**Page description appears here**

“Various multistage ensembles for prediction of heating energy consumption”

Authors: Radisa Jovanovic and Aleksandra Sretenovic,
Affiliation: University of Belgrade
Reference: 2015, Vol 36, No 2, pp. 119-132.

     Valid XHTML 1.0 Strict

Keywords: heating consumption prediction, multistage neural network ensemble, adaptive neuro-fuzzy inference

Abstract: Feedforward neural network models are created for prediction of daily heating energy consumption of a NTNU university campus Gloshaugen using actual measured data for training and testing. Improvement of prediction accuracy is proposed by using neural network ensemble. 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 member of an ensemble. Two conventional averaging methods for obtaining ensemble output are applied; simple and weighted. In order to achieve better prediction results, multistage ensemble is investigated. As second level, adaptive neuro-fuzzy inference system with various clustering and membership functions are used to aggregate the selected ensemble members. Feedforward neural network in second stage is also analyzed. It is shown that using ensemble of neural networks can predict heating energy consumption with better accuracy than the best trained single neural network, while the best results are achieved with multistage ensemble.

PDF PDF (6125 Kb)        DOI: 10.4173/mic.2015.2.4

DOI forward links to this article:
  [1] Lavinia Chiara Tagliabue, Massimiliano Manfren, Angelo Luigi Camillo Ciribini and Enrico De Angelis (2016), doi:10.1016/j.enbuild.2016.06.083

