Data-driven predictive control for smart HVAC system in IoT-integrated buildings with time-series forecasting and reinforcement learning

Dian Zhuang; Vincent J.L. Gan; Zeynep Duygu Tekler; Adrian Chong; Shuai Tian; Xing Shi

doi:10.1016/j.apenergy.2023.120936

journal article May 01, 2023

Data-driven predictive control for smart HVAC system in IoT-integrated buildings with time-series forecasting and reinforcement learning

Dian Zhuang Vincent J.L. Gan Zeynep Duygu Tekler Adrian Chong

Shuai Tian

Xing Shi

Applied Energy Vol. 338 pp. 120936 · Elsevier BV

View at Publisher Save 10.1016/j.apenergy.2023.120936

Topics

No keywords indexed for this article. Browse by subject →

References

58

[1]

IEA, 2019 Global Status Report for Buildings and Construction. 2019.

[2]

A review on buildings energy consumption information

Luis Pérez-Lombard, José Ortiz, Christine Pout

Energy and Buildings 2008 10.1016/j.enbuild.2007.03.007

[3]

IEA, The Future of Cooling. 2018: Paris.

[4]

Wang "Digital twin-enabled built environment sensing and monitoring through semantic enrichment of BIM with SensorML" Autom Constr (2022) 10.1016/j.autcon.2022.104625

[5]

Brandi "Comparison of online and offline deep reinforcement learning with model predictive control for thermal energy management" Autom Constr (2022) 10.1016/j.autcon.2022.104128

[6]

Yu "A data-driven approach to extract operational signatures of HVAC systems and analyze impact on electricity consumption" Appl Energy (2019) 10.1016/j.apenergy.2019.113497

[7]

Zou "Towards optimal control of air handling units using deep reinforcement learning and recurrent neural network" Build Environ (2020) 10.1016/j.buildenv.2019.106535

[8]

Wang "Energy conservation through flexible HVAC management in large spaces: An IPS-based demand-driven control (IDC) system" Autom Constr (2017) 10.1016/j.autcon.2017.08.021

[9]

Afram "Theory and applications of HVAC control systems – A review of model predictive control (MPC)" Build Environ (2014) 10.1016/j.buildenv.2013.11.016

[10]

Yu "A Review of Deep Reinforcement Learning for Smart Building Energy Management" IEEE Internet Things J (2021) 10.1109/jiot.2021.3078462

[11]

Field demonstration and implementation analysis of model predictive control in an office HVAC system

David Blum, Zhe Wang, Chris Weyandt et al.

Applied Energy 2022 10.1016/j.apenergy.2022.119104

[12]

Schwingshackl "LoLiMoT based MPC for air handling units in HVAC systems" Build Environ (2016) 10.1016/j.buildenv.2015.11.011

[13]

Fu "Applications of reinforcement learning for building energy efficiency control: A review" J Build Eng (2022)

[14]

Jang "Optimal HVAC System Operation Using Online Learning of Interconnected Neural Networks" IEEE Trans Smart Grid (2021) 10.1109/tsg.2021.3051564

[15]

Kakade (2003)

[16]

Wang "Reinforcement learning for building controls: The opportunities and challenges" Appl Energy (2020) 10.1016/j.apenergy.2020.115036

[17]

Li "Measuring and monitoring occupancy with an RFID based system for demand-driven HVAC operations" Autom Constr (2012) 10.1016/j.autcon.2012.02.013

[18]

Li "An event-driven multi-agent based distributed optimal control strategy for HVAC systems in IoT-enabled smart buildings" Autom Constr (2021) 10.1016/j.autcon.2021.103919

[19]

Alanne "An overview of machine learning applications for smart buildings" Sustain Cities Soc (2022) 10.1016/j.scs.2021.103445

[20]

Goyal, M., M. Pandey and R. Thakur. Exploratory Analysis of Machine Learning Techniques to predict Energy Efficiency in Buildings. 2020: IEEE. 10.1109/icrito48877.2020.9197976

[21]

Somu "A hybrid deep transfer learning strategy for thermal comfort prediction in buildings" Build Environ (2021) 10.1016/j.buildenv.2021.108133

[22]

Yang "Predicting the long-term CO2 concentration in classrooms based on the BO–EMD–LSTM model" Build Environ (2022) 10.1016/j.buildenv.2022.109568

[23]

Fan "Assessment of deep recurrent neural network-based strategies for short-term building energy predictions" Appl Energy (2019) 10.1016/j.apenergy.2018.12.004

[24]

Xiao "Impacts of data preprocessing and selection on energy consumption prediction model of HVAC systems based on deep learning" Energ Buildings (2022) 10.1016/j.enbuild.2022.111832

[25]

Elmaz "CNN-LSTM architecture for predictive indoor temperature modeling" Build Environ (2021) 10.1016/j.buildenv.2021.108327

[26]

Wong "Construction, application and validation of selection evaluation model (SEM) for intelligent HVAC control system" Autom Constr (2010) 10.1016/j.autcon.2009.10.002

[27]

Long Short-Term Memory

Sepp Hochreiter, Jürgen Schmidhuber

Neural Computation 1997 10.1162/neco.1997.9.8.1735

[28]

Goodfellow (2016)

[29]

Li "A data-driven interval forecasting model for building energy prediction using attention-based LSTM and fuzzy information granulation" Sustain Cities Soc (2022) 10.1016/j.scs.2021.103481

[30]

Fazlipour "A deep model for short-term load forecasting applying a stacked autoencoder based on LSTM supported by a multi-stage attention mechanism" Appl Energy (2022) 10.1016/j.apenergy.2022.120063

[31]

