In this paper we present a queueing model for the performance a-na-ly-sis of ABR traffic in ATM networks. We consider a multi-channel service station with two types of customers, the first having preemptive priority over the second. The arrivals occur according to two independent Poisson processes and the service times are assumed to be exponentially distributed. Each type-1 customer requires a single server, whereas type-2 customers are served in processor sharing fashion. We give a complete characterization of the joint distribution of the numbers of customers (of both types) in the system in steady state. Numerical results illustrate the effect of the high priority traffic on the service performance of the low priority traffic.

Queueing theory (msc 60K25), Performance evaluation; queueing; scheduling (msc 68M20), Operations research and management science (msc 90Bxx), Queues and service (msc 90B22)
Department of Operations Research, Statistics, and System Theory [BS]
Combinatorial Optimization and Algorithmics

Núñez Queija, R, & Boxma, O.J. (1996). Analysis of a multi-server queueing model of ABR. Department of Operations Research, Statistics, and System Theory [BS]. CWI.