Prediction model of annual energy consumption of residential buildings

Qiong Li Qiong Li,Qinglin Meng Qinglin Meng,Peng Ren Peng Ren

doi:10.1109/icaee.2010.5557576

Qiong Li Qiong Li, Qinglin Meng Qinglin Meng + Show 1 more

https://doi.org/10.1109/icaee.2010.5557576

Copy DOI

Publication Date: Jun 1, 2010

Citations: 34

Affiliation: South China University of Technology

Abstract

Based on the investigation to 59 residential buildings in China, this study establishes the prediction model of annual energy consumption of residential buidlings using four different modeling methods such as support vector machine (SVM), traditional back propagation neural network (BPNN), radial basis function neural network (RBFNN) and general regression neural network (GRNN). The simulation results show that SVM and GRNN methods achieve better accuracy and generalization than BPNN and RBFNN methods, and are effective for prediction of annual building energy consumption.

Full Text