Abstract
Building cooling load prediction is critical to the success of energy-saving measures. While many of the computational models currently available in the industry have been developed for this purpose, most require extensive computer resources and involve lengthy computational processes. Artificial neural networks (ANNs) have recently been adopted for prediction, and pioneering works have confirmed the feasibility of this approach. However, users are required to predetermine an ANN model’s parameters. This hinders the applicability of the ANN approach in actual engineering problems, as most engineers may be unfamiliar with soft computing. This paper proposes a fully autonomous kernel-based neural network (AKNN) model for noisy data regression prediction. No part of the model’s mechanism requires human intervention; rather, it self-organises its structure according to the training samples presented. Unlike the other existing autonomous models, the AKNN model is an online learning model. It is particularly suitable for online steps-ahead prediction. In this paper, we benchmark the AKNN model’s performance according to other ANN models. It is also successfully applied to predicting the cooling load of a commercial building in Hong Kong. The occupancy areas and concentration of carbon dioxide inside the building are successfully adopted to mimic the building’s internal cooling load. Training data was adopted from actual measurements taken inside the building. Its results show reasonable agreement with actual cooling loads.
Similar content being viewed by others
References
Ahmed NA, Gokhale DV (1989) Entropy expression and their estimators for multi-variate distribution. IEEE Trans Inf Theory 35(3):688–692
An SH, Heo G, Chang SH (2011) Detection of process anomalies using an improved statistical learning framework. Expert Syst Appl 38:1356–1363
Bezdek JB (1980) A convergence theorem for the fuzzy ISODATA clustering algorithms. IEEE Trans Pattern Anal Mach Intell PAMI 2:1–8
BLAST (1992) BLAST 3.0 User Manual. BLAST Support Office Department of Mechanical and Industrial Engineering, University of Illinois Urbana-Champaign, USA
Broomhead DS, Lowe D (1988) Multi-variable functional interpolation and adaptive networks. Complex Syst 2:321–355
Cai Z (2001) Weighted Nadaraya–Watson regression estimation. Stat Probab Lett 51:307–318
Cain JB (1990) Improved probabilistic neural network and its performance relative to other models. In: Proceedings of SPIE, Application of Artificial Neural Network, vol 1294, pp 354–364
Carpenter GA, Grossberg S, David BR (1991) Fuzzy ART: fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Netw 4:759–771
Cervellera C, Gaggero M, Macciò D (2012) Efficient kernel models for learning and approximate minimization problems. Neurocomputing 97:74–85
Chen CS, Cheung MY, Wu YW (2012) Seismic assessment of school buildings in Taiwan using the evolutionary support vector machine inference system. Expert Syst Appl 36(4):4102–4110
DOE (2005) DOE release 2.2.2005. Hirsch, J. J. & Associate, Lawrence Berkeley National Laboratory Simulation Research Group, Berkeley, California, USA
EnergyPlus (2011) EnergyPlus Manual Version 7.0. U.S. Department of Energy
Ferreira VH, Alves da Silva AP (2011) Chaos theory applied to input space representation of autonomous neural network-based short-term load forecasting models. Sba Controle & Automação 22(6):585–597
Ferreira VH, Alves da Silva AP (2012) Autonomous kernel based models for short-term load foresting. J Energy Power Eng 6:1984–1993
Freeman JA, Saad D (1997) Dynamics of on-line learning in radial basis function networks. Phys Rev E 56(1):907–918
Kim D, Kim C (1997) Forecasting time series with genetic fuzzy predictor ensemble. IEEE Trans Fuzzy Syst 5(4):523–535
Kitayama S, Kita K, Yamazaki K (2012) Optimization of variable blank holder force trajectory by sequential approximate optimization with RBF network. Int J Adv Manuf Technol 61(9):1067–1083
Kohonen T (1990) The self-organizing map. Proc IEEE 78(9):1464–1480
Kramer O, Gieseke F (2012) Evolutionary kernel density regression. Expert Syst Appl 39:9246–9254
Kreider JF, Rabl A (1994) Heating and cooling of buildings, chap 8. McGraw-Hill, New York
Lee EWM, Lim CP, Yuen RKK, Lo SM (2004) A hybrid neural network model for noisy data regression. IEEE Trans Syst Man Cybern Part B 34(2):951–960
Lee EWM (2011) An incremental adaptive neural network model for online noisy data regression and its application to compartment fire studies. Appl Soft Comput 11:827–836
Lee SH, Kim I (1994) Time series analysis using fuzzy learning. In: Proceedings of International Conference on Neural Information Processing, Seoul, Korea, pp 1577–1582
Lim CP, Harrison RF (1997) An incremental adaptive network for on-line supervised learning and probability estimation. Neural Netw 10(5):925–939
Mackey MC, Glass L (1977) Oscillation and chaos in physiological control systems. Science 197:287–289
Meinicke P, Klanke S, Memisevic R, Ritter H (2005) Principal surfaces from unsupervised kernel regression. IEEE Trans Pattern Anal Mach Intell 27(9):1379–1391
Nadaraya EA (1964) On estimating regression. Theory Probab Appl 9:141–142
Nkayama H, Arakawa M, Sasaki R (2002) Simulation-based optimization using computational intelligence. Optim Eng 3:201–214
Parzen E (1962) On estimation of a probability density function and mode. Annu Math Stat 33:155–167
Rosenblatt F (1962) Principles of neurodynamics. Spartan Books, New York
Saad D, Solla SA (1995) Exact solution for on-line learning in multilayer neural networks. Phys Rev Lett 74(21):4337–4340
Saad D (1998) On-line learning in neural networks. Cambridge University Press, Cambridge
Singh A, Príncipe JC (2011) Information theoretic learning with adaptive kernels. Signal Process 91:203–213
Singh S, Markou M (2004) An approach to novelty detection applied to the classification of image regions. IEEE Trans Knowl Data Eng 16(4):396–407
Soyguder S, Alli H (2009) Predicting of fan speed for energy saving in HVAC system based on adaptive network based fuzzy inference system. Expert Syst Appl 36(4):8631–8638
Specht DF (1991) A general regression neural network. IEEE Trans Neural Netw 2(6):568–576
TRNSYS (2006) TRNSYS 17 Manual Solar Energy Laboratory. University of Wisconsin, Madison, Wisconsin, USA
Watson GS (1964) Smooth regression analysis. Indian J Stat Ser A 26:359–372
Yalcintas M, Akkurt S (2005) Artificial neural networks applications in building energy predictions and a case study for tropical climates. Int J Energy Res 29(10):891–901
Yezioro A, Dong B, Leite F (2008) An applied artificial intelligence approach towards assessing building performance simulation tools. Energy Build 40(4):612–620
Yuen RKK, Lee EWM, Lo SM, Yeoh GH (2006) Prediction of temperature and velocity profiles in a single compartment fire by an improved neural network analysis. Fire Saf J 41(6):478–485
Zhou P, Li D, Wu H, Cheng F (2011) The automatic model selection and variable kernel width for RBF neural networks. Neurocomputing 74:3628–3637
Acknowledgments
This research was fully supported by a grant from the City University of Hong Kong (Project No. 7008028).
Author information
Authors and Affiliations
Corresponding author
Additional information
Communicated by V. Piuri.
Rights and permissions
About this article
Cite this article
Lee, E.W.M., Fung, I.W.H., Tam, V.W.Y. et al. A fully autonomous kernel-based online learning neural network model and its application to building cooling load prediction. Soft Comput 18, 1999–2014 (2014). https://doi.org/10.1007/s00500-013-1181-9
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-013-1181-9