-------------
Subject: IEEE SCALE 2011 Award for enabling LIGO Data-Analysis Application on Cloud Computing Environment
-------------

A team from CLOUDS Lab (Dept. of Computer Science and Software
Engineering) led by Professor Rajkumar Buyya and Astrophysics Group
(School of Physics) led by Dr. Andrew Melatos at the University of
Melbourne is one of the winners of the 4th IEEE International Scalable
Computing Challenge (SCALE 2011) Award. Their innovative work was on
developing Cloud Computing platform for LIGO (Laser Interferometer
Gravitational-Wave Observatory) data-analysis experiment. The SCALE 2011
competition was held along with CCGrid 2011 conference in California, USA
during May 22-26, 2011.

The team members of this winning entry are: Suraj Pandey, Letizia Sammut,
Andrew Melatos, Rajkumar Buyya

The final two winners are selected based on the actual presentation and
live demonstration of the work in-front of a judging panel and computer
scientists. Judging criterion include: originality, innovative technology
and application, scalability of software system and its applications, and
potential of the work to impact on scientific community.

The Laser Interferometer Gravitational Wave Observatory (LIGO) is one of
the world’s largest physics projects. It will inaugurate a new era in
astronomy by detecting Einstein’s elusive gravitational waves, one of
Nature’s great unexplored frontiers. Melbourne is a partner in an
exciting, USA-led proposal to build LIGO Australia, one of three networked
LIGO detectors, by 2015.

Gravitational waves (GW) are ripples thought to occur in the fabric of
space-time that result from interstellar collisions, explosions, or
movement of large and extremely dense objects such as neutron stars. Those
ripples can then pass through the space-time that Earth occupies, causing
a distortion which Advanced LIGO is meant to pick up. Currently, several
interferometric GW detectors around the world such as LIGO, VIRGO, GEO600,
TAMA300 have been collecting data that could then be used by scientists
for searching GWs.

Most of these searches can be represented as a workflow consisting of
tasks linked through data dependencies. Each workflow can then be
replicated using different parameter set. Numerous scientists would then
use these multiple workflows for analysing and searching GWs. Without
support for scheduling and management of data and tasks, in the worst
case, the parallel execution of these multiple workflows will be reduced
to sequential execution due to contention of common computing resources.

Scalable executions of LIGO data-analysis workflows on computing Clouds
can be made possible by:


  1. Allocating Cloud resources to tasks, workflows, and users effectively  
     to avoid resource contention – dynamic resource provisioning problem
  2. Minimising delay in executing workflows – task/workflow/users scheduling problem
  3. Minimising replication of data that are common across many workflow executions
  4. Using one or more Cloud Data centers depending upon user QoS needs

The team designed and developed a Cloudbus Workflow Engine to address the
above challenges. The engine was used for deploying LIGO data-analysis
application on Amazon EC2 and S3 using over 400 computing nodes (VM
instances). This experiment on Clouds is managed via a Web portal
supporting the entire life cycle of the experiment: from the creation of
application workflow to managing executions across distributed Cloud nodes
to collection and online visualisation of Gravitational Wave Search
results.

This work will play a significant role in demonstrating the potential of
Cloud computing environment for LIGO data-analysis applications.
======================================================================