An outer-approximation algorithm for a class of mixed-integer nonlinear programs
Mathematical Programming: Series A and B
Scheduling Soft Real-Time Jobs Over Dual Non-Real-Time Servers
IEEE Transactions on Parallel and Distributed Systems
A comparative study of load sharing in heterogeneous multicomputer systems
ANSS '92 Proceedings of the 25th annual symposium on Simulation
Heterogeneous Multi-Cluster Networking with the Madeleine III Communication Library
IPDPS '02 Proceedings of the 16th International Parallel and Distributed Processing Symposium
The MultiCluster Model to the Integrated Use of Multiple Workstation Clusters
IPDPS '00 Proceedings of the 15 IPDPS 2000 Workshops on Parallel and Distributed Processing
Performance Evaluation of Soft Real-Time Scheduling for Multicomputer Cluster
ICDCS '00 Proceedings of the The 20th International Conference on Distributed Computing Systems ( ICDCS 2000)
Optimizing Static Job Scheduling in a Network of Heterogeneous Computers
ICPP '00 Proceedings of the Proceedings of the 2000 International Conference on Parallel Processing
Performance-based middleware for Grid computing: Research Articles
Concurrency and Computation: Practice & Experience - Grid Performance
Theory, Volume 1, Queueing Systems
Theory, Volume 1, Queueing Systems
Case study: Evaluation of loadsharing algorithms for heterogeneous distributed systems
Computer Communications
Journal of Systems and Software
The impact of service demand variability on resource allocation strategies in a grid system
ACM Transactions on Modeling and Computer Simulation (TOMACS)
Hi-index | 0.00 |
Clusters are increasingly interconnected to form multi-cluster systems, which are becoming popular for scientific computation. End-users often submit their applications in the form of workflows with certain Quality of Service (QoS) requirements imposed on the workflows. These workflows describe the execution of a complex application built from individual application components, which form the workflow tasks. This paper addresses workload allocation techniques for Grid workflows. We model individual clusters as M/M/k queues and obtain a numerical solution for missed deadlines (failures) of tasks of Grid workflows. The approach is evaluated through an experimental simulation and the results confirm that the proposed workload allocation strategy combined with traditional scheduling algorithms performs considerably better in terms of satisfying QoS requirements of Grid workflows than scheduling algorithms that don't employ such workload allocation techniques.