Multi-workflow QoS-Constrained Scheduling for Utility Computing
Hamid Arabnejad, Jorge G. Barbosa · 2015
In this paper, we introduce a utility driven strategy to schedule concurrent workflows constrained to user's QoS parameters, namely Deadline and Budget. The Multi-Workflow Deadline-Budget Scheduling algorithm (MW-DBS) can schedule multiple workflows that can arrive to the system at any instant of time, with the aim of satisfying individual QoS requirements. Common approaches optimize one factor, e.g. processing time, constrained to the other factor, e.g. cost. MW-DBS produces schedules without optimizing any of the parameters but guaranteeing that the deadline and budget defined for each workflow are not exceeded. We study the scalability of the algorithm with different types of workflows and service providers. Experimental results show that our strategy is able to increase the scheduling success rate of finding valid solutions.