DOCCA project : Design and Optimization of Collaborative Computing Architecture
[ Overview | Members | Documents | Bibliography ]
Project Overview
The DOCCA project aims at developing a peer-to-peer collaborative computing protocol with a strong emphasis on theoretical aspects of fairness issues and collaboration incentives. Our target system is a fully decentralized architecture, where desktops are both volunteers and clients (they can submit jobs).Our objectives are:
- Leverage the pluridisciplinarity of the team to combine theoretical tools and metrics from the parallel computing community and from the network community, and to explore algorithmic and analytical solutions to the specific resource management problems of such systems.
- Design a P2P architecture based on the algorithms designed in the second step and to create a novel P2P collaborative computing system.
The expected results are :
- Provide user synthetic models to the scientific community that can be used as an input in modeling, simulation and experimentation of P2P collaborative computing systems.
- Provide optimal strategies and resource management algorithms in P2P collaborative computing.
- Design a decentralized protocol that implements the optimal strategies for the target user models.
- Implement a prototype and validate the approach on an experimental platform.
Members and Collaborators
Coordinator: Florence PERRONNINMembers:
- Corinne Touati (Research scientist, INRIA)
- Arnaud Legrand (Research scientist, CNRS)
- Florence Perronnin (Associate Professor, Université Joseph Fourier)
- Fanny Pascual (Associate Professor, Université Pierre et Marie Curie)
- Olivier Richard (Associate Professor, Polytech’Grenoble)
- Lucas Nussbaum (PhD Student)
- Rémi Bertin (PhD Student)
- Ricardo Czekster (PhD Student)
- Pedro Velho (PhD Student)
Collaborators:
Derrick Kondo (Research scientist, INRIA)
Documents
- Project proposal submitted to ANR.
Bibliography
- Bruno Donassolo, Arnaud Legrand, and Claudio Geyer. Non-Cooperative Scheduling Considered Harm- ful in Collaborative Volunteer Computing Environments. In Proceedings of the 11th IEEE International Symposium on Cluster Computing and the Grid (CCGrid’11). IEEE Computer Society Press, may 2011.
- Remi Bertin, Pierre Coucheney, Arnaud Legrand, and Corinne Touati. Practical Implementation Issues of Lagrangian Based Distributed Optimization Algorithms. In 12th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (Synasc), 2010.
- Bruno Donassolo, Henri Casanova, Arnaud Legrand, and Pedro Velho. Fast and scalable simulation of volunteer computing systems using simgrid. In Workshop on Large-Scale System and Application Perfor- mance (LSAP), 2010.
- Remi Bertin, Sascha Hunold, Arnaud Legrand, and Corinne Touati. From Flow Control in Multi-path Net- works to Multiple Bag-of-tasks Application Scheduling on Grids. Research Report RR-7745, INRIA, Sep- tember 2011.
- Pierre Coucheney, Corinne Touati, and Bruno Gaujal. Fair and efficient user-network association algorithm for multi-technology wireless networks. In Proc. of the 28th conference on Computer Communications miniconference (INFOCOM), 2009.
- Rémi Bertin, Arnaud Legrand, and Corinne Touati, Toward a Fully Decentralized Algorithm for Multiple Bag-of-tasks Application Scheduling on Grids. IEEE/ACM International Conference on Grid Computing (Grid 08), Tsukuba, Japon, 2008.
- Rémi Bertin, Arnaud Legrand, and Corinne Touati. Toward a Fully Decentralized Algorithm for Multiple Bag-of-tasks Application Scheduling on Grids. Research Report 6537, INRIA, May 2008. (Available here)