Skip to main content

Deep Learning Models for Future Occupancy Prediction in Residential Buildings

  • Conference paper
  • First Online:
Proceedings of the 5th International Conference on Building Energy and Environment (COBEE 2022)

Abstract

This paper contributes to the occupancy prediction problem by developing state-of-the-art deep learning models. The occupancy prediction problem is addressed from two different viewpoints: multi-label classification and a sequence-to-sequence time-series analysis using encoder-decoder architectures. The following deep learning algorithms are employed in this study to construct occupancy models: multi-layer perceptron (MLP), recurrent neural networks, long-short term memory (LSTM), gated recurrent units (GRU), and bidirectional LSTMs. The performance of these models is evaluated and compared in terms of accuracy and computational speed. The results demonstrate that addressing this problem using MLP models provides the best performance for short-term predictions, while for predictions more than 90 min ahead, GRU results in the highest accuracy. It is also demonstrated that the accuracy of the deep learning models can be approximated as a function of the occupancy index with an MAE of 0.014.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 429.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 549.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

Download references

Acknowledgements

The authors would like to express their gratitude to Concordia University—Canada for the support through the Concordia Research Chair—Energy and Environment.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Fariborz Haghighat .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Esrafilian-Najafabadi, M., Babahaji, M., Haghighat, F. (2023). Deep Learning Models for Future Occupancy Prediction in Residential Buildings. In: Wang, L.L., et al. Proceedings of the 5th International Conference on Building Energy and Environment. COBEE 2022. Environmental Science and Engineering. Springer, Singapore. https://doi.org/10.1007/978-981-19-9822-5_106

Download citation

  • DOI: https://doi.org/10.1007/978-981-19-9822-5_106

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-19-9821-8

  • Online ISBN: 978-981-19-9822-5

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics