The grid: blueprint for a new computing infrastructure
The grid: blueprint for a new computing infrastructure
Introduction to Linear Optimization
Introduction to Linear Optimization
A Policy Service for GRID Computing
GRID '02 Proceedings of the Third International Workshop on Grid Computing
XML-Based Policy Engine Framework for Usage Policy Management in Grids
GRID '02 Proceedings of the Third International Workshop on Grid Computing
End-to-End Provision of Policy Information for Network QoS
HPDC '01 Proceedings of the 10th IEEE International Symposium on High Performance Distributed Computing
Grid Computing: A Practical Guide to Technology and Applications
Grid Computing: A Practical Guide to Technology and Applications
Enabling the Co-Allocation of Grid Data Transfers
GRID '03 Proceedings of the 4th International Workshop on Grid Computing
Customer-managed end-to-end lightpath provisioning
International Journal of Network Management
New grid scheduling and rescheduling methods in the GrADS project
International Journal of Parallel Programming - Special issue: The next generation software program
Lognormal and Pareto distributions in the Internet
Computer Communications
OTM'07 Proceedings of the 2007 OTM confederated international conference on On the move to meaningful internet systems: CoopIS, DOA, ODBASE, GADA, and IS - Volume Part II
| Hi-index | 0.00 |
Processable Bulk Data Transfer (PBDT) tasks are resource intensive concurrent tasks which involve transfer of a very large amount of data that has to be processed in some way before it can be used at a remote set of destination nodes called the sink nodes. A distributed computing environment, such as the Grid is a popular way to perform these tasks. Focusing on the execution of PBDT tasks in a Grid computing environment, this paper presents an efficient resource allocation mechanism. Due to the resource thirsty nature of these tasks, an efficient resource allocation is essential to perform these tasks while achieving satisfactory performance. The time-complexity of the resource allocation algorithm rises sharply as the available number of resources in the given Grid computing environment is increased making efficient resource allocation a challenge. To meet this challenge, this paper investigates the use of approximate algorithms for the resource allocation. The benefits obtained by using the reduced complexity of the algorithm are weighed against the increased costs incurred during the task execution (due to the inaccuracies in resource allocation introduced by the approximations). This paper describes a number of approximations and discusses under which circumstances such approximations are to be used. The techniques presented in this research can be extended to non-PBDT tasks and other distributed computing environments.