Load Balancing Mechanism for QoS-aware Cloud Computing using Eucalyptus Platform

• Main Authors: Pei-jia Yang, 楊佩嘉
• Other Authors: Jiann-Liang Chen
• Format: Others
• Language: en_US
• Published: 2011
• Online Access: http://ndltd.ncl.edu.tw/handle/qa86ag

碩士 === 國立臺灣科技大學 === 電機工程系 === 99 === The Internet technologies have developed rapidly in recent years. The computing environment with the advantages of cost saving, high computing capability and performance is among the favorable technology for users. Based on aforementioned background, Cloud Computing technology is proposed, it uses Internet as communication medium to provide rich software, applications and virtualization resources. Because of its three levels division of infrastructure: Infrastructure as a Service (IaaS), Platform as a Service (PaaS) and Software as a Service (SaaS). Cloud computing technology meets the needs of user on their consideration of hardware complexity and cost. Services, private data, and servers in the cloud provide users’ access which lead to the virtual machines’ performance and reliability issues. This study investigates the load balancing issue of virtual machines in cloud computing environments. This study also distributes the virtual machines’ loading to improve performance and enhance its reliability through analyzing large data in cloud computing. This study proposes QoS system that uses Eucalyptus as the basic infrastructure. It has a uniform interface to manage virtual machines and supports EC2/S3 APIs compatibility. The EuQoS system is combined with Hadoop technology to provide the management interface allowing real-time services load balancing observation. The experimental scenario uses large log processing service to measure CPU, memory and throughput. Experimental results indicate that the proposed Eucalyptus QoS system decreases service execution time to 1.91 seconds, reduces 12.92% CPU loading, reduces 5.99% memory loading, improves 6.94% system throughput.