The sticky buffer flow control for the ATM

Abstract

Data from different applications - voice, video, file transfer, interactive - will be multiplexed in the future over broadband integrated services digital networks (BISDN). Data are segmented into 48-byte blocks prefixed by a 5-byte header and transported over the network using the asynchronous transfer mode (ATM). An ATM connection-request is a contract between the user and the network; the user specifies a rate requirement, delay constraints, a bound on the cell-loss probability and other quality of service parameters. If the network can meet these requirements, a connection is made. Bursty traffic producing peak traffic rates in excess of the projected average rate could result in congestion and lead to performance degradation. As a result, the network might no longer be able to deliver the negotiated quality of service to existing connections. To lessen the chance of congestion, input rate control must be implemented. This paper contains a performance analysis of the sticky buffer (SB), a moving window input rate control scheme intended to limit the rate at which input traffic may enter a network. Policing is achieved by buffering and hence delaying the entry of ATM-cells into the network. The scheme is determined by parameters (R, T) which specify that no more than R ATM-cells are permitted to enter the network in every window of size T cells. We present an exact analysis, deriving the probability generating function of the queue length distribution. A comparison with the leaky bucket is given. Our numerical examples show the required buffer size is comparable to that required by the leaky bucket.