Applying support vector machines to predict building energy consumption in tropical region |
| |
| Affiliation: | 1. Department of Building, School of Design and Environment, National University of Singapore, 4 Architecture Drive, 117566 Singapore, Singapore;2. Department of Mechanical Engineering, School of Engineering, National University of Singapore, 9 Engineering Drive, 117596 Singapore, Singapore;1. Department of Construction Management and Real Estate, Shenzhen University, Shenzhen, China;2. Department of Building Services Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong, China;3. Institute of Refrigeration and Cryogenics, Zhejiang University, Hangzhou, China;1. Center for Urban Science & Progress, New York University, 1 MetroTech Center, 19th Floor, Brooklyn, NY 11201, United States;2. Department of Earth and Environmental Engineering, Columbia University, S.W. Mudd Building, 500 West 120th Street, New York, NY 10027, United States;3. Institute for Data Sciences & Engineering, Department of Civil Engineering and Engineering Mechanics, Columbia University, Room 626, S.W. Mudd Building, 500 West 120th Street, New York, NY 10027, United States;4. Department of Civil and Environmental Engineering, Virginia Tech, 113B Patton Hall, Blacksburg, VA 24061, United States;1. Department of Building, School of Design and Environment, National University of Singapore, Singapore;2. Physics Department, Group Building Environmental Research, National and Kapodistrian University of Athens, Athens 15784, Greece;1. Department of Energy Systems and Environment, Ecole des Mines de Nantes, GEPEA, CNRS, UMR 6144, Nantes, France;2. Veolia Recherche et Innovation (VERI), Limay, France;3. Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands |
| |
| Abstract: | The methodology to predict building energy consumption is increasingly important for building energy baseline model development and measurement and verification protocol (MVP). This paper presents support vector machines (SVM), a new neural network algorithm, to forecast building energy consumption in the tropical region. The objective of this paper is to examine the feasibility and applicability of SVM in building load forecasting area. Four commercial buildings in Singapore are selected randomly as case studies. Weather data including monthly mean outdoor dry-bulb temperature (T0), relative humidity (RH) and global solar radiation (GSR) are taken as three input features. Mean monthly landlord utility bills are collected for developing and testing models. In addition, the performance of SVM with respect to two parameters, C and ɛ, was explored using stepwise searching method based on radial-basis function (RBF) kernel. Finally, all prediction results are found to have coefficients of variance (CV) less than 3% and percentage error (%error) within 4%. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
