Multistep ahead prediction for real-time VBR video traffic using deterministic echo state network

Xiaochuan Sun; Hongyan Cui; Renping Liu; Jianya Chen; Yunjie Liu

doi:10.1109/CCIS.2012.6664312

Multistep ahead prediction for real-time VBR video traffic using deterministic echo state network

Xiaochuan Sun, Hongyan Cui, Renping Liu, Jianya Chen, Yunjie Liu

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

5 Citations (Scopus)

Abstract

Variable bit rate (VBR) video traffic, exhibiting high self-similarity and burstiness, has been a major traffic component in high speed network. However, its complex bit rate distribution makes VBR video traffic prediction, especially multistep ahead prediction, very difficult. Recently, deterministic echo state network with adjacent-feedback loop reservoir structure (ALR) was proved to have high prediction accuracy, good memory capacity, and simple structure. In the paper, we apply ALR to real-time VBR video traffic prediction. The proposed scheme makes use of loop reservoir with identity activation function to conduct sample learning in high dimension states. Experimental results show that the simplified ALR scheme can effectively capture dynamic characteristics of VBR video traffic with less training time. Its multistep prediction accuracy is improved by 2% on average, compared with the neural network based on multi-resolution learning.

Original language	English
Title of host publication	CCIS 2012
Subtitle of host publication	Proceedings of the 2012 IEEE 2nd International Conference on Cloud Computing and Intelligence Systems
Place of Publication	Piscataway, NJ
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	928-931
Number of pages	4
ISBN (Electronic)	9781467318570, 9781467318556
ISBN (Print)	9781467318563
DOIs	https://doi.org/10.1109/CCIS.2012.6664312
Publication status	Published - 2012
Externally published	Yes
Event	2012 2nd IEEE International Conference on Cloud Computing and Intelligence Systems, IEEE CCIS 2012 - Hangzhou, China Duration: 30 Oct 2012 → 1 Nov 2012

Other

Other	2012 2nd IEEE International Conference on Cloud Computing and Intelligence Systems, IEEE CCIS 2012
Country/Territory	China
City	Hangzhou
Period	30/10/12 → 1/11/12

Keywords

Burstiness
Echo state network
Loop reservoir
Self-similarity
VBR video traffic

Access to Document

10.1109/CCIS.2012.6664312

Cite this

Sun, X., Cui, H., Liu, R., Chen, J., & Liu, Y. (2012). Multistep ahead prediction for real-time VBR video traffic using deterministic echo state network. In CCIS 2012: Proceedings of the 2012 IEEE 2nd International Conference on Cloud Computing and Intelligence Systems (pp. 928-931). Institute of Electrical and Electronics Engineers (IEEE). https://doi.org/10.1109/CCIS.2012.6664312

@inproceedings{138112be58dd45afbc64e5a747ec8e6b,

title = "Multistep ahead prediction for real-time VBR video traffic using deterministic echo state network",

abstract = "Variable bit rate (VBR) video traffic, exhibiting high self-similarity and burstiness, has been a major traffic component in high speed network. However, its complex bit rate distribution makes VBR video traffic prediction, especially multistep ahead prediction, very difficult. Recently, deterministic echo state network with adjacent-feedback loop reservoir structure (ALR) was proved to have high prediction accuracy, good memory capacity, and simple structure. In the paper, we apply ALR to real-time VBR video traffic prediction. The proposed scheme makes use of loop reservoir with identity activation function to conduct sample learning in high dimension states. Experimental results show that the simplified ALR scheme can effectively capture dynamic characteristics of VBR video traffic with less training time. Its multistep prediction accuracy is improved by 2% on average, compared with the neural network based on multi-resolution learning.",

keywords = "Burstiness, Echo state network, Loop reservoir, Self-similarity, VBR video traffic",

author = "Xiaochuan Sun and Hongyan Cui and Renping Liu and Jianya Chen and Yunjie Liu",

year = "2012",

doi = "10.1109/CCIS.2012.6664312",

language = "English",

isbn = "9781467318563",

pages = "928--931",

booktitle = "CCIS 2012",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "2012 2nd IEEE International Conference on Cloud Computing and Intelligence Systems, IEEE CCIS 2012 ; Conference date: 30-10-2012 Through 01-11-2012",

