{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/energy-efficient-thermal-comfort-control-in","title":"Energy-Efficient Thermal Comfort Control in Smart Buildings via Deep Reinforcement Learning","arxiv_id":"1901.04693","date":"2019-01-15","proceeding":null,"authors":["Guanyu Gao","Jie Li","Yonggang Wen"],"abstract":"Heating, Ventilation, and Air Conditioning (HVAC) is extremely\nenergy-consuming, accounting for 40% of total building energy consumption.\nTherefore, it is crucial to design some energy-efficient building thermal\ncontrol policies which can reduce the energy consumption of HVAC while\nmaintaining the comfort of the occupants. However, implementing such a policy\nis challenging, because it involves various influencing factors in a building\nenvironment, which are usually hard to model and may be different from case to\ncase. To address this challenge, we propose a deep reinforcement learning based\nframework for energy optimization and thermal comfort control in smart\nbuildings. We formulate the building thermal control as a cost-minimization\nproblem which jointly considers the energy consumption of HVAC and the thermal\ncomfort of the occupants. To solve the problem, we first adopt a deep neural\nnetwork based approach for predicting the occupants' thermal comfort, and then\nadopt Deep Deterministic Policy Gradients (DDPG) for learning the thermal\ncontrol policy. To evaluate the performance, we implement a building thermal\ncontrol simulation system and evaluate the performance under various settings.\nThe experiment results show that our method can improve the thermal comfort\nprediction accuracy, and reduce the energy consumption of HVAC while improving\nthe occupants' thermal comfort.","url_abs":"http://arxiv.org/abs/1901.04693v1","url_pdf":"http://arxiv.org/pdf/1901.04693v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"energy-efficient-thermal-comfort-control-in","repo_url":"https://github.com/arunajit/drl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"energy-efficient-thermal-comfort-control-in","repo_url":"https://github.com/thomasslloyd/EnvironmentMonitoring","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"deep-reinforcement-learning","task_name":"Deep Reinforcement Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}