{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T17:28:56Z","timestamp":1783445336900,"version":"3.54.6"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"No Funding"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Computing"],"DOI":"10.1007\/s10791-025-09544-y","type":"journal-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T19:58:52Z","timestamp":1745351932000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Reinforcement learning for HVAC control and energy efficiency in residential buildings with BOPTEST simulations and real-case validation"],"prefix":"10.1007","volume":"28","author":[{"given":"Youssef","family":"Boutahri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amine","family":"Tilioua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"9544_CR1","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1016\/j.rser.2014.03.027","volume":"34","author":"PH Shaikh","year":"2014","unstructured":"Shaikh PH, Nor NBM, Nallagownden P, Elamvazuthi I, Ibrahim T. A review on optimized control systems for building energy and comfort management of smart sustainable buildings. Renew Sustain Energy Rev. 2014;34:409\u201329. https:\/\/doi.org\/10.1016\/j.rser.2014.03.027.","journal-title":"Renew Sustain Energy Rev"},{"key":"9544_CR2","unstructured":"Natural Resources Canada, Energy efficiency trends in canada 1990\u2013200. 2011."},{"key":"9544_CR3","doi-asserted-by":"publisher","first-page":"102148","DOI":"10.1016\/j.rineng.(2024).102148","volume":"22","author":"Y Boutahri","year":"2024","unstructured":"Boutahri Y, Tilioua A. Machine learning-based predictive model for thermal comfort and energy optimization in smart buildings. Results Eng. 2024;22:102148. https:\/\/doi.org\/10.1016\/j.rineng.(2024).102148.","journal-title":"Results Eng"},{"key":"9544_CR4","volume-title":"36: High performance sequences of operation for HVAC systems","author":"G Ashrae","year":"2018","unstructured":"Ashrae G. 36: High performance sequences of operation for HVAC systems. Atlanta: American Society of Heating Refrigerating and Air-Conditioning Engineers; 2018."},{"key":"9544_CR5","doi-asserted-by":"publisher","first-page":"1072","DOI":"10.1016\/j.apenergy.2018.11.002","volume":"235","author":"JR Vazquez-Canteli","year":"2019","unstructured":"Vazquez-Canteli JR, Nagy Z. Reinforcement learning for demand response: a review of algorithms and modeling techniques. Appl Energy. 2019;235:1072\u201389. https:\/\/doi.org\/10.1016\/j.apenergy.2018.11.002.","journal-title":"Appl Energy"},{"key":"9544_CR6","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1016\/j.arcontrol.2020.09.001","volume":"50","author":"J Drgona","year":"2020","unstructured":"Drgona J, Arroyo J, Figueroa IC, Blum D, Arendt K, Kim D, Olle EP, Oravec J, Wetter M, Vrabie DL, et al. All you need to know about model predictive control for buildings. Annu Rev Control. 2020;50:190\u2013232. https:\/\/doi.org\/10.1016\/j.arcontrol.2020.09.001.","journal-title":"Annu Rev Control"},{"issue":"4","key":"9544_CR7","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1109\/JPROC.2016.2520678","volume":"104","author":"Y-J Kim","year":"2016","unstructured":"Kim Y-J, Blum DH, Xu N, Su L, Norford LK. Technologies and magnitude of ancillary services provided by commercial buildings. Proc IEEE. 2016;104(4):758\u201379. https:\/\/doi.org\/10.1109\/JPROC.2016.2520678.","journal-title":"Proc IEEE"},{"key":"9544_CR8","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1016\/j.rser.2016.10.072","volume":"75","author":"N Aste","year":"2017","unstructured":"Aste N, Manfren M, Marenzi G. Building automation and control systems and performance optimization: a framework for analysis. Renew Sustain Energy Rev. 2017;75:313\u201330. https:\/\/doi.org\/10.1016\/j.rser.2016.10.072.","journal-title":"Renew Sustain Energy Rev"},{"key":"9544_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2021.107952","volume":"200","author":"Y Yao","year":"2021","unstructured":"Yao Y, Shekhar DK. State of the art review on model predictive control (MPC) in heating ventilation and air-conditioning (HVAC) field. Build Environ. 