Xin Liu

Professor, University of California, Davis

March 2nd, 2018, 11am-12pm, DBH 6011


Data-driven Approach in Networking


Based on network measurement and user behavior data, much recent work has studied the modeling and prediction of network utility and user experience using machine learning techniques. While it provides important insights, such modeling and prediction is often not the ultimate goal of networks. Ideally, a network should be able to learn its optimal control and resource allocation that maximize network utility and user experience in a proactive manner. To achieve this goal, machine learning and network resource optimization techniques can play a significant role. In this talk, we discuss some of the challenges and opportunities that we observe in data-driven network control and resource allocation. Using examples from real network control challenges, we discuss both applied and theoretical aspects of data-driven networking.

Speaker Bio:

Xin Liu received her Ph.D. degree in electrical engineering from Purdue University in 2002. She is currently a Professor in the Computer Science Department at the University of California, Davis. >From March 2012-June 2014, she worked in the wireless networking group at Microsoft Research Asia. She has studied cellular scheduling algorithms, cognitive radio networks, and wireless mesh networks. Her current research focuses on data-driven approaches in networking. She has received the NSF CAREER award (2005), and the Outstanding Engineering Junior Faculty Award from the UC Davis College of Engineering (2005), and the Chancellor's Fellowship (2011), and the ICNP best paper award (2017).