Section: Partnerships and Cooperations

International Initiatives

SIMULBED

• Title: SIMULBED: Large-Scale Simulation Testbed for Realistic Evaluation of Network Protocols and Architectures

• International Partner (Institution - Laboratory - Researcher):

  • NICT and University of Tokyo (Japan), Hitoshi Asaeda and Yuji Sekiya.

• Duration: 2012 - 2014

• Participants from Inria in 2014: Walid Dabbous, Emilio Mancini, Alina Quereilhac, Hardik Soni, Julien Tribino and Thierry Turletti.

• Participants from NICT in 2014: Hitoshi Asaeda, Ruidong Li and Kazuhisa Matsuzono.

• Participants from Univeristy of Tokyo in 2014: Yuji Sekiya and Hajime Tazaki.

• Web site: http://planete.inria.fr/Simulbed/

• Abstract: Simulators and experimental testbeds are two different approaches for the evaluation of network protocols and they provide a varying degree of repeatability, scalability, instrumentation and realism. Network simulators allow fine grained control of experimentation parameters, easy instrumentation and good scalability, but they usually lack realism. However, there is a growing need to conduct realistic experiments involving complex cross-layer interactions between many layers of the communication stack and this has led network researchers to evaluate network protocols on experimental testbeds.

  The use of both simulators and testbeds to conduct experiments grants a better insight on the behavior of the evaluated network protocols and applications. In this project, we focus on the design of SIMULBED, an experimentation platform that aims at providing the best of both worlds. Our project builds on the following state-of-the-art tools and platforms: the open source ns-3 network simulator and the PlanetLab testbed. ns-3 is the first network simulator that includes a mechanism to execute directly within the simulator existing real-world Linux protocol implementations and applications. Furthermore, it can be used as a real-time emulator for mixed (simulation-experimentation) network scenarios. PlanetLab is the well-known international experimental testbed that supports the development and the evaluation of new network services. It is composed of nodes connected to the Internet across the world, and uses container-based virtualization to allow multiple experiments running independently on the same node while sharing its resources.

  The overall objective of the project is to make available to networking research community, the SIMULBED platform that will: (1) allow to conduct easily mixed simulation-experimentation evaluation of networking protocols and (2) scale up the size of the PlanetLab experimental testbed, while maintaining a high degree of realism and increasing controllability and reproducibility. We will use the NEPI unified programming environment recently developed in the Planète project-team to help in simplifying the configuration, deployment and run of network scenarios on the platform. See the 2014 Update on the Simulbed web site.

Community

• Title: COMMUNITY: Message delivery in heterogeneous networks

• International Partner (Institution - Laboratory - Researcher):

  • University of California Santa Cruz (United States) - School of Engineering - Katia Obraczka

• Duration: 2009 - 2014

• Participants from Inria in 2014: Thierry Turletti, Chadi Barakat, Damien Saucez, Xuan Nam Nguyen, Hardik Soni and Bruno Nunes.

• Participants from USCS in 2014: Katia Obraczka and Mateus Santos, PhD Student, USP (research intern at UCSC in 2014).

• Participants from USP in 2014: Cintia Borges Margi.

• Web site: http://inrg.cse.ucsc.edu/community/

• Abstract: This Inria - UC Santa Cruz Team investigates a number of research challenges raised by message delivery in environments consisting of heterogeneous networks that may be subject to episodic connectivity.

  During the first three years of the COMMUNITY associate team, we have explored solutions to enable efficient delivery mechanisms for disruption-prone and heterogeneous networks (i.e. challenged networks). In particular, we have designed the MeDeHa framework along with the Henna naming scheme, which allow communication in infrastructure and infrastructure-less networks with varying degrees of connectivity. We have also proposed efficient routing strategies adapted to environment with episodic connectivity that take into account the utility of nodes to relay messages. The various solutions have been evaluated using both simulations and real experimentations in testbeds located at Inria and UCSC. These solutions have demonstrated good performance in challenged networks. However, the ossification of the Internet prevents the deployment of such solutions in large scale. So, in 2012 we decided to extend our collaboration in two research directions: (1) The exploration of the software-defined networking paradigm to facilitate the implementation and large scale deployment of new network architectures to infrastructure-less network environments, and (2) the design of innovative information-centric communication mechanisms adapted to challenged networks. In particular, we are designing mechanisms to p rovide flexible, efficient, and secure capacity sharing solutions by leveraging SDN in hybrid networked environments, i.e., environments that consist of infrastructure-based as well as infrastructureless networks. We are also investigating solutions to optimize caching in infrastructure and infrastructureless networks using SDN. We have also designed a content-optimal delivery algorithm, called CODA, for distributing named data over challenged networks. See the 2014 Update on the Community web site.