Robust Scheduling of Scientific Workflows with Deadline and Budget Constraints in Clouds

TLDR

Dynamic resource provisioning and the promise of unlimited resources have drawn scientific workflows to the Cloud, yet existing scheduling approaches focus only on deadlines or cost, neglecting robustness against performance variability and failures. The study proposes a robust scheduling algorithm that allocates resources to workflow tasks on heterogeneous Cloud resources to minimize elapsed time and cost. The algorithm employs resource‑allocation policies that schedule tasks while handling performance variations and failures. The policies yield robust, fault‑tolerant schedules that reduce make span and increase robustness as budget rises.

Abstract

Dynamic resource provisioning and the notion of seemingly unlimited resources are attracting scientific workflows rapidly into Cloud computing. Existing works on workflow scheduling in the context of Clouds are either on deadline or cost optimization, ignoring the necessity for robustness. Robust scheduling that handles performance variations of Cloud resources and failures in the environment is essential in the context of Clouds. In this paper, we present a robust scheduling algorithm with resource allocation policies that schedule workflow tasks on heterogeneous Cloud resources while trying to minimize the total elapsed time (make span) and the cost. Our results show that the proposed resource allocation policies provide robust and fault-tolerant schedule while minimizing make span. The results also show that with the increase in budget, our policies increase the robustness of the schedule.