A new methodology is presented in this paper for resource management in a metacomputing environment using a hierarchy of homogeneous agents that has the capability of service discovery. The PACE [6] tools are used to provide quantitative data concerning the performance of sophisticated applications running on local high performance resources. At metacomputing level, an agent hierarchy is used to model the resource management system, and the implementation of resource management, ng, and allocation can be abstracted to the processes of service advertisement and service discovery. Different optimisation strategies can be used to improve the performance of the agent system.
Junwei Cao, Darren J. Kerbyson, Graham R. Nudd