"key":"2_CR21","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1016\/j.energy.2018.06.198","volume":"160","author":"T Ma","year":"2018","unstructured":"Ma, T., Wu, J., Hao, L., Lee, W.J., Yan, H., Li, D.: The optimal structure planning and energy management strategies of smart multi energy systems. Energy 160, 122\u2013141 (2018)","journal-title":"Energy"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Mancarella, P.: Smart multi-energy grids: concepts, benefits and challenges. In: 2012 IEEE Power and Energy Society General Meeting, pp. 1\u20132. IEEE (2012)","DOI":"10.1109\/PESGM.2012.6345120"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","DOI":"10.1038\/nature14236"},{"issue":"4","key":"2_CR24","doi-asserted-by":"publisher","first-page":"3698","DOI":"10.1109\/TSG.2018.2834219","volume":"10","author":"E Mocanu","year":"2018","unstructured":"Mocanu, E., et al.: On-line building energy optimization using deep reinforcement learning. IEEE Trans. Smart Grid 10(4), 3698\u20133708 (2018)","journal-title":"IEEE Trans. Smart Grid"},{"issue":"4\u20135","key":"2_CR25","doi-asserted-by":"publisher","first-page":"667","DOI":"10.1016\/S0098-1354(98)00301-9","volume":"23","author":"M Morari","year":"1999","unstructured":"Morari, M., Lee, J.H.: Model predictive control: past, present and future. Comput. Chem. Eng. 23(4\u20135), 667\u2013682 (1999)","journal-title":"Comput. Chem. Eng."},{"issue":"5","key":"2_CR26","doi-asserted-by":"publisher","first-page":"1813","DOI":"10.1109\/TCST.2013.2295737","volume":"22","author":"A Parisio","year":"2014","unstructured":"Parisio, A., Rikos, E., Glielmo, L.: A model predictive control approach to microgrid operation optimization. IEEE Trans. Control Syst. Technol. 22(5), 1813\u20131827 (2014)","journal-title":"IEEE Trans. Control Syst. Technol."},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Pflaum, P., Alamir, M., Lamoudi, M.Y.: Comparison of a primal and a dual decomposition for distributed MPC in smart districts. In: 2014 IEEE International Conference on Smart Grid Communications (SmartGridComm), pp. 55\u201360. IEEE (2014)","DOI":"10.1109\/SmartGridComm.2014.7007622"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Qin, J., Han, X., Liu, G., Wang, S., Li, W., Jiang, Z.: Wind and storage cooperative scheduling strategy based on deep reinforcement learning algorithm. In: Journal of Physics: Conference Series, vol. 1213, p. 032002. IOP Publishing (2019)","DOI":"10.1088\/1742-6596\/1213\/3\/032002"},{"issue":"19","key":"2_CR29","doi-asserted-by":"publisher","first-page":"70","DOI":"10.2352\/ISSN.2470-1173.2017.19.AVM-023","volume":"2017","author":"AE Sallab","year":"2017","unstructured":"Sallab, A.E., Abdou, M., Perot, E., Yogamani, S.: Deep reinforcement learning framework for autonomous driving. Electron. Imaging 2017(19), 70\u201376 (2017)","journal-title":"Electron. Imaging"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Silver, D., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529(7587), 484\u2013489 (2016)","DOI":"10.1038\/nature16961"},{"key":"2_CR31","unstructured":"Silver, D., Lever, G., Heess, N., Degris, T., Wierstra, D., Riedmiller, M.: Deterministic policy gradient algorithms. In: International Conference on Machine Learning, pp. 387\u2013395. PMLR (2014)"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Sogabe, T., et al.: Smart grid optimization by deep reinforcement learning over discrete and continuous action space. In: 2018 IEEE 7th World Conference on Photovoltaic Energy Conversion (WCPEC)(A Joint Conference of 45th IEEE PVSC, 28th PVSEC & 34th EU PVSEC), pp. 3794\u20133796. IEEE (2018)","DOI":"10.1109\/PVSC.2018.8547862"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"St\u0103ni\u015fteanu, C.: Smart thermal grids-a review. The Scientific Bulletin of Electrical Engineering Faculty 1(ahead-of-print) (2017)","DOI":"10.1515\/sbeef-2016-0030"},{"key":"2_CR34","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"2_CR35","unstructured":"Sutton, R.S., Barto, A.G., et al.: Introduction to Reinforcement Learning, vol. 135. MIT Press, Cambridge (1998)"},{"key":"2_CR36","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1016\/j.rser.2016.01.011","volume":"59","author":"ML Tuballa","year":"2016","unstructured":"Tuballa, M.L., Abundo, M.L.: A review of the development of smart grid technologies. Renew. Sustain. Energ. Rev. 59, 710\u2013725 (2016)","journal-title":"Renew. Sustain. Energ. Rev."},{"key":"2_CR37","unstructured":"Vecerik, M., et al.: Leveraging demonstrations for deep reinforcement learning on robotics problems with sparse rewards. arXiv preprint arXiv:1707.08817 (2017)"},{"issue":"2","key":"2_CR38","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.1109\/TSG.2013.2292525","volume":"5","author":"T Wang","year":"2014","unstructured":"Wang, T., Kamath, H., Willard, S.: Control and optimization of grid-tied photovoltaic storage systems using model predictive control. IEEE Trans. Smart Grid 5(2), 1010\u20131017 (2014)","journal-title":"IEEE Trans. Smart Grid"},{"key":"2_CR39","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1016\/j.energy.2017.01.114","volume":"122","author":"L Yang","year":"2017","unstructured":"Yang, L., Entchev, E., Rosato, A., Sibilio, S.: Smart thermal grid with integration of distributed and centralized solar energy systems. Energy 122, 471\u2013481 (2017)","journal-title":"Energy"},{"issue":"4","key":"2_CR40","doi-asserted-by":"publisher","first-page":"2751","DOI":"10.1109\/JIOT.2019.2957289","volume":"7","author":"L Yu","year":"2019","unstructured":"Yu, L., et al.: Deep reinforcement learning for smart home energy management. IEEE Internet Things J. 7(4), 2751\u20132762 (2019)","journal-title":"IEEE Internet Things J."},{"key":"2_CR41","doi-asserted-by":"publisher","first-page":"112199","DOI":"10.1016\/j.enconman.2019.112199","volume":"202","author":"B Zhang","year":"2019","unstructured":"Zhang, B., Hu, W., Cao, D., Huang, Q., Chen, Z., Blaabjerg, F.: Deep reinforcement learning-based approach for optimizing energy conversion in integrated electrical and heating system with renewable energy. Energ. Convers. Manage. 202, 112199 (2019)","journal-title":"Energ. Convers. Manage."},{"key":"2_CR42","unstructured":"Zhang, T., Luo, J., Chen, P., Liu, J.: Flow rate control in smart district heating systems using deep reinforcement learning. arXiv preprint arXiv:1912.05313 (2019)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning, Optimization, and Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-95470-3_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,2,1]],"date-time":"2022-02-01T19:08:59Z","timestamp":1643742539000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-95470-3_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030954697","9783030954703"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-95470-3_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"2 February 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"LOD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Machine Learning, Optimization, and Data Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grasmere","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mod2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lod2021.icas.cc\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"215","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"86","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"40% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5-6","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1-2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}