A deep learning-based Bayesian framework for high-resolution calibration of building energy models

Jiang, Gang; Chen, Yixing; Wang, Zhe; Powell, Kody; Billings, Blake; Chen, Jianli

doi:10.1016/j.enbuild.2024.114755

A deep learning-based Bayesian framework for high-resolution calibration of building energy models

Journal Article · Fri Sep 06 00:00:00 EDT 2024 · Energy and Buildings

DOI:https://doi.org/10.1016/j.enbuild.2024.114755· OSTI ID:2440970

Jiang, Gang ^[1]; Chen, Yixing ^[2]; Wang, Zhe ^[3]; Powell, Kody ^[1]; ^[4]; Chen, Jianli ^[1]

Univ. of Utah, Salt Lake City, UT (United States)
Hunan Univ., Changsha (China)
Hong Kong University of Science and Technology (HKUST) (Hong Kong)
Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)

Calibrating building energy models (BEMs), i.e., closing discrepancy between modeling and field measurements, is of significance to support its applications in building sustainability and resilience analysis. However, as being widely used in practice, current Bayesian calibration is mostly performed in low-resolution (annual or monthly), instead of high-resolution (hourly or sub-hourly), which is crucial to support emerging BEM applications, such as building-renewable energy integration (demand response) and smart control. This is attributable to the gaps in current Bayesian calibration process, including (1) difficulty in supporting reliable high-resolution calibration with over-parameterization and multi-solution issues, (2) inadequacy of meta-model to capture temporal building dynamics in high-resolution, and (3) excessive computational burdens of covariance matrix calculation in Bayesian inference. Therefore, to close these gaps, this research proposes a novel deep learning-based Bayesian calibration framework, involving pre-calibration mechanism, Long Short-Term Memory as surrogate models, and simplified covariance matrix calculation, to calibrate BEMs in high temporal resolution (i.e., hourly) with enhanced accuracy and computational efficiency. Finally, the case study demonstrates its effectiveness to match modeling outcomes with measurements and realize CV-RMSE of < 30 % and NMBE of < 6 % in hourly resolution, as well as a significant reduction of calibration time (by > 99 %, from > 600 h to ~ 1.5 h).

View Accepted Manuscript (DOE)

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

Sponsoring Organization:: USDOE

Grant/Contract Number:: AC05-00OR22725

OSTI ID:: 2440970

Journal Information:: Energy and Buildings, Journal Name: Energy and Buildings Vol. 323; ISSN 0378-7788

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (52)

