Scheduled System Maintenance:
Some services will be unavailable Sunday, March 29th through Monday, March 30th. We apologize for the inconvenience.
By Topic

A Prefetching-based Replication Algorithm in Data Grid

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.

The purchase and pricing options are temporarily unavailable. Please try again later.
4 Author(s)
Tian Tian ; Sch. of Comput. Sci. & Eng., Southeast Univ., Nanjing ; Junzhou Luo ; Zhiang Wu ; Aibo Song

Replica value determination plays an important role in the problem of replication in data grid, since only replicating high value replicas can improve the replication efficiency. However, replica value determination methods applied now do not perform well, because they cannot well adapt to the changes of file access patterns. We address this problem by introducing a new replica value determination method through data mining, and based on this method we propose a prefetching-based replication algorithm in a virtual organization (VO) environment in order to carry out a better replication optimization. The major idea of this algorithm is to make use of the characteristic that members in a VO have similar interests of file. Experiments show that compared with traditional replication algorithms our new replication algorithm shows better performance and efficiency in data grid.

Published in:

Pervasive Computing and Applications, 2008. ICPCA 2008. Third International Conference on  (Volume:1 )

Date of Conference:

6-8 Oct. 2008