期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2014
卷号：2
期号：5
出版社：S&S Publications
摘要：In recent years ad hoc parallel data processing has emerged to be one of the killer applications forInfrastructure-as-a-Service (IaaS ) clouds. Major Cloud computing companies have started to integrateframeworks for parallel data processing in their product portfolio, making it easy for customers to accessthese services and to deploy their programs. The opportunities and challenges for efficient parallel dataprocessing in clouds are discussed and present the research project Nephele. It is the first data processingframework to explicitly exploit the dynamic resource allocation offered by today's IaaS clouds for both, taskscheduling a nd execution. Particular tasks of a processing job can be assigned to different types of virtualmachines which are automatically instantiated and terminated during the job execution. Basedon this new framework, the extended evaluations of MapReduce -inspiredprocessing jobs on an IaaS cloud system is performed and compared the results to the popular data processingframework Hadoop.
