Study of PSO-SVM Model for Daily Water Demand Prediction

DOI

10.2991/icmmcce-17.2017.78How to use a DOI?

Keywords

Particle swarm optimization; support vector machine; Daily water demand prediction

Abstract

For solving the problem of daily water demand in G city, a method of particle swarm optimization algorithm combined support vector machine (PSO-SVM) is presented. The expansion constant and penalty factor firstly are selected by particle swarm optimization (PSO). Secondly, the historical water demands data are trained by support vector machine (SVM). Finally, the new independent variables are employed to predict water demands in next time. By comparing BP and SVM with this method, the results show that the real and predicted daily water demands errors are less than the other models. Therefore, this method is a effective way to predict daily water demands of city G.

Copyright

© 2017, 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  - Baiyi Jiang
AU  - Tianwei Mu
AU  - Ming Zhao
AU  - Danyu Shen
AU  - Lingping Wang
PY  - 2017/09
DA  - 2017/09
TI  - Study of PSO-SVM Model for Daily Water Demand Prediction
BT  - Proceedings of the 2017 5th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering (ICMMCCE 2017)
PB  - Atlantis Press
SP  - 408
EP  - 413
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmmcce-17.2017.78
DO  - 10.2991/icmmcce-17.2017.78
ID  - Jiang2017/09
ER  -