AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Building Simulation Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Research Article

Physics-based, data-driven approach for predicting natural ventilation of residential high-rise buildings

Vincent J.L. Gan1, Boyu Wang2, C.M. Chan2, A.U. Weerasuriya2( ), Jack C.P. Cheng2( )
Department of Building, School of Design and Environment, National University of Singapore, Singapore, 117566
Department of Civil and Environmental Engineering, The Hong Kong University of Science and Technology, Hong Kong, 999077, China
Show Author Information

Abstract

Natural ventilation is particularly important for residential high-rise buildings as it maintains indoor human comfort without incurring the energy demands that air-conditioning does. To improve a building's natural ventilation, it is essential to develop models to understand the relationship between wind flow characteristics and the building's design. Significantly more effort is still needed for developing such reliable, accurate, and computationally economical models instead of currently the most popular physics-based models such as computational fluid dynamics (CFD) simulation. This paper, therefore, presents a novel model developed based on physics-based modelling and a data-driven approach to evaluate natural ventilation in residential high-rise buildings. The model first uses CFD to simulate wind pressures on the exterior surfaces of a high-rise building. Once the surface pressures have been obtained, multizone modelling is used to predict the air change per hour (ACH) for different flats in various configurations. Data-driven prediction models are then developed using data from the simulation and deep neural networks that are based on mean absolute error, mean absolute percentage error, and a fusion algorithm respectively. These data-driven models are used to predict the ACH of 25 flats. The results from multizone modelling and data-driven modelling are compared. The results imply a high accuracy of the data-driven prediction in comparison with physics-based models. The fusion algorithm- based neural network performs best, achieving 96% accuracy, which is the highest of all models tested. This study contributes a more efficient and robust method for predicting wind-induced natural ventilation. The findings describe the relationship between building design (e.g., plan layout), distribution of surface pressure, and the resulting ACH, which serve to improve the practical design of sustainable buildings.

Keywords

machine learningcomputational fluid dynamicsnatural ventilationresidential buildingmultizone modeldata-driven prediction

References

 

Ai ZT, Mak CM (2014). Determination of single-sided ventilation rates in multistory buildings: Evaluation of methods. Energy and Buildings, 69: 292-300.
Crossref Google Scholar
 
Ansys (2018). Ansys Fluent Software. ANSYS Inc.
 

Asfour OS, Gadi MB (2007). A comparison between CFD and Network models for predicting wind-driven ventilation in buildings. Building and Environment, 42: 4079-4085.
Crossref Google Scholar
 
Bamdad Masouleh K (2018). Building energy optimisation using machine learning and metaheuristic algorithms. PhD Thesis, Queensland University of Technology, Australia.
 

Blocken B, Stathopoulos T, Carmeliet J (2007). CFD simulation of the atmospheric boundary layer: wall function problems. Atmospheric Environment, 41: 238-252.
Crossref Google Scholar
 

Blocken B (2018). LES over RANS in building simulation for outdoor and indoor applications: A foregone conclusion? Building Simulation, 11: 821-870.
Crossref Google Scholar
 
Bottou L (2010). Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT'2010.https://doi.org/10.1007/978-3-7908-2604-3_16
Crossref
 

Bre F, Gimenez JM, Fachinotti VD (2018). Prediction of wind pressure coefficients on building surfaces using artificial neural networks. Energy and Buildings, 158: 1429-1441.
Crossref Google Scholar
 

Cebeci T, Bradshaw P (1977). Momentum Transfer in Boundary Layer. Washington DC: Hemisphere.
 

Chen Q (2009). Ventilation performance prediction for buildings: A method overview and recent applications. Building and Environment, 44: 848-858.
Crossref Google Scholar
 

Chen Y, Kopp G, Surry D (2003). Prediction of pressure coefficients on roofs of low buildings using artificial neural networks. Journal of Wind Engineering and Industrial Aerodynamics, 91: 423-441.
Crossref Google Scholar
 

Chen Y, Tong Z, Zheng Y, et al. (2020). Transfer learning with deep neural networks for model predictive control of HVAC and natural ventilation in smart buildings. Journal of Cleaner Production, 254: 119866.
Crossref Google Scholar
 

Cheung JOP, Liu C-H (2011). CFD simulations of natural ventilation behaviour in high-rise buildings in regular and staggered arrangements at various spacings. Energy and Buildings, 43: 1149-1158.
Crossref Google Scholar
 

Chu CR, Chiu YH, Chen YJ, et al. (2009). Turbulence effects on the discharge coefficient and mean flow rate of wind-driven cross- ventilation. Building and Environment, 44: 2064-2072.
Crossref Google Scholar
 

Clifford MJ, Everitt PJ, Clarke R, et al. (1997). Using computational fluid dynamics as a design tool for naturally ventilated buildings. Building and Environment, 32: 305-312.
Crossref Google Scholar
 

Ding C, Lam KP (2019). Data-driven model for cross ventilation potential in high-density cities based on coupled CFD simulation and machine learning', Building and Environment, 165: 106394.
Crossref Google Scholar
 
Dols WS, Polidoro BJ (2015). CONTAM User Guide and Program Documentation Version 3.2 (No. Technical Note (NIST TN)-1887).https://doi.org/10.6028/NIST.TN.1887
Crossref
 
EMSD (2018). Hong Kong Energy End-use Data. Electrical and Mechanical Services Department (EMSD), Hong Kong, China.
 

