Abstract
Global urbanization causes more environmental stresses in cities and energy efficiency is one of major concerns for urban sustainability. The variable importance techniques have been widely used in building energy analysis to determine key factors influencing building energy use. Most of these applications, however, use only one type of variable importance approaches. Therefore, this paper proposes a procedure of conducting two types of variable importance analysis (predictive and variance-based) to determine robust and effective energy saving measures in urban buildings. These two variable importance methods belong to metamodeling techniques, which can significantly reduce computational cost of building energy simulation models for urban buildings. The predictive importance analysis is based on the prediction errors of metamodels to obtain importance rankings of inputs, while the variance-based variable importance can explore non-linear effects and interactions among input variables based on variance decomposition. The campus buildings are used to demonstrate the application of the method proposed to explore characteristic of heating energy, cooling energy, electricity, and carbon emissions of buildings. The results indicate that the combination of two types of metamodeling variable importance analysis can provide fast and robust analysis to improve energy efficiency of urban buildings. The carbon emissions can be reduced approximately 30% after using a few of effective energy efficiency measures and more aggressive measures can lead to the 60% of reduction of carbon emissions. Moreover, this research demonstrates the application of parallel computing to expedite building energy analysis in urban environment since more multi-core computers become increasingly available.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
CABEE (2018). China Building Energy Consumption Research Report 2018. China Association of Building Energy Efficiency (CABEE). (in Chinese)
Caputo P, Costa G, Ferrari S (2013). A supporting method for defining energy strategies in the building sector at urban scale. Energy Policy, 55: 261–270.
Chen X, Yang H, Peng J (2019a). Energy optimization of high-rise commercial buildings integrated with photovoltaic facades in urban context. Energy, 172: 1–17.
Chen Y, Hong T, Luo X, Hooper B (2019b). Development of city buildings dataset for urban building energy modeling. Energy and Buildings, 183: 252–265.
China Meteorological Administration (2005). Special Meteorological Data Set for Building Thermal Environment Analysis of China. Beijing: China Architecture & Building Press. (in Chinese)
D’Amico B, Pomponi F (2019). A compactness measure of sustainable building forms. Royal Society Open Science, 6: 181265.
DOE (2020). EnergyPlus V9.3. U.S. Department of Energy. Grömping U (2015). Variable importance in regression models. Wiley Interdisciplinary Reviews: Computational Statistics, 7: 137–152.
Hansen CW, Helton JC, Sallaberry CJ (2012). Use of replicated Latin hypercube sampling to estimate sampling variance in uncertainty and sensitivity analysis results for the geologic disposal of radioactive waste. Reliability Engineering & System Safety, 107: 139–148.
Hastie T, Tibshirani R, Friedman J (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd edn. New York: Springer.
Iooss B, Da Veiga S, Janon A, Pujol G (2018). R package sensitivity V1.16.1. Sensitivity: Global Sensitivity Analysis of Model Outputs. Available at https://CRAN.R-project.org/package=sensitivity. Accessed 7 Jul 2019.
Kristensen MH, Hedegaard RE, Petersen S (2018). Hierarchical calibration of archetypes for urban building energy modeling. Energy and Buildings, 175: 219–234.
Kuhn M, Johnson K (2013). Applied Predictive Modeling. New York: Springer.
Kuhn M (2018). R Package Caret: Classification and Regression Training. Available at https://CRAN.R-project.org/package=caret. Accessed 10 Nov 2019.
Liu Y (2018). Energy saving of urban buildings based on 3D geographic information system. Master Thesis, Tianjin University of Science and Technology, China. (in Chinese)
Liu Y, Tian W, Zhou X (2019). Carbon performance evaluation of urban buildings using machine learning-based energy models. In: Proceedings of the International Symposium on Heating, Ventilation and Air Conditioning.
Mara TA, Tarantola S (2008). Application of global sensitivity analysis of model output to building thermal simulations. Building Simulation, 1: 290–302.
Mastrucci A, Pérez-López P, Benetto E, Leopold U, Blanc I (2017). Global sensitivity analysis as a support for the generation of simplified building stock energy models. Energy and Buildings, 149: 368–383.
MEE (2018). China Regional Grid Based Line Emission Factor in 2017. Ministry of Ecology and Environment (MEE) of China. (in Chinese)
MOC (2005). GB50189-2005. Energy Conservation Design Regulation for Public Buildings. Ministry of Construction (MOC) of China. (in Chinese)
MOC (2015). GB50189-2015. Design Standard for Energy Efficiency of Public Buildings. Ministry of Construction (MOC) of China. (in Chinese)
MOC (2016). GB51141-2015. Assessment Standard for Green Retrofiting of Existing Building. Ministry of Construction (MOC) of China. (in Chinese)
MOC (2019). GB/T 51350-2019. Technical Standard for Nearly Zero Energy Buildings. Ministry of Construction (MOC) of China. (in Chinese)
Molnar C (2019). Interpretable Machine Learning: A Guide for Making Black Box Models Explainable. Avaible at https://christophm.github.io/interpretable-ml-book/.