Exact indexing of dynamic time warping Keogh, Eamonn; Ratanamahatana, Chotirat Ann Knowledge and Information Systems, Vol. 7, Issue 3 https://doi.org/10.1007/s10115-004-0154-9	journal	March 2005
Building simulation: Ten challenges Hong, Tianzhen; Langevin, Jared; Sun, Kaiyu Building Simulation, Vol. 11, Issue 5 https://doi.org/10.1007/s12273-018-0444-x	journal	April 2018
Why is the reliability of building simulation limited as a tool for evaluating energy conservation measures? Li, Nan; Yang, Zheng; Becerik-Gerber, Burcin Applied Energy, Vol. 159 https://doi.org/10.1016/j.apenergy.2015.09.001	journal	December 2015
Building energy model calibration with schedules derived from electricity use data Kim, Yang-Seon; Heidarinejad, Mohammad; Dahlhausen, Matthew Applied Energy, Vol. 190 https://doi.org/10.1016/j.apenergy.2016.12.167	journal	March 2017
A simultaneous calibration and parameter ranking method for building energy models Yuan, Jun; Nian, Victor; Su, Bin Applied Energy, Vol. 206 https://doi.org/10.1016/j.apenergy.2017.08.220	journal	November 2017
Bottom-up modelling methodology for urban-scale analysis of residential space heating demand response Hedegaard, Rasmus Elbæk; Kristensen, Martin Heine; Pedersen, Theis Heidmann Applied Energy, Vol. 242 https://doi.org/10.1016/j.apenergy.2019.03.063	journal	May 2019
A Bayesian deep-learning framework for assessing the energy flexibility of residential buildings with multicomponent energy systems Bampoulas, Adamantios; Pallonetto, Fabiano; Mangina, Eleni Applied Energy, Vol. 348 https://doi.org/10.1016/j.apenergy.2023.121576	journal	October 2023
Sensitivity analysis of multiple time-scale building energy using Bayesian adaptive spline surfaces Zhang, Hu; Tian, Wei; Tan, Jingyuan Applied Energy, Vol. 363 https://doi.org/10.1016/j.apenergy.2024.123042	journal	June 2024
A rapid calibration procedure and case study for simplified simulation models of commonly used HVAC systems Liu, Guopeng; Liu, Mingsheng Building and Environment, Vol. 46, Issue 2 https://doi.org/10.1016/j.buildenv.2010.08.002	journal	February 2011
Calibration of simplified building energy models for parameter estimation and forecasting: Stochastic versus deterministic modelling Rouchier, Simon; Rabouille, Mickaël; Oberlé, Pierre Building and Environment, Vol. 134 https://doi.org/10.1016/j.buildenv.2018.02.043	journal	April 2018
Automatic model calibration for coupled HVAC and building dynamics using Modelica and Bayesian optimization Martinez-Viol, Victor; Urbano, Eva M.; Delgado-Prieto, Miguel Building and Environment, Vol. 226 https://doi.org/10.1016/j.buildenv.2022.109693	journal	December 2022
In-situ sensor calibration for building HVAC systems with limited information using general regression improved Bayesian inference Li, Guannan; Xiong, Jiahao; Tang, Rui Building and Environment, Vol. 234 https://doi.org/10.1016/j.buildenv.2023.110161	journal	April 2023
Surrogate modeling of elasto-plastic problems via long short-term memory neural networks and proper orthogonal decomposition Im, Sunyoung; Lee, Jonggeon; Cho, Maenghyo Computer Methods in Applied Mechanics and Engineering, Vol. 385 https://doi.org/10.1016/j.cma.2021.114030	journal	November 2021
Bayesian calibration with summary statistics for the prediction of xenon diffusion in UO2 nuclear fuel Robbe, Pieterjan; Andersson, David; Bonnet, Luc Computational Materials Science, Vol. 225 https://doi.org/10.1016/j.commatsci.2023.112184	journal	June 2023
Bayesian multi-level calibration of a process-based maize phenology model Viswanathan, Michelle; Scheidegger, Andreas; Streck, Thilo Ecological Modelling, Vol. 474 https://doi.org/10.1016/j.ecolmodel.2022.110154	journal	December 2022
Bayesian calibration of building energy models: Comparison of predictive accuracy using metered utility data of different temporal resolution Kristensen, Martin Heine; Choudhary, Ruchi; Petersen, Steffen Energy Procedia, Vol. 122 https://doi.org/10.1016/j.egypro.2017.07.322	journal	September 2017
Calibrated building energy simulation and its application in a high-rise commercial building in Shanghai Pan, Yiqun; Huang, Zhizhong; Wu, Gang Energy and Buildings, Vol. 39, Issue 6 https://doi.org/10.1016/j.enbuild.2006.09.013	journal	June 2007
Calibrating whole building energy models: An evidence-based methodology Raftery, Paul; Keane, Marcus; O’Donnell, James Energy and Buildings, Vol. 43, Issue 9 https://doi.org/10.1016/j.enbuild.2011.05.020	journal	September 2011
