Effects of Multiple Node Crossing on ATM Traffic Performance

It is commonly recognized that traffic statistics change when a stream of ATM cells crosses several network nodes. In particular, some cells may experience a shorter delay than the previous ones, and thus the peak rate of the traffic stream may increase. In order to control this “cell clumping” effect, on one side spacing techniques have been proposed to restore the original peak rate of the sources at the outlets of each network node, while on the other side bounds to keep into account the peak rate increase have been suggested. Although some contributes have evaluated the effects of multiple node crossing on the distribution of the cell interarrival time, little attention has been paid to the effect of these modifications in terms of cell loss probability. Scope of this paper is to show, by adopting a realistic simulation model, that multiple node crossing produces a negligible effect on cell loss probability, when the admitted traffic is suitably regulated by a connection admission control rule. Moreover, a notable result is that, in the case of large buffers at the network nodes and traffic loads well over the limits imposed by the CAC rule, the per node cell loss probability eventually reduces as network nodes are crossed.