March 2013 Heavy tails in queueing systems: impact of parallelism on tail performance
Bo Jiang, Jian Tan, Wei Wei, Ness Shroff, Don Towsley
Author Affiliations +
J. Appl. Probab. 50(1): 127-150 (March 2013). DOI: 10.1239/jap/1363784429

Abstract

In this paper we quantify the efficiency of parallelism in systems that are prone to failures and exhibit power law processing delays. We characterize the performance of two prototype schemes of parallelism, redundant and split, in terms of both the power law exponent and exact asymptotics of the delay distribution tail. We also develop the optimal splitting scheme which ensures that split always outperforms redundant.

Citation

Download Citation

Bo Jiang. Jian Tan. Wei Wei. Ness Shroff. Don Towsley. "Heavy tails in queueing systems: impact of parallelism on tail performance." J. Appl. Probab. 50 (1) 127 - 150, March 2013. https://doi.org/10.1239/jap/1363784429

Information

Published: March 2013
First available in Project Euclid: 20 March 2013

zbMATH: 1262.68024
MathSciNet: MR3076777
Digital Object Identifier: 10.1239/jap/1363784429

Subjects:
Primary: 68M20
Secondary: 60G99

Keywords: multipath , parallelism , power law

Rights: Copyright © 2013 Applied Probability Trust

JOURNAL ARTICLE
24 PAGES

This article is only available to subscribers.
It is not available for individual sale.
+ SAVE TO MY LIBRARY

Vol.50 • No. 1 • March 2013
Back to Top