[1] AgroMetbase. (2014). Weather database, http://lmt.bioforsk.no/agrometbase/getweatherdata.php.
[2] Bergesen, B., Groth, L.H., Langseth, B., Magnussen, I.H., Spilde, D., and Toutain, J. E.W. (2013). Energy consumption 2012-household energy consumption, Technical report, Technical Report 16, Norwegian Water Resources and Energy Directorate.
[3] Bezdek, J.C. (1981). Pattern recognition with fuzzy objective function algorithms, Kluwer Academic Publishers.
[4] Breiman, L. (1996). Bagging predictors, Machine learning. 24(2):123--140. doi:10.1007/BF00058655
[5] Chiu, S.L. (1994). Fuzzy model identification based on cluster estimation, Journal of intelligent and Fuzzy systems. 2(3):267--278.
[6] Cibulka, J., Ebbesen, M.K., Hovland, G., Robbersmyr, K.G., and Hansen, M.R. (2012). A review on approaches for condition based maintenance in applications with induction machines located offshore, Modeling, identification and control. 15(3):191--203. doi:10.4173/mic.2012.2.4
[7] Council., E. (2010). 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. (18):13--35.
[8] Dombayci, O.A. (2010). The prediction of heating energy consumption in a model house by using artificial neural networks in denizli--turkey, Advances in Engineering Software. 41(2):141--147. doi:10.1016/j.advengsoft.2009.09.012
[9] Dunn, J.C. (1973). A fuzzy relative of the ISODATA process and its use in detecting compact well-separated clusters, Taylor & Francis.
[10] Ekici, B.B. and Aksoy, U.T. (2009). Prediction of building energy consumption by using artificial neural networks, Advances in Engineering Software. 40(5):356--362. doi:10.1016/j.advengsoft.2008.05.003
[11] Ekonomou, L. (2010). Greek long-term energy consumption prediction using artificial neural networks, Energy. 35(2):512--517. doi:10.1016/j.energy.2009.10.018
[12] EnergyRemoteMonitoring. (2014). ERM, http://erm.tac.com/erm/.
[13] Fu, Q., Hu, S.-X., and Zhao, S.-Y. (2004). A pso-based approach for neural network ensemble, Journal of Zhejiang University (Engineering Science). 38(12):1596--1600.
[14] Granitto, P.M., Verdes, P.F., and Ceccatto, H.A. (2005). Neural network ensembles: evaluation of aggregation algorithms, Artificial Intelligence. 163(2):139--162. doi:10.1016/j.artint.2004.09.006
[15] Hansen, L.K. and Salamon, P. (1990). Neural network ensembles, IEEE transactions on pattern analysis and machine intelligence. 12(10):993--1001. doi:10.1109/34.58871
[16] Ilic, S.A., Vukmirovic, S.M., Erdeljan, A.M., and Kulic, F.J. (2012). Hybrid artificial neural network system for short-term load forecasting, Thermal Science. 16(suppl. 1):215--224. doi:10.2298/TSCI120130073I
[17] Jang, J.-S. (1993). Anfis: adaptive-network-based fuzzy inference system, Systems, Man and Cybernetics, IEEE Transactions on. 23(3):665--685. doi:10.1109/21.256541
[18] Johannessen, T. (1956). Varmeutviklingen i bygninger og klimaet, 1956.
[19] Karatasou, S., Santamouris, M., and Geros, V. (2006). Modeling and predicting building's energy use with artificial neural networks: Methods and results, Energy and Buildings. 38(8):949--958. doi:10.1016/j.enbuild.2005.11.005
[20] Kumar, R., Aggarwal, R., and Sharma, J. (2013). Energy analysis of a building using artificial neural network: A review, Energy and Buildings. 65:352--358. doi:10.1016/j.enbuild.2013.06.007
[21] Kusiak, A., Li, M., and Zhang, Z. (2010). A data-driven approach for steam load prediction in buildings, Applied Energy. 87(3):925--933. doi:10.1016/j.apenergy.2009.09.004
[22] Lazarevic, A. and Obradovic, Z. (2001). Effective pruning of neural network classifier ensembles, In Neural Networks. Proceedings. IJCNN'01. International Joint Conference on, volume2. IEEE, pages 796--801.
[23] Li, K., Su, H., and Chu, J. (2011). Forecasting building energy consumption using neural networks and hybrid neuro-fuzzy system: A comparative study, Energy and Buildings. 43(10):2893--2899. doi:10.1016/j.enbuild.2011.07.010
[24] MacQueen, J. etal. (1967). Some methods for classification and analysis of multivariate observations, In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, volume1. Oakland, CA, USA., pages 281--297, 1967.
[25] Melin, P., Soto, J., Castillo, O., and Soria, J. (2012). A new approach for time series prediction using ensembles of anfis models, Expert Systems with Applications. 39(3):3494--3506. doi:10.1016/j.eswa.2011.09.040
[26] Navone, H.D., Verdes, P.F., Granitto, P.M., and Ceccatto, H.A. (2000). Selecting diverse members of neural network ensembles, In Neural Networks. Proceedings. Sixth Brazilian Symposium on. IEEE, pages 255--260.
[27] Opitz, D.W. and Shavlik, J.W. (1996). Actively searching for an effective neural network ensemble, Connection Science. 8(3-4):337--354. doi:10.1080/095400996116802
[28] Perera, D. W.U., Pfeiffer, C., and Skeie, N.-O. (2014). Modelling the heat dynamics of a residential building unit: Application to norwegian buildings, Modeling, Identification and Control. 35(1):43--57. doi:10.4173/mic.2014.1.4
[29] Qiang, F., Shang-Xu, H., and Sheng-Ying, Z. (2005). Clustering-based selective neural network ensemble, Journal of Zhejiang University SCIENCE A. 6(5):387--392.
[30] Schapire, R.E. (1990). The strength of weak learnability, Machine learning. 5(2):197--227. doi:10.1007/BF00116037
[31] Sharkey, A.J. (1999). Multi-net systems, In Combining artificial neural nets, pages 1--30. Springer, 1999. doi:10.1007/978-1-4471-0793-4_1
[32] Singh, R., Kainthola, A., and Singh, T. (2012). Estimation of elastic constant of rocks using an anfis approach, Applied Soft Computing. 12(1):40--45. doi:10.1016/j.asoc.2011.09.010
[33] Siwek, K., Osowski, S., and Szupiluk, R. (2009). Ensemble neural network approach for accurate load forecasting in a power system, International Journal of Applied Mathematics and Computer Science. 19(2):303--315. doi:10.2478/v10006-009-0026-2
[34] Skullestad, A., Olsen, K., Rennehvammen, S., and Floystad, H. (2001). Control of a gravity gradient stabilised satellite using fuzzy logic, Modeling, Identification and Control. 22(3):141--152. doi:10.4173/mic.2001.3.2
[35] Sretenovic, A. (2013). Analysis of energy use at university campus, M. sc. thesis, Norwegian University of Science and Technology, Department of Energy and Process Engineering.
[36] Takagi, T. and Sugeno, M. (1985). Fuzzy identification of systems and its applications to modeling and control, Systems, Man and Cybernetics, IEEE Transactions on. (1):116--132. doi:10.1109/TSMC.1985.6313399
[37] Taylor, J.W. and Buizza, R. (2002). Neural network load forecasting with weather ensemble predictions, Power Systems, IEEE Transactions on. 17(3):626--632. doi:10.1109/MPER.2002.4312413
[38] Tveito, T. (2002). Heating degree-days - present consitions and scenario for the period 2021-2050, 2002.
[39] Wojdyga, K. (2008). An influence of weather conditions on heat demand in district heating systems, Energy and Buildings. 40(11):2009--2014. doi:10.1016/j.enbuild.2008.05.008
[40] Zadeh, L.A. (1994). The role of fuzzy logic in modeling, identification and control, Modeling, identification and control. 15(3):191--203. doi:10.4173/mic.1994.3.9
[41] Zhang, G.P., Berardi, V., etal. (2001). Time series forecasting with neural network ensembles: an application for exchange rate prediction, Journal of the Operational Research Society. 52(6):652--664. doi:10.1057/palgrave.jors.2601133
[42] Zhou, Z.-H., Wu, J., and Tang, W. (2002). Ensembling neural networks: many could be better than all, Artificial intelligence. 137(1):239--263. doi:10.1016/S0004-3702(02)00190-X
[43] Zhou, Z.-H., Wu, J.-x., Tang, W., and Chen, Z.-Q. (2001). Combining regression estimators: Ga-based selective neural network ensemble, International Journal of Computational Intelligence and Applications. 1(04):341--356 doi:10.1142/S1469026801000287

  title={{Various multistage ensembles for prediction of heating energy consumption}},
  author={Jovanovic, Radisa and Sretenovic, Aleksandra},
  journal={Modeling, Identification and Control},
  publisher={Norwegian Society of Automatic Control}


Oct 2018: MIC reaches 3000 DOI Forward Links. The last 1000 took 2 years and 5 months.

May 2016: MIC reaches 2000 DOI Forward Links. The first 1000 took 34 years, the next 1000 took 2.5 years.

July 2015: MIC's new impact factor is now 0.778. The number of papers published in 2014 was 21 compared to 15 in 2013, which partially explains the small decrease in impact factor.

Aug 2014: For the 3rd year in a row MIC's impact factor increases. It is now 0.826.

Dec 2013: New database-driven web-design enabling extended statistics. Article number 500 is published and MIC reaches 1000 DOI Forward Links.

Jan 2012: Follow MIC on your smartphone by using the RSS feed.


July 2011: MIC passes 1000 ISI Web of Science citations.

Mar 2010: MIC is now indexed by DOAJ and has received the Sparc Seal seal for open access journals.

Dec 2009: A MIC group is created at LinkedIn and Twitter.

Oct 2009: MIC is now fully updated in ISI Web of Knowledge.