BigdataNet (2013-2015) with UCSB (USA)

ucsbBigdataNet is an associated team (“équipe associée”) between Zenith and the distributed systems team of Profs. Amr El Abbadi and Divy Agrawal at University of California, Santa Barbara, since january 2013. The associated team is headed by Esther Pacitti and Patrick Valduriez for Zenith, and Amr El Abbadi and Divy Agrawal for UCSB.

With the advent of the Internet and the World-wide-web, there is an emergent need to develop user applications that access data and resources stored in the network. In order to facilitate the development of network-centric applications, new computational paradigms are needed that are scalable, elastic, available, and fault-tolerant. During the past decades two dominant paradigms referred to as Peer-to-Peer (P2P) Computing and Cloud Computing have become widely prevalent as computational paradigms for distributed applications. Peer-to-peer computing is a highly decentralized computing paradigm that leverages computing resources at the user level for supporting decentralized user level applications such as wide-scale media file sharing, telecommunication services (e.g., Skype), and others. Cloud computing on the other hand relies on large data-centers consisting of thousands of server-class machines and all application processing and application data is centralized in the network core, i.e., data-centers. The two paradigms in many ways are complimentary and provide different trade-offs. For instance, the cost for computing and storage is almost free in P2P but it suffers from the challenges of churn and low reliability of user machines. Cloud computing, on the other hand significantly simplifies the task of system administration in the data-center but requires a very large investment in building large-scale data-centers.

We plan to develop a hybrid platform that combines the two paradigms and leverages computing, storage, and network resources both in the data-centers (i.e., the cloud) as well as at the edges of the network (i.e., the peer or user machines). During this project, we will explore the suitability of this hybrid model for big-data applications such as scientific applications, social networks, and massive data analytics. The research challenges that need to be addressed are the massive scale of both systems and data, complexity of the overall architecture, and heterogeneity of overlay network.

Participants

Objectives

Scientific Achievements

Publications

Workshops

Permanent link to this article: https://team.inria.fr/zenith/bigdatanet/

Bigdatanet participants

UCSB Amr El Abbadi, Professor of Computer Science Divyakant Agrawal, Professor of Computer Science Aaron Elmore, Ph.D. student Faisal Nawab, Ph.D. student Cetin Sahin, Ph.D. student INRIA Reza Akbarinia, Researcher at INRIA Florent Masseglia, Researcher at INRIA Esther Pacitti, Professor of Computer Science, University Montpellier 2 Patrick Valduriez, Director Research at INRIA Tristan Allard (University …

Bigdatanet achievements

The project has achieved its initial objectives, wrt to the definition of a P2P/cloud architecture and basic data management techniques. Furthermore, it has been the basis for a new research direction on privacy-preserving database outsourcing, which is now continuing a major track in Zenith. P2P/cloud architecture We defined a P2P/Cloud as a hybrid architecture that …

Bigdatanet objectives

The rationale and vision of this project is to leverage from the above two paradigms especially since the Inria team has expertise in P2P computing and the UCSB team has expertise in Cloud computing. At present, in the commercial realm, cloud computing has emerged as a dominant paradigm. However, we contend that cloud computing is …

Bigdatanet publications

[Akbarinia 2015] R. Akbarinia, M. Liroz-Gistau, D. Agrawal, P. Valduriez. An Efficient Solution for Processing Skewed MapReduce Jobs. Int. Conf. on Data Management in Grid and P2P Systems (Globe), 417-429, 2015. [Allard 2015a] T. Allard, C. Sahin, A. El Abaddi, F. Masseglia, E. Pacitti. A Differentially-Private Index for Querying Encrypted Data. In preparation, 2015. [Allard …

Bigdatanet workshops

12 May 2015, BIS workshop, Berkeley, keynote “The Practical and System Challenges of Managing Big Data” by A. El Abbadi 13 May 2015, BIS workshop, Berkeley, presentations of the Bigdatanet work by R. Bouadjenek and T. Allard, Working session on Scientific and Large Scale Computing 16-19 June 2014, BIS workshop, Paris, presentations of the Bigdatanet …