Title of the Talk:

Edge-based Machine Learning for Cyber Physical Systems

Talk Abstract

As the scale of cyber physical systems (CPS) grows, many CPS systems or subsystems of larger CPS are now deployed at the computing edge where real-time control of these CPS must be enforced primarily using data available locally. Data-driven ML models are increasingly being adopted in the controller designs for these CPS. However, due to emergent properties of CPS, the installed ML-trained models often incur concept drift thereby requiring model re-training. Unfortunately, due both to communication overhead and timeliness constraints of CPS, such ML re-training cannot be conducted in a resource-rich cloud environment but rather must be conducted at the edge while continuing to host the existing control logic until new models are learned. In this talk, we will briefly describe our recent research on a system called DeepEdge that addresses these problems. We will also highlight potential opportunities for using SDN in these use cases and security vulnerabilities that may manifest in these deployed systems.

Speaker Bio

Aniruddha Gokhale is a Full Professor in the Department of Electrical Engineering and Computer Science, and Senior Research Scientist at the Institute for Software Integrated Systems (ISIS) both at Vanderbilt University, Nashville, TN, USA. His current research focuses on developing novel resource management algorithms and model-driven engineering tools to address emerging challenges in edge-to-cloud computing, real-time stream processing, and publish/subscribe systems as applied to cyber physical systems including smart transportation and smart cities. He is also working on using cloud computing technologies for STEM education. Dr. Gokhale obtained his B.E (Computer Engineering) from University of Pune, India, 1989; MS (Computer Science) from Arizona State University, 1992; and D.Sc (Computer Science) from Washington University in St. Louis, 1998. Prior to joining Vanderbilt, Dr. Gokhale was a member of technical staff at Lucent Bell Laboratories, NJ. Dr. Gokhale is a Senior member of both IEEE and ACM, and a member of ASEE. His research has been funded over the years by DARPA, DoD, industry and NSF including a NSF CAREER award in 2009