The Department of Computer Science at the University of Cyprus cordially invites you to the Colloquium entitled:
Load Management for Big Streaming Data
Speaker: Prof. Panos K. Chrysanthis
For the past few years, our group has been working on problems related to Big Data through several projects. After briefly discussing these projects, the rest of this talk will present DILoS, which focuses on three of the eight Big Data's Vs, i.e., volume, velocity and variability. Today, the ubiquity of sensing devices as well as of mobile and web applications continuously generates a huge volume of data which takes the form of streams that are typically high-velocity (speed) and high-variability (bursty). In order to meet the near-real-time requirements of the monitoring applications and of the emerging ``Big Data'' applications, data streams need to be continuously processed and analyzed. Such processing happens inside Data stream management systems (DSMSs), which efficiently support continuous queries (CQs). CQs inherently have different levels of criticality and hence different levels of expected quality of service (QoS) and quality of data (QoD). In order to provide different quality guarantees to different client stream applications, we developed DILoS, a novel framework that exploits the synergy between scheduling and load shedding in DSMS. In overload situations, DILoS enforces worst-case response times for all CQs while providing prioritized QoD, i.e., minimize data loss for query classes according to their priorities. We further propose ALoMa, a new adaptive load manager scheme that enables the realization of the DILoS framework. ALoMa is a general, practical DSMS load shedder that outperforms the state-of-the-art in deciding when the DSMS is overload and how much load needs to be shed. We implemented DILoS in our real DSMS prototype system (AQSIOS) and evaluate its performance for a variety of real and synthetic workloads. Our experiments show that our framework (1) allows the scheduler and load shedder to consistently honor CQs' priorities and (2) maximizes the utilization of the system processing capacity to reduce load shedding.
Dr. Panos K. Chrysanthis is a Professor of Computer Science and the founding director of the Advanced Data Management Technologies Laboratory (ADMT Lab) [http://db.cs.pitt.edu] at the University of Pittsburgh. His lab has a broad focus on user-centric data management for scalable network-centric and collaborative applications and has fostered interdisciplinary collaborations between computer science, medicine and astronomy, both within and outside the University of Pittsburgh -- he is an Adjunct Professor at the Carnegie Mellon University and at the University of Cyprus, Cyprus. In 1995, he received one of the first NSF CAREER Awards for his pioneer work on mobile data management and in 2010, he was recognized as a Distinguished Scientist by ACM. In 2007, he was also elevated to the level of a Senior Member of IEEE. He is currently on the editorial board of IEEE TKDE and the Parallel and Distributed Databases Journal. DILoS was developed in collaboration with Thao N. Pham (as part of her PhD thesis) and Alexandros Labrinidis who is the co-director of the ADMT lab. This work has been funded in part by two NSF Awards and a gift from EMC/Greenplum.
|Mailing List: https://listserv.cs.ucy.ac.cy/mailman/listinfo/cs-colloquium|
|Sponsor: The CS Colloquium Series is supported by a generous donation from