Surrogate modelling for urban building energy simulation based on the bidirectional long short-term memory model

Pan, Xiyu; Xu, Yujie; Hong, Tianzhen

doi:10.1080/19401493.2024.2359985

Surrogate modelling for urban building energy simulation based on the bidirectional long short-term memory model

Journal Article · Tue May 28 00:00:00 EDT 2024 · Journal of Building Performance Simulation

DOI:https://doi.org/10.1080/19401493.2024.2359985· OSTI ID:2377673

Pan, Xiyu ^[1]; ^[2]; Hong, Tianzhen ^[2]

Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States); Georgia Institute of Technology, Atlanta, GA (United States)
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)

Here, the urban microclimate is essential for accurate simulation-based urban building energy modelling (UBEM). However, a high spatial-resolution microclimate can increase the computational resources demands of UBEM. Surrogate modelling is one of the promising approaches for fast UBEM. This study proposes a bidirectional Long Short-Term Memory (LSTM)-based approach for simulation-based UBEM surrogate modelling. The estimations are aggregated into census tracts using total building floor area. A case study using UBEM to estimate annual hourly building energy use and anthropogenic heat from all existing buildings in Los Angeles County found that most of the surrogate models can complete the annual hourly simulation within 90 minutes with a normalized mean absolute error lower than 10%, and that the bidirectional LSTM outperforms the standard LSTM in accuracy. This study demonstrates the advantages of bidirectional RNN architecture in building energy surrogate modelling and is expected to promote long-term and high-resolution UBEM with detailed microclimates.

View Accepted Manuscript (DOE)

Research Organization:: Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)

Sponsoring Organization:: USDOE Office of Energy Efficiency and Renewable Energy (EERE), Energy Efficiency Office. Building Technologies Office

Grant/Contract Number:: AC02-05CH11231

OSTI ID:: 2377673

Journal Information:: Journal of Building Performance Simulation, Journal Name: Journal of Building Performance Simulation; ISSN 1940-1493

Publisher:: Taylor & FrancisCopyright Statement

Country of Publication:: United States

Language:: English

References (44)

