The use of learning algorithms in ATM networks call admission control problem: a methodology

Atlasis, AF; Loukas, NH; Vasilakos, AV

dc.contributor.author	Atlasis, AF	en
dc.contributor.author	Loukas, NH	en
dc.contributor.author	Vasilakos, AV	en
dc.date.accessioned	2014-03-01T01:15:56Z
dc.date.available	2014-03-01T01:15:56Z
dc.date.issued	2000	en
dc.identifier.issn	1389-1286	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/13835
dc.subject	ATM	en
dc.subject	call admission control	en
dc.subject	equivalent bandwidth	en
dc.subject	quality of service	en
dc.subject	learning automaton	en
dc.subject.classification	Computer Science, Hardware & Architecture	en
dc.subject.classification	Computer Science, Information Systems	en
dc.subject.classification	Engineering, Electrical & Electronic	en
dc.subject.classification	Telecommunications	en
dc.subject.other	BANDWIDTH	en
dc.subject.other	SCHEMES	en
dc.title	The use of learning algorithms in ATM networks call admission control problem: a methodology	en
heal.type	journalArticle	en
heal.identifier.primary	10.1016/S1389-1286(00)00090-6	en
heal.identifier.secondary	http://dx.doi.org/10.1016/S1389-1286(00)00090-6	en
heal.language	English	en
heal.publicationDate	2000	en
heal.abstract	Call Admission Control (CAC) is one of the most fundamental preventive congestion control mechanisms in Asynchronous Transfer Mode (ATM) networks. Several mathematical approaches that have been proposed in the literature, which usually estimate the equivalent bandwidth that is required, achieve conservative approximations that result in reduced statistical gain and thus, in under-utilisation of the network resources. In this study, a new methodology is proposed which uses a Learning Automaton (LA) in combination with equivalent bandwidth approximations to reduce the percentage of overestimation. The learning algorithm that is used attempts to predict in real-time if a call-request should be accepted or not receiving as feedback a function of an estimate of the equivalent bandwidth. As will be shown, the proposed mechanism, whose hardware implementation is feasible, exhibits remarkable statistical gain compared with some classical CAC schemes of the literature and distinct improvement of the equivalent bandwidth approximations, Finally, some issues for extending this work are also discussed. (C) 2000 Elsevier Science B.V. All rights reserved.	en
heal.publisher	ELSEVIER SCIENCE BV	en
heal.journalName	COMPUTER NETWORKS-THE INTERNATIONAL JOURNAL OF COMPUTER AND TELECOMMUNICATIONS NETWORKING	en
dc.identifier.doi	10.1016/S1389-1286(00)00090-6	en
dc.identifier.isi	ISI:000088894100001	en
dc.identifier.volume	34	en
dc.identifier.issue	3	en
dc.identifier.spage	341	en
dc.identifier.epage	353	en