A new hybrid network traffic prediction method

Lin Xiang; Xiao H. Ge; Chuang Liu; Lei Shu; Cheng Xiang Wang

doi:10.1109/GLOCOM.2010.5684249

A new hybrid network traffic prediction method

Lin Xiang, Xiao H. Ge, Chuang Liu, Lei Shu, Cheng Xiang Wang

School of Engineering & Physical Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

27 Citations (Scopus)

Abstract

How to predict the self-similar network traffic with high burstiness is a great challenge for network management. The covariation orthogonal prediction could effectively capture the burstiness in the network traffic, and the artificial neural network prediction could adapt the network traffic change by self-learning. To improve the prediction accuracy, we propose a new hybrid network traffic prediction method based on the combination of the covariation orthogonal prediction and the artificial neural network prediction. Through empirical study, the accuracy of the new prediction method can be effectively improved seen from the mean and the prediction error. ©2010 IEEE.

Original language	English
Title of host publication	2010 IEEE Global Telecommunications Conference, GLOBECOM 2010
DOIs	https://doi.org/10.1109/GLOCOM.2010.5684249
Publication status	Published - 2010
Event	53rd IEEE Global Communications Conference 2010 - Miami, FL, United States Duration: 6 Dec 2010 → 10 Dec 2010

Conference

Conference	53rd IEEE Global Communications Conference 2010
Abbreviated title	GLOBECOM 2010
Country/Territory	United States
City	Miami, FL
Period	6/12/10 → 10/12/10

Keywords

Artificial Neural Networks (ANNs)
Burstiness
Covariation Orthogonal (CO)
Self-similarity
Traffic prediction

Access to Document

10.1109/GLOCOM.2010.5684249

Cite this

@inproceedings{09ddf1479f7e424d80c6c070ac998544,

title = "A new hybrid network traffic prediction method",

abstract = "How to predict the self-similar network traffic with high burstiness is a great challenge for network management. The covariation orthogonal prediction could effectively capture the burstiness in the network traffic, and the artificial neural network prediction could adapt the network traffic change by self-learning. To improve the prediction accuracy, we propose a new hybrid network traffic prediction method based on the combination of the covariation orthogonal prediction and the artificial neural network prediction. Through empirical study, the accuracy of the new prediction method can be effectively improved seen from the mean and the prediction error. {\textcopyright}2010 IEEE.",

keywords = "Artificial Neural Networks (ANNs), Burstiness, Covariation Orthogonal (CO), Self-similarity, Traffic prediction",

author = "Lin Xiang and Ge, {Xiao H.} and Chuang Liu and Lei Shu and Wang, {Cheng Xiang}",

year = "2010",

doi = "10.1109/GLOCOM.2010.5684249",

language = "English",

isbn = "9781424456383",

booktitle = "2010 IEEE Global Telecommunications Conference, GLOBECOM 2010",

note = "53rd IEEE Global Communications Conference 2010, GLOBECOM 2010 ; Conference date: 06-12-2010 Through 10-12-2010",

}

TY - GEN

T1 - A new hybrid network traffic prediction method

AU - Xiang, Lin

AU - Ge, Xiao H.

AU - Liu, Chuang

AU - Shu, Lei

AU - Wang, Cheng Xiang

PY - 2010

Y1 - 2010

N2 - How to predict the self-similar network traffic with high burstiness is a great challenge for network management. The covariation orthogonal prediction could effectively capture the burstiness in the network traffic, and the artificial neural network prediction could adapt the network traffic change by self-learning. To improve the prediction accuracy, we propose a new hybrid network traffic prediction method based on the combination of the covariation orthogonal prediction and the artificial neural network prediction. Through empirical study, the accuracy of the new prediction method can be effectively improved seen from the mean and the prediction error. ©2010 IEEE.

AB - How to predict the self-similar network traffic with high burstiness is a great challenge for network management. The covariation orthogonal prediction could effectively capture the burstiness in the network traffic, and the artificial neural network prediction could adapt the network traffic change by self-learning. To improve the prediction accuracy, we propose a new hybrid network traffic prediction method based on the combination of the covariation orthogonal prediction and the artificial neural network prediction. Through empirical study, the accuracy of the new prediction method can be effectively improved seen from the mean and the prediction error. ©2010 IEEE.

KW - Artificial Neural Networks (ANNs)

KW - Burstiness

KW - Covariation Orthogonal (CO)

KW - Self-similarity

KW - Traffic prediction

U2 - 10.1109/GLOCOM.2010.5684249

DO - 10.1109/GLOCOM.2010.5684249

M3 - Conference contribution

SN - 9781424456383

BT - 2010 IEEE Global Telecommunications Conference, GLOBECOM 2010

T2 - 53rd IEEE Global Communications Conference 2010

Y2 - 6 December 2010 through 10 December 2010

ER -

A new hybrid network traffic prediction method

Abstract

Conference

Keywords

Access to Document

Fingerprint

Cite this