Network Traffic Prediction Based on LMD and Neural Network

DOI

10.2991/icmmita-15.2015.72How to use a DOI?

Keywords

network traffic; LMD; wavelet neural network; prediction

Abstract

The network traffic data has a very strong burst and self similarity and so on, which results in the system flow is not stable and inaccurate. The traditional network traffic prediction model is not accurate enough. To solve the above problems, a network traffic prediction model based on local mean decomposition (LMD) and wavelet neural network (WNN) was proposed. The original network traffic data is decomposed into a series product function (PF), which can reflect the fractal characteristic of the network traffic data. The PFs are taken as the input of the WNN to establish the prediction model. In this method, the network traffic prediction model can make full use of the inherent characteristics of the network traffic data, and get more accurate prediction results. Experimental data processing results show that the prediction accuracy of the network traffic prediction model based on LMD and WNN is higher than the traditional models.

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  - Yongsheng Luo
PY  - 2015/11
DA  - 2015/11
TI  - Network Traffic Prediction Based on LMD and Neural Network
BT  - Proceedings of the 2015 3rd International Conference on Machinery, Materials and Information Technology Applications
PB  - Atlantis Press
SP  - 371
EP  - 374
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmita-15.2015.72
DO  - 10.2991/icmmita-15.2015.72
ID  - Luo2015/11
ER  -