File(s) under permanent embargo
Networking for Big Data: A Survey
journal contribution
posted on 2017-01-01, 00:00 authored by Shui Yu, M Liu, W Dou, X Liu, S ZhouComplementary to the fancy big data applications, networking for big data is an indispensable supporting platform for these applications in practice. This emerging research branch has gained extensive attention from both academia and industry in recent years. In this new territory, researchers are facing many unprecedented theoretical and practical challenges. We are therefore motivated to solicit the latest works in this area, aiming to pave a comprehensive and solid starting ground for interested readers. We first clarify the definition of networking for big data based on the cross disciplinary nature and integrated needs of the domain. Second, we present the current understanding of big data from different levels, including its formation, networking features, mathematical representations, and the networking technologies. Third, we discuss the challenges and opportunities from various perspectives in this hopeful field. We further summarize the lessons we learned based on the survey. We humbly hope this paper will shed light for forthcoming researchers to further explore the uncharted part of this promising land.
History
Journal
IEEE Communications Surveys and TutorialsVolume
19Issue
1Pagination
531 - 549Publisher DOI
eISSN
1553-877XPublication classification
C Journal article; C1 Refereed article in a scholarly journalCopyright notice
2016, IEEEUsage metrics
Categories
Keywords
Science & TechnologyTechnologyComputer Science, Information SystemsTelecommunicationsComputer ScienceBig datanetworkingmathematical representationheterogeneitydynamic networkNONNEGATIVE MATRIX FACTORIZATIONDISCRIMINANT-ANALYSISINCENTIVE MECHANISMSDATA-COLLECTIONK-ANONYMITYLARGE-SCALETENSORCOMPLEXTIMEFRAMEWORK