Advertisement

Importance of Feature Selection for Recurrent Neural Network Based Forecasting of Building Thermal Comfort

  • Martin Macas
  • Fabio Moretti
  • Fiorella Lauro
  • Stefano Pizzuti
  • Mauro Annunziato
  • Alessandro Fonti
  • Gabriele Comodi
  • Andrea Giantomassi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8779)

Abstract

The paper demonstrates the importance of feature selection for recurrent neural network applied to problem of one hour ahead forecasting of thermal comfort for office building heated by gas. Although the accuracy of the forecasting is similar for both the feed-forward and the recurrent network, the removal of features leads to accuracy reduction much earlier for the feed-forward network. The recurrent network can perform well even with less than 50% of features. This brings significant benefits in scenarios, where the neural network is used as a blackbox model of thermal comfort, which is called by an optimizer that minimizes the deviance from a target value. The reduction of input dimensionality can lead to reduction of costs related to measurement equipment, data transfer and also computational demands of optimization.

Keywords

Forecasting thermal comfort gas heating neural networks feature selection 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Elman, J.L.: Finding structure in time. Cognitive Science 14(2), 179–211 (1990)CrossRefGoogle Scholar
  2. 2.
    de Jesús Rubio, J.: Evolving intelligent algorithms for the modelling of brain and eye signals. Applied Soft Computing 14, Part B, 259–268 (2014)Google Scholar
  3. 3.
    Macas, M., Lauro, F., Moretti, F., Pizzuti, S., Annunziato, M., Fonti, A., Comodi, G., Giantomassi, A.: Sensitivity based feature selection for recurrent neural network applied to forecasting of heating gas consumption. In: de la Puerta, J.G., et al. (eds.) International Joint Conference SOCO’14-CISIS’14-ICEUTE’14. AISC, vol. 299, pp. 259–268. Springer, Heidelberg (2014)CrossRefGoogle Scholar
  4. 4.
    Macaš, M., Lhotská, L.: Wrapper feature selection significantly improves nonlinear prediction of electricity spot prices. In: 2013 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 1171–1174 (2013)Google Scholar
  5. 5.
    Mathworks: Neural Network Toolbox for Matlab ver. 2012b (2012)Google Scholar
  6. 6.
    Moody, J.E.: The effective number of parameters: An analysis of generalization and regularization in nonlinear learning systems. In: NIPS, pp. 847–854. Morgan Kaufmann (1991)Google Scholar
  7. 7.
    Schijndel, A.W.M.V.: HAMLab: Integrated heat air and moisture modeling and simulation. Ph.D. thesis, Technische Universiteit, Eindhoven (2007), http://archbps1.campus.tue.nl/bpswiki/index.php/Hamlab
  8. 8.
    Villar, J.R., González, S., Sedano, J., Corchado, E., Puigpinós, L., de Ciurana, J.: Meta-heuristic improvements applied for steel sheet incremental cold shaping. Memetic Computing 4(4), 249–261 (2012)CrossRefGoogle Scholar
  9. 9.
    de Wit, M.: HAMBASE: Heat, Air and Moisture Model for Building and Systems Evaluation. Technische Universiteit Eindhoven, Faculteit Bouwkunde (2006)Google Scholar
  10. 10.
    de Wit, M.: Calculation of the predicted mean vote (pmv) and the predicted percentage of dissatisfied (ppd) according Fanger. Online Matlab SW (1998)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Martin Macas
    • 1
  • Fabio Moretti
    • 2
  • Fiorella Lauro
    • 2
  • Stefano Pizzuti
    • 2
  • Mauro Annunziato
    • 2
  • Alessandro Fonti
    • 3
  • Gabriele Comodi
    • 3
  • Andrea Giantomassi
    • 4
  1. 1.Department of CyberneticsCzech Technical University in PraguePragueCzech Republic
  2. 2.Unità Tecnica Tecnologie Avanzate per l’Energia e l’IndustriaENEA (Italian National Agency for New Technologies, Energy and Sustainable Economic Development), Cassacia Research CenterRomaItaly
  3. 3.Dipartimento di Ingegneria Industriale e Scienze MatematicheUniversità Politecnica delle MarcheAnconaItaly
  4. 4.Dipartimento di Ingegneria dell’InformazioneUniversità Politecnica delle MarcheAnconaItaly

Personalised recommendations