Source time scale and optimal buffer/bandwidth tradeoff for heterogeneous regulated traffic in a network node

In this paper, we study the problem of resource allocation and control for a network node with regulated traffic. Both guaranteed lossless service and statistical service with small loss probability are considered. We investi gate the relationship between source characteristics and the buffer/bandwid th tradeoff under both services. Our contributions are the following. For g uaranteed lossless service, we find that the optimal resource allocation sc heme suggests that sources sharing a network node with finite bandwidth and buffer space divide into groups according to time scales defined by their leaky-bucket parameters, This time-scale separation determines the manner b y which the buffer and bandwidth resources at the network node are shared a mong the sources. For statistical service with a small loss probability, we present a new approach for estimating the loss probability in a shared buf fer multiplexor using the "extremal" ON-OFF, periodic sources. Under this a pproach, the optimal resource allocation for statistical service is achieve d by maximizing both the benefits of buffering sharing and bandwidth sharin g. The optimal buffer/bandwidth tradeoff is again determined by a timescale separation.