|
Title: Autonomic Grid Computing
Speakers:
Manish Parashar, Rutgers University (USA)
Omer Rana, Cardiff University (UK)
Abstract:
Grids are rapidly emerging as the dominant
environments for distributed problem solving and are enabling
a new generation of scientific and engineering applications
that are based on seamless aggregations and interactions.
However Grids are inherently large, complex, heterogeneous
and dynamic, globally aggregating large numbers of independent
computing and communication resources, data stores and sensor
networks. Furthermore, emerging applications are similarly
complex and highly dynamic in their behaviors and interactions.
Together, these characteristics result in application development,
configuration and management complexities that break current
paradigms based on passive components and static compositions.
Increasing complexity is also likely to lead to system administrators
finding it difficult to take advantage of changes in individual
components. Furthermore, system administrators may often prefer
to utilize their prior experience and techniques for managing
systems - and may not be effectively utilizing improvements
in individual components.
Clearly, there is a need for a fundamental
change in how these applications are developed and managed.
This has led researchers to consider alternative programming
paradigms and management techniques that are inspired by strategies
used by biological systems to deal with complexity, dynamism,
heterogeneity and uncertainty. The approach, referred to as
autonomic computing, aims at realizing computing systems and
applications capable of managing themselves with minimal human
intervention. An autonomic system/application has the capabilities
of being contextually aware, self-defining, self-healing,
self-configuring, self-optimizing and self-protecting.
From a research perspective, autonomic computing
brings together a number of different areas in artificial
intelligence, self-organization/emergent behavior, distributed
computing, security, and dependability. The activities necessary
to construct such systems include:
-
the expectations a user has of such
a system - generally translated to a high-level policy
being implemented;
-
the measurements that must be made
of the actual system in operation;
-
analyzing these measurements, and
comparing these with the requirements set out in the expectations;
and
-
actions that need to be undertaken
as a response - ranging from gathering of additional data
to reconfiguring components of the system.
The goal of this tutorial is to motivate
and introduce autonomic Grid computing, highlight its challenges
and opportunity and illustrate how it can be used to enable
science and engineering applications.
About the Speakers
Manish Parashar is Professor of Electrical
and Computer Engineering at Rutgers University, where he also
is co-director of the Center for Advanced Information Processing
(CAIP). He received a BE degree in Electronics and Telecommunications
from Bombay University, India and
MS and Ph.D. degrees in Computer Engineering from Syracuse
University. He has received the Rutgers Board of Trustees
Award for Excellence in Research (2004-2005), NSF CAREER Award
(1999) and the Enrico Fermi Scholarship from Argonne National
Laboratory (1996). His research interests include autonomic
computing, parallel & distributed computing (including
peer-to-peer and Grid computing), scientific computing, and
software engineering. Manish is a member of the
executive committee of the IEEE Computer Society Technical
Committee on Parallel Processing (TCPP), part of the IEEE
Computer Society Distinguished Visitor Program (2004-2006),
and a member of ACM. He is the co-founder of the IEEE International
Conference on Autonomic Computing (ICAC) and is the co-editor
the handbook "Autonomic Computing: Concepts, Infrastructure,
and Applications" published in December 2006. For more
information please visit
http://www.caip.rutgers.edu/~parashar/.
Omer Rana is a Professor in Performance Engineering
at the School of Computer Science (Cardiff University) and
the Deputy Director of the Welsh eScience Centre. He holds
a PhD in "Neural Computing and Parallel Architectures"
from the Department of Computing, Imperial College (University
of London). He is currently involved in three European projects
related to Grid Computing - the "Provenance" project
(within which he leads a work package on Tools and Setup),
the "CATNETS" project (within which he leads a work
package on application deployment) and the "SORMA"
project (within which he undertakes work on Service Level
Agreements). His research has focused on the use of intelligent
techniques for resource and performance management within
distributed systems. This has ranged from work on distributed
object systems based on CORBA, integration of parallel computing
libraries with distributed objects (such as Java MPI and MPI-CORBA),
and since 2000 on service oriented approaches. He has participated
in the Semantic Grid research group at the Global Grid Forum
(GGF), and previously co-lead the "Jini" working
group and the "Service Management Frameworks" research
group at the GGF. Currently he participates in the GRAAP working
group - investigating the WS-Agreement specification for defining
Service Level Agreements. He worked as the Grid Computing
liaison for the EU "AgentLink III" network of excellence
(from 2003 to 2005). He participates on the Editorial boards
of the "Concurrency and Computation: Practice and Experience",
"Scientific Programming", and the "ACM Transactions
on Autonomous and Adaptive Systems" journals. He was
program co-chair for the IEEE Autonomic Computing conference
in 2006. He was also program co-chair for IEEE CCGrid 2005
and for IEEE CCGrid 2007. |
