Prof. Peter Brezany
          Institute of Scientific Computing, University of Vienna
         Nordbergstrasse 15/C/3, A-1090 Vienna, Austria

                         in cooperation with

                     Prof. Abdelkader Hameurlain
           Institut der Recherche en Informatique de Toulouse
                     Universite Paul Sabatier
       118, Route de Narbonne, 3, 1062 Toulouse Cedex, France


              "Mobile Agent Based Query Processing on the Grid"
               -----------------------------------------------

The trend of Grid computing is strongly oriented towards data intensive
applications, accessing more and more  relational databases, domain
specific scientific databases and other types of data repositories.
The benefits accruing from the joint application of database and grid
technologies have  been recognised by many fields of science
and technology.
The tasks associated with these issues have driven the Grid database
research in the last five years. In this effort, distributed query
processing is especially challenging research topic.

Because Grid represents a highly volatile distributed environment, dynamic
query processing able to sense the query execution status and Grid status
in specified time intervals and appropriately adapt the query execution
workflow, plays an important role. So far, to the best of our knowledge,
only one research effort, the U.K. Grid database project OGSA-DQP,
addressing this issue has been reported in the literature. The project
responded to the needs of e-Science applications, especialy life-science
ones, running long-time queries to distributed databases integrated into
the Grid. In this project, the researchers developed a solution based on
centralized control of dynamic optimization processing, which is a
bottleneck in large-scale applications.

To avoid it, this talk presents a novel  approach to dynamic query
processing on the Grid, which is based on integration of mobile agent
optimization, cost models and monitoring methodology, and agent-oriented
Grid architectures to one coherent framework.

Keywords: Grid, Data Sets, Dynamic Query Optimization, Mobile Agents,
          Monitoring, Cost Model