Title :
Study on operation energy efficiency model of chiller based on SVR
Author :
Yan Jun-wei ; Yu Zhou ; Zhou Xuan
Author_Institution :
Sch. of Mech. & Automotive Eng., South China Univ. of Technol., Guangzhou, China
fDate :
May 31 2014-June 2 2014
Abstract :
Chillers operation energy efficiency is the main factors affecting the efficiency of air conditioning systems. A chillers operation energy efficiency model and its method for a real chiller plant were proposed in this paper, whose parameters were optimized by GA optimization algorithm. Moreover, as R_RMSE (Relative Root Mean Square Error) was adopted as the evaluation of the prediction accuracy, the results showed that the prediction accuracy of SVR model based on GA optimization algorithm was better than other models, which average R_RMSE was 4.52%. The method proposed in this paper can predict the operation energy efficiency of the chiller accurately to provide basic for chiller energy efficiency analysis, fault detection and diagnosis, and optimizing control.
Keywords :
air conditioning; energy conservation; fault diagnosis; genetic algorithms; least mean squares methods; power engineering computing; regression analysis; support vector machines; GA optimization algorithm; R_RMSE; SVR; air conditioning systems; chiller operation energy efficiency model; chiller plant; fault detection; fault diagnosis; optimizing control; relative root mean square error; support vector regression; Accuracy; Atmospheric modeling; Cooling; Data models; Energy efficiency; Optimization; Predictive models; Chiller; Operation Energy Efficiency Model; Support Vector Regression;
Conference_Titel :
Control and Decision Conference (2014 CCDC), The 26th Chinese
Conference_Location :
Changsha
Print_ISBN :
978-1-4799-3707-3
DOI :
10.1109/CCDC.2014.6852932
