Grey-box and ANN-based building models for multistep-ahead prediction of indoor temperature to implement model predictive control

Talib, Abu; Park, Semi; Im, Piljae; Joe, Jaewan

doi:10.1016/j.engappai.2023.107115

Title: Grey-box and ANN-based building models for multistep-ahead prediction of indoor temperature to implement model predictive control

Journal Article · 10 September 2023 · Engineering Applications of Artificial Intelligence

DOI: https://doi.org/10.1016/j.engappai.2023.107115 · OSTI ID:2229217

Talib, Abu ^[1]; Park, Semi ^[1];

^[2];

^[1]

Inha University, Incheon (Korea, Republic of)
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Model-based predictive control (MPC) strategies for heating, ventilation, and air-conditioning (HVAC) systems present an opportunity to lower building energy consumption and operational costs. Such approaches rely on the development of a model to precisely forecast building thermal dynamics, such as room air temperature or heating/cooling rate, and make control-related decisions. The control-oriented modeling of building energy systems should be accurate in predicting indoor conditions and present low computational complexity. These features are the key challenge of implementing advanced control methods such as MPC. Extant studies on building modeling for MPC have focused on step-ahead forecasting techniques to forecast building thermal dynamics, while multistep-ahead forecasting is essential. Moreover, machine learning model suitable in case of the domain-based engineering expertise are also not available. To this aim, we perform a comparative analysis of the grey-box model based on a resistance-capacitance (RC) thermal network and a machine learning model composed of an artificial neural network (ANN) for multistep-ahead prediction of building thermal dynamics using current and historical data. Actual experimental data obtained from the Flexible Research Platform (FRP) in Oak Ridge National Laboratory (US) are used for estimation and validation purposes. The average root mean squared error (RMSE) of the grey-box and ANN models are 0.89 °C and 1.02°C, respectively. Finally, the results indicate that the grey-box model outperforms the ANN model in the considered validation periods in terms of accuracy and prediction stability.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE); National Research Foundation of Korea (NRF)

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 2229217

Journal Information:: Engineering Applications of Artificial Intelligence, Journal Name: Engineering Applications of Artificial Intelligence Journal Issue: D Vol. 126; ISSN 0952-1976

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (61)

