I dream of GENI

People often ask me what I see in my crystal ball regarding the future of the Internet and computing technologies. Recently when I looked, I saw a GENI! At the First GENI Engineering Conference held back in October in Minneapolis, I was formally introduced to the Global Environment for Network Innovations (GENI). GENI is a new initiative, announced by the NSF back in May of this year, and it is very much still getting off the ground.

So what is GENI? According to GENI’s website,

GENI is an experimental facility called the Global Environment for Network Innovation. GENI is designed to allow experiments on a wide variety of problems in communications, networking, distributed systems, cyber-security and networked services and applications. The emphasis is on enabling researchers to experiment with radical network designs in a way that is far more realistic than they can today. Researchers will be able to build their own new versions of the “net” or to study the “net” in ways that are not possible today. Compatibility, with the Internet is NOT required. The purpose of GENI is to give researchers the opportunity to experiment unfettered by assumptions or requirements and to support those experiments at a large scale with real user populations.

Note that this description does not talk about GENI being a network, but rather an environment for networking research. At the conference there was not discussion about building another network for GENI. The presentations and discussions were on the ‘experiments’ with a fundamental belief that ‘slices’ and/or ‘slivers’ from existing networks would be available. Think dedicated wavelengths and/or Ethernet VPN’s interconnecting experiment partners as examples.

What exactly do GENI participants hope to accomplish with these slices and slivers? One of the things they are thinking about is what a network might look like and require, not just in five or maybe ten years, but even 20 years from now. They want to use pieces of existing networks to experiment and then use the findings to plan for future needs.

As highlighted in the conference title, this was the first (public) GENI conference. As result, an appropriate amount of time was spent reviewing what GENI is, isn’t, history, etc. Particular treatment was given to the distinction between the GENI Project Office (GPO) and the GENI Science Council (GSC). The Council is about the research activities, the GPO is about the administration and operation of the project. The GPO was awarded to BBN by NSF. A very good treatment of the relationship of the GSC, GPO and the NSF can be viewed “here”:

It was clear from the onset that there were a lot of very smart people attending this conference. I’d estimate at least 100 people were in attendance and there was a strong showing of the actual research community that will likely be submitting the first round of proposals in December.

Much like the early Internet2 meetings, the GENI community has formed its own lexicon:

  • Experiment: this was the popular word, much like the popularity of ‘application’ in the early I2 days.
  • GENI-ize: to make something appropriate for use in a GENI environment.
  • Instantiate: from Unix and object-oriented programming world, to create an instance of. A very popular word at the conference.
  • Slice: from the GENI architecture, that portion of the network that a particular experiment runs in or across.
  • Sliver: a portion of a particular slice.

If you are interested in advanced networking research, I encourage you to visit the GENI website

Ben Colley is MOREnet Director of Strategic Technologies.

Ben Colley | Friday, December 7, 2007 | |


Copyright © 2007 The Curators of the University of Missouri. All rights reserved. DMCA and other copyright information.