A multi-scale time-series dataset of anthropogenic heat from buildings in Los Angeles County Xu, Yujie; Vahmani, Pouya; Jones, Andrew MultiSector Dynamics - Living, Intuitive, Value-adding, Environment https://doi.org/10.57931/1892041	dataset	January 2022
Uncertainty Analysis of Urban Building Energy Based on Two-Dimensional Monte Carlo Method Fu, Xing; Tian, Wei; Sun, Yu Proceedings of the 11th International Symposium on Heating, Ventilation and Air Conditioning (ISHVAC 2019) https://doi.org/10.1007/978-981-13-9528-4_133	book	March 2020
Development of an ANN-based building energy model for information-poor buildings using transfer learning Li, Ao; Xiao, Fu; Fan, Cheng Building Simulation, Vol. 14, Issue 1 https://doi.org/10.1007/s12273-020-0711-5	journal	September 2020
On the performance of meta-models in building design optimization Prada, A.; Gasparella, A.; Baggio, P. Applied Energy, Vol. 225 https://doi.org/10.1016/j.apenergy.2018.04.129	journal	September 2018
Using a deep temporal convolutional network as a building energy surrogate model that spans multiple climate zones Westermann, Paul; Welzel, Matthias; Evins, Ralph Applied Energy, Vol. 278 https://doi.org/10.1016/j.apenergy.2020.115563	journal	November 2020
Data-driven district energy management with surrogate models and deep reinforcement learning Pinto, Giuseppe; Deltetto, Davide; Capozzoli, Alfonso Applied Energy, Vol. 304 https://doi.org/10.1016/j.apenergy.2021.117642	journal	December 2021
Evaluation of the impact of input uncertainty on urban building energy simulations using uncertainty and sensitivity analysis Prataviera, Enrico; Vivian, Jacopo; Lombardo, Giulia Applied Energy, Vol. 311 https://doi.org/10.1016/j.apenergy.2022.118691	journal	April 2022
Multiobjective optimization of building design using TRNSYS simulations, genetic algorithm, and Artificial Neural Network Magnier, Laurent; Haghighat, Fariborz Building and Environment, Vol. 45, Issue 3 https://doi.org/10.1016/j.buildenv.2009.08.016	journal	March 2010
Importance analysis and meta-model construction with correlated variables in evaluation of thermal performance of campus buildings Tian, Wei; Choudhary, Ruchi; Augenbroe, Godfried Building and Environment, Vol. 92 https://doi.org/10.1016/j.buildenv.2015.04.021	journal	October 2015
Urban energy use modeling methods and tools: A review and an outlook Abbasabadi, Narjes; Ashayeri, Mehdi Building and Environment, Vol. 161 https://doi.org/10.1016/j.buildenv.2019.106270	journal	August 2019
Ten questions on urban building energy modeling Hong, Tianzhen; Chen, Yixing; Luo, Xuan Building and Environment, Vol. 168 https://doi.org/10.1016/j.buildenv.2019.106508	journal	January 2020
Transfer learning based methodology for migration and application of fault detection and diagnosis between building chillers for improving energy efficiency Zhu, Xu; Chen, Kang; Anduv, Burkay Building and Environment, Vol. 200 https://doi.org/10.1016/j.buildenv.2021.107957	journal	August 2021
ESMUST: EnergyPlus-driven surrogate model for urban surface temperature prediction Yoo, Wonjae; Clayton, Mark J.; Yan, Wei Building and Environment, Vol. 229 https://doi.org/10.1016/j.buildenv.2022.109935	journal	February 2023
Surrogate modeling for long-term and high-resolution prediction of building thermal load with a metric-optimized KNN algorithm Liang, Yumin; Pan, Yiqun; Yuan, Xiaolei Energy and Built Environment, Vol. 4, Issue 6 https://doi.org/10.1016/j.enbenv.2022.06.008	journal	December 2023
Surrogate modelling for sustainable building design – A review Westermann, Paul; Evins, Ralph Energy and Buildings, Vol. 198 https://doi.org/10.1016/j.enbuild.2019.05.057	journal	September 2019
A building clustering approach for urban energy simulations De Jaeger, Ina; Reynders, Glenn; Callebaut, Chadija Energy and Buildings, Vol. 208 https://doi.org/10.1016/j.enbuild.2019.109671	journal	February 2020
End-to-end deep meta modelling to calibrate and optimize energy consumption and comfort Cohen, Max; Le Corff, Sylvain; Charbit, Maurice Energy and Buildings, Vol. 250 https://doi.org/10.1016/j.enbuild.2021.111218	journal	November 2021
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
A dynamic intelligent building retrofit decision-making model in response to climate change Ma, Dingyuan; Li, Xiaodong; Lin, Borong Energy and Buildings, Vol. 284 https://doi.org/10.1016/j.enbuild.2023.112832	journal	April 2023
Building energy model calibration using a surrogate neural network Herbinger, Florent; Vandenhof, Colin; Kummert, Michaël Energy and Buildings, Vol. 289 https://doi.org/10.1016/j.enbuild.2023.113057	journal	June 2023
Optimal building retrofit pathways considering stock dynamics and climate change impacts Streicher, Kai Nino; Berger, Matthias; Panos, Evangelos Energy Policy, Vol. 152 https://doi.org/10.1016/j.enpol.2021.112220	journal	May 2021
Estimation of the relationship between remotely sensed anthropogenic heat discharge and building energy use Zhou, Yuyu; Weng, Qihao; Gurney, Kevin R. ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 67 https://doi.org/10.1016/j.isprsjprs.2011.10.007	journal	January 2012
High spatial- and temporal-resolution anthropogenic heat discharge estimation in Los Angeles County, California Zheng, Yuanfan; Weng, Qihao Journal of Environmental Management, Vol. 206 https://doi.org/10.1016/j.jenvman.2017.07.047	journal	January 2018
A machine-learning-based method for thermal design optimization of residential buildings in highly urbanized areas of Turkey Yigit, Sadik Journal of Building Engineering, Vol. 38 https://doi.org/10.1016/j.jobe.2021.102225	journal	June 2021
