Predicting hourly cooling load in the building: A comparison of support vector machine and different artificial neural networks

This study presents four modeling techniques for the prediction of hourly cooling load in the building. In addition to the traditional back propagation neural network (BPNN), the radial basis function neural network (RBFNN), general regression neural network (GRNN) and support vector machine (SVM) are considered. All the prediction models have been applied to an office building in Guangzhou, China. Evaluation of the prediction accuracy of the four models is based on the root mean square error (RMSE) and mean relative error (MRE). The simulation results demonstrate that the four discussed models can be effective for building cooling load prediction. The SVM and GRNN methods can achieve better accuracy and generalization than the BPNN and RBFNN methods.

[1]  Li-Chih Ying,et al.  Using adaptive network based fuzzy inference system to forecast regional electricity loads , 2008 .

[2]  Ping-Feng Pai,et al.  Forecasting regional electricity load based on recurrent support vector machines with genetic algorithms , 2005 .

[3]  Nor Mariah Adam,et al.  A Simple Approach for Building Cooling Load Estimation , 2005 .

[4]  Omar M. Al-Rabghi,et al.  Utilizing transfer function method for hourly cooling load calculations , 1997 .

[5]  Zhiwei Lian,et al.  Hourly cooling load prediction by a combined forecasting model based on Analytic Hierarchy Process , 2004 .

[6]  Vildan Ok,et al.  A procedure for calculating cooling load due to solar radiation : the shading effects from adjacent or nearby buildings , 1992 .

[7]  Jan F. Kreider,et al.  Monthly-Averaged Cooling Load Calculations—Residential and Small Commercial Buildings , 1987 .

[8]  Guang-Yi Cao,et al.  Modeling and control of PEMFC based on least squares support vector machines , 2006 .

[9]  Greg Schoenau,et al.  A correlation method for predicting monthly and annual cooling loads in direct gain passive solar heated buildings , 1989 .

[10]  N. K. Bansal,et al.  A comparison of the admittance and Fourier methods for predicting heating/cooling loads , 1986 .

[11]  K. W. Mui,et al.  Cooling load calculations in subtropical climate , 2007 .

[12]  Jin Yang,et al.  On-line building energy prediction using adaptive artificial neural networks , 2005 .

[13]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[14]  Siaw Kiang Chou,et al.  Large building cooling load and energy use estimation , 1997 .

[15]  Abdullatif Ben-Nakhi,et al.  Cooling load prediction for buildings using general regression neural networks , 2004 .

[16]  Khamron Sunat,et al.  Low cost RISC implementation of intelligent ultra fast charger for Ni–Cd battery , 2008 .

[17]  Yasar Islamoglu,et al.  Performance prediction for non-adiabatic capillary tube suction line heat exchanger: an artificial neural network approach , 2005 .

[18]  Donald F. Specht,et al.  A general regression neural network , 1991, IEEE Trans. Neural Networks.

[19]  Soteris A. Kalogirou,et al.  Artificial neural networks in renewable energy systems applications: a review , 2001 .

[20]  Chen Quanshi,et al.  Support vector machine based battery model for electric vehicles , 2006 .

[21]  Jesús M. Zamarreño,et al.  Prediction of hourly energy consumption in buildings based on a feedback artificial neural network , 2005 .

[22]  Caixin Sun,et al.  Dynamic intelligent cleaning model of dirty electric load data , 2008 .

[23]  Jean-Louis Scartezzini,et al.  A simplified correlation method accounting for heating and cooling loads in energy-efficient buildings , 1998 .

[24]  B. Dong,et al.  Applying support vector machines to predict building energy consumption in tropical region , 2005 .

[25]  Alexander J. Smola,et al.  Support Vector Method for Function Approximation, Regression Estimation and Signal Processing , 1996, NIPS.

[26]  Francis W.H. Yik,et al.  Cooling energy evaluation for high-rise residential buildings in Hong Kong , 2005 .