Short-term Prediction of Building Energy Consumption Based on GALM Neural Network

DOI

10.2991/ameii-15.2015.161How to use a DOI?

Keywords

Building Energy Consumption; Short-term Prediction; ANN; Genetic Algorithm; Levenberg-Marquardt Algorithm

Abstract

In order to improve the conventional method of predicting building energy consumption using artificial neural networks (ANN), we proposed a novel neural network model to forecast building energy consumption. The model optimized the neural network based on genetic algorithm and Levenberg- Marquardt algorithm Firstly genetic algorithm was used to optimize the weight and threshold of ANN, Secondly Levenberg-Marquardt algorithm (LM) was adopted to optimize the neural network training. Then the predicting model based on the new algorithm was set up in terms of the main factors effecting the energy consumption. Furthermore, a public building electric consumption data for one month is collected to train and test the model. The testing results show that the model is more accurate and efficient than the conventional method in predicting short-term energy consumption.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Bocheng Zhong
AU  - Kuo Lu
AU  - Dinghao Lv
AU  - Jing Luo
AU  - Xuan Fang
PY  - 2015/04
DA  - 2015/04
TI  - Short-term Prediction of Building Energy Consumption Based on GALM Neural Network
BT  - Proceedings of the International Conference on Advances in Mechanical Engineering and Industrial Informatics
PB  - Atlantis Press
SP  - 867
EP  - 871
SN  - 2352-5401
UR  - https://doi.org/10.2991/ameii-15.2015.161
DO  - 10.2991/ameii-15.2015.161
ID  - Zhong2015/04
ER  -