}

Sun, X, Cui, H, Liu, R, Chen, J & Liu, Y 2012, Multistep ahead prediction for real-time VBR video traffic using deterministic echo state network. in CCIS 2012: Proceedings of the 2012 IEEE 2nd International Conference on Cloud Computing and Intelligence Systems. Institute of Electrical and Electronics Engineers (IEEE), Piscataway, NJ, pp. 928-931, 2012 2nd IEEE International Conference on Cloud Computing and Intelligence Systems, IEEE CCIS 2012, Hangzhou, China, 30/10/12. https://doi.org/10.1109/CCIS.2012.6664312

Multistep ahead prediction for real-time VBR video traffic using deterministic echo state network. / Sun, Xiaochuan; Cui, Hongyan; Liu, Renping et al.
CCIS 2012: Proceedings of the 2012 IEEE 2nd International Conference on Cloud Computing and Intelligence Systems. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE), 2012. p. 928-931.

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

TY - GEN

T1 - Multistep ahead prediction for real-time VBR video traffic using deterministic echo state network

AU - Sun, Xiaochuan

AU - Cui, Hongyan

AU - Liu, Renping

AU - Chen, Jianya

AU - Liu, Yunjie

PY - 2012

Y1 - 2012

N2 - Variable bit rate (VBR) video traffic, exhibiting high self-similarity and burstiness, has been a major traffic component in high speed network. However, its complex bit rate distribution makes VBR video traffic prediction, especially multistep ahead prediction, very difficult. Recently, deterministic echo state network with adjacent-feedback loop reservoir structure (ALR) was proved to have high prediction accuracy, good memory capacity, and simple structure. In the paper, we apply ALR to real-time VBR video traffic prediction. The proposed scheme makes use of loop reservoir with identity activation function to conduct sample learning in high dimension states. Experimental results show that the simplified ALR scheme can effectively capture dynamic characteristics of VBR video traffic with less training time. Its multistep prediction accuracy is improved by 2% on average, compared with the neural network based on multi-resolution learning.

AB - Variable bit rate (VBR) video traffic, exhibiting high self-similarity and burstiness, has been a major traffic component in high speed network. However, its complex bit rate distribution makes VBR video traffic prediction, especially multistep ahead prediction, very difficult. Recently, deterministic echo state network with adjacent-feedback loop reservoir structure (ALR) was proved to have high prediction accuracy, good memory capacity, and simple structure. In the paper, we apply ALR to real-time VBR video traffic prediction. The proposed scheme makes use of loop reservoir with identity activation function to conduct sample learning in high dimension states. Experimental results show that the simplified ALR scheme can effectively capture dynamic characteristics of VBR video traffic with less training time. Its multistep prediction accuracy is improved by 2% on average, compared with the neural network based on multi-resolution learning.

KW - Burstiness

KW - Echo state network

KW - Loop reservoir

KW - Self-similarity

KW - VBR video traffic

UR - http://www.scopus.com/inward/record.url?scp=84890331940&partnerID=8YFLogxK

U2 - 10.1109/CCIS.2012.6664312

DO - 10.1109/CCIS.2012.6664312

M3 - Conference proceeding contribution

AN - SCOPUS:84890331940

SN - 9781467318563

SP - 928

EP - 931

BT - CCIS 2012

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Piscataway, NJ

T2 - 2012 2nd IEEE International Conference on Cloud Computing and Intelligence Systems, IEEE CCIS 2012

Y2 - 30 October 2012 through 1 November 2012

ER -

Sun X, Cui H, Liu R, Chen J, Liu Y. Multistep ahead prediction for real-time VBR video traffic using deterministic echo state network. In CCIS 2012: Proceedings of the 2012 IEEE 2nd International Conference on Cloud Computing and Intelligence Systems. Piscataway, NJ: Institute of Electrical and Electronics Engineers (IEEE). 2012. p. 928-931 doi: 10.1109/CCIS.2012.6664312

Multistep ahead prediction for real-time VBR video traffic using deterministic echo state network

Abstract

Other

Keywords

Access to Document

Other files and links

Fingerprint

Cite this