Muñoz D, Besuievsky G, Patow G (2019). A procedural technique for thermal simulation and visualization in urban environments. Building Simulation, 12: 1013–1031.
Nguyen A-T, Reiter S (2015). A performance comparison of sensitivity analysis methods for building energy models. Building Simulation, 8: 651–664.
Pang Z, O’Neill Z, Li Y, Niu F (2020). The role of sensitivity analysis in the building performance analysis: A critical review. Energy and Buildings, 209: 109659.
Pasichnyi O, Levihn F, Shahrokni H, Wallin J, Kordas O (2019). Data-driven strategic planning of building energy retrofitting: The case of Stockholm. Journal of Cleaner Production, 233: 546–560.
R Core Team (2019). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. Available at https://www.R-project.org/. Accessed 10 Nov 2019.
Saltelli A, Ratto M, Andres T, Campolongo F, Cariboni J, et al. (2008). Global Sensitivity Analysis. The primer. Chichester, UK: John Wiley & Sons.
Shao Q, Gao E, Mara T, Hu H, Liu T, et al. (2020). Global sensitivity analysis of solid oxide fuel cells with Bayesian sparse polynomial chaos expansions. Applied Energy, 260: 114318.
Silvero F, Lops C, Montelpare S, Rodrigues F (2019). Impact assessment of climate change on buildings in Paraguay—Overheating risk under different future climate scenarios. Building Simulation, 12: 943–960.
Tian W (2013). A review of sensitivity analysis methods in building energy analysis. Renewable and Sustainable Energy Reviews, 20: 411–419.
Tian W, Choudhary R, Augenbroe G, Lee SH (2015). Importance analysis and meta-model construction with correlated variables in evaluation of thermal performance of campus buildings. Building and Environment, 92: 61–74.
Tian W, Liu Y, Heo Y, Yan D, Li Z, et al. (2016). Relative importance of factors influencing building energy in urban environment. Energy, 111: 237–250.
Tian W, Liu Y, Zuo J, Yin B, Sun Y, et al. (2017a). Building energy assessment based on a sequential sensitivity analysis approach. Procedia Engineering, 205: 1042–1048.
Tian W, Yang S, Zuo J, Li Z, Liu Y (2017b). Relationship between built form and energy performance of office buildings in a severe cold Chinese region. Building Simulation, 10: 11–24.
Tian W, Heo Y, de Wilde P, Li Z, Yan D, et al. (2018). A review of uncertainty analysis in building energy assessment. Renewable and Sustainable Energy Reviews, 93: 285–301.
Tian W, Zhu C, Liu Y, et al. (2019). Energy Assessment of Urban Buildings Based on Geographic Information System. Journal of Green Building, (in press).
Tian W, Zhu C, Sun Y, Li Z, Yin B (2020). Energy characteristics of urban buildings: Assessment by machine learning. Building Simulation, https://doi.org/10.1007/s12273-020-0608-3.
UN (2019). World Urbanization Prospects, the 2018 revisions. United Nations, Department of Economic and Social Affaris.
Vartholomaios A (2017). A parametric sensitivity analysis of the influence of urban form on domestic energy consumption for heating and cooling in a Mediterranean city. Sustainable Cities and Society, 28: 135–145.
Wei L, Tian W, Silva EA, Choudhary R, Meng Q, et al. (2015a). Comparative study on machine learning for urban building energy analysis. Procedia Engineering, 121: 285–292.
Wei P, Lu Z, Song J (2015b). Variable importance analysis: A comprehensive review. Reliability Engineering & System Safety, 142: 399–432.
Zhang J (2018). Low carbon energy planning of university buildings in cold area. Master Thesis, Tianjin University, China. (in Chinese)
Acknowledgements
This research was supported by the National Natural Science Foundation of China (No. 51778416) and the Key Projects of Philosophy and Social Sciences Research, Ministry of Education of China “Research on Green Design in Sustainable Development” (contract No. 16JZDH014, approval No. 16JZD014).
Author information
Authors and Affiliations
Corresponding authors
Rights and permissions
About this article
Cite this article
Liu, Y., Tian, W. & Zhou, X. Energy and carbon performance of urban buildings using metamodeling variable importance techniques. Build. Simul. 14, 535–547 (2021). https://doi.org/10.1007/s12273-020-0688-0
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12273-020-0688-0