Last year's Open Networking Summit far surpassed its expectations, resulting in a waiting list of 120 people looking to get into Stanford University's Li Ka Shing Center.
So this year, organizers moved the 2012 Open Networking Summit to a larger location, the Marriott Hotel in Santa Clara, Calif., and expanded its capacity from 800 to 860 registered attendees. The result was a second consecutive sellout and a waiting list of 50 and counting.
Given that the success of last year's Open Networking Summit helped spark a call to action for the software-defined networking movement, another year of research and publicity could make this year's event an important step in the development of the OpenFlow protocol.
Much of the anticipation heading into this year's event, which will run from April 16-18, surrounds the next step for what began as a research initiative and now holds the potential to revolutionize networking.
Software-defined networking essentially replaces much of the equipment and hardware used for controlling the network with an API, thus giving administrators more flexible control over the network while also eliminating much of the hardware investment previously required to do so. OpenFlow, consequently, is a protocol by which network administrators can gain control of a software-defined network and was the impetus for the Open Networking Foundation, a nonprofit organization formed in 2011 by a consortium of private- and public-sector organizations that are holding the Open Networking Summit.
This year's keynote speakers include Google Fellow and senior vice president for Technical Infrastructure Urs Holzle, NTT Communications' senior vice president for service infrastructure Yukio Ito, and NEC Corporation's board chairman and representative director Kaoru Yano.
Joining them will be a host of executives, experts and researchers from Yahoo, Verizon, Dell, HP, Stanford University, Big Switch Networks, Indiana University, Ncirca Networks, and Deutsche Telekom, among many others. Topics covered range from the impact of SDN on wide area networks and the internet as a whole to networking cost and management and overall performance at the enterprise level.
All told, the general feeling is that software-defined networking is a pretty big deal.
For some of the largest enterprises behind the Open Networking Foundation, the bigger picture of OpenFlow is beginning to become clear. Dr. Stuart Elby, chief technologist of Verizon Digital Media Services, who will also speak at the event, says SDN could provide an alternative that makes the service provider's current cost structure, which has served it well for that past 50 years, "not so attractive anymore."
Verizon's vast network involves an equally massive collection of network equipment installed in the field, where the technology behind the company's service offerings and network intelligence reside. Through SDN, Elby says Verizon will be able to centralize its intelligence from a high number of remote locations to its more accessible data centers. The software layer that would grant control to its network intelligence would enable Verizon to communicate and manage its network elements more flexibly, "so that we can explicitly define paths that might be based not just on traditional routing protocols, but will be based on things like service awareness or subscriber awareness or state of the network in terms of congestion or capabilities."
OpenFlow, consequently, will be critical to making this transition not just for Verizon, but any other organization looking to benefit from SDN.
"Software defined networking itself is a framework and it's very disruptive. It's sort of a radical change in how we do networking," Elby says. "But once you decide to do that, unless you think you're going to get all your software or all your components from one vendor, you need some standardization, some ways where your software can speak to any switch or router."
That's why Verizon, as well as fellow board members Yahoo, Google, Facebook, Microsoft, Deutsche Telekom and NTT, "jumped at" OpenFlow after the initial research work done at Stanford grabbed their attention, Elby says. By standardizing SDN, Elby says the ONF can "take OpenFlow from its initial academic inception and harden it up, expand it into something that can really be operational in our environments."
Currently, OpenFlow appears to be at the intersection of research and deployment. A few vendors, namely Big Switch Networks, NEC, IBM, and HP, have introduced their offerings to get in on this soon-to-be burgeoning market early, while Cisco is rumored to be quietly developing its own strategy.
At ONS, a bevy of other vendors plan to introduce their own contributions to bringing SDN capabilities to life in the enterprise. Dell will focus on ease-of-use and "cloud orchestration" techniques that could facilitate management of a software-defined network. Vello Systems will showcase its offerings for preventing latency in networks for both enterprises and service providers. Extreme Networks will present options for workflow, provisioning and management in campus networks and data centers. The list goes on and on.
From here, the ONF will continue to analyze the potential for SDN as the wheels of OpenFlow meet the road of enterprise and service providers' networks. Since February 2011, the foundation has already approved two versions of the OpenFlow protocol, having published Version 1.2 just two months ago.
Other research initiatives, such as the Open Networking Research Center, have reportedly recruited the assistance of founding researchers at Stanford University and the University of California, Berkeley.
Growing support for OpenFlow and SDN suggests that the standard has turned a corner toward large-scale deployment, Elby says.
"I really think the end of last year and beginning of this year we've really sort of crossed that line where companies realize that this is the real roadmap, the real product," Elby says. "It's not just something that's on the research side anymore."