Weighted LS-SVM Method for Building Cooling Load Prediction

Abstract:

A number of different forecasting methods have been proposed for cooling load forecasting including historic method, real-time method, time series analysis, and artificial neural networks, but accuracy and time efficiency in prediction are a couple of contradictions to be hard to resolve for building cooling load prediction. In order to improve the prediction accuracy of cooling load time series, weighted least squares support vector machine regression (WLS-SVM) method for a chaotic cooling load prediction is proposed. In this method, a sliding time window is built and data in the sliding time window are employed to reconstruct the dynamic model. Different weights are assigned to different data in the sliding time window, and the model parameters are refreshed on-line with the rolling of the time window. The results show that the method has more superior performance than other methods like LS-SVM.

• Periodical: Advanced Materials Research (Volumes 121-122)
• Pages: 606-612
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.121-122.606
• Online since: June 2010
• Authors: Xue Mei Li, Jia Shu Chen, Li Xing Ding
• Keywords: Cooling Load Prediction, Phase Space Reconstruction, Saving Energy, Support Vector Machine (SVM)

References

[1] Bida M, Kreider JF. Monthly-averaged cooling load calculations-residential and small commercial buildings. J Sol Energy Eng Trans ASME 1987, 109(4): 311-20.

DOI: 10.1115/1.3268223

[2] Vildan Ok. A procedure for calculating cooling load due to solar radiation: the shading effects from adjacent or nearby buildings. Energy Build 1992, 19(1): 11-20.

DOI: 10.1016/0378-7788(92)90032-c

[3] Yao Y, Lian ZW, Liu SQ, Hou ZJ. Hourly cooling load prediction by a combined forecasting model based on analytic hierarchy process. Int J Therm Sci 2004, 43(11): 1107-18.

DOI: 10.1016/j.ijthermalsci.2004.02.009

[4] Hironobu Morita, De-Ping Zhang, Yasuo Tamura, Long-Term Load Forecasting Using Grey System Theory, Electrical Engineering in Japan, 115(2), pp.11-20.

DOI: 10.1002/eej.4391150202

[5] Li Xuemei, Ding Lixing, et al. A Novel Air-Conditioning Load Prediction Based on ARIMA and BPNN Model, Proc. of Asia-Pacific Conference on Information Processing, vol. 1, pp.51-54, (2009).

DOI: 10.1109/apcip.2009.21

[6] M.O. Stitson, J.A.E. Weston, A Gammerman, V. Vork, V. Vapnik, Theory of Support Vector Machines, Technical Report CSD-TR-96-17, Department of Computer Science, Royal Holloway College, University of London, Dec. (1996).

[7] Suykens J A K, De Brabanter J, Lukas L, et al. Weighted least Squares Support Vector Machines: robustness and sparse approximation. Neurocomputing (S0925-2312), 2002, 48(1-4): 85-105.

DOI: 10.1016/s0925-2312(01)00644-0

[8] H.A. David, Early sample measures of variability, Stat. Sci. 13 (1998) 368-377.

[9] P.J. Rousseeuw, A. Leroy, Robust Regression and Outlier Detection, Wiley, New York, (1987).

DOI: 10.1002/0471725382

[10] DeST Development Group in Tsinghua University. Building environmental system simulation and analysis-DeST. Beijing: China Architecture & Building Press, (2006).