System support for large-scale data stream processing
Dr. Xiaohui Gu
IBM T. J. Watson Research Center
Monday, October 16, 2006
Talk: 10:00 am - 11:00 am
Host: Phillip McKinley
Data stream processing has become increasingly important as many emerging applications call for sophisticated realtime processing over data streams, such as stock trading surveillance, sensor data analysis, network traffic monitoring and video surveillance. One of the major challenges for large-scale data stream processing is to provide an efficient, adaptive, and resilient system infrastructure that can support continuous query operations (e.g., windowed stream joins) over multiple high-volume and time-varying data streams in realtime. In this talk, I will present several new system management techniques to address the challenge including (1) adaptive load diffusion for multi-way stream joins, and (2) QoS-aware/sharing-aware component composition in distributed stream processing service overlay. I will also briefly mention several on-going work that applies machine learning techniques to achieve autonomic system management.
Xiaohui Gu is currently a research staff member at IBM T. J. Watson Research Center, New York. Her general research interests include distributed systems, operating systems, and computer networks with a current focus on large-scale data stream processing and autonomic system management using machine learning techniques. She received ILLIAC fellowship, David J. Kuck Best Master Thesis Award, and Saburo Muroga Fellowship from University of Illinois at Urbana-Champaign. She received IBM first Invention Award on 2004, and first Plateau Invention Achievement Award on 2006. She has served program committee and/ organizing committee in PerCom 2006-07, RTSS 2006, ICPS 2005-07, ACM Multimedia 2005 service composition workshop, ICDE 2007 AIMS workshop. She received her PhD degree in 2004 and MS degree in 2001 from the Department of Computer Science, University of Illinois at Urbana-Champaign. She received her BS degree in computer science from Peking University, Beijing, China. More information can be found at her homepage http://www.research.ibm.com/people/x/xgu.