2021;200: 107952. https:\/\/doi.org\/10.1016\/j.buildenv.2021.107952.","journal-title":"Build Environ"},{"key":"9544_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.applthermaleng.2022.118552","volume":"212","author":"X Fang","year":"2022","unstructured":"Fang X, Gong G, Li G, Chun L, Peng P, Li W, Shi X, Chen X. Deep reinforcement learning optimal control strategy for temperature setpoint real-time reset in multi-zone building HVAC system. Appl Therm Eng. 2022;212: 118552. https:\/\/doi.org\/10.1016\/j.applthermaleng.2022.118552.","journal-title":"Appl Therm Eng"},{"key":"9544_CR11","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1016\/j.scs.2018.05.044","volume":"41","author":"Y Zhang","year":"2018","unstructured":"Zhang Y, Meng F, Wang R, Zhu W, Zeng X-J. A stochastic MPC based approach to integrated energy management in microgrids. Sustain Cities Soc. 2018;41:349\u201362. https:\/\/doi.org\/10.1016\/j.scs.2018.05.044.","journal-title":"Sustain Cities Soc"},{"issue":"5","key":"9544_CR12","doi-asserted-by":"publisher","first-page":"586","DOI":"10.1080\/19401493.2021.1986574","volume":"14","author":"D Blum","year":"2021","unstructured":"Blum D, Arroyo J, Huang S, Drgona J, Jorissen F, Walnum HT, Chen Y, Benne K, Vrabie D, Wetter M, Helsen L. Building optimization testing framework (BOPTEST) for simulation-based benchmarking of control strategies in buildings. J Build Perform Simul. 2021;14(5):586\u2013610.","journal-title":"J Build Perform Simul"},{"key":"9544_CR13","doi-asserted-by":"publisher","first-page":"173","DOI":"10.3384\/ecp12076173","volume-title":"9th International Modelica conference","author":"T Blochwitz","year":"2012","unstructured":"Blochwitz T, Otter M, Akesson J, Arnold M, Clauss C, Elmqvist H, Friedrich M, Junghanns A, Mauss J, Neumerkel D, et al. Functional Mockup Interface 2.0: the standard for tool independent exchange of simulation models. In: 9th International Modelica conference. Munich: The Modelica Association; 2012. p. 173\u201384. https:\/\/doi.org\/10.3384\/ecp12076173."},{"issue":"4","key":"9544_CR14","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/S1474-6670(17)43628-7","volume":"30","author":"SE Mattsson","year":"1997","unstructured":"Mattsson SE, Elmqvist H. Modelica-an international effort to design the next generation modeling language. IFAC Proceedings. 1997;30(4):151\u20135. https:\/\/doi.org\/10.1016\/S1474-6670(17)43628-7.","journal-title":"IFAC Proceedings"},{"key":"9544_CR15","doi-asserted-by":"publisher","unstructured":"Lample G, Chaplot DS. Playing fps games with deep reinforcement learning, in: Proceedings of the AAAI Conference on Artificial Intelligence. 2017;31. https:\/\/doi.org\/10.1609\/aaai.v31i1.10827.","DOI":"10.1609\/aaai.v31i1.10827"},{"key":"9544_CR16","first-page":"3389","volume-title":"2017 IEEE International conference on robotics and automation","author":"S Gu","year":"2017","unstructured":"Gu S, Holly E, Lillicrap T, Levine T. Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates. In: 2017 IEEE International conference on robotics and automation. Piscataway: IEEE; 2017. p. 3389\u201396."},{"key":"9544_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2020.110225","volume":"224","author":"S Brandi","year":"2020","unstructured":"Brandi S, Piscitelli MS, Martellacci M, Capozzoli A. Deep reinforcement learning to optimize indoor temperature control and heating energy consumption in buildings. Energy Build. 2020;224: 110225. https:\/\/doi.org\/10.1016\/j.enbuild.2020.110225.","journal-title":"Energy Build"},{"key":"9544_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.jobe.2020.101739","volume":"34","author":"A Gupta","year":"2021","unstructured":"Gupta A, Badr Y, Negahban A, Qiu RG. Energy-efficient heating control for smart buildings with deep reinforcement learning. J Build Eng. 2021;34: 101739. https:\/\/doi.org\/10.1016\/j.jobe.2020.101739.","journal-title":"J Build Eng"},{"key":"9544_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.epsr.2020.106959","volume":"192","author":"Y Du","year":"2021","unstructured":"Du Y, Li F, Munk J, Kurte K, Kotevska O, Amasyali K, Zandi H. Multi-task deep reinforcement learning for intelligent multi-zone residential HVAC control. Electric Power Syst Res. 2021;192: 106959. https:\/\/doi.org\/10.1016\/j.epsr.2020.106959.","journal-title":"Electric Power Syst Res"},{"key":"9544_CR20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1805.03777","author":"A Nagy","year":"2018","unstructured":"Nagy A, Kazmi H, Cheaib F, Driesen J. Deep reinforcement learning for optimal control of space heating. arXiv. 2018. https:\/\/doi.org\/10.48550\/arXiv.1805.03777.","journal-title":"arXiv"},{"key":"9544_CR21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1901.04693","author":"G Gao","year":"2019","unstructured":"Gao G, Li J, Wen Y. Energy-efficient thermal comfort control in smart buildings via deep reinforcement learning. arXiv. 