About the Workshop

In today's world of pervasive networks and ubiquitous computing, people and organizations often rely on time-critical tasks that require accessing data from dynamic information sources and generating responses derived from on-line processing of data in near real-time. In many application domains information sources are increasingly taking the form of data streams, i.e. time ordered series of events or readings. Examples include stock tickers in financial services, link statistics in networking, sensor readings in environmental monitoring, and surveillance data in Homeland Security, to name a few. The ever increasing rates of data stream sources and the stringent response time requirements of stream processing applications force a paradigm shift in how we process data, moving away from the "store and then process" model of database management systems towards the "on-the-fly processing" model of emerging stream processing systems (SPSs). Due to the large and growing number of users, queries, and information sources, as well as the high aggregate rate of data streams distributed across remote sources, scalability becomes a key challenge, necessitating the development of architectures, protocols, and algorithms that can support building highly scalable, available, and reliable SPSs.

This workshop aims at promoting novel research in the area of stream processing systems, looking for bringing together research ideas, concepts, and techniques from the fields of databases, information systems, and distributed systems.

Important Dates

Submission Deadline: November 24, 2008

Notification of Acceptance: January 15, 2009

Camera-Ready Copy Due: February 15, 2009

Workshop: May 29, 2009

Keynote Speaker

Dr. Tim Cornwell
Research Program Leader for Software Development at the Australia Telescope National Facility

Stream processing and the Square Kilometre Array
The Square Kilometre Array Project is an international collaboration to build a new radio telescope offering many orders of magnitude improvement over existing telescopes in survey speed. Australia is one of the two sites (the other is South Africa) shortlisted to host the SKA.
By 2020, SKA will be operational, consuming some large fraction of an Exaflop to process the data into scientific results. Thus the SKA computing system will be one of the very top of the Top 500 supercomputers. Scaling this peak of processing, "Mount Exaflop", can only be done a step at a time, starting in the lowlands. For us, this is the Australian Square Kilometre Array Pathfinder now being constructed at Boolardy in Western Australia. This 1% pathfinder, operational in 2013, has a number of technical challenges, including the development of phased array feeds for astronomy, the provision of 100 TeraFlop computing at reasonable capital and operational cost, and the development of a computing infrastructure capable of supporting the full potential of the telescope. For the infrastructure, we have evaluated a number of options, including classical message passing, workflow, and streaming systems. Our conclusion is that streaming is the best model for the processing, both for ASKAP and SKA, and that IBM System S is the implementation most suited to our needs and timescale. We have prototyped a number of our algorithms, moving the implementation from MPI to streaming under System S. I will discuss this work, and the implications for ASKAP, SKA, and other radio astronomical instruments.

About the Speaker
Tim Cornwell has a PhD (1980) from the University of Manchester in England where he worked on image processing algorithms for radio synthesis telescopes. His first significant contribution was the development of the self-calibration algorithm widely used in radio astronomy. In 1980, he moved to Socorro, New Mexico to work on the newly completed Very Large Array telescope run by the National Radio Astronomy Observatory. Over the 25 years at the NRAO, he made many contributions to radio astronomical techniques, including the key algorithms needed for wide fields of view. He also contributed in the areas of telescope design (for the Atacama Large Millimeter Array), telescope commissioning (the Very Long Baseline Array), observatory management, and software development. In 2004, he joined the Square Kilometre Array International Engineering Working Group, primarily to contribute towards computing and algorithms. In 2005, he moved to Australia to take the lead role in computing for the Australia SKA Pathfinder.