What is GENI?

Global Environment for Network Innovations (GENI) is a facility concept being explored by the US computing community. The goal of GENI is to increase the quality and quantity of experimental research outcomes in networking and distributed systems, and to accelerate the transition of these outcomes into products and services that will enhance economic competitiveness and secure the Nation's future. Ultimately, research performed on GENI is expected to lead to a transition of the Internet as we know it today.

With the support of the NSF Directorate for Computer and Information Science and Engineering (CISE), the computing community is currently developing the conceptual design of the facility. A number of workshops have already taken place, and under the leadership of a planning group an initial strawman design has been completed. This design is being shared broadly herein for comment. CISE will support a number of town hall meetings in the early spring of 2006 to gather community input that further informs and refines the design.

Using a competitive merit review process, CISE is planning to support the establishment of a GENI Coordinating Consortium (GCC) in 2006. The GCC will represent the computing community's broad research interests in the GENI facility.

This web site is currently maintained by the GENI planning group as a forum for discussing GENI, which will in turn help guide CISE as it makes GENI a reality. It should be viewed as continually under construction. Please send comments on these web pages, as well as feedback on GENI, to the discussion mailing list. There is also an official NSF web site for GENI, and NSF welcomes questions and comments at geni-info@nsf.gov.

While this site includes information on research enabled by a GENI facility, its main purpose is to facilitate the further development of the conceptual design of a GENI facility. We expect the research enabled by GENI will be shaped by both the discussion that takes place in this forum, and other conversations that take place within the CISE research community (e.g., in the context of the NeTS, Cyber Trust, CSR, and other programs).

Who is GENI?

The research community is helping NSF define GENI. Its roots go back to an NSF workshop on Disruptive Network Innovation in early 2005. That workshop recommended that NSF's NeTS program focus on architectural research, and provide the experimental infrastructure needed to support that research. Subsequent workshops focused on the research agenda (and infrastructure needs) of the optical, wireless, sensor network, and distributed systems communities. Today, representatives of those communities form the planning and working groups that are driving the effort. The computing research community at large will be largely responsible for overseeing the construction of the GENI facility, and continues to contribute to its design.

Research Opportunities

While there is universal agreement that creating a Future Internet that meets the demands of the 21st century is both a national priority and ripe with research challenges and opportunities, there are two general schools of thought as to how to pursue this goal.

One view is that we may be at an inflection point in the societal utility of the Internet, with eroding trust, reduced innovation, and slowing rates of update. This view points to assumptions built into today's 30-year-old architecture that limit its ability to cope with emerging threats and opportunities, and argues that it is time for a "clean slate" reconceptualization of the Internet architecture.

The other view takes today's Internet as a given, and argues that future innovation will take the form of new services and applications running on top of the Internet. Over time, these innovations will likely have a transformational effect on the Internet, but it is simply not practical to think in terms of replacing all of today's Internet infrastructure.

We take the position that this is a false, or at least unnecessary, dichotomy. First, we interpret "Future Internet" very broadly to include innovations at any level of the architecture; there should be no pre-conceived notion that the outcome of a research program creating a Future Internet will be limited to any one protocol or layer. Research is equally likely to result in alternative protocols and architectures running inside the network, as in new applications and services running as overlays on top of today's network. Collectively, all these layers will form the Future Internet. Second, research should employ clean slate thinking that is not constrained by today's Internet, but this does not imply that the outcome will necessarily be an entirely new Internet. In other words, "clean slate" is a process, not a result. It is likely that different researchers will chose to leverage different aspects of today's Internet, while exploring alternatives to other elements. Third, there will likely be opportunities at the boundary between these two perspectives, that is, in exploring how today's architecture is best evolved over time to better support emerging overlay services.

Facility Concept

The GENI facility will be unique among experimental platforms in that it will be designed to support both research and deployment, effectively filling the gap between small-scale experiments in the lab, and mature technology that is ready for commercial deployment. We envision researchers using GENI to evaluate new network systems on large-scale (global) system, learning from real workloads as users begin to exercise those systems, and hardening the successful systems as user adoption grows.

At the physical level, GENI will consist of a collection of physical networking components, including links, forwarders, storage, processor clusters, and wireless subnets. These resources are collectively called the GENI substrate. On top of this substrate, a software management framework will overlay network experiments on the substrate, where each experiment is said to run in a slice of the substrate.

Four key ideas make this possible. First, the substrate components will be programmable. This will make it possible to embed any network experiment in GENI, including clean-slate designs that are radically different from today's Internet architecture and protocols. Second, the substrate will be virtualizable. This will make it possible to embed multiple slices in the substrate at the same time. This is important because it will allow experimental services and architectures to run continuously, rather only in a reserved time slot. Third, GENI will include mechanisms that allow end-users to seamlessly opt-in to experimental services. This will make it possible to attract real users, which is critical to evaluating new services under real-world conditions. It also enables incremental adoption, which is key to encouraging wide-spread deployment. Finally, GENI will be modular, with a well-defined architecture and set of interfaces. This will make it possible to extend GENI with new networking technologies as they become available. That is, GENI will not be a static artifact, but rather a dynamic infrastructure that is continually renewed.