Download Now Free registration required
Common hurdles in the data grid are: ensuring availability, improving fault tolerance, reducing file access time, minimizing file transfer cost and controlling network bandwidth usage. The appropriate solution to overcome these hurdles is data replication. Two data replication algorithms are proposed in this paper; for the storage servers of geographically distributed areas, a centralized data replication algorithm that solves the data replication problem of reducing the access cost of the data files across the grid is proposed and for the storage servers in data grid of higher proximity, a distributed data replication algorithm that solves the replica placement problem of reducing the access time of the data files across the distributed replication groups of storage servers is proposed.
- Format: PDF
- Size: 658.01 KB