Response Surface Modelling for Performance Analysis of Scientific Workflow Application in Cloud
- PDF / 1,220,099 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 66 Downloads / 175 Views
(0123456789().,-volV)(0123456789(). ,- volV)
Response Surface Modelling for Performance Analysis of Scientific Workflow Application in Cloud Prathibha Soma1
•
B. Latha2
Received: 25 June 2019 / Revised: 29 August 2020 / Accepted: 31 August 2020 Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Scientific workflow applications are used by scientists to carry out research in various domains such as Physics, Chemistry, Astronomy etc. These applications require huge computational resources and currently cloud platform is used for efficiently running these applications. To improve the makespan and cost in workflow execution in cloud platform it requires to identify proper number of Virtual Machines (VM) and choose proper VM type. As cloud platform is dynamic, the available resources and the type of the resources are the two important factors on the cost and makespan of workflow execution. The primary objective of this work is to analyze the relationship among the cloud configuration parameters (Number of VM, Type of VM, VM configurations) for executing scientific workflow applications in cloud platform. In this work, to accurately analyze the influence of cloud platform resource configuration and scheduling polices a new predictive modelling using Box–Behnken design which is one of the modelling technique of Response Surface Methodology (RSM). It is used to build quadratic mathematical models that can be used to analyze relationships among input and output variables. Workflow cost and makespan models were built for real world scientific workflows using ANOVA and it was observed that the models fit well and can be useful in analyzing the performance of scientific workflow applications in cloud Keywords Cloud computing Scientific workflow application Virtual machine Modelling Response surface methodology
1 Introduction Cloud computing refers to a pool of computing resources which are provided as service to the users who can access them through Internet [1]. Cloud computing works on the belief to alter the way computing is done from local systems into the network. Infrastructure as a Service (IaaS) is one of the earliest and fundamental computing service models of cloud platform which allows customers to get computing resources for rent through virtualization [2].
& Prathibha Soma [email protected] 1
Department of Information Technology, Sri Sai Ram Engineering College, Anna University, Chennai 600044, India
2
Department of Computer Science and Engineering, Sri Sai Ram Engineering College, Anna University, Chennai 600044, India
Computing resources like virtual machines, storage and networking devices are delivered on demand to the customers. IaaS service can be used for constructing cost effective and scalable IT infrastructure. Currently there are a large number of IaaS providers available in the public domain to offer unlimited resource pool to the customers. Large number of problems in many areas of science such as Physics, Biology, Astronomy and Earth Sciences are art
Data Loading...
