A taxonomy and survey of grid resource management systems for distributed computing
Software—Practice & Experience
Simulation of Dynamic Data Replication Strategies in Data Grids
IPDPS '03 Proceedings of the 17th International Symposium on Parallel and Distributed Processing
Data Replication Strategies in Grid Environments
ICA3PP '02 Proceedings of the Fifth International Conference on Algorithms and Architectures for Parallel Processing
Decentralized data management framework for data grids
Decentralized data management framework for data grids
Dynamic replication algorithms for the multi-tier Data Grid
Future Generation Computer Systems - Special issue: Parallel computing technologies
| Hi-index | 0.00 |
Replication is a useful technique for distributed database systems and can be implemented in a grid computation environment to provide a high availability, fault tolerant and enhance the performance of the system. The performances addressed in this paper are data availability for read and write operations and communication cost, which are compared with the previous replication protocol, Three Dimensional Grid Structure (TDGS). This paper discusses a new protocol of replicating data for grid environment by putting the topology of the grid network in a logical grid structure and in a quorum where the selected replicas will be the primary database for replicating data to enhance the read and write availability of the data and to reduce the communication cost. The selection of replica is dependent on the diagonal location of the structured grid network. The middle replica is selected because it is easy to access and is the shortest path to get a copy of the data. To evaluate our model, we developed a simulation model in Java. Our results prove that by replicating diagonally in a quorum improves the performance of the data availability and communication cost in a large network size such as grid computational.