Solving Task Scheduling Problem in the Cloud Using a Hybrid Particle Swarm Optimization Approach

Solving Task Scheduling Problem in the Cloud Using a Hybrid Particle Swarm Optimization Approach

Salmi Cheikh, Jessie J. Walker
Copyright: © 2022 |Pages: 25
DOI: 10.4018/IJAMC.2022010105
Article PDF Download
Open access articles are freely available for download

Abstract

Synergistic confluence of pervasive sensing, computing, and networking is generating heterogeneous data at unprecedented scale and complexity. Cloud computing has emergered in the last two decades as a unique storage and computing resource to support a diverse assortment of applications. Numerous organizations are migrating to the cloud to store and process their information. When the cloud infrastructures and resources are insufficient to satisfy end-users requests, scheduling mechanisms are required. Task scheduling, especially in a distributed and heterogeneous system is an NP-hard problem since various task parameters must be considered for an appropriate scheduling. In this paper we propose a hybrid PSO and extremal optimization-based approach to resolve task scheduling in the cloud. The algorithm optimizes makespan which is an important criterion to schedule a number of tasks on different Virtual Machines. Experiments on synthetic and real-life workloads show the capability of the method to successfully schedule task and outperforms many known methods of the state of the art.
Article Preview
Top

Introduction

The notion of cloud computing has evolved as an innovative computing platform, but a close examination of the paradigm, reveals it is a collection of off the shelf components loosely connected together. The notion of the cloud is really the integration of applications delivered as a service over existing cyber infrastructure such as the Internet. These infrastructure networks have joined food, water, transportation, and energy as critical resources for the functioning of the global economy. As an on demand digital ecosystem that provides massive storage and computing resources, allowing customers to consume resources utilizing flexible pricing or pay-as-you-go model.

Cloud computing has revolutionized the way software and hardware resources are acquired and used in every sector. Every company in every sector now looks to the cloud as the means for storing and processing their data and as the means for running their applications. Cloud providers stand up data centers running state-of-the-art processors (e.g., GPUs and FPGAs), storage, and networking, and state-of-the-art services (e.g., machine learning algorithms and models). These resources benefit customers of cloud providers. As more and more companies make their internal processes and external businesses increasingly data-driven, the demand for cloud capability will continue to grow.

Currently the three most common cloud computing service models which each satisfy a unique set of requirements. These three models are known as Software as a Service (SaaS), Platform as a Service (PaaS), and Infrastructure as a Service (IaaS). These models are generally deployed in the following manner, public, private, community and hybrid. Each model has its own benefits and detriments.

Complete Article List

Search this Journal:
Reset
Volume 15: 1 Issue (2024)
Volume 14: 1 Issue (2023)
Volume 13: 4 Issues (2022): 2 Released, 2 Forthcoming
Volume 12: 4 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing