Measurement‐based admission control for bufferless multiplexers

Abstract

In this paper we study measurement-based admission control for bufferless multiplexing, which is very attractive for real-time traffic. We first discuss a novel large deviations (LD) approach to measurement-based admission control. We then provide an extensive review of the existing literature on measurement-based admission control. We conduct simulation studies with traces of MPEG 1 encoded movies to compare the performance of the admission rules in the literature with that of our large deviations approach. We demonstrate that our LD approach achieves higher link utilizations. Finally, we compare the performance of measurement-based admission control with that of traditional admission control, which relies on a priori traffic descriptors. Our numerical work indicates that measurement-based admission control achieves significant gains in link utilizations over traditional admission control

Hierarchical time-sliced optical burst switching

“…Loss estimates under bufferless fluid approximations have been used extensively in literature (e.g. [23], [24]) for analysing packet switching systems, and are justified in this case given the very small buffering (OTSIs) that core HiTSOBS nodes are likely to have. If N denotes the number of flows multiplexed at the core link, and X the overall arrival rate to the core link at a random instant of time, then X = N i=1 X i .…”

Statistical dealy garantees of VPLS connections over MPLS networks

“…He concluded that only one algorithm among the tested algorithms, the algorithm proposed by [7], achieved acceptable results for the desired loss ratio. Breslau et al [12] used simulation to compare the performance of some of the MBAC algorithms [4,7,11,13,14]-some of these algorithms are studied by Moore as well. They found that all of the algorithms achieve nearly the same link utilization for a given packet loss rate, and that none of them are capable of accurately meeting loss targets including [7].…”

“…Moore [10] presented an implementation-based comparison of several MBAC algorithms [4,5,7,8,11]. He concluded that only one algorithm among the tested algorithms, the algorithm proposed by [7], achieved acceptable results for the desired loss ratio.…”

“…Breslau et al [12] used simulation to compare the performance of some of the MBAC algorithms [4,7,11,13,14]-some of these algorithms are studied by Moore as well. They found that all of the algorithms achieve nearly the same link utilization for a given packet loss rate, and that none of them are capable of accurately meeting loss targets including [7]. The algorithm presented by paper [15] is the only algorithm that uses the statistical multiplexing based on delay measurements.…”

“…Examples of MBAC mechanisms are the algorithms which use the notion of effective bandwidth-a formal definition of effective bandwidth can be found in [3]. Other mechanisms use the Chernoff Bounds [4], the largedeviation theory [5,6], the multiplexed traffic envelop [7], and the statistical analysis such as mean-variance estimators over one time scale [8] or different time scales [9].…”