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

Qiong Li; Qinglin Meng; Jiejin Cai; Hiroshi Yoshino; Akashi Mochida

doi:10.1016/j.apenergy.2008.11.035

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

Qiong Li, Qinglin Meng, Jiejin Cai, Hiroshi Yoshino, Akashi Mochida

Research output: Contribution to journal › Article › peer-review

258 Citations (Scopus)

Abstract

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.

Original language	English
Pages (from-to)	2249-2256
Number of pages	8
Journal	Applied Energy
Volume	86
Issue number	10
DOIs	https://doi.org/10.1016/j.apenergy.2008.11.035
Publication status	Published - 2009 Oct

Keywords

Artificial neural network
Building
Cooling load
Prediction
Support vector machine

ASJC Scopus subject areas

Building and Construction
Energy(all)
Mechanical Engineering
Management, Monitoring, Policy and Law

Access to Document

10.1016/j.apenergy.2008.11.035

Fingerprint Dive into the research topics of 'Applying support vector machine to predict hourly cooling load in the building'. Together they form a unique fingerprint.

Cite this

@article{35f8204acfa642bd9da5905dc16a8dfd,

title = "Applying support vector machine to predict hourly cooling load in the building",

abstract = "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.",

keywords = "Artificial neural network, Building, Cooling load, Prediction, Support vector machine",

author = "Qiong Li and Qinglin Meng and Jiejin Cai and Hiroshi Yoshino and Akashi Mochida",

year = "2009",

month = oct,

doi = "10.1016/j.apenergy.2008.11.035",

language = "English",

volume = "86",

pages = "2249--2256",

journal = "Applied Energy",

issn = "0306-2619",

publisher = "Elsevier BV",

number = "10",

}

TY - JOUR

T1 - Applying support vector machine to predict hourly cooling load in the building

AU - Li, Qiong

AU - Meng, Qinglin

AU - Cai, Jiejin

AU - Yoshino, Hiroshi

AU - Mochida, Akashi

PY - 2009/10

Y1 - 2009/10

N2 - 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.

AB - 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.

KW - Artificial neural network

KW - Building

KW - Cooling load

KW - Prediction

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=64849083683&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=64849083683&partnerID=8YFLogxK

U2 - 10.1016/j.apenergy.2008.11.035

DO - 10.1016/j.apenergy.2008.11.035

M3 - Article

AN - SCOPUS:64849083683

VL - 86

SP - 2249

EP - 2256

JO - Applied Energy

JF - Applied Energy

SN - 0306-2619

IS - 10

ER -