Abstract—Data grid provides scalable infrastructure for storage resource and data files management, which supports several scientific applications. Replication is a technique used in data grid to increase the files availability, to improve the access time and to reduce the bandwidth consumption. An important problem to be addressed is when replication should be trigged (called period). The period has an important effect on the effectiveness of the replication strategy. In this paper, we propose a model for managing the dynamic period. The proposed model automatically adapts to the grid behavior. We also evaluate the performance of the proposed period using the OptorSim simulator [1]. Our obtained results show that the dynamic period is more effective than the static period.
Index Terms—Data grid, dynamic period, optorsim, replication.
The authors are with Department of Computer Sciences at the Faculty of Sciences of Tunis, Tunisia (e-mail: f.charrada@gnet.tn, habib.ounelli@fst.rnu.tn, hanene1ch@gmail.com).
[PDF]
Cite:Faouzi Ben Charrada, Habib Ounelli, and Hanène Chettaoui, "A Model for Dynamic Period in Data Grid Replication," International Journal of Modeling and Optimization vol. 3, no. 2, pp. 163-166, 2013.