VLDB Workshop on
Data Management in Grids
http://liris.cnrs.fr/~jpierson/DMG_VLDB05/
Co-located with VLDB’05
Trondheim,
Norway, 2-3 September 2005
Context
VLDB'05
(Very Large Data Bases, http://www.vldb.org/) is the 31st Conference in
the series: It is one of the top conferences on the management of data bases in
the world. This year, a new workshop is organized at VLDB'05 : Data Management
in Grids.
Topics of Interest
Since the mid nineties and the emergence of
Grids, many research activities have been initiated in relation to data
management in these dynamic, heterogeneous and cross-organizational
environments. The database community can offer her unique expertise in the
management of very large, widely distributed databases. Conversely, Grids offer
a novel and very exciting field of research for database scientists both in
terms of application domains and fundamental research.
This workshop is intended to bring together
these two communities, and thus to offer a unique workspace for researchers to
discuss and exchange ideas about the emerging challenges and opportunities
offered by Data Grids.
Relevant topics for the workshop include all
aspects related to the management of data in a Grid (non-exhaustive list) :
-
Data
Access
-
Data
Interoperability
-
Semantic
Grids
-
Mediation
/ Negotiation
-
Security:
access control, policy, privacy
-
Authenticity
and integrity
-
Data
Placement: replication, migration
-
Data
Streams
-
Metadata
Management
-
Indexing
-
Query
processing
-
Caching
-
Data
Warehouses
-
Unique
identification of data entities
-
Data
Definition/Model Management
-
Data
De-identification
-
Data
scheduler and data-aware scheduling
-
Information
sharing
-
Information
dissemination
-
Infrastructure
independence for data management
-
Federation
of data management systems
-
Applications
dealing with large databases
Submission
Authors are
invited to submit original, unpublished research papers that are not being
considered for publication elsewhere.
Manuscripts
should be submitted electronically as PDF or PS files via email to : Jean-Marc.Pierson@liris.cnrs.fr
Research
papers should not exceed 12 pages in length.
They should
be formatted using the camera-ready templates of Springer Lecture Notes in
Computer Science (http://www.springer.de/comp/lncs/authors.html).
Revised
versions of full papers will be published as a post-conference LNCS 
(http://www.springeronline.com/lncs)
volume.
At least
one author is required to register for the workshop and present the work.
Registration is done via the VLDB registration site (the
fee
includes the post conference proceedings as well).
Important Dates :
Submission
deadline : 22 May 2005
Acceptance
notification : 24 June 2005
Final paper
due : 18 July 2005
Workshop
dates : 2-3 September 2005
Program Chair
Jean-Marc
Pierson
LIRIS Lab.,
CNRS
National
Institute of Applied Sciences (INSA)
Lyon,
France
Program Committee
Lionel BRUNIE,
LIRIS, France
Rajkumar
BUYYA, University of Melbourne, Australia
Neil P.
CHUE HONG, EPCC, The University of Edinburgh, UK
Alvaro A.A.
FERNANDES, The University of Manchester, UK
Ian FOSTER,
Argone National Laboratory, USA
Dieter
GAWLICK, Oracle, USA
Peter KACSUK, Mta Sztaki Research Institute, Hungary
Peter
KUNSZT, CERN, Switzerland
Stephen A.
LANGELLA, The Ohio State University, USA
Susan
MALAIKA, IBM, USA
Johan
MONTAGNAT, CNRS, France
Reagan
MOORE, SDSC, USA
Gianluca
MORO, DEIS - University of Bologna, Italy
Brigitte
PLATEAU, ID-IMAG, France
Thierry
PRIOL, IRISA, France
Heinz
STOCKINGER, University of Vienna, Austria
Accepted papers : 9 contributions have been accepted
over 24 papers submitted. Authors will have 20 minutes to present their work.
Final Program
Friday, September 2th
2:00 PM :
Opening of the workshop. J-M Pierson. [PPT]
2:05 :
Keynote : Reagan Moore, San Diego Supercomputing Center, CA, USA [PPT]
Title : Globally
Distributed Data
Abstract :
The
management of globally distributed data is simplified through the use of data
grids which enable data sharing environments. Data grids provide
both the interoperability mechanisms needed to interact with legacy storage
systems and legacy applications, as well as the logical name spaces
needed to identify files, resources, and users. Data grids also provide support
for consistent management of state information about each file within the
distributed environment. The state information includes access
controls, descriptive metadata, and administration metadata. These
capabilities enable data virtualization, the ability to manage data
independently of the chosen storage repositories. Examples of management
of globally distributed data will be provided including data grid federation,
distributed digital libraries, and distributed persistent archives.
3:00 :
Session 1. Chair: Jean-Marc Pierson
XML Data
Integration in OGSA Grids [PPT]
Carmela Comito and
Domenico Talia
Towards
Dynamic Information Integration [PPT]
Juergen Goeres, University of Kaiserslautern, Heterogeneous
Information Systems Group
3:45 :
Coffee Break
4:15 :
Session 2. Chair : Alvaro A.A. Fernandez
Adapting to
Changing Resource Performance in Grid Query Processing [PPT]
Gounaris et al.
An adaptive
distributed query processing grid service [PPT]
Fabio Porto, Vinícius
F. V. da Silva, Márcio L. Dutra and Bruno Schulze
Framework
for Querying Distributed Objects Managed by a Grid Infrastructure [PPT]
R. Fomkin et al.
Saturday, September 3rd
9 AM : Invited Talk : Mario Antonioletti,
EPCC, The University of Edinburgh, UK [PPT]
Title : Overview of the
DAIS specifications
Abstract :
Grid computing provides functionalities to support the sharing of heterogeneous distributed computational and data resources. The Global Grid Forum (GGF) is a community of users, developers and vendors that forms the focus for a global standardization effort for grid computing. Central to this is the Open Grid Services Architecture (OGSA), and its associated specifications, which define consistent interfaces through web services to components of a grid infrastructure. Both the web service and grid communities stand to benefit from the provision of consistent and agreed web service interfaces for data resources and the systems that manage them. (optional in italics) This presentation describes, motivates and presents the context for the results of the GGF Data Access and Integration Services Working Group (DAIS-WG), which is defining data access and integration services for OGSA. These services are defined in a family of specifications: WS-DAI, which specifies a collection of generic data resource properties and messages; and WS-DAIR and WS-DAIX, which specialise WS-DAI for use with relational and XML data resources, respectively. The WS-DAI specifications can be applied in regular web services environments or as part of a grid fabric.
9:45 : Session 3 : Chair : Reagan Moore
RRS:
Replica Registration Service for Data Grids [PPT]
Arie Shoshani, Alex Sim, Kurt Stockinger, Lawrence
Berkeley National Laboratory, California, USA
File
Caching in Data Intensive Scientific Applications on Data-Grids [PPT]
Ekow Otoo , Doron Rotem
, Alexandru Romosan , and Sridhar Seshadri
10:30 :
Coffee Break
11:00 : Session 4 : Chair: Lionel Brunie
Datagridflows:
Managing Long-Run Processes on Datagrids [PPT]
Arun Jagatheesan, Jonathan Weinberg, Reena Mathew, Allen Ding, Erik Vandekieft, Daniel Moore, Reagan Moore, Lucas Gilbert, Mark Tran
Servicing
Seismic and Oil Reservoir Simulation Data through Grid Data Services [PPT]
Sivaramakrishnan Narayanan, Tahsin Kurc, Umit Catalyurek, Joel Saltz
11:45 : Discussion
and Closing Remarks