<?xml version="1.0" encoding="utf-8"?>
<rss version="2.0" xml:base="https://drupalinl.info.ucl.ac.be" xmlns:dc="http://purl.org/dc/elements/1.1/">
<channel>
 <title>INL: IP Networking Lab - clustering</title>
 <link>https://drupalinl.info.ucl.ac.be/taxonomy/term/75/0</link>
 <description></description>
 <language>en</language>
<item>
 <title>On the Impact of Clustering on Measurement Reduction</title>
 <link>https://drupalinl.info.ucl.ac.be/publications/impact-clustering-measurement-reduction</link>
 <description>&lt;p&gt;Measuring a path performance according to one or several metrics, such as delay or bandwidth, is becoming more and more popular for applications. However, constantly probing the network is not suitable. To make measurements more scalable, the notion of clustering has emerged. In this paper, we demonstrate that clustering can limit the measurement overhead in such a context without loosing too much accuracy. We first explain that measurement reduction can be observed when vantage points collaborate and use clustering to estimate path&lt;br /&gt;
performance.&lt;/p&gt;
&lt;p&gt;&lt;a href=&quot;https://drupalinl.info.ucl.ac.be/publications/impact-clustering-measurement-reduction&quot;&gt;read more&lt;/a&gt;&lt;/p&gt;</description>
 <category domain="https://drupalinl.info.ucl.ac.be/category/visibility/public">Public</category>
 <category domain="https://drupalinl.info.ucl.ac.be/keywords/accuracy">accuracy</category>
 <category domain="https://drupalinl.info.ucl.ac.be/keywords/clustering">clustering</category>
 <category domain="https://drupalinl.info.ucl.ac.be/keywords/measurements">measurements</category>
 <category domain="https://drupalinl.info.ucl.ac.be/keywords/scalability">scalability</category>
 <enclosure url="https://drupalinl.info.ucl.ac.be/system/files/clustering.pdf" length="767480" type="application/pdf" />
 <pubDate>Fri, 20 Feb 2009 09:55:50 +0000</pubDate>
 <dc:creator>donnet</dc:creator>
 <guid isPermaLink="false">558 at https://drupalinl.info.ucl.ac.be</guid>
</item>
<item>
 <title>On Network-Aware Clustering of Web Clients</title>
 <link>https://drupalinl.info.ucl.ac.be/blogs/08-04-14-network-aware-clustering-web-clients</link>
 <description>&lt;p&gt;The paper &quot;On network-aware clustering of web clients&quot; presented at SIGCOMM ’00 by Krishnamurthy and Wang proposes clustering techniques to move content closer to the clients which are generating most of the traffic.&lt;/p&gt;
&lt;p&gt;Before the paper, cluster of clients were simply /24 networks. The authors propose to group clients by BGP prefixes.&lt;/p&gt;
&lt;p&gt;The paper is focused on web traffic and to determine the quality of the BGP clustering, the authors analyses web server logs. Based on the logs, they map client IP addresses to BGP prefixes.&lt;/p&gt;
&lt;p&gt;&lt;a href=&quot;https://drupalinl.info.ucl.ac.be/blogs/08-04-14-network-aware-clustering-web-clients&quot;&gt;read more&lt;/a&gt;&lt;/p&gt;</description>
 <category domain="https://drupalinl.info.ucl.ac.be/category/visibility/public">Public</category>
 <category domain="https://drupalinl.info.ucl.ac.be/keywords/clustering">clustering</category>
 <category domain="https://drupalinl.info.ucl.ac.be/keywords/krishnamurthy">Krishnamurthy</category>
 <category domain="https://drupalinl.info.ucl.ac.be/keywords/network">network</category>
 <category domain="https://drupalinl.info.ucl.ac.be/keywords/wang">Wang</category>
 <category domain="https://drupalinl.info.ucl.ac.be/keywords/web">web</category>
 <pubDate>Mon, 14 Apr 2008 20:23:57 +0000</pubDate>
 <dc:creator>dsaucez</dc:creator>
 <guid isPermaLink="false">455 at https://drupalinl.info.ucl.ac.be</guid>
</item>
</channel>
</rss>
