• Classified by Topic • Classified by Publication Type • Sorted by Date • Sorted by First Author Last Name • Classified by Funding Source •
Adaptive Job Routing and Scheduling.
Shimon Whiteson
and Peter Stone.
Engineering Applications of Artificial Intelligence,
17(7):855–69, October 2004. Special issue on Autonomic Computing and Automation
Available from the publisher's
webpage
The version from this page corrects a minor error in the published version.
An earlier version appeared
in the proceedings of The Sixteenth Innovative Applications of Artificial
Intelligence Conference (IAAI 2004)
[PDF]664.7kB [postscript]1.1MB
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 job routing and CPU scheduling in the networks we simulate. Our experimental results verify that methods using machine learning outperform reasonable heuristic and hand-coded approaches on example networks designed to capture many of the complexities that exist in real systems.
@Article(EAAI04,
author="Shimon Whiteson and Peter Stone",
title="Adaptive Job Routing and Scheduling",
journal="Engineering Applications of Artificial Intelligence",
note="Special issue on Autonomic Computing and Automation",
volume="17",number="7",
pages="855--69",
month="October",
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 job routing and CPU scheduling in the networks we
simulate. Our experimental results verify that
methods using machine learning outperform reasonable
heuristic and hand-coded approaches on example
networks designed to capture many of the
complexities that exist in real systems.
},
wwwnote={
Available from the <a href="http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6V2M-4DGW3D2-1&_user=108429&_handle=B-WA-A-W-AV-MsSAYZW-UUW-AAUEABZWYE-AAUZDADUYE-YDBCBCYVZ-AV-U&_fmt=full&_coverDate=10%2F01%2F2004&_rdoc=13&_orig=browse&_srch=%23toc%235706%232004%23999829992%23530554!&_cdi=5706&view=c&_acct=C000059713&_version=1&_urlVersion=0&_userid=108429&md5=dc3e878e117abe3ed6d8347340800824">publisher's webpage</a><br>
The version from this page corrects a minor error in the published version.<br>
An earlier version appeared in the proceedings of <a href="http://www.aaai.org/Conferences/IAAI/iaai04.php">The Sixteenth Innovative Applications of Artificial Intelligence Conference</a> (IAAI 2004)},
)
Generated by bib2html.pl (written by Patrick Riley ) on Sat Nov 15, 2025 21:30:08