Advertisement

Deep Learning in Modeling Energy Cost of Buildings in the Public Sector

  • Marijana Zekić-SušacEmail author
  • Marinela Knežević
  • Rudolf Scitovski
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 950)

Abstract

The cost of energy consumed in educational, health, public administration, military, and other types of public buildings constitutes a substantial proportion of the total expenditure of the public sector. Due to a large number of attributes that influence the energy cost of a building, most of the models developed in the literature use only a subset of predictors, often neglect occupational data, and do not exploit enough the potential of deep learning methods. In this paper a real data from Croatian public sector is used including constructional, energetic, geographical, occupational and other attributes. Algorithms for data preprocessing and for deep learning modelling procedure are suggested. The number of hidden units in the deep neural network is optimized by a cross-validation procedure, while the sigmoid activation function was tested with Adam optimization algorithm. The feature selection was conducted using the recursive feature elimination method with a regression random forest kernel. The aims were to identify the subset of relevant predictors of energy cost in public buildings that could assist decision makers in determining the priority of reconstruction measures as well as to test the potential of deep learning in predicting the yearly energy cost. The results have shown that the deep learning network with three hidden layers was the most successful in predicting energy cost using the wrapper-based method of feature extraction. The selection of features confirms the importance of occupational data, as well as heating, cooling, electricity lightning, and constructional attributes for estimating the total energy cost. Those predictors can be used in decision making on allocating resources in public buildings reconstructions. The model implementation could improve public sector energy efficiency, save costs and contribute to the concepts of smart buildings and smart cities.

Keywords

Energy cost Deep learning Neural networks Public sector 

Notes

Acknowledgments

This work was supported by Croatian Science Foundation through research grant IP-2016-06-8350 and research grant IP-2016-06-6545.

References

  1. 1.
    Bengio, Y.: Learning deep architectures for AI. Found. Trends Mach. Learn. 2, 1–127 (2009).  https://doi.org/10.1561/2200000006CrossRefzbMATHGoogle Scholar
  2. 2.
    Calvillo, C.F., Sánchez-Miralles, A., Villar, J.: Energy management and planning in smart cities. Renew. Sustain. Energy Rev. 55, 273–287 (2016).  https://doi.org/10.1016/j.rser.2015.10.133CrossRefGoogle Scholar
  3. 3.
    Kingma, D.P., Ba, M.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations (2014). https://arxiv.org/abs/1412.6980
  4. 4.
    Krstić, H., Teni, M.: Algorithm for constructional characteristics data cleansing of large-scale public buildings database. In: High Performance and Optimum Design of Structures and Materials III, WIT Transactions on The Built Environment, vol. 175, pp. 213–224 (2018).  https://doi.org/10.2495/HPSM180221
  5. 5.
    LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015).  https://doi.org/10.1038/nature14539CrossRefGoogle Scholar
  6. 6.
    Liang, X., Hong, T.Z., Shen, G.Q.: Improving the accuracy of energy baseline models for commercial buildings with occupancy data. Appl. Energy 179, 247–260 (2016).  https://doi.org/10.1016/j.apenergy.2016.06.141CrossRefGoogle Scholar
  7. 7.
    Mangold, M., Osterbring, M., Wallbaum, H.: Handling data uncertainties when using Swedish energy performance certificate data to describe energy usage in the building stock. Energy Build. 102, 328–336 (2015).  https://doi.org/10.1016/j.enbuild.2015.05.045CrossRefGoogle Scholar
  8. 8.
    Marinakis, V., Doukas, H.: An advanced IoT-based system for intelligent energy management in buildings. Sensors 18(2/610), 1–16 (2018).  https://doi.org/10.3390/s18020610CrossRefGoogle Scholar
  9. 9.
    Naji, S., Shamshirband, S., Basser, H., Alengaram, U.J., Jumaat, M.Z., Amirmojahedi, M.: Soft computing methodologies for estimation of energy consumption in buildings with different envelope parameters. Energ. Effi. 9(2), 435–453 (2016).  https://doi.org/10.1007/s12053-015-9373-zCrossRefGoogle Scholar
  10. 10.
    Odyssée-Mure: Key indicators (2016). http://www.indicators.odyssee-mure.eu/online-indicators.html. Accessed 03 Jan 2019
  11. 11.
    Pérez-Lombard, L., Ortiz, J., Pout, C.: A review on buildings energy consumption information. Energy Build. 40(3), 394–398 (2008).  https://doi.org/10.1016/j.enbuild.2007.03.007CrossRefGoogle Scholar
  12. 12.
    Scitovski, R., Zekić-Sušac, M., Has, A.: Searching for an optimal partition of incomplete data with application in modeling energy efficiency of public buildings. Croatian Oper. Res. Rev. 9(2), 255–268 (2018).  https://doi.org/10.17535/crorr.2018.0020MathSciNetCrossRefGoogle Scholar
  13. 13.
    Srivastava, N.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15, 1929–1958 (2014)MathSciNetzbMATHGoogle Scholar
  14. 14.
    Tofallis, C.: A better measure of relative prediction accuracy for model selection and model estimation. J. Oper. Res. Soc. 66, 1352–1362 (2015).  https://doi.org/10.1057/jors.2014.103CrossRefGoogle Scholar
  15. 15.
    Torres, J., Fernandez, A., Troncoso, A., Martínez-Álvarez, F.: Deep Learning-Based Approach for Time Series Forecasting with Application to Electricity Load. Lecture Notes in Computer Science, vol. 10338, pp. 203–212 (2017).  https://doi.org/10.1007/978-3-319-59773-7_21CrossRefGoogle Scholar
  16. 16.
    Touzani, S., Ravache, B., Crowe, E., Granderson, J.: Statistical change detection of building energy consumption: applications to savings estimation. Energy Build. 185, 123–136 (2019).  https://doi.org/10.1016/j.enbuild.2018.12.020CrossRefGoogle Scholar
  17. 17.
    Viswanath, P., Babu, V.S.: Rough-DBSCAN: a fast hybrid density based clustering method for large data sets. Pattern Recognit. Lett. 30, 1477–1488 (2009).  https://doi.org/10.1016/j.patrec.2009.08.008CrossRefGoogle Scholar
  18. 18.
    Wang, Z.X., Ding, Y.: An occupant-based energy consumption prediction model for office equipment. Energy Build. 109, 12–22 (2015).  https://doi.org/10.1016/j.enbuild.2015.10.002CrossRefGoogle Scholar
  19. 19.
    Zekić-Sušac, M., Scitovski, R., Has, A.: Cluster analysis and artificial neural networks in predicting energy efficiency of public buildings as a cost-saving approach. Croatian Rev. Econ. Bus. Soc. Stat. 4(2), 57–66 (2018).  https://doi.org/10.2478/crebss-2018-0013CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Marijana Zekić-Sušac
    • 1
    Email author
  • Marinela Knežević
    • 1
  • Rudolf Scitovski
    • 2
  1. 1.Faculty of EconomicsUniversity of Josip Juraj Strossmayer in OsijekOsijekCroatia
  2. 2.Department of MathematicsUniversity of Josip Juraj Strossmayer in OsijekOsijekCroatia

Personalised recommendations