Powered by OpenAIRE graph
Found an issue? Give us feedback
addClaim

Generalization of the Pollaczek-Khinchin formula for throughput analysis of input-buffered switches

Authors: Cheng-Shang Chang; Duan-Shin Lee; Chao-Lin Yu;

Generalization of the Pollaczek-Khinchin formula for throughput analysis of input-buffered switches

Abstract

Many switch architectures with buffers placed at input ports suffer from the head-of-line blocking (HOL) problem and thus can not achieve 100% throughput. For an input-buffered switch, the number of HOL packets is often characterized by the Lindley equation for a discrete-time queue, i.e. q(t+1)=(q(t)-F)/sup +/+a(t), where q(t) is the number of HOL packets at time t, a(t) is the number of new HOL packets at time t, and F is the maximum number of HOL packets that can depart per unit of time. As the total number of HOL packets is bounded in a switch, it places an upper limit on the expected number of HOL packets. Thus, the maximum throughput is the utilization that makes the expected HOL packets equal to the upper limit. For the case with F=1, the expected number of HOL packets can be found via the Pollaczek-Khinchin formula and the maximum throughput can be solved by a quadratic equation as reported in [M.J. Karol et al. (1987), C. Kolias et al. (1996), G. Thomas (1997)]. One of the main contributions of this paper is that we derive a generalized Pollaczek-Khinchin formula for the case F>1. Such a formula is then used for finding the maximum throughput of several input-buffered switches. For the case F/spl Gt/1, numerical computation of the maximum throughput becomes difficult. For large F, we present several bounds and approximations for the throughput. Numerical studies and simulation results confirm that our approximation methods work well.

Related Organizations
  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    1
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
1
Average
Average
Average
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!