Comparison of machine-learning models for predicting short-term building heating load using operational parameters Zhou, Yong; Liu, Yanfeng; Wang, Dengjia Energy and Buildings, Vol. 253 https://doi.org/10.1016/j.enbuild.2021.111505	journal	December 2021
Multi-step ahead forecasting of heat load in district heating systems using machine learning algorithms Xue, Puning; Jiang, Yi; Zhou, Zhigang Energy, Vol. 188 https://doi.org/10.1016/j.energy.2019.116085	journal	December 2019
Advanced machine learning techniques for building performance simulation: a comparative analysis Chakraborty, Debaditya; Elzarka, Hazem Journal of Building Performance Simulation, Vol. 12, Issue 2 https://doi.org/10.1080/19401493.2018.1498538	journal	July 2018
Development of prediction models for next-day building energy consumption and peak power demand using data mining techniques Fan, Cheng; Xiao, Fu; Wang, Shengwei Applied Energy, Vol. 127 https://doi.org/10.1016/j.apenergy.2014.04.016	journal	August 2014
A machine-learning-based approach to predict residential annual space heating and cooling loads considering occupant behaviour Li, Xinyi; Yao, Runming Energy, Vol. 212 https://doi.org/10.1016/j.energy.2020.118676	journal	December 2020
Neural network-based model predictive control system for optimizing building automation and management systems of sports facilities Elnour, Mariam; Himeur, Yassine; Fadli, Fodil Applied Energy, Vol. 318 https://doi.org/10.1016/j.apenergy.2022.119153	journal	July 2022
A practical artificial intelligence-based approach for predictive control in commercial and institutional buildings Cotrufo, N.; Saloux, E.; Hardy, J. M. Energy and Buildings, Vol. 206 https://doi.org/10.1016/j.enbuild.2019.109563	journal	January 2020
Economic model predictive control for demand flexibility of a residential building Finck, Christian; Li, Rongling; Zeiler, Wim Energy, Vol. 176 https://doi.org/10.1016/j.energy.2019.03.171	journal	June 2019
A model predictive control strategy to optimize the performance of radiant floor heating and cooling systems in office buildings Joe, Jaewan; Karava, Panagiota Applied Energy, Vol. 245 https://doi.org/10.1016/j.apenergy.2019.03.209	journal	July 2019
Artificial neural network (ANN) based model predictive control (MPC) and optimization of HVAC systems: A state of the art review and case study of a residential HVAC system Afram, Abdul; Janabi-Sharifi, Farrokh; Fung, Alan S. Energy and Buildings, Vol. 141 https://doi.org/10.1016/j.enbuild.2017.02.012	journal	April 2017
Data requirements and performance evaluation of model predictive control in buildings: A modeling perspective Zhan, Sicheng; Chong, Adrian Renewable and Sustainable Energy Reviews, Vol. 142 https://doi.org/10.1016/j.rser.2021.110835	journal	May 2021
Model predictive control of a building heating system: The first experience Prívara, Samuel; Široký, Jan; Ferkl, Lukáš Energy and Buildings, Vol. 43, Issue 2-3 https://doi.org/10.1016/j.enbuild.2010.10.022	journal	February 2011
Applying support vector machines to predict building energy consumption in tropical region Dong, Bing; Cao, Cheng; Lee, Siew Eang Energy and Buildings, Vol. 37, Issue 5 https://doi.org/10.1016/j.enbuild.2004.09.009	journal	May 2005
A Dynamic Model for Indoor Temperature Prediction in Buildings Hietaharju, Petri; Ruusunen, Mika; Leiviskä, Kauko Energies, Vol. 11, Issue 6 https://doi.org/10.3390/en11061477	journal	June 2018
AI enabled applications towards intelligent transportation Iyer, Lakshmi Shankar Transportation Engineering, Vol. 5 https://doi.org/10.1016/j.treng.2021.100083	journal	September 2021
Random Forest based hourly building energy prediction Wang, Zeyu; Wang, Yueren; Zeng, Ruochen Energy and Buildings, Vol. 171 https://doi.org/10.1016/j.enbuild.2018.04.008	journal	July 2018
Machine Learning Approach to Predict Building Thermal Load Considering Feature Variable Dimensions: An Office Building Case Study Chen, Yongbao; Ye, Yunyang; Liu, Jingnan Buildings, Vol. 13, Issue 2 https://doi.org/10.3390/buildings13020312	journal	January 2023
