Advertisement

Sensitivity Analysis of Building Energy Performance Assessment Based on Machine-Learning Models

  • Wei TianEmail author
  • Jiaxin Shi
  • Pieter de Wilde
  • Yu Sun
  • Chuanqi Zhu
  • Baoquan Yin
Conference paper
  • 236 Downloads
Part of the Environmental Science and Engineering book series (ESE)

Abstract

Variance-based sensitivity analysis in combination with machine-learning techniques has been increasingly applied in energy analysis of buildings in order to reduce computational cost of running a large number of energy models with sufficient accuracy. This paper compares the performance of two sensitivity analysis methods based on machine-learning models for building energy assessment: multivariate adaptive regression splines (MARS) and Cubist (CB). An office building located in Tianjin, China, is used as a case study with the EnergyPlus simulation program, to study the characteristics of these two sensitivity analysis methods. The results indicate that sufficient sample number is required to obtain reliable sensitivity analysis results in building energy assessment and subsequent HVAC system design and sizing. It is recommended to use at least two machine-learning models for variance-based sensitivity methods to allow the comparison of ranking results. The consistency of results from these learning methods should be thoroughly checked since the parameters in tuning these machine-learning models have significant influences on ranking results.

Keywords

Sensitivity analysis Building energy model Machine-learning models Predictive performance 

Notes

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 (China) (contract No. 16JZDH014).

References

  1. 1.
    Tian, W.: A review of sensitivity analysis methods in building energy analysis. Renew. Sustain. Energy Rev. 20, 411–419 (2013)CrossRefGoogle Scholar
  2. 2.
    Li, Z., Peng, W., Yujiao, H., Wei, T., Yong, S.: Relationships between design parameters of see-through thin film photovoltaic facade and energy performance of office building in China cold zone. Energy Procedia 152, 401–406 (2018)CrossRefGoogle Scholar
  3. 3.
    Li, H., Wang, S., Cheung, H.: Sensitivity analysis of design parameters and optimal design for zero/low energy buildings in subtropical regions. Appl. Energy 228, 1280–1291 (2018)CrossRefGoogle Scholar
  4. 4.
    O’Neill, Z., Niu, F.: Uncertainty and sensitivity analysis of spatio-temporal occupant behaviors on residential building energy usage utilizing Karhunen-Loève expansion. Build. Environ. 115, 157–172 (2017)CrossRefGoogle Scholar
  5. 5.
    Tian, W., Heo, Y., de Wilde, P., et al.: Augenbroe, a review of uncertainty analysis in building energy assessment. Renew. Sustain. Energy Rev. 93, 285–301 (2018)CrossRefGoogle Scholar
  6. 6.
    Tian, W., Song, J., Li, Z., et al.: Bootstrap techniques for sensitivity analysis and model selection in building thermal performance analysis. Appl. Energy 135, 320–328 (2014)CrossRefGoogle Scholar
  7. 7.
    Song, J., Wei, L., Sun, Y., Tian, W.: Implementation of meta-modelling for sensitivity analysis in building energy analysis. In: The eSim 2014 Conference, May 7 to 10, Ottawa, Canada (2014)Google Scholar
  8. 8.
    Tian, W., Wilde, P.D.: Impact of global warming on thermal performance of domestic buildings using probabilistic climate data. Int. J. Glob. Warming 10(4), 514–535 (2016)CrossRefGoogle Scholar
  9. 9.
    MOC, GB50189-2015.: Design standard for energy efficiency of public buildings. In: Ministry of Construction (MOC) of P.R. China Planning Press (2015) (in Chinese) (2015)Google Scholar
  10. 10.
    DOE.: EnergyPlus V9.0.1, October 2018, Department of Energy, USA, in (2018)Google Scholar
  11. 11.
    R Core Team: R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL https://www.R-project.org/. Accessed 12 Oct 2018, in (2017)
  12. 12.
    Saltelli, A.: Global Sensitivity Analysis: The Primer. Wiley, Chichester (2008)zbMATHGoogle Scholar
  13. 13.
    Gilles Pujol, B.I., Alexandre J.: R package sensitivity V1.12.2: sensitivity: global sensitivity analysis of model outputs. https://CRAN.R-project.org/package=sensitivity. Accessed on 20 Dec 2018, in (2018)
  14. 14.
    Tian, W., Wilde, P.D., Li, Z., Song, J., Yin, B.: Uncertainty and sensitivity analysis of energy assessment for office buildings based on dempster-shafer theory. Energy Convers. Manage. 174, 705–718 (2018)CrossRefGoogle Scholar
  15. 15.
    Wei, L., Tian, W., Silva, E.A., et al.: Comparative study on machine learning for urban building energy analysis. Procedia Engineering 121, 285–292 (2015)CrossRefGoogle Scholar
  16. 16.
    Kuhn, M., Johnson, K., Applied Predictive Modeling, Springer (2013)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.College of Mechanical EngineeringTianjin University of Science and TechnologyTianjinChina
  2. 2.Tianjin International Joint Research and Development Center of Low-Carbon Green Process EquipmentTianjinChina
  3. 3.Chair of Building Performance Analysis, Environmental Building GroupUniversity of PlymouthPlymouthUK
  4. 4.School of ArchitectureHarbin Institute of TechnologyHarbinChina
  5. 5.Tianjin Architecture Design InstituteTianjinChina

Personalised recommendations