A measurement-based admission control algorithm using variable-sized window in ATM networks

The decisions of Connection Admission in ATM networks should be made in real time through the use of fast algorithm. Since it is difficult to construct an accurate model for the multiplexed traffic, approximation of the multiplexed load is necessary. In this paper, we focus on a dynamic CAC (Connection Admission Control) algorithm as a different approach, in which admission control decisions are made based on network measurements. The algorithm observes the traffic through a moving window and the window size is recomputed from the measured cell loss amount. Unlike analytic modeling, the proposed method is based on the measurements of the network load over a period that is long enough to reflect the current traffic behavior. This approach also makes is possible to reallocate network resources (bandwidth and buffers) for multiple traffic classes. The performance of the proposed method is analyzed by means of simulated tests. As will be seen in the simulation results, this approach enables us to achieve a high level of bandwidth utilization and can be easily implemented for real-time admission control while still reliably keeping the cell loss ratio below a certain level.