Load prediction in communications network

Kongluan Lin; Simeon Simoff; Ante Prodan; John Debenham

doi:10.1109/ICINA.2010.5636395

Load prediction in communications network

Kongluan Lin, Simeon Simoff, Ante Prodan, John Debenham

School of Computer, Data & Mathematical Sciences

Research output: Chapter in Book / Conference Paper › Conference Paper › peer-review

Abstract

The prediction of load in communications networks provides a scientific basis for conserving power that is currently attracting considerable interest. This paper reports the results of experiments to predict communications network load using real network data. The problem considered is simply to predict whether load is "generally" increasing, decreasing or unchanged in the immediate future. Various linear and non-linear predictive models were investigated. We conclude that the most efficient solution to the problem considered is a subtle combination of a linear regression model and a highly reactive model applied to the data aggregated at two levels of granularity.

Original language	English
Title of host publication	Proceedings of the 2010 International Conference on Information, Networking and Automation (ICINA 2010): 17-19 October, 2010, Kunming, China
Publisher	IEEE
Pages	250-255
Number of pages	6
ISBN (Print)	9781424481040
DOIs	https://doi.org/10.1109/ICINA.2010.5636395
Publication status	Published - 2010
Event	International Conference on Information_Networking and Automation - Duration: 1 Jan 2010 → …

Conference

Conference	International Conference on Information_Networking and Automation
Period	1/01/10 → …

Keywords

forecasting
load
network analysis
telecommunication systems

Access to Document

10.1109/ICINA.2010.5636395

Cite this

@inproceedings{a7a49449077c4fe2a667d9b57dbd5bf0,

title = "Load prediction in communications network",

abstract = "The prediction of load in communications networks provides a scientific basis for conserving power that is currently attracting considerable interest. This paper reports the results of experiments to predict communications network load using real network data. The problem considered is simply to predict whether load is {"}generally{"} increasing, decreasing or unchanged in the immediate future. Various linear and non-linear predictive models were investigated. We conclude that the most efficient solution to the problem considered is a subtle combination of a linear regression model and a highly reactive model applied to the data aggregated at two levels of granularity.",

keywords = "forecasting, load, network analysis, telecommunication systems",

author = "Kongluan Lin and Simeon Simoff and Ante Prodan and John Debenham",

year = "2010",

doi = "10.1109/ICINA.2010.5636395",

language = "English",

isbn = "9781424481040",

pages = "250--255",

booktitle = "Proceedings of the 2010 International Conference on Information, Networking and Automation (ICINA 2010): 17-19 October, 2010, Kunming, China",

publisher = "IEEE",

note = "International Conference on Information_Networking and Automation ; Conference date: 01-01-2010",

}

Lin, K, Simoff, S , Prodan, A & Debenham, J 2010, Load prediction in communications network. in Proceedings of the 2010 International Conference on Information, Networking and Automation (ICINA 2010): 17-19 October, 2010, Kunming, China. IEEE, pp. 250-255, International Conference on Information_Networking and Automation, 1/01/10. https://doi.org/10.1109/ICINA.2010.5636395

TY - GEN

T1 - Load prediction in communications network

AU - Lin, Kongluan

AU - Simoff, Simeon

AU - Prodan, Ante

AU - Debenham, John

PY - 2010

Y1 - 2010

N2 - The prediction of load in communications networks provides a scientific basis for conserving power that is currently attracting considerable interest. This paper reports the results of experiments to predict communications network load using real network data. The problem considered is simply to predict whether load is "generally" increasing, decreasing or unchanged in the immediate future. Various linear and non-linear predictive models were investigated. We conclude that the most efficient solution to the problem considered is a subtle combination of a linear regression model and a highly reactive model applied to the data aggregated at two levels of granularity.

AB - The prediction of load in communications networks provides a scientific basis for conserving power that is currently attracting considerable interest. This paper reports the results of experiments to predict communications network load using real network data. The problem considered is simply to predict whether load is "generally" increasing, decreasing or unchanged in the immediate future. Various linear and non-linear predictive models were investigated. We conclude that the most efficient solution to the problem considered is a subtle combination of a linear regression model and a highly reactive model applied to the data aggregated at two levels of granularity.

KW - forecasting

KW - load

KW - network analysis

KW - telecommunication systems

UR - http://handle.uws.edu.au:8081/1959.7/513001

UR - http://ezproxy.uws.edu.au/login?url=http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=5636395

U2 - 10.1109/ICINA.2010.5636395

DO - 10.1109/ICINA.2010.5636395

M3 - Conference Paper

SN - 9781424481040

SP - 250

EP - 255

BT - Proceedings of the 2010 International Conference on Information, Networking and Automation (ICINA 2010): 17-19 October, 2010, Kunming, China

PB - IEEE

T2 - International Conference on Information_Networking and Automation

Y2 - 1 January 2010

ER -

Load prediction in communications network

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this