NSF Equipment Award
May 2006
Congratulations to Profs. Elke Rundensteiner, Murali Mani, and George Heineman for winning an NSF equipment award for "High Performance Infrastructure for Data-Intensive Stream Processing Techniques". The award, for $100,000, will add significantly to the CS Department's ability to perform state-of-the-art research.
Edited Extracts from the Abstract:
- The database and software engineering faculty in the Computer Science department at Worcester Polytechnic Institute propose to explore a set of closely related research projects around the common theme of data- and compute-intensive stream processing technologies.
In particular, we expect that our collaborative research agendas will result in novel break-throughs in the following areas:
1. ETL: High-performance data warehouse load and maintenance strategies using innovative memory-resident pipelined processing techniques;
2. D-CAPE: Continuous stream processing technologies supporting on-line plan adaptation and optimization strategies coordinating run-time query workload re-distribution versus disk spilling;
3. RAINDROP: Scalable Xquery processing over XML streams offering novel advances in automata-style processing, in stream-specific multi-query optimization, and in XML-specific load shedding;
4. XMONITOR: Real-time monitoring infrastructure of complex distributed systems, enabled by scalable processing of complex content-based filtering queries against XML event message streams;
5. PYRAMID: Configurable performance modeling infrastructure for distributed application evaluation to enable researchers to rapidly set up and execute performance runs in distributed environments.
Support of stream processing will have a significant impact on applications such as monitoring for changes in environmental conditions such as smoke in buildings, medical conditions that require attention or medication, or critical military movements, to name a few.
Common to our projects is the desire to deal with the challenges and opportunities raised by the tools of the new era of computing environments: portable computers, wireless communications and high bandwidth. In such environments, high volumes of stream data sources may be present anywhere and at any instant. The amount of data from applications we work with are typically enormous, possibly in the order of tera-bytes. Clearly, high-performance computing power needs to be employed for processing such high volumes of data.
Last modified: August 02, 2006 16:11:42