Multi-objective Energy Aware Scheduling of Deadline Constrained Workflows in Clouds using Hybrid Approach

  • PDF / 2,492,040 Bytes
  • 22 Pages / 439.37 x 666.142 pts Page_size
  • 37 Downloads / 224 Views

DOWNLOAD

REPORT


Multi‑objective Energy Aware Scheduling of Deadline Constrained Workflows in Clouds using Hybrid Approach Mala Kalra1 · Sarbjeet Singh2

© Springer Science+Business Media, LLC, part of Springer Nature 2020

Abstract Cloud computing is undoubtedly one of the most significant advances in the domain of information technology. It facilitates elastic and on-demand provisioning of high performance computing capabilities employing pay-per-use model that has snowballed its adoption by scientists and engineers over the past few years. They often exploit workflows to represent their massive applications. Workflow scheduling in cloud has been devoted considerable investigation by researchers owing to its NP-complete nature of problem. Most of the previous studies targeted optimization of schedule length and execution cost within given deadlines/budget restrictions, or both. However, enormous energy consumption in the cloud data centers is not only negatively impacting the environment but also resulting in increased operational costs and thus cannot be ignored. Efficient scheduling strategies can significantly lessen the energy usage while complying with the user’s Quality of Service limitations. This research study proposes a Hybrid Approach for Energy aware scheduling of Deadline constrained workflows (HAED) using Intelligent Water Drops algorithm and Genetic Algorithm, which provides non-dominated solutions to the user. In particular, it focuses on multiple objectives i.e. reduction of schedule length, execution cost and energy usage within deadlines specified by the user. Its performance has been assessed on four scientific workflows from diverse domains using hypervolume and set coverage. The results achieved with the simulations demonstrate that the solutions produced by HAED are of better quality in terms of accuracy and diversity than non-dominated sorting genetic algorithm and hybrid particle swarm optimization. Keywords  Cloud computing · Energy aware scheduling · Genetic algorithm · Intelligent water drops algorithm · Multi-objective optimization · Evolutionary computing

* Mala Kalra [email protected] Sarbjeet Singh [email protected] 1

National Institute of Technical Teachers Training and Research, Chandigarh, India

2

University Institute of Engineering and Technology, Panjab University, Chandigarh, India



13

Vol.:(0123456789)



M. Kalra, S. Singh

1 Introduction Cloud Computing has emerged as a revolutionary technology which offers massive IT resources through virtualization following pay-per-use model. The resources can be acquired or released as per requirement and are easily accessible through Internet. Resources are provisioned as a service with three key models: Infrastructure as a Service (IaaS) in which high performance computing capabilities are outsourced, Platform as a service (PaaS) comprises of a set of tools for creating software applications and Software as a Service (SaaS) provides software on rental basis. Cloud Computing is also empowering mobile applications by overcoming resourc