Link-sharing method for ABR/UBR services in ATM networks1This work is currently supported by the R.O.C. Ministry of Economic Affairs under the project No. 3P12200 conducted by ITRI.1

Authors:
Chiung-Shien Wu
Affiliations:
Computer and Communication Research Labs., ITRI, Hsinchu, 310 Taiwan, ROC
Venue:
Computer Communications
Year:
1998

Citing 7
Cited 1

A stop-and-go queueing framework for congestion management

SIGCOMM '90 Proceedings of the ACM symposium on Communications architectures & protocols
VirtualClock: a new traffic control algorithm for packet-switched networks

ACM Transactions on Computer Systems (TOCS)
A generalized processor sharing approach to flow control in integrated services networks: the single-node case

IEEE/ACM Transactions on Networking (TON)
Intelligent congestion control for ABR service in ATM networks

ACM SIGCOMM Computer Communication Review
Allocating fair rates for available bit rate service in ATM networks

IEEE Communications Magazine
RSVP and integrated services in the Internet: a tutorial

IEEE Communications Magazine
A scheme for real-time channel establishment in wide-area networks

IEEE Journal on Selected Areas in Communications

Dynamic traffic scheduling for QoS support in WDM/TDM networks with arbitrary tuning latencies

Optical networks

Quantified Score

Hi-index	0.24

Visualization

Abstract

This paper presents an efficient link-sharing method for available bit rate and unspecified bit rate services in ATM networks. The method comprises an algorithm that performs cell multiplexing and scheduling such that the outgoing link is fairly shared by multiple traffic flows. The proposed algorithm adopts a dynamic priority assignment to each ATM cell, and schedules those cells having the same priority level into repeating cycles in a round-robin fashion. The algorithm also guarantees each ABR connection a specified minimum cell rate and a satisfied cell loss rate. The performance is evaluated through simulations and is also compared with another fixed method called weighted round robin. Finally, a corresponding hardware design that uses a two-stage leaky bucket circuit is presented.