|
|
|
Almaden Institute
| |
Continuously Adaptive Processing of Data and Query Streams
|
Abstract:
Emerging networked applications such as real-time business processing,
information dissemination, and pervasive computing present new challenges
for data management and query processing. Unlike traditional applications,
in which data is relatively static and queries are short-lived, these
new applications require continuous processing of queries over dynamic
streams of data. Such needs are poorly served by existing database
technology, which depends on a priori knowledge of data and workload
characteristics. In this talk, I will describe the Telegraph system
currently under development by the database group at University of
California, Berkeley. Telegraph is based on an adaptive dataflow paradigm
that enables processing to adjust continuously to data and workload
variation. Telegraph also aggressively exploits shared processing
for dynamic multi-user workloads and attempts to leverage underutilized
resources as they are detected.
Michael Franklin is an Associate Professor of Computer Science
at the University of California, Berkeley where his research focuses
on the architecture and performance of distributed databases and
information systems. He received his Ph.D. from the University
of Wisconsin in 1993. He currently serves as an Editor of ACM
Transactions on Database Systems, Program Chair for the 2002 ACM
SIGMOD Conference, Vice Chair of the ACM SIGMOD Advisory Board,
and as a member of the Board of Trustees of the VLDB Endowment.
|
|
|
