Rate regulation with feedback controller in ATM networks - A neural network approach

Liu, Y-C; Douligeris, C

dc.contributor.author	Liu, Y-C	en
dc.contributor.author	Douligeris, C	en
dc.date.accessioned	2014-03-01T01:46:06Z
dc.date.available	2014-03-01T01:46:06Z
dc.date.issued	1997	en
dc.identifier.issn	07338716	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/24854
dc.subject	Congestion control	en
dc.subject	Feedback controllers	en
dc.subject	Leaky bucket	en
dc.subject	Neural networks	en
dc.subject	Rate regulation	en
dc.subject.other	Backpropagation	en
dc.subject.other	Broadband networks	en
dc.subject.other	Congestion control (communication)	en
dc.subject.other	Feedback control	en
dc.subject.other	Feedforward neural networks	en
dc.subject.other	Learning algorithms	en
dc.subject.other	Network protocols	en
dc.subject.other	Packet switching	en
dc.subject.other	Telecommunication traffic	en
dc.subject.other	Voice/data communication systems	en
dc.subject.other	Cell discarding	en
dc.subject.other	Leaky bucket mechanisms	en
dc.subject.other	Motion picture expert group (MPEG) standard	en
dc.subject.other	Rate regulation	en
dc.subject.other	Asynchronous transfer mode	en
dc.title	Rate regulation with feedback controller in ATM networks - A neural network approach	en
heal.type	journalArticle	en
heal.identifier.primary	10.1109/49.552070	en
heal.identifier.secondary	http://dx.doi.org/10.1109/49.552070	en
heal.publicationDate	1997	en
heal.abstract	In this paper, we propose the use of an artificial neural network (ANN) technique for a rate-based feedback controller in asynchronous transfer mode (ATM) networks. A leaky bucket (LB) mechanism is used to do cell discarding, when the traffic violates a predefined threshold. Since the network cannot rely on the user's compliance with its declared parameters, it is extremely difficult to select the best threshold value and depletion rate for the LB. We propose an ANN model which monitors the status of the LB and predicts the possible cell discarding at the LB in the near future. The source rate is regulated to a certain amount depending on the feedback signal ""strength"" when possible cell discarding is detected. The lower the value carried in the feedback cell, the higher the possibility of cell discarding and, subsequently, the higher the probability that the traffic is regulated to a lower rate. Our model considers the propagation delay time of the feedback signal making our approach more realistic. This mechanism is transparent to the source if the LB is correctly set up and the traffic follows its declared parameters. We use the same trained ANN for different MPEG traces and the results of a simulation study suggest that our mechanisms provide simple and effective traffic management for ATM networks. Cell loss rate due to the congestion shows a two to five times improvement compared with the static approach, while transmission delays introduced by our ANN controller are also smaller than in the static approach. Channel utilization is also improved, showing that our mechanisms provides a better alternative to static feedback controllers.	en
heal.journalName	IEEE Journal on Selected Areas in Communications	en
dc.identifier.doi	10.1109/49.552070	en
dc.identifier.volume	15	en
dc.identifier.issue	2	en
dc.identifier.spage	200	en
dc.identifier.epage	208	en