The Rodeo Group

Click on me !

Rodeo is a contrived acronym that stands for ``High speed networks, open networks''. The main objective of the project is to design, implement, and evaluate mechanisms for the efficient and flexible use of network resources.

 To achieve the above objective, we focus our activities in three main areas, namely:

This work is performed in relation with academic, research, and industrial partners.

 You will also find in this page a list of project members and some additional information.

 We also have a page in french.

 

Resource allocation and control

We are designing resource allocation mechanisms for both stateless networks (such as the current Internet) and integrated networks. With stateless networks, resource allocation is done using edge (i.e. end-to-end) mechanisms. Our emphasis these past few years have been on mechanisms that integrate multicast delivery, flexible flow and error control, etc. These mechanisms are used in particular in the FreePhone Internet telephony tool, in the Rendez-Vous videoconferencing tool (successor of IVS, one of the first s/w videoconferencing tool for the Internet) , and in the MiMaze distributed game.

High performance architectures

Previous research in the group led to the development of the MAVROS compiler, and of fast algorithms for the management of data transparency in heterogeneous systems. We are extending this work so as to allow the compiler to handle detailed specifications of the applications. This will lead to further optimizations.

We expect the two research areas described above to eventually merge within the framework of the Application Layer Framing (ALF) architecture. It will then be possible to take into account specifications of an application, of the network ressources required by the application, and to automatically generate tailored communication modules that handle both data transparency, synchronization, and transmission control for this application.

New Transmission Media

Our work is carried out over IP networks using a variety of underlying technologies. Recently, we have carried out specific work on wireless links (robust coding for wireless links), satellite links (routing over unidirectional links, check out the UDLR page), and over ATM links (specifically over the regional ATM testbed dubbed EuroSud155 - check out experimental results).

Partners

Work on resource allocation and control is carried out in a variety of projects and a variety of industrial, academic, and research partners. Much of it revolves around the MERCI project (a successor to the MICE and MICE-2 projects) with University College London (UK), KTH (Sweden), University of Oslo (Norway), GMD, RUS, and Teles (Germany).

Work on high performance architectures is carried out in collaboration with University College London (UK), SICS (Sweden), and the University of Technology of Sydney (Australia) within the HIPPARCH project.

We are active in various working groups in the IETF (Internet Engineering Task Force), in particular the AVT, UDLR, and LSMA groups.

Group members

Jean-Chrysostome Bolot
Patrick Cipière
Antoine Clerget
Walid Dabbous
Christophe Diot
Emmanuel Duros
Sacha Fosse-Parisis
Laurent Gautier
Matthias Grossglauser
Delphine Kaplan
Emmanuel Léty
Frank Lyonnet
Martin May
Thierry Turletti
Francoise Martin-Trucas

Former group members

Benoit Brodard
Jean-Patrick Giacometti
Claude Castellucia now at INRIA Grenoble
Isabelle Chrisment now at ESSI
Philipp Hoschka now at the Web Consortium
Christian Huitema now at Bellcore
Andrés Vega-García now at Microsoft

More information on the project

Pointers to specific current work and/or software:
Internet audio tool FreePhone
Internet video tool Rendez-Vous
Internet distributed game MiMaze
Routing over satellite/unidirectional links UDLR
IPv6 router software IPv6
The MAVROS ASN.1 compiler
Reliable Multicast Framing Protocol RMFP

Pointers to general information:
The annual report (in french)
Project seminars
The Sophia-Antipolis unit of INRIA
Programme 1

Calls for Papers