Dai "Improving the Bi-LSTM model with XGBoost and attention mechanism: A combined approach for short-term power load prediction" Appl Soft Comput (2022) 10.1016/j.asoc.2022.109632

[32]

Chung "District heater load forecasting based on machine learning and parallel CNN-LSTM attention" Energy (2022) 10.1016/j.energy.2022.123350

[33]

Zhao "Prediction of functional zones cooling load for shopping mall using dual attention based LSTM: A case study" Int J Refrig (2022) 10.1016/j.ijrefrig.2022.07.020

[34]

Jiang "Attention-LSTM architecture combined with Bayesian hyperparameter optimization for indoor temperature prediction" Build Environ (2022)

[35]

Li "Short-mid term electricity consumption prediction using non-intrusive attention-augmented deep learning model" Energy Rep (2022) 10.1016/j.egyr.2022.08.195

[36]

Predicting residential energy consumption using CNN-LSTM neural networks

Tae-Young Kim, Sung-Bae Cho

Energy 2019 10.1016/j.energy.2019.05.230

[37]

Sendra-Arranz "A long short-term memory artificial neural network to predict daily HVAC consumption in buildings" Energ Buildings (2020) 10.1016/j.enbuild.2020.109952

[38]

Jang "Prediction of heating energy consumption with operation pattern variables for non-residential buildings using LSTM networks" Energ Buildings (2022) 10.1016/j.enbuild.2021.111647

[39]

Fang "Multi-zone indoor temperature prediction with LSTM-based sequence to sequence model" Energ Buildings (2021) 10.1016/j.enbuild.2021.111053

[40]

Ben Taieb "A review and comparison of strategies for multi-step ahead time series forecasting based on the NN5 forecasting competition" Expert Syst Appl (2012) 10.1016/j.eswa.2012.01.039

[41]

Pinto "Data-driven district energy management with surrogate models and deep reinforcement learning" Appl Energy (2021) 10.1016/j.apenergy.2021.117642

[42]

Blad "Data-driven Offline Reinforcement Learning for HVAC-systems" Energy (2022) 10.1016/j.energy.2022.125290

[43]

Wu "Towards comfortable and cost-effective indoor temperature management in smart homes: A deep reinforcement learning method combined with future information" Energ Buildings (2022) 10.1016/j.enbuild.2022.112491

[44]

Liu "A multi-step predictive deep reinforcement learning algorithm for HVAC control systems in smart buildings" Energy (2022) 10.1016/j.energy.2022.124857

[45]

Fanger "Thermal comfort: Analysis and applications in environmental engineering" Appl Ergon (1972) 10.1016/s0003-6870(72)80074-7

[46]

Evaluation of the accuracy of PMV and its several revised models using the Chinese thermal comfort Database

Heng Du, Zhiwei Lian, Dayi Lai et al.

Energy and Buildings 2022 10.1016/j.enbuild.2022.112334

[47]

ASHRAE (2020). ANSI/ASHRAE Standard 55, Thermal Environmental Conditions for Human Occupancy, Atlanta, GA, United States.

[48]

Bidirectional recurrent neural networks

M. Schuster, K.K. Paliwal

IEEE Transactions on Signal Processing 10.1109/78.650093

[49]

Mnih, V., et al., Recurrent Models of Visual Attention, in Advances in Neural Information Processing Systems. 2014.

[50]

Du "Intelligent multi-zone residential HVAC control strategy based on deep reinforcement learning" Appl Energy (2021) 10.1016/j.apenergy.2020.116117

Showing 50 of 58 references

Cited By

182

Prediction-guided deep reinforcement learning for energy-efficient HVAC control with PICVs in smart buildings

Younghyun Baek, Guwon Yoon · 2026

Energy Reports

Learning across modalities: Multi-scale contrastive forecasting with time-frequency representations and adversarial augmentations

Yangyang Shi, Qianqian Ren · 2026

Information Sciences

Review of optimization control methods for HVAC systems in Demand Response (DR): Transition from model-driven to model-free approaches and challenges

Ruiying Jin, Peng Xu · 2025

Building and Environment

Exploring the comprehensive integration of artificial intelligence in optimizing HVAC system operations: A review and future outlook

Shengze Lu, Shiyu Zhou · 2025

Results in Engineering

Energy Forecasting: A Comprehensive Review of Techniques and Technologies

Aristeidis Mystakidis, Paraskevas Koukaras · 2024

Energies

Dynamic Modeling of Heat Exchangers Based on Mechanism and Reinforcement Learning Synergy

Hao Sun, Zile Jia · 2024

Buildings

Optimizing Building Short-Term Load Forecasting: A Comparative Analysis of Machine Learning Models

Paraskevas Koukaras, Akeem Mustapha · 2024

Energies

Smart Transportation: An Overview of Technologies and Applications

Damilola Oladimeji, Khushi Gupta · 2023

Sensors

Metrics

182

Citations

58

References

Details

Published: May 01, 2023
Vol/Issue: 338
Pages: 120936
License: View

Authors

College of Architecture and Urban Planning, Tongji University, No. 1239 Si Ping Road, Shanghai 200092, China

Funding

National University of Singapore Award: A-0008324-01-00

Cite This Article

Dian Zhuang, Vincent J.L. Gan, Zeynep Duygu Tekler, et al. (2023). Data-driven predictive control for smart HVAC system in IoT-integrated buildings with time-series forecasting and reinforcement learning. Applied Energy, 338, 120936. https://doi.org/10.1016/j.apenergy.2023.120936

Data-driven predictive control for smart HVAC system in IoT-integrated buildings with time-series forecasting and reinforcement learning

You May Also Like