Processing of Aggregations over Big Data Streams

Speaker : Professor Panos Chrysanthis
University of Pittsburg
Date: 27/02/2019
Time: 2:00 pm - 3:00 pm
Location: Paris-Rennes Room (EIT Digital)

Abstract

Online analytics and real-time data processing in most advanced IoT, scientific, business, and defense applications, rely heavily on the efficient execution of large numbers of Aggregate Continuous Queries (ACQs). ACQs continuously aggregate streaming data and periodically produce results such as max or average over a given window of the latest data.  Low operational cost and timely processing are of paramount importance in these applications. To meet these requirements under fixed resources, we have developed incremental evaluation algorithms as well as scheduling, stream partitioning and load shedding techniques for window-based aggregations.  In this talk, we will first overview our aforementioned contributions and then focus on two recent ones, (1) SlickDeque that optimizes the execution of multi-ACQs and (2) Concept-driven load shedding that adapts grouped aggregations to changing workloads.

Bio

Panos K. Chrysanthis is a Professor of Computer Science and the founding director of the Advanced Data Management Technologies Laboratory in the School of Computing and Information at the University of Pittsburgh.  He is also an Adjunct Professor at the Carnegie Mellon University and University of Cyprus. His research interests lie at the intersection of data management (Big Data, Databases, Data Streams & Sensor networks), distributed & mobile computing, operating and real-time systems.  He is a recipient of the NSF CAREER Award for his pioneer work on mobile data management, and he is an ACM Distinguished Scientist and a Senior Member of IEEE. He is also a recipient of the University of Pittsburgh Provost Award for Excellence in Mentoring (doctoral students). He is currently the Special Issues Coordinator for the Distributed and Parallel Databases Journal and on the editorial board of several journals, and has repeatedly served as a program committee chair and member in all major data management conferences. He earned his BS degree from the University of Athens, Greece and his MS and PhD degrees from the University of Massachusetts at Amherst.