CALL ESTABLISHMENT OVERLOAD IN LARGER ATM NETWORKS

The call establishment process in asynchronous transfer mode (ATM) net works can constitute a source of overload in the switches of the netwo rk. The purpose of this paper is to use analytic modeling and simulati on to investigate this effect. The call establishment overload can be particularly significant when the network will contain a relatively la rge number of switches, due to the inaccuracy of the information avail able to the switch accepting or rejecting the call, and because of the multiple paths which need to be assessed and then utilized to establi sh the call. We simulate the call set-up phase of an ATM connection, i ncluding path selection, bandwidth reservation and call rejection, and simulate the dow of call establishment messages to estimate by simula tion and analytically the queue lengths of call establishment processi ng at the input, output and intermediate switches. Average usage of ba ndwidth at the links, and the probability that a call request is rejec ted due to insufficient capacity at some link, are measured via simula tion and also predicted using an analytical model. Simulation results show that if bandwidth is not reserved at input nodes, very large queu es of call establishment jobs can build up in the switches of the netw ork. A simplified analytical model is derived to estimate the queue le ngths of call establishment jobs at each node of the network when adva nced reservation with perfect information is implemented. Simulation r esults are compared to approximate model predictions for each individu al switching node in a 100-node (switch) ATM network model. It is show n that the analytical model dealing with a large ATM network can quali tatively predict the locations of queue build-up of jobs for call esta blishment processing, with accurate queue length predictions for being made in the case of light traffic load. The analytical model provides a lower bound to queue lengths, and remains within the same order of magnitude when the call request traffic is high. (C) 1997 Elsevier Sci ence B.V.