Guru Parulkar: 2017 Designing Self-driving Networks Workshop


Wednesday, April 12, 2017
Location: McCaw Hall, Arrillaga Alumni Center

"From SDN to SDN"



This talk will explore how self driving networks (SDN) can be realized with software defined networking (SDN).

Software-Defined networking provides separation of forwarding and control planes and allows a network operator to program the forwarding plane via logically centralized control to enable various innovative applications and services. Software-Defined Networking is ready to go mainstream in data center, service provider, and enterprise networks.

Now we have an opportunity to build Self-Driving Networks (SDN) by bringing machine learning techniques to networking. Self-Driving Networks can take advantage of Software-Defined Networking to program the network in real time based on sensing, inference, learning, and control using machine learning techniques.


Guru is the Executive Director of Stanford Platform Lab at Stanford University. He has been in the field of networking for close to 25 years and has worked in academia, startups, a large company, and a top tier venture capital firm. At Stanford, Guru helped to create three large programs: OpenFlow / Software-Defined Networking, Programmable Open Mobile Internet 2020, and Stanford Experimental Data Center Laboratory. Prior to Stanford, Guru spent four years at the National Science Foundation (NSF) and worked with the broader research community to create programs such as GENI, Future Internet Design, and Network of Sensor Systems. Guru co-founded two startups, Growth Networks (acquired by Cisco) and Sceos (evolved to be Ruckus Wireless). Prior to Startups, Guru spent over 12 years at Washington University in St. Louis where he was a Professor of Computer Science and Director of Applied Research Laboratory.