Time-Aware Task Allocation for Cloud Computing Environment

Time-Aware Task Allocation for Cloud Computing Environment

Sushanta Meher (Institute of Engineering and Management, Jeypore, Burla, India), Sohan Kumar Pande (VSSUT, Burla, India) and Sanjaya Kumar Panda (Indian Institute of Technology (ISM), Dhanbad and VSSUT, Burla, India)
Copyright: © 2017 |Pages: 13
DOI: 10.4018/IJKDB.2017010101

Abstract

Cloud computing provides access to various services such as servers, storage and applications to the customers' as and when required. The services on the cloud can be accessed with minimum efforts through any handheld devices that are connected to the Internet. In IaaS cloud, the services to the customers are provided in the form of two leases, AR and BE. Here, a running BE lease can be preempted upon arrival of an AR lease as BE has lower priority. However, frequent preemption of the BE lease causes an overhead to the system and leads to customer dissatisfaction. In this paper, we propose a fairness algorithm called TATA to provide fairness among the leases. We evaluate the proposed algorithm on various synthetic datasets and compare the results with an existing fairness algorithm. The results of simulation show that TATA produces better response time for both the leases than the existing algorithm.
Article Preview
Top

Introduction

Cloud computing is an innovative platform for the service provider to deliver various services such as servers, networks, storage, virtual desktop and applications to the customers. These services are based on the three fundamental service models, namely infrastructure as a service (IaaS), platform as a service (PaaS) and software as a service (SaaS) (Buyya, Yeo, Venugopal et, 2009; Durao, Carvalho, Fonseka, & Garcia, 2014). IaaS cloud provides the services in the form of virtual machines that are deployed in the datacenters (Li, Qiu, Niu et al., 2010; Li et al., 2012; Panda, & Jana, 2015; Panda, & Jana, 2016). On the other hand, users demand the services in the form of leases which basically contain the requirements of the users such as number of computing nodes, start time, deadline, duration, etc. (Nathani, Chaudhary, & Somani, 2012; Panda, & Jana, 2016; Panda, & Jana, 2017). The cloud service provider (CSP), namely Amazon EC2 (Amazon EC2, 2016), Haizea (Haizea, 2016), Eucalyptus (Eucalyptus, 2016) and OpenNebula (OpenNebula, 2016) support various leases to provide the computational resources. These leases include advance reservation (AR), best effort (BE) and immediate (IM).

An AR lease (A) is a type of lease that holds a specific start time (S) and execution time (E). The tuple representation of an AR lease is as follows:A = <S, E, M> (1) where:

An AR lease is non-preemptive in nature. Therefore, M = 0. Note that the end time (EN) of an AR lease is the sum of start time and execution time. Mathematically:

EN = S + E(2)

In this paper, we assume that an AR lease has 2-tuple (i.e., < E, M >) for the simplicity of the problem. This assumption is taken based on the assumption made in (Li et al., 2012; Panda, & Jana, 2015).

A BE lease (B) is a type of lease that needs an execution time without any specific start time. The tuple form of a BE lease is as follows:

B = < E, M > (3)

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 8: 2 Issues (2018)
Volume 7: 2 Issues (2017)
Volume 6: 2 Issues (2016)
Volume 5: 2 Issues (2015)
Volume 4: 2 Issues (2014)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing