Applying support vector machine to predict hourly cooling load in the building

被引：392

作者：

Li, Qiong ^{[1
,2
]}

Meng, Qinglin ^{[1
]}

Cai, Jiejin ^{[3
]}

Yoshino, Hiroshi ^{[2
]}

Mochida, Akashi ^{[2
]}

机构：

[1] S China Univ Technol, Bldg Environm & Energy Lab, State Key Lab Subtrop Bldg Sci, Guangzhou 510640, Guangdong, Peoples R China

[2] Tohoku Univ, Grad Sch Engn, Sendai, Miyagi 9808579, Japan

[3] Univ Tokyo, Sch Engn, Tokyo 1138656, Japan

来源：

APPLIED ENERGY | 2009年 / 86卷 / 10期

基金：

中国国家自然科学基金;

关键词：

Support vector machine; Building; Cooling load; Prediction; Artificial neural network; HIGHRISE RESIDENTIAL BUILDINGS; ENERGY-CONSUMPTION; PARAMETERS; EFFICIENCY;

D O I：

10.1016/j.apenergy.2008.11.035

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

080707 [能源环境工程]; 082001 [油气井工程];

摘要：

In this paper, support vector machine (SVM) is used to predict hourly building cooling load. The hourly building cooling load prediction model based on SVM has been established, and applied to an office building in Guangzhou, China. The simulation results demonstrate that the SVM method can achieve better accuracy and generalization than the traditional back-propagation (BP) neural network model, and it is effective for building cooling load prediction. (C) 2008 Elsevier Ltd. All rights reserved.

引用

页码：2249 / 2256

页数：8

共 40 条

[1]

[Anonymous], 2001, HKIE T

[2]

[Anonymous], 1981, ASHRAE T

[3]

[Anonymous], 2006, BUILDING ENV SYSTEM

[4]

[Anonymous], INFLUENCE PURITY COP