Favoino F, Jin Q, Overend M (2017). Design and control optimisation of adaptive insulation systems for office buildings. Part 1: Adaptive technologies and simulation framework. Energy, 127: 301-309.
Crossref Google Scholar
 

Franke J, Hellsten A, Schlünzen KH, et al. (2011). The COST 732 Best Practice Guideline for CFD simulation of flows in the urban environment: a summary. International Journal of Environment and Pollution, 44: 419-427.
Crossref Google Scholar
 

Gan VJL, Wong HK, Tse KT, et al. (2019). Simulation-based evolutionary optimization for energy-efficient layout plan design of high-rise residential buildings. Journal of Cleaner Production, 231: 1375-1388.
Crossref Google Scholar
 

Gan VJL, Lo IMC, Ma J, et al. (2020). Simulation optimisation towards energy efficient green buildings: Current status and future trends. Journal of Cleaner Production, 254: 120012.
Crossref Google Scholar
 

Gao CF, Lee WL (2011). Evaluating the influence of openings configuration on natural ventilation performance of residential units in Hong Kong. Building and Environment, 46: 961-969.
Crossref Google Scholar
 

Geyer P, Singaravel S (2018). Component-based machine learning for performance prediction in building design. Applied Energy, 228: 1439-1453.
Crossref Google Scholar
 

Gimenez JM, Bre F (2019). Optimization of RANS turbulence models using genetic algorithms to improve the prediction of wind pressure coefficients on low-rise buildings. Journal of Wind Engineering and Industrial Aerodynamics, 193: 103978.
Crossref Google Scholar
 
Hong Kong Housing Authority (2013). Modular Flat Design for Public Housing Development of the Hong Kong Housing Authority.
 

Hornik K, Stinchcombe M, White H (1989). Multilayer feedforward networks are universal approximators. Neural Networks, 2: 359-366.
Crossref Google Scholar
 
Ioffe S, Szegedy C (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proceedings of the 32nd International Conference on Machine Learning, Lille, France.
 

Jiang Y, Chen Q (2002). Effect of fluctuating wind direction on cross natural ventilation in buildings from large eddy simulation. Building and Environment, 37: 379-386.
Crossref Google Scholar
 

Jiru TE, Bitsuamlak GT (2010). Application of CFD in modelling wind-induced natural ventilation of buildings - A review. International Journal of Ventilation, 9: 131-147.
Crossref Google Scholar
 
Ketkar N (2017). Introduction to Keras. In: Deep Learning with Python. Berkeley, CA, USA: Apress.https://doi.org/10.1007/978-1-4842-2766-4
Crossref
 
Launder BE, Spalding DB (1983). The numerical computation of turbulent flows. In: Patankar SV, Pollard A, Singhal AK (eds), Numerical Prediction of Flow, Heat Transfer, Turbulence and Combustion. New York: Pergamon Press.https://doi.org/10.1016/B978-0-08-030937-8.50016-7
Crossref
 

Leshno M, Lin VY, Pinkus A, et al. (1993). Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Networks, 6: 861-867.
Crossref Google Scholar
 

Li C, Ding Z, Zhao D, et al. (2017). Building energy consumption prediction: An extreme deep learning approach. Energies, 10: 1525.
Crossref Google Scholar
 

Liu X, Niu J, Kwok KCS (2013). Evaluation of RANS turbulence models for simulating wind-induced mean pressures and dispersions around a complex-shaped high-rise building. Building Simulation, 6: 151-164.
Crossref Google Scholar
 

Mousa WAY, Lang W, Auer T, et al. (2017). A pattern recognition approach for modeling the air change rates in naturally ventilated buildings from limited steady-state CFD simulations. Energy and Buildings, 155: 54-65.
Crossref Google Scholar
 
Nair V, Hinton GE (2010). Rectified linear units improve restricted boltzmann machines. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10).
 

