THERMAL SCIENCE

International Scientific Journal

Radiša Ž Jovanović

,

Aleksandra A. Sretenović

,

Branislav Živković

MULTISTAGE ENSEMBLE OF FEEDFORWARD NEURAL NETWORKS FOR PREDICTION OF HEATING ENERGY CONSUMPTION

ABSTRACT
Feedforward neural network models are created for prediction of heating energy consumption of a university campus. Actual measured data are used for training and testing the models. Multistage neural network ensemble is proposed for the possible improvement of prediction accuracy. Previously trained feed-forward neural networks are first separated into clusters, using k-means algorithm, and then the best network of each cluster is chosen as a member of the ensemble. Three different averaging methods (simple, weighted and median) for obtaining ensemble output are applied. Besides this conventional approach, single radial basis neural network in the second level is used to aggregate the selected ensemble members. It is shown that heating energy consumption can be predicted with better accuracy by using ensemble of neural networks than using the best trained single neural network, while the best results are achieved with multistage ensemble.
KEYWORDS
heating consumption prediction, neural networks, k-means clustering, multistage ensemble
PAPER SUBMITTED: 2015-01-22
PAPER REVISED: 2015-08-22
PAPER ACCEPTED: 2015-09-07
PUBLISHED ONLINE: 2015-09-26
DOI REFERENCE: https://doi.org/10.2298/TSCI150122140J
CITATION EXPORT: view in browser or download as text file
THERMAL SCIENCE YEAR 2016, VOLUME 20, ISSUE Issue 4, PAGES [1321 - 1331]
REFERENCES
  1. Council., E. P. a. Directive 2010/31/EU of the European Parliament and of the Council of 19 May 2010 on the energy performance of buildings. Official Journal of the European Union 2010, L153 (2010), pp. 13-35.
  2. Kusiak, A., et al., A data-driven approach for steam load prediction in buildings. Applied Energy, 87 (2010), 3, pp. 925-933. doi:10.1016/j.apenergy.2009.09.004
  3. Vujić, B., et al., Experimental and artificial neural network approach for forecasting of traffic air pollution in urban areas: the case of subotica. Thermal Science, 14 (2010), pp. 79-87. doi:10.2298/TSCI100507032V
  4. Ganapathy, T., et al., Artificial neural network modeling of jatropha oil fueled diesel engine for emission predictions. Thermal Science, 13 (2009), 3, pp. 91-102. doi:10.2298/TSCI0903091G
  5. Ćirić, I. T., et al., Air quality estimation by computational intelligence methodologies. Thermal Science, 16 (2012), suppl. 2, pp. 493-504. doi:10.2298/TSCI120503186C
  6. Özener, O., et al., Artificial neural network approach to predicting engine-out emissions and performance parameters of a turbo charged diesel engine. Thermal Science, 17 (2013), 1, pp. 153-166. doi:10.2298/TSCI120321220O
  7. Ekici, B. B. and Aksoy, U. T. Prediction of building energy consumption by using artificial neural networks. Advances in Engineering Software, 40 (2009), 5, pp. 356-362. doi:10.1016/j.advengsoft.2008.05.003
  8. Dombaycı, Ö. A. The prediction of heating energy consumption in a model house by using artificial neural networks in Denizli-Turkey. Advances in Engineering Software, 41 (2010), 2, pp. 141-147. doi:10.1016/j.advengsoft.2009.09.012
  9. Ekonomou, L. Greek long-term energy consumption prediction using artificial neural networks. Energy, 35 (2010), 2, pp. 512-517. doi:10.1016/j.energy.2009.10.018
  10. Kumar, R., et al., Energy analysis of a building using artificial neural network: A review. Energy and Buildings, 65 (2013), pp. 352-358. doi:10.1016/j.enbuild.2013.06.007
  11. Zhou, Z.-H., et al., Ensembling neural networks: many could be better than all. Artificial intelligence, 137 (2002), 1, pp. 239-263. doi:10.1016/S0004-3702(02)00190-X
  12. Melin, P., et al., A new approach for time series prediction using ensembles of ANFIS models. Expert Systems with Applications, 39 (2012), 3, pp. 3494-3506. doi:10.1016/j.eswa.2011.09.040
  13. Taylor, J. W. and Buizza, R. Neural network load forecasting with weather ensemble predictions. Power Systems, IEEE Transactions on, 17 (2002), 3, pp. 626-632.
  14. Siwek, K., et al., Ensemble neural network approach for accurate load forecasting in a power system. International Journal of Applied Mathematics and Computer Science, 19 (2009), 2, pp. 303-315.
  15. Hansen, L. K. and Salamon, P. Neural network ensembles. IEEE transactions on pattern analysis and machine intelligence, 12 (1990), 10, pp. 993-1001. doi.ieeecomputersociety.org/10.1109/34.58871
  16. Qiang, F., et al., Z. Clustering-based selective neural network ensemble. Journal of Zhejiang University SCIENCE A, 6 (2005), 5, pp. 387-392.
  17. Granitto, P. M., et al., Neural network ensembles: evaluation of aggregation algorithms. Artificial Intelligence, 163 (2005), 2, pp. 139-162. doi:10.1016/j.artint.2004.09.006
  18. Sharkey, A. J. Multi-net systems. Springer, City, 1999.
  19. Zhang, G. P. and Berardi, V. Time series forecasting with neural network ensembles: an application for exchange rate prediction. Journal of the Operational Research Society, 52 (2001), 6, pp. 652-664.
  20. Breiman, L. Bagging predictors. Machine learning, 24 (1996), 2, pp. 123-140.
  21. Schapire, R. E. The strength of weak learnability. Machine learning, 5 (1990), 2, pp. 197-227.
  22. Opitz, D. W. and Shavlik, J. W. Actively searching for an effective neural network ensemble. Connection Science, 8 (1996), 3-4, pp. 337-354.
  23. Lazarevic, A. and Obradovic, Z. Effective pruning of neural network classifier ensembles. IEEE, City, 2001. doi:10.1109/IJCNN.2001.939461
  24. Navone, H. D., et al., Selecting diverse members of neural network ensembles. IEEE, City, 2000. doi:10.1109/SBRN.2000.889748
  25. MacQueen, J. Some methods for classification and analysis of multivariate observations. California, USA, 1967.
  26. Ilić, S. A., et al., Hybrid artificial neural network system for short-term load forecasting. Thermal Science, 16 (2012), suppl. 1, pp. 215-224. doi:10.2298/TSCI120130073I
  27. Sretenovic, A. Analysis of energy use at university campus. Master, Norwegian University of Science and Technology, Trondheim, 2013.
  28. ***, Energy Remote Monitoring, erm.tac.com/erm/
  29. ***, AgroBase Weather Database, lmt.bioforsk.no/agrometbase/getweatherdata.php
  30. Johannessen, T. W. Varmeutviklingen I bygninger og klimaet. Norges Byggforskingsinstitutt, 1956.
  31. Skaugen, T. E., et al., Heating degree-days - Present conditions and scenario for the period 2021-2050. DNMI Report 01/02KLIMA, Norwegian Meteorological Institute, Oslo, Norway, 2002.
  32. Wojdyga, K. An influence of weather conditions on heat demand in district heating systems. Energy and Buildings, 40 (2008), 11, pp. 2009-2014. doi:10.1016/j.enbuild.2008.05.008
PDF VERSION [DOWNLOAD]
Multistage ensemble of feedforward neural networks for prediction of heating energy consumption

© 2024 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence