A Deadline and Budget Constrained Cost-Time Optimisation Algorithm for Scheduling Task Farming Applications on Global Grids

TL;DR

This paper introduces a novel deadline and budget constrained scheduling algorithm for global grids that optimizes for minimal computation time while respecting user-defined cost and deadline constraints, demonstrated through simulation.

Contribution

It presents a new cost-time optimisation algorithm extending existing methods to improve job completion times in grid scheduling under economic constraints.

Findings

The new algorithm achieves lower job completion times in simulations.

It effectively balances cost and time constraints for task farming applications.

Simulation results show superiority over previous cost-optimisation algorithms.

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.