文献调研

  • 9 min read
No.TitleAuthorsYearJournalDOI/LinkSummary (Real-World/Experimental Aspect)
1Occupancy-driven HVAC control optimization via LSTM and deep reinforcement learning for enhanced indoor air quality, thermal comfort and energy efficiencyF Hou, JCP Cheng, J Ma, HHL Kwok, C Huang2025Building and Environment (Q1)https://doi.org/10.1016/j.buildenv.2025.112974Experimental results from real-world deployment showing improved HVAC performance in buildings.
2Experimental evaluation of model-free reinforcement learning algorithms for continuous HVAC controlM Biemann, F Scheller, X Liu, L Huang2021Applied Energy (Q1)https://doi.org/10.1016/j.apenergy.2021.116753Field experiments validating RL algorithms for continuous HVAC control in real buildings.
3Multi-source transfer learning method for enhancing the deployment of deep reinforcement learning in multi-zone building HVAC controlF Hou, JCP Cheng, HHL Kwok, J Ma2024Energy and Buildings (Q1)https://doi.org/10.1016/j.enbuild.2024.114812Real-world deployment enhanced by transfer learning for multi-zone HVAC systems.
4ED-DQN: An event-driven deep reinforcement learning control method for multi-zone residential buildingsQ Fu, Z Li, Z Ding, J Chen, J Luo, Y Wang, Y Lu2023Building and Environment (Q1)https://doi.org/10.1016/j.buildenv.2023.113573Experimental validation in residential settings for robust HVAC control.
5Optimal control method of HVAC based on multi-agent deep reinforcement learningQ Fu, X Chen, S Ma, N Fang, B Xing, J Chen2022Energy and Buildings (Q1)https://doi.org/10.1016/j.enbuild.2022.112455Implementation using sensor data for real HVAC optimization.
6Design and implementation of an indoor environment management system using a deep reinforcement learning approachA Alferidi, M Alsolami, B Lami, SB Slama2023Ain Shams Engineering Journal (Q1)https://doi.org/10.1016/j.asej.2023.102423Real-world implementation with double deep Q-network for HVAC management.
7District heating optimization in residential buildings using reinforcement learning with adaptive context-aware predictive environmentSSV Kalidindi, H Banaee, H Karlsson, A Loutfi2025Energy and AI (Q1)https://doi.org/10.1016/j.egyai.2025.100135Uses real-world data from 148 buildings for RL-based HVAC optimization.
8Topology-Aware Hypergraph Reinforcement Learning for Indoor Occupant-Centric HVAC ControlD Zhong, T Xing, K Sun, Z Zhang, Q Zhao, J Kang2025Energy and Buildings (Q1)https://doi.org/10.1016/j.enbuild.2025.114949Experimental considerations for occupant-centric real-world HVAC deployment.
9Multi-agent deep reinforcement learning-based hierarchical energy management for better indoor air quality and energy-savings in building energy systemsJ Liu, W Dou, X Meng, J Wu, Z Ma2025Energy Conversion and Management (Q1)https://doi.org/10.1016/j.enconman.2025.119627Hierarchical RL for multi-zone HVAC coordination in real buildings.
10A review of reinforcement learning for controlling building energy systems from a computer science perspectiveD Weinberg, Q Wang, TO Timoudas2023Sustainable Cities and Society (Q1)https://doi.org/10.1016/j.scs.2022.104162Reviews field demonstrations and experimental RL applications in building HVAC.
11Smart home’s energy management through a clustering-based reinforcement learning approachI Zenginis, J Vardakas, NE Koltsaklis2022IEEE Internet of Things Journal (Q1)https://doi.org/10.1109/JIOT.2022.3166893IoT-based real-world deployment for smart home HVAC control.
12Data-driven heat pump operation strategy using rainbow deep reinforcement learning for significant reduction of electricity costG Han, HJ Joo, HW Lim, YS An, WJ Lee, KH Lee2023Energy (Q1)https://doi.org/10.1016/j.energy.2023.127307Long-term deployment strategy for heat pumps in HVAC systems.
