The Wide Area Large Data Object Architecture Page (WALDO) Page
WALDO at Supercomputing `97
Read about our demos and try them for yourself
We are exploring the use of highly distributed computing and storage
architectures to provide all aspects of collecting, storing,
analyzing, and accessing large data-objects. These data-objects can be
anywhere from tens of MBytes to tens of GBytes in size. They are
typically the result of a single operational cycle of an
instrument, such as: single large images from electron microscopes,
video images from cardio-angiography, sets of related images from
MRI procedures and images and numerical from a particle accelerator experiment.
The source of such data objects, e.g. centralized health care
facilities or large scientific instruments is often remote from the
users of the data and from available large-scale storage and
computation systems.
Our Large Data-object Architecture utilizes a high-speed
wide-area ATM network between the object sources and a mutli-level
distributed storage system
(DPSS).
As the data is being stored, a cataloguing system
(ImgLib)
automatically creates and stores condensed versions
of the data, textual metadata and pointers to the original data. The
catalogue system provides a Web based graphical interface to the
data. The user is able the view the low-resolution data with a
standard internet connection and Web browser, or if high-resolution is
required can use a high-speed connection and special application
programs to view the high-resolution original data.
WALDO Architecture
WALDO example
This example of a WALDO / ImgLib interface illustrates the
versatility of the approach. This
ImgLib
collection is built in real-time from
an on-line medical instrument that generates video data. Each rectangular area
in the background represents a large-data-object in terms of
textual metadata, URLs to related components (including several formats of
video clips), and a representative frame from the video clip.
In the foreground is a specialized video player (the "video" from the medical
system is in a special format) that can access data on the
DPSS
for playback at video rates.
(click on image for full screen version)
|
|
WALDO Papers |
-
"Real-Time Digital Libraries based on Widely Distributed, High Performance
Management of Large-Data-Objects"
(This paper describes real-time Generation and cataloguing of large data-objects in
widely distributed environments, i.e.,
a distributed, wide area network based approach to collecting, cataloguing, storing, and
providing Web access for large-data-objects that originate as high-speed data streams.)
Invited paper, International
Journal of Digital Libraries - Special Issue on “Digital Libraries in Medicine”. May, 1998.
-
PDF of paper
-
Internetworking '96 paper:
A Distributed Environments for Large Data-Objects:
Broadband Networks and a New View of High Performance, Large-Scale
Storage-Based Applications.
(Postscript)
-
APII Test-bed Forum paper: Distributed Environments for Large Data-Objects:
The Use of Public ATM Networks for Health Care Imaging Information Systems
-
Fifth NASA/Goddard
Conference on Mass Storage Systems and
Technologies paper:
Distributed Large Data-Object Environments:
End-to-End Performance Analysis of High Speed Distributed Storage
Systems in Wide Area ATM Networks
|
WALDO Applications |
-
A
Medical Imaging application using the DPSS and
ImgLib
-
A High Energy Physics data processing application.
|
This page last modified: Tuesday, 24-Aug-1999 14:06:41 PDT