2019. https:\/\/doi.org\/10.48550\/arXiv.1901.04693.","journal-title":"arXiv"},{"issue":"3","key":"9544_CR22","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1109\/TSUSC.2019.2910533","volume":"6","author":"T Wei","year":"2019","unstructured":"Wei T, Ren S, Zhu Q. Deep reinforcement learning for joint datacenter and HVAC load control in distributed mixed-use buildings. IEEE Trans Sustain Comput. 2019;6(3):370\u201384. https:\/\/doi.org\/10.1109\/TSUSC.2019.2910533.","journal-title":"IEEE Trans Sustain Comput"},{"issue":"4","key":"9544_CR23","doi-asserted-by":"publisher","first-page":"3698","DOI":"10.1109\/TSG.2018.2834219","volume":"10","author":"E Mocanu","year":"2018","unstructured":"Mocanu E, Mocanu DC, Nguyen PH, Liotta A, Webber ME, Gibescu M, Slootweg JG. On-line building energy optimization using deep reinforcement learning. IEEE Trans Smart Grid. 2018;10(4):3698\u2013708. https:\/\/doi.org\/10.1109\/TSG.2018.2834219.","journal-title":"IEEE Trans Smart Grid"},{"key":"9544_CR24","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1016\/j.enbuild.2019.07.029","volume":"199","author":"Z Zhang","year":"2019","unstructured":"Zhang Z, Chong A, Pan Y, Zhang C, Lam KP. Whole building energy model for HVAC optimal control: a practical framework based on deep reinforcement learning. Energy Build. 2019;199:472\u201390. https:\/\/doi.org\/10.1016\/j.enbuild.2019.07.029.","journal-title":"Energy Build"},{"issue":"1","key":"9544_CR25","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1080\/23744731.2019.1680234","volume":"26","author":"KU Ahn","year":"2020","unstructured":"Ahn KU, Park CS. Application of deep q-networks for model-free optimal control balancing between different HVAC systems. Sci Technol Built Environ. 2020;26(1):61\u201374. https:\/\/doi.org\/10.1080\/23744731.2019.1680234.","journal-title":"Sci Technol Built Environ"},{"issue":"3","key":"9544_CR26","doi-asserted-by":"publisher","first-page":"46","DOI":"10.3390\/pr5030046","volume":"5","author":"Y Wang","year":"2017","unstructured":"Wang Y, Velswamy K, Huang B. A long-short term memory recurrent neural network-based reinforcement learning controller for office heating ventilation and air conditioning systems. Processes. 2017;5(3):46. https:\/\/doi.org\/10.3390\/pr5030046.","journal-title":"Processes"},{"issue":"4","key":"9544_CR27","doi-asserted-by":"publisher","first-page":"3259","DOI":"10.1109\/TSG.2016.2629450","volume":"9","author":"BJ Claessens","year":"2016","unstructured":"Claessens BJ, Vrancx P, Ruelens F. Convolutional neural networks for automatic state-time feature extraction in reinforcement learning applied to residential load control. IEEE Trans Smart Grid. 2016;9(4):3259\u201369. https:\/\/doi.org\/10.1109\/TSG.2016.2629450.","journal-title":"IEEE Trans Smart Grid"},{"key":"9544_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.115036","volume":"269","author":"Z Wang","year":"2020","unstructured":"Wang Z, Hong T. Reinforcement learning for building controls: the opportunities and challenges. Appl Energy. 2020;269: 115036. https:\/\/doi.org\/10.1016\/j.apenergy.2020.115036.","journal-title":"Appl Energy"},{"key":"9544_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2021.110835","volume":"142","author":"S Zhan","year":"2021","unstructured":"Zhan S, Chong A. Data requirements and performance evaluation of model predictive control in buildings: a modeling perspective. Renew Sustain Energy Rev. 2021;142: 110835. https:\/\/doi.org\/10.1016\/j.rser.2021.110835.","journal-title":"Renew Sustain Energy Rev"},{"key":"9544_CR30","doi-asserted-by":"publisher","unstructured":"Wolfle D, Vishwanath A, Schmeck H. A guide for the design of benchmark environments for building energy optimization. in: Proceedings of the 7th ACM international conference on systems for energy-efficient buildings, cities, and transportation. 2020;220\u2013229. https:\/\/doi.org\/10.1145\/3408308.3427614","DOI":"10.1145\/3408308.3427614"},{"key":"9544_CR31","doi-asserted-by":"crossref","unstructured":"Ding, Xianzhong, Alberto Cerpa, and Wan Du. \"Multi-zone hvac control with model-based deep reinforcement learning.\"\u00a0IEEE Transactions on Automation Science and Engineering\u00a0(2024).","DOI":"10.1109\/TASE.2024.3410951"},{"key":"9544_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.enbuild.2024.115241","author":"W Xue","year":"2025","unstructured":"Xue W, Jia N, Zhao M. Multi-agent deep reinforcement learning based HVAC control for multi-zone buildings considering zone-energy-allocation optimization. Energy Build. 