Future Generation Computer Systems - Special issue on metacomputing
HTTP redirection for replica catalogue lookups in data grids
Proceedings of the 2002 ACM symposium on Applied computing
Random Processes: Filtering, Estimation, and Detection
Random Processes: Filtering, Estimation, and Detection
HPDC '00 Proceedings of the 9th IEEE International Symposium on High Performance Distributed Computing
Simulation of Dynamic Data Replication Strategies in Data Grids
IPDPS '03 Proceedings of the 17th International Symposium on Parallel and Distributed Processing
Towards an Economy-Based Optimisation of File Access and Replication on a Data Grid
CCGRID '02 Proceedings of the 2nd IEEE/ACM International Symposium on Cluster Computing and the Grid
A Prediction-Based and Cost-Based Replica Replacement Algorithm Research and Simulation
AINA '05 Proceedings of the 19th International Conference on Advanced Information Networking and Applications - Volume 1
The Anatomy of the Grid: Enabling Scalable Virtual Organizations
International Journal of High Performance Computing Applications
Grid supporting platform for AMS data processing
ISPA'05 Proceedings of the 2005 international conference on Parallel and Distributed Processing and Applications
Hi-index | 0.00 |
Due to high latency of the Internet, it becomes a challenge to access large and widely distributed data quickly and efficiently on data grids. Replication is a process to address this issue, by storing data in different locations to reduce access latency and improve data locality. However, because of the limited storage capacity, a good replica replacement algorithm is needed to improve the efficiency of the access to the replicas. In this paper, a VO-based two-stage replica replacement algorithm is proposed, which provides a good solution to deal with the relations between value and cost. In a VO, replica value is determined according to popularity to make sure which replica will be replaced, and the bandwidth is predicted to make replacement cost as low as possible. Experiments show that compared with traditional replacement algorithms our new replica replacement algorithm shows better performance and efficiency of the data access on Data Grids.