A methodology for meta-model based optimization in building energy models Eisenhower, Bryan; O’Neill, Zheng; Narayanan, Satish Energy and Buildings, Vol. 47 https://doi.org/10.1016/j.enbuild.2011.12.001	journal	April 2012
Calibration of building energy models for retrofit analysis under uncertainty Heo, Y.; Choudhary, R.; Augenbroe, G. A. Energy and Buildings, Vol. 47 https://doi.org/10.1016/j.enbuild.2011.12.029	journal	April 2012
Identifying informative energy data in Bayesian calibration of building energy models Tian, Wei; Yang, Song; Li, Zhanyong Energy and Buildings, Vol. 119 https://doi.org/10.1016/j.enbuild.2016.03.042	journal	May 2016
Assessment of linear emulators in lightweight Bayesian calibration of dynamic building energy models for parameter estimation and performance prediction Li, Qi; Augenbroe, Godfried; Brown, Jason Energy and Buildings, Vol. 124 https://doi.org/10.1016/j.enbuild.2016.04.025	journal	July 2016
Sensitivity analysis methods for building energy models: Comparing computational costs and extractable information Menberg, Kathrin; Heo, Yeonsook; Choudhary, Ruchi Energy and Buildings, Vol. 133 https://doi.org/10.1016/j.enbuild.2016.10.005	journal	December 2016
IEA EBC annex 53: Total energy use in buildings—Analysis and evaluation methods Yoshino, Hiroshi; Hong, Tianzhen; Nord, Natasa Energy and Buildings, Vol. 152 https://doi.org/10.1016/j.enbuild.2017.07.038	journal	October 2017
Bayesian calibration of building energy models with large datasets Chong, Adrian; Lam, Khee Poh; Pozzi, Matteo Energy and Buildings, Vol. 154 https://doi.org/10.1016/j.enbuild.2017.08.069	journal	November 2017
Comprehensive evaluation of the influence of meta-models on Bayesian calibration Lim, Hyunwoo; Zhai, Zhiqiang John Energy and Buildings, Vol. 155 https://doi.org/10.1016/j.enbuild.2017.09.009	journal	November 2017
Guidelines for the Bayesian calibration of building energy models Chong, Adrian; Menberg, Kathrin Energy and Buildings, Vol. 174 https://doi.org/10.1016/j.enbuild.2018.06.028	journal	September 2018
Calibrating building energy simulation models: A review of the basics to guide future work Chong, Adrian; Gu, Yaonan; Jia, Hongyuan Energy and Buildings, Vol. 253 https://doi.org/10.1016/j.enbuild.2021.111533	journal	December 2021
Calibrating building simulation models using multi-source datasets and meta-learned Bayesian optimization Zhan, Sicheng; Wichern, Gordon; Laughman, Christopher Energy and Buildings, Vol. 270 https://doi.org/10.1016/j.enbuild.2022.112278	journal	September 2022
Identifiability study of an RC building model based on the standard ISO13790 Marty-Jourjon, Victor; Goyal, Anchal; Berthou, Thomas Energy and Buildings, Vol. 276 https://doi.org/10.1016/j.enbuild.2022.112446	journal	December 2022
A novel method of creating machine learning-based time series meta-models for building energy analysis Li, Guangchen; Tian, Wei; Zhang, Hu Energy and Buildings, Vol. 281 https://doi.org/10.1016/j.enbuild.2022.112752	journal	February 2023
Fault detection and calibration for building energy system using Bayesian inference and sparse autoencoder: A case study in photovoltaic thermal heat pump system Wang, Peng; Li, Congwei; Liang, Ruobing Energy and Buildings, Vol. 290 https://doi.org/10.1016/j.enbuild.2023.113051	journal	July 2023
How spatio-temporal resolution impacts urban energy calibration Dilsiz, Aysegul Demir; Nweye, Kingsley E.; Wu, Allen J. Energy and Buildings, Vol. 292 https://doi.org/10.1016/j.enbuild.2023.113175	journal	August 2023
A review of annual, monthly, and hourly electricity use in buildings Melo, Frederico C.; Carrilho da Graça, Guilherme; Oliveira Panão, Marta J. N. Energy and Buildings, Vol. 293 https://doi.org/10.1016/j.enbuild.2023.113201	journal	August 2023
Benchmarking the energy performance of European commercial buildings with a bayesian modeling framework Guy, Horace; Vittoz, Simon; Caputo, Giulia Energy and Buildings, Vol. 299 https://doi.org/10.1016/j.enbuild.2023.113595	journal	November 2023
Industrial battery operation and utilization in the presence of electrical load uncertainty using Bayesian decision theory Billings, Blake W.; Smith, Philip J.; Smith, Sean T. Journal of Energy Storage, Vol. 53 https://doi.org/10.1016/j.est.2022.105054	journal	September 2022
