Using Queue Model to Evaluate the Reliability in Cloud Platforms
Author(s) -
Zhichao Liu,
Xiao Ze
Publication year - 2016
Publication title -
international journal of grid and distributed computing
Language(s) - English
Resource type - Journals
eISSN - 2207-6379
pISSN - 2005-4262
DOI - 10.14257/ijgdc.2016.9.10.08
Subject(s) - computer science , queue , cloud computing , reliability (semiconductor) , reliability engineering , computer network , operating system , engineering , power (physics) , physics , quantum mechanics
In recent years, cloud platforms have been widely applied in various areas to provide flexible service for users. However, how to evaluate the reliability of cloud platforms still remains a challenging issue because of its complexity and dynamical characteristic. In this paper, we present a novel reliability evaluation model which is aiming at providing a technique to accurately evaluate the reliability of virtualized cloud platforms. The proposed model is deprived from the classical tree-structure based reliability model and incorporates some new mechanisms to overcome the shortcomings of previous models. Extensive experiments are conducted to investigate the effectiveness of the proposed model. The results shown that, comparing with the existing approaches, the proposed model can significantly improve the accuracy of reliability evaluation, especially when the target cloud platform is in presence of intensive workloads.
Accelerating Research
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom
Address
John Eccles HouseRobert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom