Loading [MathJax]/extensions/MathMenu.js
A distributed cloud resource management framework for High-Performance Computing (HPC) applications | IEEE Conference Publication | IEEE Xplore

A distributed cloud resource management framework for High-Performance Computing (HPC) applications


Abstract:

The High-Performance Computing (HPC) users require the high-end compute, storage, and, network execution environment in a dynamic manner for testing HPC applications. The...Show More

Abstract:

The High-Performance Computing (HPC) users require the high-end compute, storage, and, network execution environment in a dynamic manner for testing HPC applications. The High-Performance Computing Cloud (HPCC) provides a kind of execution environment in an on-demand manner. Generally, the cloud resource management system or cloud resource broker manages the compute, storage, and network resources in HPCC. However, it faces the challenges of scalability, interoperability, and achieving guaranteed Quality of Service (QoS). Hence, the proposed research work addresses the above-said issues by employing the distributed cloud resource management framework. The proposed system can be able to handle a large number of user application requests and manage the multiple cloud resources in an interoperable manner. The proposed system is evaluated by submitting a large number of real-world HPC applications. The performance metrics such as response time, a number of successfully handled requests, and user satisfaction are measured to evaluate the performance of proposed system.
Date of Conference: 19-21 January 2017
Date Added to IEEE Xplore: 19 June 2017
ISBN Information:
Conference Location: Chennai, India

I. Introduction

Cloud Computing is the blended technology of parallel and distributed computing which provides compute, storage, and network resources in an on-demand manner and charges based on the usage of the resources. The cloud service models are categorized into Software as a Service (SaaS), Platform as a Service (PaaS), and Infrastructure as a Service (IaaS). And, the service models are deployed based on the deployment models of private, public, or hybrid. The cloud computing provides the compute and storage resources for scientific users using the open-source Cloud middleware tools such as Cloudstack [1], OpenStack [2], and OpenNebula [3] for testing their scientific applications. Those applications are highly compute and data intensive and complex in nature which requires large amount of computational cycles and data storage. The High-Performance Computing Cloud (HPCC) or Science Cloud (SC) provide the required High-Performance computing resources to scientific and research community for testing their scientific experiments. In addition to that, it delivers benefits to the scientific applications using the concept of resource provisioning through virtualization technology by providing distinct operating systems with different software configurations to run and test their applications. However, resource management is one of the challenging task which involves representation of distinct cloud provides in an interoperable format.

Contact IEEE to Subscribe

References

References is not available for this document.