Nautilus Systems, Inc. logo and menu bar Site Index Home
News Books
Button Bar Menu- Choices also at bottom of page About Nautilus Services Partners Case Studies Contact Us
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index] [Subscribe]

DM: Call for Papers: Special Issue of CP&E

From: Omer F Rana
Date: Wed, 30 Jun 1999 15:45:36 -0400 (EDT)

                Scalability and  Performance Management

        A Special Issue of Concurrency: Practice and Experience

                Publication Date: March/April 2000


Deadline for submissions        Friday October 1 1999
Notification sent               Monday November 15 1999
Final papers due                Wednesday December 15 1999
Publication                     March/April 2000


Rapid advances in technologies such as networking, parallel computing
and information management, have led to the development of intelligent
software components that act autonomously on the behalf of users, can
analyse and access a diverse range of information, can react to 
in their environment, and can cooperate and coordinate their 
to complete a task or goal.  Such components may be distributed across
a network, and may work seamlessly to perform this goal, and do so
without the direct intervention of a user. Such technology involves 
integration of ideas from many different disciplines such as 
intelligence, parallel processing, knowledge sharing, object-oriented
design, information retrieval, distributed workflows, and databases.
The objectives of developing such systems are to provide an emergent
functionality that allows a robust, flexible, and scalable approach to
solving problems and providing services in various application

Recent interest in large-scale distributed-computing environments, or
computational grids, that provide dependable, consistent and pervasive
access to high-end computational resources is one focus of the
high-performance computing community.  These environments have the
potential to change fundamentally the way we think about computing, as
our ability to compute will no longer be limited to the resources we
currently have on hand.  The ability to integrate supercomputing
resources, on demand, will enable integration of sophisticated data
analysis, image processing and real-time control to be utilised within
scientific instruments and simulations. Or, resources of a nation-
wide, or a continent-wide strategic-computing reserve may be used to
perform time-critical computational tasks in times of crisis.
Agent-based computing is therefore the next obvious step. The use of
techniques such as code mobility and speech-acts (through KQML and
FIPA) open up new research challenges when used with approaches and
themes familiar to high-performance computing. The combined use of
commodity computing ideas and agent technologies could lead to new
applications, in areas like resource management, data mining, data
warehousing, and electronic commerce.

Many issues remain in bringing about this change, however, such as
understanding how agents can be deployed on a large scale, and how to
build effective "agent communities". In agent systems with a large
number of agents, or where the agent environment is highly dynamic or
heterogeneous, special challenges arise in managing and controlling
agents.  Furthermore, agent deployment must be sufficiently robust and
reliable, so that scientists and commercial organisations will entrust
agents with mission-critical applications.


Include, but are by no means restricted to:

Practical Deployment
   * Performance analysis/modeling of multi-agent systems
   * Performance enhancement methodologies for mobile and multi-agent
   * Agents in Problem Solving Environments (PSEs)
   * Computational steering using agents
   * Agent based load balancing and resource discovery
Communication and Scalability
   * Scalability of communications mechanisms, Naming Scheme and 
     Name Service
   * Communications reliability and support for network
   * Scalability of negotiation protocol designs 
   * Role of strategies such as caching and adaptive searching in
     time needed to perform common actions, such as converge on a 
   * Optimal agent size for migration
Robustness and Persistence
   * How can we move or update agents or agent servers without 
     stopping them?
   * Given the possibility of thousands of agents running on a single
     server, what are the mechanisms we need to support agent
     such as reactivate-on-event and check pointing? For large 
     intelligent) agents, how can we efficiently handle the 
     long-term data?

Emergent Behaviour in Large Agent Systems

   * Emergent behaviours through interaction amongst a large number 
     communicating agents

Note that all submissions should clearly show their relevance to the
fields of scalability, performance analysis or practical deployment
in large agent communities. Potential authors unsure about their 
paper topic and the relevance criteria are encouraged to contact 
the guest editors below. 


 Professor David Kotz               Dr Omer Rana
 (Department of Computer Science,   (Parallel and Scientific
 Dartmouth College,                 Department of Computer Science,
 Hanover,                           Cardiff University,
 New Hampshire 03755, USA           PO Box 916,
 email:       Cardiff CF24 3XF, UK

 Professor David Walker             Dr Hyacinth S. Nwana
 (Department of Computer Science,   (Admin 2, PP5,
 Cardiff University,                BT Laboratories,
 PO Box 916,                        Martlesham Heath, Ipswich,
 Cardiff CF24 3XF, UK               IP5 3RE, UK
 email:          email:

We are grateful to Kate Stout (SUN Microsystems), for her comments
and suggestions in developing this Call for Papers.

Initial Submission
Authors who wish to submit to the special issue should send either
PostScript or PDF versions of their paper by email to Omer Rana (see
editors above), or else provide a URL for an online version of the
paper. (For online submissions, authors should ensure that relevant
servers are reliable, and that links are kept live.)  Hardcopy
submission is discouraged, but may be possible if arranged in advance.
Papers should report new work and should be printable on A4 paper 
12 point type (10 characters per inch for typewriters). Paper bodies
be no longer than 20 pages.
The first page of each submission should list the full contact details
(including full name, postal address, email address, phone and fax
number) of at least one author. Following peer review, notification of
acceptance or rejection will be sent (by email where possible) on or
around Monday 15 November 1999. 

Note that relevance will be a key factor in determining acceptance for
the special issue. If in doubt about relevance, please contact one of
the guest editors in advance. Final papers will be due no later than 
December 1999, and the special issue is scheduled for publication in
March/April 2000.

*** Deadline for initial submission: Friday, October 1, 1999 ***

Final Submissions

See author submission guidelines at:
Deadline for submissions        Friday October 1 1999
Notification sent               Monday November 15 1999
Final papers due                Wednesday December 15 1999
Publication                     March/April 2000

ABOUT `Concurrency: Practice and Experience' JOURNAL

Further details of the journal are available at:

[ Home | About Nautilus | Case Studies | Partners | Contact Nautilus ]
[ Subscribe to Lists | Recommended Books ]

logo Copyright © 1999 Nautilus Systems, Inc. All Rights Reserved.
Mail converted by MHonArc 2.2.0