IPDPS '05 Proceedings of the 19th IEEE International Parallel and Distributed Processing Symposium (IPDPS'05) - Workshop 1 - Volume 02
A grid workflow-based Monte Carlo simulation environment
Neural, Parallel & Scientific Computations - Special issue: Grid computing
A multi-dimensional scheduling scheme in a Grid computing environment
Journal of Parallel and Distributed Computing
Characterizing resource availability in enterprise desktop grids
Future Generation Computer Systems
Fault-aware grid scheduling using performance prediction by workload modeling
The Journal of Supercomputing
Monte Carlo simulation with the GATE software using grid computing
NOTERE '08 Proceedings of the 8th international conference on New technologies in distributed systems
A Peer to Peer Grid Computing System Based on Mobile Agents
Agents and Peer-to-Peer Computing
Providing Fault-Tolerance in Unreliable Grid Systems Through Adaptive Checkpointing and Replication
ICCS '07 Proceedings of the 7th international conference on Computational Science, Part I: ICCS 2007
An adaptive and trustworthy software testing framework on the grid
The Journal of Supercomputing
Performance models for hierarchical grid architectures
GRID '06 Proceedings of the 7th IEEE/ACM International Conference on Grid Computing
A parallel solution for scheduling of real time applications on grid environments
Future Generation Computer Systems
Pro-active failure handling mechanisms for scheduling in grid computing environments
Journal of Parallel and Distributed Computing
A fair replica placement for parallel download on cluster grid
NBiS'07 Proceedings of the 1st international conference on Network-based information systems
Availability Prediction Based Replication Strategies for Grid Environments
CCGRID '10 Proceedings of the 2010 10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing
A demand based fault tolerant file replication model for clouds
Proceedings of the CUBE International Information Technology Conference
International Journal of Information and Communication Technology
Hi-index | 0.00 |
High performance computing on a large-scalecomputational grid is complicated by the heterogeneouscomputational capabilities of each node, nodeunavailability, and unreliable network connectivity.Replicating computation on multiple nodes cansignificantly improve performance by reducing taskcompletion time on a grid's dynamic environment. Wedevelop an analytical model to determine the number oftask replicas to meet the performance goals in differentcomputational grid configurations. Furthermore, takingadvantage of the statistical nature of grid-based MonteCarlo applications, we extend the computationalreplication technique to an N-out-of-M schedulingstrategy for grid-based Monte Carlo applications, whichcan potentially form a large category of grid-computingapplications. In addition, we establish a correspondingmodel for the N-out-of-M scheduling mechanism.Simulations are used to validate the computationalreplication models. Our preliminary results show that themodels we use are effective in predicting the requirednumber of replicas to achieve short task completion timewith a given high probability.