Personal and Ubiquitous Computing

, Volume 23, Issue 5–6, pp 921–929 | Cite as

Accurately forecasting temperatures in smart buildings using fewer sensors

  • Bruce SpencerEmail author
  • Feras Al-Obeidat
  • Omar Alfandi
Original Article


Forecasts of temperature in a “smart” building, i.e. one that is outfitted with sensors, are computed from data gathered by these sensors. Model predictive controllers can use accurate temperature forecasts to save energy by optimally using heating, ventilation and air conditioners while achieving comfort. We report on experiments from such a house. We select different sets of sensors, build a temperature model from each set, and compare the accuracy of these models. While a primary goal of this research area is to reduce energy consumption, in this paper, besides the cost of energy, we consider the cost of data collection and management. Our approach informs the selection of an optimal set of sensors for any model predictive controller to reduce overall costs, using any forecasting methodology. We use lasso regression with lagged observations, which compares favourably to previous methods using the same data.


Energy efficiency Sensor networks Model predictive control Temperature forecast Feature selection Internet of things 


Funding information

The authors gratefully acknowledge the financial support of their organizations, and Zayed University’s RIF 17062 fund.


  1. 1.
    Álvarez J, Redondo J, Camponogara E, Normey-Rico J, Berenguel M, Ortigosa P (2013) Optimizing building comfort temperature regulation via model predictive control. Energ Buildings 57:361–372CrossRefGoogle Scholar
  2. 2.
    Bjørn-Helge MRW (2007) The pls package: principal component and partial least squares regression in R. J Stat Softw 18(2):1–24. Google Scholar
  3. 3.
    EIA (2017) Frequently asked questions how much energy is consumed in u.s. residential and commercial buildings?
  4. 4.
    Friedman J, Hastie T, Tibshirani R (2010) Regularization paths for generalized linear models via coordinate descent. J Stat Softw 33(1):1–22. CrossRefGoogle Scholar
  5. 5.
    Friedman J, Hastie T, Simon N, Tibshirani R (2016) Package glmnet: lasso and elastic-net regularized generalized linear models ver 2.0-.
  6. 6.
    Mevik BH, Wehrens R, Liland KH (2015) pls: Partial least squares and principal component regression., r package version 2.5-0
  7. 7.
    Moreno MV, Zamora MA, Skarmeta AF (2014) User-centric smart buildings for energy sustainable smart cities. Transactions on emerging telecommunications technologies 25(1):41–55. CrossRefGoogle Scholar
  8. 8.
    Morosan P, Bourdais R, Dumur D, Buisson J (2010) Building temperature regulation using a distributed model predictive control. Energ Buildings 42(9):1445–1452CrossRefGoogle Scholar
  9. 9.
    Pan D, Yuan Y D W, Xu X, Peng Y, Peng X, Wan P J (2012) Thermal inertia: towards an energy conservation room management system. In: Greenberg A, Sohraby K (eds) INFOCOM. IEEE, pp 2606–2610Google Scholar
  10. 10.
    Pérez-Lombard L, Ortiz J, Pout C (2008) A review on buildings energy consumption information. Energ Buildings 40:394–398CrossRefGoogle Scholar
  11. 11.
    Prívara S, Široký J, Ferkl L, Cigler J (2011) Model predictive control of a building heating system: The first experience. Energ Buildings 43(2):564–572. . CrossRefGoogle Scholar
  12. 12.
    Romanski P, Kotthoff L (2016) Package ‘FSelector’ selecting attributes. R package version 0:21. Google Scholar
  13. 13.
    Simon N, Friedman J, Hastie T, Tibshirani R (2011) Regularization paths for cox’s proportional hazards model via coordinate descent. J Stat Softw 39(5):1–13. CrossRefGoogle Scholar
  14. 14.
    Spencer B, Al-Obeidat F (2016) Temperature forecasts with stable accuracy in a smart home. In: SEIT Sustainable Energy Information Technology Conference. CrossRefGoogle Scholar
  15. 15.
    Spencer B, Al-Obeidat F, Alfandi O (2016) Short term forecasts of internal temperature with stable accuracy in smart homes. Int J Thermal Environ Eng 13(2):81–89Google Scholar
  16. 16.
    Spencer B, Al-Obeidat F, Alfandi O (2017) Selecting sensors when forecasting temperature in smart buildings, vol 109, pp 777–784., 8th International Conference on Ambient Systems, Networks and Technologies, ANT-2017 and the 7th International Conference on Sustainable Energy Information Technology, SEIT 2017, 16-19 May 2017, Madeira, PortugalCrossRefGoogle Scholar
  17. 17.
    Tibshirani R (1996) Regression shrinkage and selection via the lasso: a retrospective. J R Stat Soc Ser B (Stat Methodol) 58(1):267–288. zbMATHGoogle Scholar
  18. 18.
  19. 19.
    United States Department of Energy (2012) Solar decathlon Europe competition.
  20. 20.
    Yuan Y, Pan D, Wang D, Xu X, Peng Y, Peng X, Wan PJ (2013) A study towards applying thermal inertia for energy conservation in rooms. ACM Trans Sen Netw 10(1):7:1–7:25. . CrossRefGoogle Scholar
  21. 21.
    Zamora-Martínez F, Romeu P, Botella-Rocamora P, Pardo J (2013) Towards energy efficiency: forecasting indoor temperature via multivariate analysis. Energies 6(9):4639. CrossRefGoogle Scholar
  22. 22.
    Zamora-Martínez F, Romeu P, Botella-Rocamora P, Pardo J (2014) On-line learning of indoor temperature forecasting models towards energy efficiency. Energ Buildings 83:162–172CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2017

Authors and Affiliations

  1. 1.University of New BrunswickFrederictonCanada
  2. 2.Zayed UnivesityAbu DhabiUnited Arab Emirates

Personalised recommendations