Evolutionary Multi-Objective Workflow Scheduling for Volatile Resources in the Cloud

The cloud has been widely used as a distributed computing platform for running scientific workflow applications. Most of the providers encourage use their underutilized resources spot instances much cheaper prices compared with common on-demand instances, however, promise lower costs results in volatility such that can be interrupted at any time by providers. Many scheduling algorithms have proposed to deal volatile resources. In this article, we consider two most important features namely fulfillment and interruption rates fully model instability infrastructure. Subsequently, propose novel evolutionary multi-objective approach generate set trade-off solutions outperform state-of-the-art both makespan economic costs. addition, explore fluctuation our obtained schedules under different levels rates. Experimental five well-known real-world workflows demonstrate algorithm is competitive terms cost techniques.