Load Prediction in Communications Network

Lin, K; Simoff, SJ; Prodan, A; Debenham, JK

Load Prediction in Communications Network

Lin, K Simoff, SJ Prodan, A Debenham, JK

Permalink

Publisher:: Institute of Electrical and Electronics Engineers
Publication Type:: Conference Proceeding
Citation:: Proceedings - 2010 International Conference on Information, Networking and Automation (ICINA 2010), 2010, pp. 250 - 255
Issue Date:: 2010-01

Closed Access

	Filename	Description	Size
	2010000461OK.pdf		1.68 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Lin, K	en_US
dc.contributor.author	Simoff, SJ	en_US
dc.contributor.author	Prodan, A	en_US
dc.contributor.author	Debenham, JK	en_US
dc.contributor.editor	Jiang Hui	en_US
dc.date	2010-10-17	en_US
dc.date.issued	2010-01	en_US
dc.identifier.citation	Proceedings - 2010 International Conference on Information, Networking and Automation (ICINA 2010), 2010, pp. 250 - 255	en_US
dc.identifier.isbn	978-1-4244-8106-4	en_US
dc.identifier.uri	http://hdl.handle.net/10453/16205
dc.description.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.	en_US
dc.publisher	Institute of Electrical and Electronics Engineers	en_US
dc.relation.ispartof	Proceedings - 2010 International Conference on Information, Networking and Automation (ICINA 2010)	en_US
dc.relation.ispartof	International Conference on Information, Networking and Automation	en_US
dc.relation.isbasedon	10.1109/ICINA.2010.5636395	en_US
dc.title	Load Prediction in Communications Network	en_US
dc.type	Conference Proceeding
utslib.location	Piscataway, NJ, USA	en_US
utslib.location.activity	Kunming, China	en_US
utslib.for	080503 Networking and Communications	en_US
dc.location.activity	Kunming, China	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Software
pubs.organisational-group	/University of Technology Sydney/Strength - AAI - Advanced Analytics Institute Research Centre
utslib.copyright.status	closed_access
pubs.consider-herdc	true	en_US
pubs.place-of-publication	Piscataway, NJ, USA	en_US
pubs.start-date	2010-10-17	en_US

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.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/16205