Advertisement

Modeling the cost of energy in public sector buildings by linear regression and deep learning

  • Marijana Zekić-SušacEmail author
  • Marinela Knežević
  • Rudolf Scitovski
Article

Abstract

Modeling the cost of energy consumption of public buildings is vital for planning reconstruction measures in the public sector. The methods of predictive analytics have not been sufficiently exploited in this domain. This paper aimed to create a model for predicting the cost of the total energy consumption of a building based on deep learning (DL) and compare it to the standard linear regression (MLR), as well to identify key predictors that can significantly influence the cost of energy. An algorithm for modeling procedure is proposed which includes data pre-processing, variable reduction procedures, training and testing MLR and deep neural networks (DNN) and, finally, performance evaluation. Variable reduction in the MLR model was conducted by a backward procedure; while in DNN, the Olden method was used. The algorithm was tested on a high-dimensional real dataset of Croatian public buildings. The results showed that there is a statistically significant difference in the distribution of DNN predictions and distribution of actual values in the validation set, as opposed to distribution of MLR predictions and real values. However, DNN model had a lower normalized root mean square error, while the MLR model had a lower symmetric mean average error. Those findings reveal the potential of DL for solving this type of problems but also the need for more advanced algorithms adjusted to deal with large-range numeric outputs. The created models could be implemented in public sector business intelligence systems to support policy and decision makers in allocating resources for building reconstructions.

Keywords

Energy cost Data analytics Deep learning Multiple linear regression Public sector buildings 

Notes

Acknowledgments

This work was supported by Croatian Science Foundation through research Grant IP-2016-06-8350 “Methodological framework for efficient energy management by intelligent data analytics” MERIDA and research Grant IP-2016-06-6545 “The optimization and statistical models and methods in recognizing properties of data sets measured with errors”.

References

  1. Anastasiadis A et al (2005) New globally convergent training scheme based on the resilient propagation algorithm. Neurocomputing 64:253–270.  https://doi.org/10.1016/j.neucom.2004.11.016 CrossRefGoogle Scholar
  2. Bengio Y (2009) Learning deep architectures for AI. Found Trends Mach Learn 2:1–127.  https://doi.org/10.1561/2200000006 CrossRefGoogle Scholar
  3. Borozan D, Borozan L (2018) Analyzing total-factor energy efficiency in Croatian counties: evidence from a nonparametric approach. Cent Eur J Oper Res 26(3):673–694.  https://doi.org/10.1007/s10100-017-0493-8 CrossRefGoogle Scholar
  4. Box GEP, Cox DR (1964) An analysis of transformations. J R Stat Soc 26:211–252Google Scholar
  5. Hrebik R, Kukal J, Jablonsky J (2019) Optimal unions of hidden classes. Cent Eur J Oper Res 27(1):161–177.  https://doi.org/10.1007/s10100-017-0496-5 CrossRefGoogle Scholar
  6. Kemp SJ, Zaradic P, Hansen F (2007) An approach for determining relative input parameter importance and significance in artificial neural networks. Ecol Model 204(3–4):326–334.  https://doi.org/10.1016/j.ecolmodel.2007.01.009 CrossRefGoogle Scholar
  7. LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521:436–444.  https://doi.org/10.1038/nature14539 CrossRefGoogle Scholar
  8. Mangold M, Osterbring M, Wallbaum H (2015) Handling data uncertainties when using Swedish energy performance certificate data to describe energy usage in the building stock. Energy Buildings 102:328–336.  https://doi.org/10.1016/j.enbuild.2015.05.045 CrossRefGoogle Scholar
  9. Masters T (1995) Advanced algorithms for neural networks, a C++ sourcebook. Wiley, New YorkGoogle Scholar
  10. Naji S, Shamshirband S, Basser H, Alengaram UJ, Jumaat MZ, Amirmojahedi M (2016) Soft computing methodologies for estimation of energy consumption in buildings with different envelope parameters. Energy Effic 9(2):435–453.  https://doi.org/10.1007/s12053-015-9373-z CrossRefGoogle Scholar
  11. Olden JD, Joy MK, Death RG (2004) An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data. Ecol Model 178:389–397.  https://doi.org/10.1016/j.ecolmodel.2004.03.013 CrossRefGoogle Scholar
  12. Pérez-Lombard L, Ortiz J, Pout C (2008) A review on buildings energy consumption information. Energy Build 40(3):394–398.  https://doi.org/10.1016/j.enbuild.2007.03.007 CrossRefGoogle Scholar
  13. Rauner MS, Niessner H, Odd S et al (2018) An advanced decision support system for European disaster management: the feature of the skills taxonomy. Cent Eur J Oper Res 26(2):485–530.  https://doi.org/10.1007/s10100-018-0528-9 CrossRefGoogle Scholar
  14. Tofallis C (2015) A better measure of relative prediction accuracy for model selection and model estimation. J Oper Res Soc 66:1352–1362.  https://doi.org/10.1057/jors.2014.103 CrossRefGoogle Scholar
  15. Tommerup H, Rose J, Svendsen S (2007) Energy-efficient houses built according to the energy performance requirements introduced in Denmark in 2006. Energy Build 39:1123–1130.  https://doi.org/10.1016/j.enbuild.2006.12.011 CrossRefGoogle Scholar
  16. Touzani S, Ravache B, Crowe E, Granderson J (2019) Statistical change detection of building energy consumption: applications to savings estimation. Energy Build 185:123–136.  https://doi.org/10.1016/j.enbuild.2018.12.020 CrossRefGoogle Scholar
  17. Viswanath P, Babu VS (2009) Rough-DBSCAN: a fast hybrid density based clustering method for large data sets. Pattern Recognit Lett 30:1477–1488.  https://doi.org/10.1016/j.patrec.2009.08.008 CrossRefGoogle Scholar
  18. Wang ZX, Ding Y (2015) An occupant-based energy consumption prediction model for office equipment. Energy Build 109:12–22.  https://doi.org/10.1016/j.enbuild.2015.10.002 CrossRefGoogle Scholar
  19. Wooldrige JM (2012) Introductory econometrics—a modern approach, 5th edn. Cengage Learning, BostonGoogle Scholar
  20. Zekić-Sušac M (2017) Overview of prediction models for buildings energy efficiency. In: Proceedings of the 6th international scientific symposium economy of Eastern Croatia—vision and growth. Faculty of Economics in Osijek, Osijek, pp 697–706Google Scholar
  21. Zekić-Sušac M, Šarlija N, Has A, Bilandžić A (2016) Predicting company growth using logistic regression and neural networks. Croat Oper Res Rev 7:229–248.  https://doi.org/10.17535/crorr.2016.0016 CrossRefGoogle Scholar
  22. Zekić-Sušac M, Scitovski R, Has A (2018) Cluster analysis and artificial neural networks in predicting energy efficiency of public buildings as a cost-saving approach. Croat Rev Econ Bus Soc Stat 4(2):57–66.  https://doi.org/10.2478/crebss-2018-0013 CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Faculty of Economics in OsijekUniversity of Josip Juraj Strossmayer in OsijekOsijekCroatia
  2. 2.Department of MathematicsUniversity of Josip Juraj Strossmayer in OsijekOsijekCroatia

Personalised recommendations