By Topic

Assessing risk in Grids at resource level considering Grid resources as repairable using two state Semi Markov model

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Sangrasi, A. ; Sch. of Comput., Univ. of Leeds, Leeds, UK ; Djemame, K.

Service Level Agreements in Grids improve upon the Best Effort Approach which provides no guarantees for provision of any Quality of Service (QoS) between the End User and the Resource Provider. Risk Assessment in Grids improves upon SLA by provision of Risk information to resource provider. Most of the previous studies of Risk Assessment in Grids work at node level. As a node failure can be a failure of any component such as Disk, CPU, Memory, Software, etcetera, the risk assessment at component level in Grids was introduced. In this work, we propose a Risk Assessment Model at component level while considering Grid resources as repairable. This work can be differentiated from the other works by the fact that the past efforts in Risk Assessment in Grids consider Grid Resources as replaceable rather than repairable. This Semi Markov model relies on the distribution fitting for both time to Failure and Time to Repair, extracted from the Grid Failure data during the data analysis section. By using Grid Failure data, the utilization of this Grid model is demonstrated by providing (Probability of Failure) PoF and (Probability of Repair) PoR values for different components. The experimental results indicate the PoF and PoR behave vary differently with the latter showing considerably times required for repair as compared to expectance of a failure. The risk information provided by this Risk Assessment Model will help Resource provider to use the Grid Resources efficiently and achieve effective scheduling.

Published in:

Digital Ecosystems Technologies (DEST), 2012 6th IEEE International Conference on

Date of Conference:

18-20 June 2012