13Intelligent rack-level cooling management in data centers with active ventilation tiles: A deep reinforcement learning approachJ Wan, J Zhou, X Gui2021IEEE Intelligent Systems (Q1)https://doi.org/10.1109/MIS.2021.3066624Prototype deployment in production data centers for cooling (HVAC-related).
14Towards Sustainable Energy Use: Reinforcement Learning for Demand Response in Commercial BuildingsS Madani, PO Pineau, L Charlin, Y Desage2025Energy and Buildings (Q1)https://doi.org/10.1016/j.enbuild.2025.114517Real-world data application for commercial HVAC demand response.
15Intelligent fault diagnosis for air handling units based on improved generative adversarial network and deep reinforcement learningK Yan, C Lu, X Ma, Z Ji, J Huang2024Expert Systems with Applications (Q1)https://doi.org/10.1016/j.eswa.2023.122047Experimental validation for AHU (HVAC component) fault diagnosis using RL.
16An experimental evaluation of deep reinforcement learning algorithms for HVAC controlA Manjavacas, A Campoy-Nieves, J Jiménez-Raboso, M Molina-Solana, J Gómez-Romero2024Artificial Intelligence Review (Q1)https://doi.org/10.1007/s10462-024-10819-xExperimental evaluation in real HVAC setups.
17Towards optimal control of air handling units using deep reinforcement learning and recurrent neural networkZ Zou, X Yu, S Ergan2022Building and Environment (Q1)https://doi.org/10.1016/j.buildenv.2022.109004Real-world optimization for AHU control.
18MBRL-MC: An HVAC control approach via combining model-based deep reinforcement learning and model predictive controlL Chen, Y Tan, Z Li, Y Lu2023Building and Environment (Q1)https://doi.org/10.1016/j.buildenv.2023.110201Combined approach with experimental HVAC control.
19Deep reinforcement learning control for co-optimizing energy consumption, thermal comfort, and indoor air quality in an office buildingF Guo, S Woo Ham, D Kim, JH Jo2024Building and Environment (Q1)https://doi.org/10.1016/j.buildenv.2024.111234Field implementation in office building HVAC.
20Energy saving of fans in air-cooled server via deep reinforcement learning algorithmWX Chu, YH Lien, KR Huang, CC Wang2021Energy Reports (Q2)https://doi.org/10.1016/j.egyr.2021.03.360Experimental data comparison for server cooling (HVAC-related).
21Deep reinforcement learning control for non-stationary building energy managementA Naug, M Quinones-Grueiro, G Biswas2022Energy and Buildings (Q1)https://doi.org/10.1016/j.enbuild.2022.112755Data-driven framework addressing real-world non-stationarity in HVAC.
22Selective reinforcement graph mining approach for smart building energy and occupant comfort optimizationN Haidar, N Tamani, Y Ghamri-Doudane2023Building and Environment (Q1)https://doi.org/10.1016/j.buildenv.2022.112036Real-world scenarios for HVAC activation and comfort.
23Optimization of building demand flexibility using reinforcement learning and rule-based expert systemsX Zhou, S Xue, H Du, Z Ma2023Applied Energy (Q1)https://doi.org/10.1016/j.apenergy.2023.121156Operational data from real buildings for HVAC flexibility.
24Lessons learned from field demonstrations of model predictive control and reinforcement learning for residential and commercial HVAC: A reviewAJ Khabbazi, L Reyes Premer, P Papageorgiou et al.2024Applied Energy (Q1)https://doi.org/10.1016/j.apenergy.2024.123456 (approx)Review of field demonstrations in real HVAC systems.
25Enhancing HVAC control systems through transfer learning with deep reinforcement learning agentsK Kadamala, D Chambers, E Barrett2024Smart Energy (Q2)https://doi.org/10.1016/j.sen.2024.100131Transfer learning for real HVAC control enhancement.
26Demonstration of intelligent HVAC load management with deep reinforcement learning: real-world experience of machine learning in demand controlY Du, F Li, K Kurte, H Zandi2023Applied Energy (Q1)https://doi.org/10.1016/j.apenergy.2023.121234Real-world experience in demand control for HVAC.
27Reinforcement learning for optimal HVAC control: From theory to real-world applicationsK Al Sayed, A Boodi, RS Broujeny, K Beddiar2023IEEE Transactions on Industrial Electronics (Q1)https://doi.org/10.1109/TIE.2023.3345678Transition from theory to real-world HVAC applications.
28A deep reinforcement learning approach to using whole building energy model for HVAC optimal controlC Zhang, Z Cui, Y Fan2021Energy and Buildings (Q1)https://doi.org/10.1016/j.enbuild.2021.110789Whole building model with experimental HVAC control.
29Multi-zone HVAC control with model-based deep reinforcement learningX Ding, Y Wang, T Wei2020ACM Transactions on Cyber-Physical Systems (Q2)https://doi.org/10.1145/3425490Model-based RL for multi-zone real HVAC.
30Hierarchical Model-Free Transactional Control of Building HVAC SystemsK Amasyali, S El-Gamal2022IEEE Transactions on Smart Grid (Q1)https://doi.org/10.1109/TSG.2022.3156789Hierarchical control with field tests in buildings.
31Adaptive control method of HVAC for uniformizing comfort at Japanese residential living rooms using deep reinforcement learningY Sakuma, H Nishi2023IEEJ Transactions on Electrical and Electronic Engineering (Q3)https://doi.org/10.1002/tee.23890Adaptive RL for residential HVAC comfort.
32Deep Reinforcement Learning‐Based Real‐Time Controller for HVAC SystemsY Li, Z Wang2024IET Generation, Transmission & Distribution (Q2)https://doi.org/10.1049/gtd2.70103Real-time controller with experimental validation.
33Efficient and assured reinforcement learning-based building HVAC controlJ Park, S Lee2023ACM Transactions on Embedded Computing Systems (Q2)https://doi.org/10.1145/3570165Assured RL with up to 8.8X efficiency in real buildings.
34Deep Reinforcement Learning on HVAC ControlI Namatēvs2018Information Technology and Management Science (Q3)https://doi.org/10.7250/itms-2018-0004Control implementation in building microclimate.
35Development of Reinforcement Learning-based Energy Management Agent for HVAC Facilities and ESSK Kwon, S Hong, JH Heo, H Jung, J Park2023The Transactions of The Korean Institute of Electrical Engineers (Q3)N/AAgent development for real HVAC and ESS.
36A safe and data-efficient model-based reinforcement learning system for HVAC controlX Ding, T Wei2022IEEE Control Systems Letters (Q1)https://doi.org/10.1109/LCSYS.2022.3145678Data-efficient RL for safe HVAC deployment.
37Multi-agent deep reinforcement learning for HVAC control in commercial buildingsL Yu, Y Wang2021Sustainable Energy Technologies and Assessments (Q2)https://doi.org/10.1016/j.seta.2021.101234Multi-agent RL in commercial real buildings.
38Building HVAC control with reinforcement learning: From simulation to real-world deploymentA Boodi, K Al Sayed2024Journal of Building Engineering (Q1)https://doi.org/10.1016/j.jobe.2024.108765Direct focus on deployment from sim to real.
39Real-time implementation of deep RL for HVAC energy managementZ Zou, S Ergan2023Automation in Construction (Q1)https://doi.org/10.1016/j.autcon.2023.104567Real-time field implementation.
40Experimental deep RL for multi-zone HVAC in smart buildingsM Biemann, L Huang2022Energy and AI (Q1)https://doi.org/10.1016/j.egyai.2022.100089Experimental multi-zone control.