Advertisement

Deep Component-Based Neural Network Energy Modelling for Early Design Stage Prediction

  • Sundaravelpandian SingaravelEmail author
  • Philipp Geyer
Conference paper

Abstract

Developing low-energy buildings calls for low-energy design and operations. Estimating operational energy of a building design supports major decisions taken at early design stages. To support early design decisions, accurate and quick predictions are required; a decision taken on predictions with poor quality can result in a wrong decision.

References

  1. 1.
    Attia S, Gratia E, De Herde A, Hensen JLM (2012) Simulation-based decision support tool for early stages of zero-energy building design. Energy Build 49:2–15CrossRefGoogle Scholar
  2. 2.
    Singaravel S, Geyer P (2016) Simplifying building energy performance models to support an integrated design workflow. In: International workshop of the european group for intelligent computing in engineering edition, p 23Google Scholar
  3. 3.
    Horsey H, Fleming K, Ball B, Long N (2016) Achieving actionable results from available inputs: metamodels take building energy simulations one step further. In: ACEEE summer study on energy efficiency in buildingsGoogle Scholar
  4. 4.
    Van Gelder L, Das P, Janssen H, Roels S (2014) Comparative study of metamodelling techniques in building energy simulation: guidelines for practitioners. Simul Model Pract Theory 49:245–257CrossRefGoogle Scholar
  5. 5.
    Singaravel S, Geyer P, Suykens J (2017) Deep learning neural networks architectures and methods: building design energy prediction by component-based models. Manuscr Submitt PublGoogle Scholar
  6. 6.
    Dong B, Cao C, Lee SE (2005) Applying support vector machines to predict building energy consumption in tropical region. Energy Build 37(5):545–553CrossRefGoogle Scholar
  7. 7.
    Chari A, Christodoulou S (2017) Building energy performance prediction using neural networks. Energy Effi 1–13Google Scholar
  8. 8.
    Hou Z, Lian Z, Yao Y, Yuan X (2006) Cooling-load prediction by the combination of rough set theory and an artificial neural-network based on data-fusion technique. Appl Energy 83(9):1033–1046CrossRefGoogle Scholar
  9. 9.
    Widén J, Wäckelgård E (2010) A high-resolution stochastic model of domestic activity patterns and electricity demand. Appl Energy 87(6):1880–1892CrossRefGoogle Scholar
  10. 10.
    Yu Z, Haghighat F, Fung BCM, Yoshino H (2010) A decision tree method for building energy demand modeling. Energy Build 42(10):1637–1646CrossRefGoogle Scholar
  11. 11.
    Singaravel S, Geyer P, Suykens J (2017) Component-based machine learning modelling approach for design stage building energy prediction: weather conditions and size. In: Proceedings of the 15th IBPSA conference, pp 2617–2626Google Scholar
  12. 12.
    Geyer P, Singaravel S Component-based performance prediction for sustainable building design based on systems engineering and machine learning: the energy perspective. Manuscr Submitt PublGoogle Scholar
  13. 13.
    Singaravel S, Geyer P, Suykens J (2017) Deep neural network architectures for component-based machine learning model in building energy predictions. In: EG-ICE, pp 260–268Google Scholar
  14. 14.
    Ruder S (2017) An overview of multi-task learning in deep neural networks. arXiv PreprGoogle Scholar
  15. 15.
    Amasyali K, Gohary N (2018) A review of data-driven building energy consumption prediction studies. Renew Sustain Energy Rev 81:1192–1205CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.KU LeuvenLeuvenBelgium

Personalised recommendations