Other founding members of the ONF include: Broadcom, Brocade, Ciena, Cisco, Citrix, Dell, Ericsson, Force10, HP, IBM, Juniper Networks, Marvell, NEC, Netgear, NTT, Riverbed Technology, and VMware.
SDN promises to make network data handling more efficient and flexible through automation and programming. Existing network switches provide mechanisms for quality-of-service adjustments, allowing network data types to be differentiated or blocked. SDN offers a way to optimize the use of many of these capabilities and to deploy new ones. It could help network switches communicate to determine optimal solutions to network problems.
For example, SDN could assist with re-routing data flows dynamically during a particularly popular online event. It could be used to detect denial of service attacks more efficiently, or to provide the infrastructure to outsource the management of home networks.
"Software-Defined Networking will allow networks to evolve and improve more quickly than they can today," said Urs Hoelzle, ONF president and chairman of the board, and SVP of engineering at Google. "Over time, we expect SDN will help networks become both more secure and more reliable."
Arne Josefsberg, general manager of Windows Azure Infrastructure at Microsoft, said that programmable network management systems would benefit Microsoft's cloud services platform.
Arising from a six-year research collaboration between Stanford University and the University of California at Berkeley, SDN consists of two primary elements, a software component called OpenFlow and a set of management interfaces for network service providers.
The aim of the ONF initially will be to encourage the adoption of the OpenFlow standard through free licensing.
The nascent technology is already prompting some concern. In a message posted to David Farber's Interesting People mailing list, privacy advocate Lauren Weinstein observed that without a network neutrality framework, SDN could limit the services or options of Internet users.
"While the stated possible positives of such technology are real enough, the same mechanisms could be used to impose exactly the sorts of walled gardens, service degradations, and 'pay to play' limits that are at the heart of Net Neutrality concerns, as dominant ISPs in particular would be tempted to leverage this technology to further restrict user applications to the benefit of their own profit centers," he wrote.
Yet any technology can be misused. Absent a clear and present danger, technical innovation shouldn't be shunned because the politics of network management remain unsettled.