Maximizing the completion rate of concurrent scientific applications under time and budget constraints

Abstract

In many domains of science, scientific applications are represented by workflows. In this paper, we introduce a resource management strategy to maximize the success rate of concurrent workflow applications constrained by individual deadline and budget values. The Multi-Workflow Deadline-Budget Scheduling (MW-DBS) algorithm can schedule multiple workflows that can arrive in the system at any time, with the aim of satisfying individual job requirements. MW-DBS produces schedules without performing optimizations but guarantees that the deadline and budget defined for each job are not exceeded. Experimental results show that our strategy increases the scheduling success rate of finding valid solutions.