Toggle Main Menu Toggle Search

ePrints

Empirical and Analytical Evaluation of Systems with Multiple Unreliable Servers

Lookup NU author(s): Dr Jennie Palmer, Emeritus Professor Isi Mitrani

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


Abstract

We construct, analyze and solve models of systems where a number of servers offer services to an incoming stream of demands. Each server goes through alternating periods of being operative and inoperative. The objective is to evaluate and optimize performance and cost metrics. A large real-life data set containing information about server breakdowns is analyzed first. The results indicate that the durations of the operative periods are not distributed exponentially. However, hyperexponential distributions are found to be a good fit for the observed data. A model based on these distributions is then formulated, and is solved exactly using the method of spectral expansion. A simple approximation which is accurate for heavily loaded systems is also proposed. The results of a number of numerical experiments are reported.


Publication metadata

Author(s): Palmer J, Mitrani I

Publication type: Conference Proceedings (inc. Abstract)

Conference Name: International Conference on Dependable Systems and Networks (DSN)

Year of Conference: 2006

Pages: 517-525

Publisher: IEEE Computer Society

URL: http://dx.doi.org/10.1109/DSN.2006.32

DOI: 10.1109/DSN.2006.32

Library holdings: Search Newcastle University Library for this item

ISBN: 0769526071


Actions

Link to this publication


Share