Big data (lost) in the cloud. (1st January 2014)

• Record Type: Journal Article
• Authors: Di Martino, Beniamino; Aversa, Rocco; Cretella, Giuseppina; Esposito, Antonio; Kołodziej, Joanna
• Is Part Of: International journal of big data intelligence. Volume 1:Number 1/2(2014)
• Page Start: 3
• Page End: 17
• Publication Date: 2014-01-01
• Subjects: distributed data centre -- resource provisioning -- big data -- big data workflow -- cloud computing -- high performance computing -- MapReduce -- Hadoop -- data analysis -- data curation -- data storage; Big data -- Periodicals; 005.705
• Languages: English
• ISSNs: 2053-1389

Abstract

The big data era poses a critically difficult challenge and striking development opportunities to high performance computing (HPC). The major problem is an efficient transformation of the massive data of various types into valuable information and meaningful knowledge. Computationally-effective HPC is required in a fast-increasing number of data-intensive domains. With its special features of self-service and pay-as-you-use, cloud computing (CC) offers suitable abstractions to manage the complexity of the analysis of large data in various scientific and engineering domains. This paper surveys briefly the most recent developments on CC support for solving the big data problems. It presents a comprehensive critical analysis of the existing solutions and shows the further possible directions of the research in this domain including new generation multi-datacentre cloud architectures for the storage and management of the huge big data streams.