Assessment of deep recurrent neural network-based strategies for short-term building energy predictions Fan, Cheng; Wang, Jiayuan; Gang, Wenjie Applied Energy, Vol. 236 https://doi.org/10.1016/j.apenergy.2018.12.004	journal	February 2019
Model-based predictive control of multi-zone commercial building with a lumped building modelling approach Joe, Jaewan; Im, Piljae; Cui, Borui Energy, Vol. 263 https://doi.org/10.1016/j.energy.2022.125494	journal	January 2023
Accuracy of different machine learning algorithms and added-value of predicting aggregated-level energy performance of commercial buildings Walker, Shalika; Khan, Waqas; Katic, Katarina Energy and Buildings, Vol. 209 https://doi.org/10.1016/j.enbuild.2019.109705	journal	February 2020
Building thermal load prediction through shallow machine learning and deep learning Wang, Zhe; Hong, Tianzhen; Piette, Mary Ann Applied Energy, Vol. 263 https://doi.org/10.1016/j.apenergy.2020.114683	journal	April 2020
A distributed approach to model-predictive control of radiant comfort delivery systems in office spaces with localized thermal environments Joe, Jaewan; Karava, Panagiota; Hou, Xiaodong Energy and Buildings, Vol. 175 https://doi.org/10.1016/j.enbuild.2018.06.068	journal	September 2018
Model predictive control optimization for rapid response and energy efficiency based on the state-space model of a radiant floor heating system Chen, Qiong; Li, Nan; Feng, Wei Energy and Buildings, Vol. 238 https://doi.org/10.1016/j.enbuild.2021.110832	journal	May 2021
Virtual storage capability of residential buildings for sustainable smart city via model-based predictive control Joe, Jaewan; Dong, Jin; Munk, Jeffrey Sustainable Cities and Society, Vol. 64 https://doi.org/10.1016/j.scs.2020.102491	journal	January 2021
Performance evaluation of deep learning architectures for load and temperature forecasting under dataset size constraints and seasonality Choi, Wonjun; Lee, Sangwon Energy and Buildings, Vol. 288 https://doi.org/10.1016/j.enbuild.2023.113027	journal	June 2023
Ceiling radiant cooling: Comparison of ARMAX and subspace identification modelling methods Ferkl, Lukáš Building and Environment, Vol. 45, Issue 1, p. 205-212 https://doi.org/10.1016/j.buildenv.2009.06.004	journal	June 2009
Empirical Modeling of Direct Expansion (DX) Cooling System for Multiple Research Use Cases Joe, Jaewan; Im, Piljae; Dong, Jin Sustainability, Vol. 12, Issue 20 https://doi.org/10.3390/su12208738	journal	October 2020
Ethical, legal, and social considerations of AI-based medical decision-support tools: A scoping review Čartolovni, Anto; Tomičić, Ana; Lazić Mosler, Elvira International Journal of Medical Informatics, Vol. 161 https://doi.org/10.1016/j.ijmedinf.2022.104738	journal	May 2022
A zone-level, building energy optimisation combining an artificial neural network, a genetic algorithm, and model predictive control Reynolds, Jonathan; Rezgui, Yacine; Kwan, Alan Energy, Vol. 151 https://doi.org/10.1016/j.energy.2018.03.113	journal	May 2018
Data-driven models for short-term thermal behaviour prediction in real buildings Ferracuti, Francesco; Fonti, Alessandro; Ciabattoni, Lucio Applied Energy, Vol. 204 https://doi.org/10.1016/j.apenergy.2017.05.015	journal	October 2017
Smart farming using artificial intelligence: A review Akkem, Yaganteeswarudu; Biswas, Saroj Kumar; Varanasi, Aruna Engineering Applications of Artificial Intelligence, Vol. 120 https://doi.org/10.1016/j.engappai.2023.105899	journal	April 2023
Learning-Based Predictive Building Energy Model Using Weather Forecasts for Optimal Control of Domestic Energy Systems Jeon, Byung-Ki; Kim, Eui-Jong; Shin, Younggy Sustainability, Vol. 11, Issue 1 https://doi.org/10.3390/su11010147	journal	December 2018