Model predictive control of heating, ventilation, and air conditioning (HVAC) systems: A state-of-the-art review Taheri, Saman; Hosseini, Paniz; Razban, Ali Journal of Building Engineering, Vol. 60 https://doi.org/10.1016/j.jobe.2022.105067	journal	November 2022
Estimating spatial and temporal patterns of urban building anthropogenic heat using a bottom-up city building heat emission model Chen, Wei; Zhou, Yuyu; Xie, Yanhua Resources, Conservation and Recycling, Vol. 177 https://doi.org/10.1016/j.resconrec.2021.105996	journal	February 2022
On the accuracy of Urban Building Energy Modelling Oraiopoulos, A.; Howard, B. Renewable and Sustainable Energy Reviews, Vol. 158 https://doi.org/10.1016/j.rser.2021.111976	journal	April 2022
Urban microclimate and building energy models: A review of the latest progress in coupling strategies Sezer, Nurettin; Yoonus, Hamad; Zhan, Dongxue Renewable and Sustainable Energy Reviews, Vol. 184 https://doi.org/10.1016/j.rser.2023.113577	journal	September 2023
Urban building energy modeling (UBEM) tools: A state-of-the-art review of bottom-up physics-based approaches Ferrando, Martina; Causone, Francesco; Hong, Tianzhen Sustainable Cities and Society, Vol. 62 https://doi.org/10.1016/j.scs.2020.102408	journal	November 2020
High-resolution hourly surrogate modeling framework for physics-based large-scale building stock modeling Zhang, Liang; Plathottam, Siby; Reyna, Janet Sustainable Cities and Society, Vol. 75 https://doi.org/10.1016/j.scs.2021.103292	journal	December 2021
Anthropogenic heat from buildings in Los Angeles County: A simulation framework and assessment Xu, Yujie; Vahmani, Pouya; Jones, Andrew Sustainable Cities and Society, Vol. 107 https://doi.org/10.1016/j.scs.2024.105468	journal	July 2024
SciPy 1.0: fundamental algorithms for scientific computing in Python Virtanen, Pauli; Gommers, Ralf; Oliphant, Travis E. Nature Methods https://doi.org/10.1038/s41592-019-0686-2	journal	February 2020
Continental United States climate projections based on thermodynamic modification of historical weather Jones, Andrew D.; Rastogi, Deeksha; Vahmani, Pouya Scientific Data, Vol. 10, Issue 1 https://doi.org/10.1038/s41597-023-02485-5	journal	September 2023
Evaluation of Deep Learning Models for Multi-Step Ahead Time Series Prediction Chandra, Rohitash; Goyal, Shaurya; Gupta, Rishabh IEEE Access, Vol. 9 https://doi.org/10.1109/ACCESS.2021.3085085	journal	January 2021
Load Forecasting of Large-space Stadium Based on Surrogate Modeling Li, Zhongbo; Zhang, Ning; Zhang, Junwei 2022 International Conference on High Performance Big Data and Intelligent Systems (HDIS) https://doi.org/10.1109/HDIS56859.2022.9991695	conference	December 2022
An Experimental Review on Deep Learning Architectures for Time Series Forecasting Lara-Benítez, Pedro; Carranza-García, Manuel; Riquelme, José C. International Journal of Neural Systems, Vol. 31, Issue 03 https://doi.org/10.1142/S0129065721300011	journal	February 2021
Partial Cross-Correlation Analysis Resolves Ambiguity in the Encoding of Multiple Movement Features Stark, Eran; Drori, Rotem; Abeles, Moshe Journal of Neurophysiology, Vol. 95, Issue 3 https://doi.org/10.1152/jn.00981.2005	journal	March 2006
The Los Angeles 100% Renewable Energy Study (LA100): Executive Summary Cochran, Jaquelin; Denholm, Paul; Mooney, Meghan https://doi.org/10.2172/1774871	report	March 2021
Multi-Task Learning for Multiple Language Translation Dong, Daxiang; Wu, Hua; He, Wei Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) https://doi.org/10.3115/v1/P15-1166	conference	January 2015
City-Scale Building Anthropogenic Heating during Heat Waves Luo, Xuan; Vahmani, Pouya; Hong, Tianzhen Atmosphere, Vol. 11, Issue 11 https://doi.org/10.3390/atmos11111206	journal	November 2020
A Deep-Learning-Based Meta-Modeling Workflow for Thermal Load Forecasting in Buildings: Method and a Case Study Zhou, Yuhao; Liang, Yumin; Pan, Yiqun Buildings, Vol. 12, Issue 2 https://doi.org/10.3390/buildings12020177	journal	February 2022
Influence of Input Climatic Data on Simulations of Annual Energy Needs of a Building: EnergyPlus and WRF Modeling for a Case Study in Rome (Italy) Ciancio, Virgilio; Falasca, Serena; Golasi, Iacopo Energies, Vol. 11, Issue 10 https://doi.org/10.3390/en11102835	journal	October 2018
A Comparison of Various Bottom-Up Urban Energy Simulation Methods Using a Case Study in Hangzhou, China Li, Yanxia; Wang, Chao; Zhu, Sijie Energies, Vol. 13, Issue 18 https://doi.org/10.3390/en13184781	journal	September 2020
A Building Retrofit and Sensitivity Analysis in an Automatically Calibrated Model Considering the Urban Heat Island Effect in Abu Dhabi, UAE Bande, Lindita; Cabrera, Adalberto Guerra; Kim, Young Ki Sustainability, Vol. 11, Issue 24 https://doi.org/10.3390/su11246905	journal	December 2019

Similar Records

Ten questions on urban building energy modeling

Journal Article · Wed Oct 30 20:00:00 EDT 2019 · Building and Environment · OSTI ID:1582366

Development of city buildings dataset for urban building energy modeling

Journal Article · Fri Nov 16 19:00:00 EST 2018 · Energy and Buildings · OSTI ID:1484220

Related Subjects

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATION
97 MATHEMATICS AND COMPUTING
Bidirectional LSTM model
anthropogenic heat
building stock
energy use
machine learning
surrogate model

Surrogate modelling for urban building energy simulation based on the bidirectional long short-term memory model

Citation Formats

References (44)

Similar Records

Related Subjects