Ramponi R, Blocken B (2012). CFD simulation of cross-ventilation for a generic isolated building: Impact of computational parameters. Building and Environment, 53: 34-48.
Crossref Google Scholar
 

Ramponi R, Gaetani I, Angelotti A (2014). Influence of the urban environment on the effectiveness of natural night-ventilation of an office building. Energy and Buildings, 78: 25-34.
Crossref Google Scholar
 

Ramponi R, Blocken B, de Coo LB, et al. (2015). CFD simulation of outdoor ventilation of generic urban configurations with different urban densities and equal and unequal street widths. Building and Environment, 92: 152-166.
Crossref Google Scholar
 

Shih T-H, Liou WW, Shabbir A, et al. (1995). A new k-ε eddy viscosity model for high reynolds number turbulent flows. Computers & Fluids, 24: 227-238.
Crossref Google Scholar
 

Shirzadi M, Tominaga Y, Mirzaei PA (2019). Wind tunnel experiments on cross-ventilation flow of a generic sheltered building in urban areas. Building and Environment, 158: 60-72.
Crossref Google Scholar
 

Singaravel S, Suykens J, Geyer P (2018). Deep-learning neural-network architectures and methods: Using component-based models in building-design energy prediction. Advanced Engineering Informatics, 38: 81-90.
Crossref Google Scholar
 

Srivastava N, Hinton G, Krizhevsky A, et al. (2014). Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15: 1929-1958.
Google Scholar
 

Tominaga Y, Mochida A, Yoshie R, et al. (2008). AIJ guidelines for practical applications of CFD to pedestrian wind environment around buildings. Journal of Wind Engineering and Industrial Aerodynamics, 96: 1749-1761.
Crossref Google Scholar
 

Tong Z, Chen Y, Malkawi A (2016). Defining the Influence Region in neighborhood-scale CFD simulations for natural ventilation design. Applied Energy, 182: 625-633.
Crossref Google Scholar
 

Tong Z, Chen Y, Malkawi A (2017). Estimating natural ventilation potential for high-rise buildings considering boundary layer meteorology. Applied Energy, 193: 276-286.
Crossref Google Scholar
 

Van Hooff T, Blocken B (2010a). On the effect of wind direction and urban surroundings on natural ventilation of a large semi- enclosed stadium', Computers & Fluids, 39: 1146-1155.
Crossref Google Scholar
 

van Hooff T, Blocken B (2010b). Coupled urban wind flow and indoor natural ventilation modelling on a high-resolution grid: A case study for the Amsterdam ArenA stadium. Environmental Modelling & Software, 25: 51-65.
Crossref Google Scholar
 

Van Moeseke G, Gratia E, Reiter S, et al. (2005). Wind pressure distribution influence on natural ventilation for different incidences and environment densities. Energy and Buildings, 37: 878-889.
Crossref Google Scholar
 
Vrachimi I, Melo AP, Cóstola D (2017). Prediction of wind pressure coefficients in building energy simulation using machine learning. In: Proceedings of International IBPSA Building Simulation Conference, San Francisco, USA.
 

Wang W, Zmeureanu R, Rivard H (2005). Applying multi-objective genetic algorithms in green building design optimization. Building and Environment, 40: 1512-1525.
Crossref Google Scholar
 

Weerasuriya AU, Zhang X, Gan VJL, et al. (2019). A holistic framework to utilize natural ventilation to optimize energy performance of residential high-rise buildings. Building and Environment, 153: 218-232.
Crossref Google Scholar
 

Wilkinson S, Hanna (2014). Approximating computational fluid dynamics for generative tall building design. International Journal of Architectural Computing, 12: 155-177.
Crossref Google Scholar
 

Yik FWH, Lun YF (2010). Energy saving by utilizing natural ventilation in public housing in Hong Kong. Indoor and Built Environment, 19: 73-87.
Crossref Google Scholar
 

Yoshie R, Mochida A, Tominaga Y, et al. (2007). Cooperative project for CFD prediction of pedestrian wind environment in the Architectural Institute of Japan. Journal of Wind Engineering and Industrial Aerodynamics, 95: 1551-1578.
Crossref Google Scholar
 

Zhang X, Weerasuriya AU, Tse KT (2020). CFD simulation of natural ventilation of a generic building in various incident wind directions: Comparison of turbulence modelling, evaluation methods, and ventilation mechanisms. Energy and Buildings, 229: 110516.
Crossref Google Scholar
Building Simulation
Volume 15 Issue 1,
January 2022
Pages 129-148
DOI: 10.1007/s12273-021-0784-9
Cite this article:
Gan VJ, Wang B, Chan C, et al. Physics-based, data-driven approach for predicting natural ventilation of residential high-rise buildings. Building Simulation, 2022, 15(1): 129-148. https://doi.org/10.1007/s12273-021-0784-9

688

Views

29

Crossref

29

Web of Science

33

Scopus

0

CSCD

Altmetrics
Received: 09 October 2020
Revised: 19 January 2021
Accepted: 13 February 2021
Published: 14 April 2021
© Tsinghua University Press and Springer-Verlag GmbH Germany, part of Springer Nature 2021
Return