Selection of model discrepancy priors in Bayesian calibration Ling, You; Mullins, Joshua; Mahadevan, Sankaran Journal of Computational Physics, Vol. 276 https://doi.org/10.1016/j.jcp.2014.08.005	journal	November 2014
Fundamentals of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) network Sherstinsky, Alex Physica D: Nonlinear Phenomena, Vol. 404 https://doi.org/10.1016/j.physd.2019.132306	journal	March 2020
A review of sensitivity analysis methods in building energy analysis Tian, Wei Renewable and Sustainable Energy Reviews, Vol. 20 https://doi.org/10.1016/j.rser.2012.12.014	journal	April 2013
A review of methods to match building energy simulation models to measured data Coakley, Daniel; Raftery, Paul; Keane, Marcus Renewable and Sustainable Energy Reviews, Vol. 37 https://doi.org/10.1016/j.rser.2014.05.007	journal	September 2014
Review of data-driven energy modelling techniques for building retrofit Deb, C.; Schlueter, A. Renewable and Sustainable Energy Reviews, Vol. 144 https://doi.org/10.1016/j.rser.2021.110990	journal	July 2021
A review of computing-based automated fault detection and diagnosis of heating, ventilation and air conditioning systems Chen, Jianli; Zhang, Liang; Li, Yanfei Renewable and Sustainable Energy Reviews, Vol. 161 https://doi.org/10.1016/j.rser.2022.112395	journal	June 2022
Equation of State Calculations by Fast Computing Machines Metropolis, Nicholas; Rosenbluth, Arianna W.; Rosenbluth, Marshall N. The Journal of Chemical Physics, Vol. 21, Issue 6 https://doi.org/10.1063/1.1699114	journal	June 1953
Factorial Sampling Plans for Preliminary Computational Experiments Morris, Max D. Technometrics, Vol. 33, Issue 2 https://doi.org/10.1080/00401706.1991.10484804	journal	May 1991
A methodology for auto-calibrating urban building energy models using surrogate modeling techniques Nagpal, Shreshth; Mueller, Caitlin; Aijazi, Arfa Journal of Building Performance Simulation, Vol. 12, Issue 1 https://doi.org/10.1080/19401493.2018.1457722	journal	April 2018
Dynamic programming algorithm optimization for spoken word recognition Sakoe, H.; Chiba, S. IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 26, Issue 1 https://doi.org/10.1109/TASSP.1978.1163055	journal	February 1978
Bayesian calibration of computer models Kennedy, Marc C.; O'Hagan, Anthony Journal of the Royal Statistical Society: Series B (Statistical Methodology), Vol. 63, Issue 3 https://doi.org/10.1111/1467-9868.00294	journal	August 2001
Calibration Procedure for Energy Performance Simulation of a Commercial Building Yoon, Jongho; Lee, E. J.; Claridge, D. E. Journal of Solar Energy Engineering, Vol. 125, Issue 3 https://doi.org/10.1115/1.1564076	journal	August 2003
Procedures for Calibrating Hourly Simulation Models to Measured Building Energy and Environmental Data Haberl, J. S.; Bou-Saada, T. E. Journal of Solar Energy Engineering, Vol. 120, Issue 3 https://doi.org/10.1115/1.2888069	journal	August 1998
Application of an End-Use Disaggregation Algorithm for Obtaining Building Energy-Use Data Akbari, H.; Konopacki, S. J. Journal of Solar Energy Engineering, Vol. 120, Issue 3 https://doi.org/10.1115/1.2888070	journal	August 1998
A Comparison of MCMC Algorithms for the Bayesian Calibration of Building Energy Models for Building Simulation 2017 Conference Chong, Adrian; Poh Lam, Khee Building Simulation Conference Proceedings https://doi.org/10.26868/25222708.2017.336	conference	August 2017
A Science Mapping Approach Based Review of Model Predictive Control for Smart Building Operation Management Wang, Jun; Chen, Jianli; Hu, Yuqing JOURNAL OF CIVIL ENGINEERING AND MANAGEMENT, Vol. 28, Issue 8 https://doi.org/10.3846/jcem.2022.17566	journal	October 2022

Similar Records

Empirical validation of building energy simulation model input parameter for multizone commercial building during the cooling season

Journal Article · Fri Oct 13 20:00:00 EDT 2023 · Renewable and Sustainable Energy Reviews · OSTI ID:2205416

Model calibration of a variable refrigerant flow system with a dedicated outdoor air system: A case study

Journal Article · Sun Oct 15 20:00:00 EDT 2017 · Energy and Buildings · OSTI ID:1409253

Related Subjects

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
Bayesian calibration
Bayesian optimization
building energy modeling
deep learning
machine learning
model calibration

A deep learning-based Bayesian framework for high-resolution calibration of building energy models

Citation Formats

References (52)

Similar Records

Related Subjects