Equivalent bandwidth characterization for real-time CAC in ATM networks

Many call admission control schemes for ATM-type networks are based on the concept of eeective bandwidth (EB). Most such schemes focus on the cell loss rate as the exclusive QoS metric and therefore base their EB on cell-loss rate approximations. We use simulation data to train an adaptive logic network (ALN) to estimate cell loss and delay; these estimates can then be used to compute eeective bandwidths to satisfy both cell loss and delay. The simulation data is also used to develop regression models for cell loss and delay. We compare the accuracy of the ALN and regression models with that of the well-known uid-ow model by Anick et al. Results indicate that the ALN and regression models are computationally simple and suuciently accurate for practical use.