• Classified by Research Category • Classified by Publication Type • Sorted by Date •
Shimon Whiteson and Peter Stone.
Towards Autonomic Computing: Adaptive Network Routing and Scheduling. In The Sixteenth Innovative Applications of
Artificial Intelligence Conference, July 2004. To appear
IAAI2004
Extended version(under review for journal publication)
(pdf version).
[PDF]152.3kB [postscript]295.0kB
Computer systems are rapidly becoming so complex that maintaining them with human support staffs will be prohibitively expensive and inefficient. In response, visionaries have begun proposing that computer systems be imbued with the ability to configure themselves, diagnose failures, and ultimately repair themselves in response to these failures. However, despite convincing arguments that such a shift would be desirable, as of yet there has been little concrete progress made towards this goal. We view these problems as fundamentally machine learning challenges. Hence, this article presents a new network simulator designed to study the application of machine learning methods from a system-wide perspective. We also introduce learning-based methods for addressing the problems of packet routing and CPU scheduling in the networks we simulate. Our experimental results verify that methods using machine learning outperform heuristic and hand-coded approaches on an example network designed to capture many of the complexities that exist in real systems.
@InProceedings(IAAI04,
author="Shimon Whiteson and Peter Stone",
title="Towards Autonomic Computing: Adaptive Network Routing and Scheduling",
booktitle="The Sixteenth Innovative Applications of Artificial
Intelligence Conference",
note="To appear",
month="July",year="2004",
abstract={
Computer systems are rapidly becoming so complex
that maintaining them with human support staffs will
be prohibitively expensive and inefficient. In
response, visionaries have begun proposing that
computer systems be imbued with the ability to
configure themselves, diagnose failures, and
ultimately repair themselves in response to these
failures. However, despite convincing arguments
that such a shift would be desirable, as of yet
there has been little concrete progress made towards
this goal. We view these problems as fundamentally
\emph{machine learning} challenges. Hence, this
article presents a new network simulator designed to
study the application of machine learning methods
from a system-wide perspective. We also introduce
learning-based methods for addressing the problems
of packet routing and CPU scheduling in the networks
we simulate. Our experimental results verify that
methods using machine learning outperform heuristic
and hand-coded approaches on an example network
designed to capture many of the complexities that
exist in real systems.
},
wwwnote={<a href="http://www.aaai.org/Conferences/IAAI/2004/iaai04.html">IAAI
2004</a><br>
<a href="http://www.cs.utexas.edu/~pstone/Papers/2004eaai/paper.ps">Extended version</a>(under review for journal publication) <a href="http://www.cs.utexas.edu/~pstone/Papers/2004eaai/paper.pdf">(pdf version)</a>.
},
)
Generated by bib2html.pl (written by Patrick Riley ) on Thu Jul 15, 2004 09:56:42