Welcome to the home page of the Data Management Research Group at Brown University's Department of Computer Science.
We have a strong interest in data management
for object-oriented and networked systems, including the intelligent use of resources for
broadcast and dissemination-based systems. We focus on the emerging area of
data-stream management systems with an emphasis on real-time
processing, quality of service maintenance, and approximate answers. Our work
also includes content-based data access in wireless and ad hoc
networks and parallel OLTP databases.
Latest News
The New England database community will hold the fifth annual New England Database Summit on February 3rd at MIT in Cambridge, Massachusetts. In this all day conference-style event, participants from the research community and industry in the New England area come together to present ideas and discuss their research and experiences. Registration for the event is free, and anyone is welcome to attend. The event will feature keynotes from Johannes Gehrke (Cornell) and Mark Callaghan (MySQL Team @ Facebook).
The Brown Data Management Research Group will present new research on the H-Store OLTP database system.
We hope to see you there.
The Brown Data Management Research Group has the following paper in ICDE 2012:
- Learning-based Query Performance Modeling and Prediction
Mert Akdere, Ugur Cetintemel, Matteo Riondato, Eli Upfal, Stanley Zdonik (Project Longview)
This paper studies the practicality and utility of sophisticated learning-based models for accurate query performance prediction (QPP). We propose and evaluate predictive modeling techniques that learn query execution behavior at different granularities, ranging from coarse-grained plan-level models to fine-grained operator-level models. We demonstrate that these two extremes offer a tradeoff between high accuracy for static workload queries and generality to unforeseen queries in dynamic workloads, respectively, and introduce a hybrid approach that combines their respective strengths by selectively composing them in the process of QPP. We discuss how we can use a training workload to (i) pre-build and materialize such models offline, so that they are readily available for future predictions, and (ii) build new models online as new predictions are needed. All prediction models are built using only static features (available prior to query execution) and the performance values obtained from the offline execution of the training workload. The results of an extensive experimental evaluation provide quantitative evidence that learning-based modeling for QPP is both feasible and effective for both static and dynamic workload scenarios.
The Brown Data Management Research Group has the following paper in VLDB 2012:
The Brown Department of Computer Science is hosting several database talks this semester:
Please see the Brown CS event calender for more details and times.
Mert Akdere has completed his Ph.D. and joined Google. Congratulations!