2025. https:\/\/doi.org\/10.1016\/j.enbuild.2024.115241.","journal-title":"Energy Build"},{"key":"9544_CR33","doi-asserted-by":"publisher","first-page":"29","DOI":"10.3992\/jgb.19.1.29","volume":"191","author":"T Van Quang","year":"2024","unstructured":"Van Quang T, Phuong NL. Using deep learning to optimize HVAC systems in residential buildings. J Green Build. 2024;191:29\u201350.","journal-title":"J Green Build"},{"key":"9544_CR34","doi-asserted-by":"publisher","first-page":"114065","DOI":"10.1016\/j.enbuild.2024.114065","volume":"310","author":"AT Nguyen","year":"2024","unstructured":"Nguyen AT, et al. Modelling building HVAC control strategies using a deep reinforcement learning approach. Energy Build. 2024;310:114065.","journal-title":"Energy Build"},{"key":"9544_CR35","unstructured":"CBECS terminology. 2021. https:\/\/www.eia.gov\/consumption\/commercial\/terminology.php."},{"key":"9544_CR36","unstructured":"2015 recs square footage methodology. 2021. https:\/\/www.eia.gov\/consumption\/residential\/reports\/2015\/squarefootage\/."},{"key":"9544_CR37","doi-asserted-by":"publisher","first-page":"175","DOI":"10.26868\/25222708.2021.30380","volume":"17","author":"J Arroyo","year":"2021","unstructured":"Arroyo J, Manna C, Spiessens F, Helsen L. An open-AI gym environment for the building optimization testing (BOPTEST) framework. Build Simulat. 2021;17:175\u201382. https:\/\/doi.org\/10.26868\/25222708.2021.30380.","journal-title":"Build Simulat"},{"key":"9544_CR38","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1606.01540","author":"G Brockman","year":"2016","unstructured":"Brockman G, Cheung V, Pettersson L, Schneider J, Schulman J, Tang J, Zaremba W. Openai gym. arXiv. 2016. https:\/\/doi.org\/10.48550\/arXiv.1606.01540.","journal-title":"arXiv"},{"key":"9544_CR39","doi-asserted-by":"publisher","first-page":"276","DOI":"10.3390\/make4010013","volume":"41","author":"J Moos","year":"2022","unstructured":"Moos J, et al. Robust reinforcement learning: a review of foundations and recent advances. Mach Learn Knowl Extract. 2022;41:276\u2013315.","journal-title":"Mach Learn Knowl Extract"},{"key":"9544_CR40","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1007\/s40435-020-00665-4","volume":"9","author":"RP Borase","year":"2021","unstructured":"Borase RP, Maghade DK, Sondkar SY, Pawar SN. A review of PID control, tuning methods and applications. Int J Dyn Control. 2021;9:818\u201327. https:\/\/doi.org\/10.1007\/s40435-020-00665-4.","journal-title":"Int J Dyn Control"},{"key":"9544_CR41","doi-asserted-by":"publisher","unstructured":"Pivonka P. Comparative analysis of fuzzy PI\/PD\/PID controller based on classical PID controller approach.\u00a02002 IEEE World Congress on Computational Intelligence. 2002 IEEE International Conference on Fuzzy Systems. FUZZ-IEEE'02. Proceedings (Cat. No.02CH37291), Honolulu, HI, USA, 2002; 541\u2013546. https:\/\/doi.org\/10.1109\/FUZZ.2002.1005048.","DOI":"10.1109\/FUZZ.2002.1005048"},{"issue":"4","key":"9544_CR42","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1016\/j.enconman.2006.10.023","volume":"48","author":"J Bai","year":"2007","unstructured":"Bai J, Zhang X. A new adaptive PI controller and its application in HVAC systems. Energy Convers Manage. 2007;48(4):1043\u201354. https:\/\/doi.org\/10.1016\/j.enconman.2006.10.023.","journal-title":"Energy Convers Manage"},{"key":"9544_CR43","unstructured":"AMEE. \u201cAgence Marocaine de l\u2019Efficacit\u00e9 \u00c9nerg\u00e9tique\u201d. https:\/\/www.amee.ma."}],"container-title":["Discover Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-025-09544-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10791-025-09544-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10791-025-09544-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T19:58:57Z","timestamp":1745351937000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10791-025-09544-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":43,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["9544"],"URL":"https:\/\/doi.org\/10.1007\/s10791-025-09544-y","relation":{},"ISSN":["2948-2992"],"issn-type":[{"value":"2948-2992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"13 November 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"45"}}