1 / 7

Testbeds and the evolving research paradigm

Testbeds and the evolving research paradigm. Shivendra Panwar Based on discussions with Fraida Fund, Pei Liu and Thanasis Korakis Polytechnic Institute of New York University Brooklyn, NY CCW 2012. How has the research paradigm changed in networking?.

lorne
Download Presentation

Testbeds and the evolving research paradigm

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Testbeds and the evolving research paradigm Shivendra Panwar Based on discussions with Fraida Fund, Pei Liu and ThanasisKorakis Polytechnic Institute of New York University Brooklyn, NY CCW 2012

  2. How has the research paradigm changed in networking? • Major corporations do not dominate research as they once did • Puts more of a spotlight on academic researchers • This implies the need to push research further out to reality • Increases the importance of testbed-based research • Even testbed “failures” are often successful! • A counter-example, and is this all good?

  3. Platforms for Future Internet Experimentation Internet as a Testbed (Seattle) Collection of Heterogeneous Testbeds (GENI, FIRE projects) Distributed Testbed (PlanetLab) Testbed with Programmable Network (ORBIT, OFELIA, CORNET) Fidelity to “real” Internet Emulation (Emulab, DETER) Simulation (ns-2/ns-3,OPNET) Programmability of network

  4. Platforms for Future Internet Experimentation Complex experiments Complex experiments Results likely to hold in “real” world Less repeatable Fidelity to “real” Internet Results less likely to hold in “real” world Repeatability Controlled experiments Controlled experiments

  5. Platforms for Future Internet Experimentation Good for testing future technology Technology can be deployed today Support clean-slate experiments, fundamental changes Easy to learn Programmability of network Limited ability Steep learning curve

  6. Shared Design Challenges • Future-proof: Design testbeds to study solutions that haven’t been developed yet • Flexible use: Support “clean slate” experiments but allow experimenters to re-use existing technologies • Open: Simple, open architectures encourage user-contributed tools and resources.

  7. Shared Operational Challenges • Support real experimenters: Adapt to the way experimenters actually use testbed, rather than what designers anticipated • Clear expectations: Help users understand advantages and limitations of testbed platform and design experiments accordingly

More Related