An architecture for distributed grid brokering

Authors:
John M. Brooke;Donal K. Fellows
Affiliations:
University of Manchester, Manchester, UK;University of Manchester, Manchester, UK
Venue:
Euro-Par'05 Proceedings of the 11th international Euro-Par conference on Parallel Processing
Year:
2005

Citing 2
Cited 1

Grid Information Services for Distributed Resource Sharing

HPDC '01 Proceedings of the 10th IEEE International Symposium on High Performance Distributed Computing
The Anatomy of the Grid: Enabling Scalable Virtual Organizations

International Journal of High Performance Computing Applications

Agent-oriented privacy-based information brokering architecture for healthcare environments

International Journal of Telemedicine and Applications - Special issue on electronic health

Quantified Score

Hi-index	0.00

Visualization

Abstract

Computational resource brokering on the Grid is the process of discovering what systems are capable of running a job, obtaining estimates for when that job may run and how much it will cost, and submitting the job to the system that best meets the users' requirements. This paper identifies how resource brokers differ from superschedulers, and describes a resource brokering architecture which is adapted to the emergent structure of the large-scale Grid. We outline the architecture of the UNICORE resource broker which is the basis of our prototype implementation, and discusses both how the existing UNICORE architecture is relevant to the wider brokering picture and what will be done in the future to bring them into closer alignment.