Abstract
Computational Grids and peer-to-peer (P2P) networks enable the sharing,
selection, and aggregation of geographically distributed resources for solving
large-scale problems in science, engineering, and commerce. The management and
composition of resources and services for scheduling applications, however,
becomes a complex undertaking. We have proposed a computational economy
framework for regulating the supply and demand for resources and allocating them
for applications based on the users' quality of services requirements. The
framework requires economy driven deadline and budget constrained (DBC)
scheduling algorithms for allocating resources to application jobs in such a way
that the users' requirements are met. In this paper, we propose a new scheduling
algorithm, called DBC cost-time optimisation, which extends the DBC
cost-optimisation algorithm to optimise for time, keeping the cost of
computation at the minimum. The superiority of this new scheduling algorithm, in
achieving lower job completion time, is demonstrated by simulating the
World-Wide Grid and scheduling task-farming applications for different deadline
and budget scenarios using both this new and the cost optimisation scheduling
algorithms.