A predictive control approach for thermal energy management in buildings Berouine, Anass; Ouladsine, Radouane; Bakhouya, Mohamed Energy Reports, Vol. 8 https://doi.org/10.1016/j.egyr.2022.07.037	journal	November 2022
Comparison of four rule-based demand response control algorithms in an electrically and heat pump-heated residential building Alimohammadisagvand, Behrang; Jokisalo, Juha; Sirén, Kai Applied Energy, Vol. 209 https://doi.org/10.1016/j.apenergy.2017.10.088	journal	January 2018
Experimental analysis of model predictive control for an energy efficient building heating system Široký, Jan; Oldewurtel, Frauke; Cigler, Jiří Applied Energy, Vol. 88, Issue 9 https://doi.org/10.1016/j.apenergy.2011.03.009	journal	September 2011
Review on optimization techniques and role of Artificial Intelligence in home energy management systems Nutakki, Mounica; Mandava, Srihari Engineering Applications of Artificial Intelligence, Vol. 119 https://doi.org/10.1016/j.engappai.2022.105721	journal	March 2023
Forecasting heating and cooling loads of buildings: a comparative performance analysis Roy, Sanjiban Sekhar; Samui, Pijush; Nagtode, Ishan Journal of Ambient Intelligence and Humanized Computing, Vol. 11, Issue 3 https://doi.org/10.1007/s12652-019-01317-y	journal	May 2019
Inverse blackbox modeling of the heating and cooling load in office buildings Gunay, Burak; Shen, Weiming; Newsham, Guy Energy and Buildings, Vol. 142 https://doi.org/10.1016/j.enbuild.2017.02.064	journal	May 2017
Building energy metering and environmental monitoring – A state-of-the-art review and directions for future research Ahmad, Muhammad Waseem; Mourshed, Monjur; Mundow, David Energy and Buildings, Vol. 120 https://doi.org/10.1016/j.enbuild.2016.03.059	journal	May 2016
Machine Learning, Deep Learning and Statistical Analysis for forecasting building energy consumption — A systematic review Khalil, Mohamad; McGough, A. Stephen; Pourmirza, Zoya Engineering Applications of Artificial Intelligence, Vol. 115 https://doi.org/10.1016/j.engappai.2022.105287	journal	October 2022
An Ensemble Learning Approach for Accurate Energy Load Prediction in Residential Buildings Al-Rakhami, Mabrook; Gumaei, Abdu; Alsanad, Ahmed IEEE Access, Vol. 7 https://doi.org/10.1109/ACCESS.2019.2909470	journal	January 2019
Buildings-to-Grid Integration Framework Taha, Ahmad F.; Gatsis, Nikolaos; Dong, Bing IEEE Transactions on Smart Grid, Vol. 10, Issue 2 https://doi.org/10.1109/TSG.2017.2761861	journal	March 2019
Energy management in residential microgrid using model predictive control-based reinforcement learning and Shapley value Cai, Wenqi; Kordabad, Arash Bahari; Gros, Sébastien Engineering Applications of Artificial Intelligence, Vol. 119 https://doi.org/10.1016/j.engappai.2022.105793	journal	March 2023
A Control-oriented Simplified Building Modelling Strategy Agustin CANDANEDO, Jose; R. Dehkordi, Vahid; Lopez, Phylroy Building Simulation Conference Proceedings https://doi.org/10.26868/25222708.2013.1057	conference	August 2013
Practical implementation and evaluation of model predictive control for an office building in Brussels De Coninck, Roel; Helsen, Lieve Energy and Buildings, Vol. 111 https://doi.org/10.1016/j.enbuild.2015.11.014	journal	January 2016
Model predictive control for thermal energy storage and thermal comfort optimization of building demand response in smart grids Tang, Rui; Wang, Shengwei Applied Energy, Vol. 242 https://doi.org/10.1016/j.apenergy.2019.03.038	journal	May 2019
Toolbox for development and validation of grey-box building models for forecasting and control De Coninck, Roel; Magnusson, Fredrik; Åkesson, Johan Journal of Building Performance Simulation, Vol. 9, Issue 3 https://doi.org/10.1080/19401493.2015.1046933	journal	June 2015
A short-term building cooling load prediction method using deep learning algorithms Fan, Cheng; Xiao, Fu; Zhao, Yang Applied Energy, Vol. 195 https://doi.org/10.1016/j.apenergy.2017.03.064	journal	June 2017
Modeling heating and cooling loads by artificial intelligence for energy-efficient building design Chou, Jui-Sheng; Bui, Dac-Khuong Energy and Buildings, Vol. 82 https://doi.org/10.1016/j.enbuild.2014.07.036	journal	October 2014
Evaluation of optimal control for active and passive building thermal storage Henze, Gregor P.; Felsmann, Clemens; Knabe, Gottfried International Journal of Thermal Sciences, Vol. 43, Issue 2 https://doi.org/10.1016/j.ijthermalsci.2003.06.001	journal	February 2004
A model-based control strategy to recover cooling energy from thermal mass in commercial buildings Shan, Kui; Wang, Jiayuan; Hu, Maomao Energy, Vol. 172 https://doi.org/10.1016/j.energy.2019.02.045	journal	April 2019
An online physical-based multiple linear regression model for building’s hourly cooling load prediction Chen, Sihao; Zhou, Xiaoqing; Zhou, Guang Energy and Buildings, Vol. 254 https://doi.org/10.1016/j.enbuild.2021.111574	journal	January 2022
MPC solution for optimal load shifting for buildings with ON/OFF staged packaged units: Experimental demonstration, and lessons learned Kim, Donghun; Braun, James E. Energy and Buildings, Vol. 266 https://doi.org/10.1016/j.enbuild.2022.112118	journal	July 2022
Trees vs Neurons: Comparison between random forest and ANN for high-resolution prediction of building energy consumption Ahmad, Muhammad Waseem; Mourshed, Monjur; Rezgui, Yacine Energy and Buildings, Vol. 147 https://doi.org/10.1016/j.enbuild.2017.04.038	journal	July 2017
Neural network design for engineering applications Rafiq, M. Y.; Bugmann, G.; Easterbrook, D. J. Computers & Structures, Vol. 79, Issue 17 https://doi.org/10.1016/S0045-7949(01)00039-6	journal	July 2001
Artificial Neural Networks to assess energy and environmental performance of buildings: An Italian case study D'Amico, A.; Ciulla, G.; Traverso, M. Journal of Cleaner Production, Vol. 239 https://doi.org/10.1016/j.jclepro.2019.117993	journal	December 2019
Heating load prediction based on attention long short term memory: A case study of Xingtai Xue, Guixiang; Qi, Chengying; Li, Han Energy, Vol. 203 https://doi.org/10.1016/j.energy.2020.117846	journal	July 2020
A novel improved model for building energy consumption prediction based on model integration Wang, Ran; Lu, Shilei; Feng, Wei Applied Energy, Vol. 262 https://doi.org/10.1016/j.apenergy.2020.114561	journal	March 2020
Model predictive control for building loads connected with a residential distribution grid Mirakhorli, Amin; Dong, Bing Applied Energy, Vol. 230 https://doi.org/10.1016/j.apenergy.2018.08.051	journal	November 2018
Comparisons of inverse modeling approaches for predicting building energy performance Zhang, Yuna; O'Neill, Zheng; Dong, Bing Building and Environment, Vol. 86 https://doi.org/10.1016/j.buildenv.2014.12.023	journal	April 2015
Building temperature regulation using a distributed model predictive control Moroşan, Petru-Daniel; Bourdais, Romain; Dumur, Didier Energy and Buildings, Vol. 42, Issue 9 https://doi.org/10.1016/j.enbuild.2010.03.014	journal	September 2010

Similar Records

One-Step Ahead Prediction of Thermal Mixing Tee Sensors with Long Short Term Memory (LSTM) Neural Networks

Technical Report · 2020 · OSTI ID:1760289

Ankel, Victoria; Pantopoulou, Stella; Weathered, Matthew; +3 more

Probabilistic Day-Ahead Forecasting Using an Analog Ensemble Approach for Wind Farm Grid Services

Conference · 2021 · OSTI ID:1823425

Kumler, Andrew; Lundquist, Julie K.; King, Jennifer

DECENTRALIZED APPROACH TO MULTI-ZONE GREY-BOX MODELING FOR MODEL-BASED PREDICTIVE CONTROL

Conference · 2020 · OSTI ID:1671389

Joe, Jaewan; Cui, Borui; Im, Piljae; +2 more

Related Subjects

42 ENGINEERING
grey-box model
artificial neural network
model-based predictive control
multi-step ahead prediction

Title: Grey-box and ANN-based building models for multistep-ahead prediction of indoor temperature to implement model predictive control

Citation Formats

References (61)

Similar Records

Related Subjects