<P>I'm sorry I made a mistake when copying web links , the paper is 
<P>named: "Provisioning IP Backbone Networks to Support Latency Sensitive Traffic"
<P>(<A href="http://ipmon.sprintlabs.com/pubs_trs/pubs/cdiot/infocom03_provisionbb.pdf">http://ipmon.sprintlabs.com/pubs_trs/pubs/cdiot/infocom03_provisionbb.pdf</A>)
<P>best regards
<P>&nbsp;
<P>&nbsp;<B><I>Jing Shen &lt;jshen_cad@yahoo.com.cn&gt;</I></B> wrote:
<BLOCKQUOTE style="PADDING-LEFT: 5px; MARGIN-LEFT: 5px; BORDER-LEFT: #1010ff 2px solid">
<P>Hi,</P>
<P>I just read&nbsp; a paper published on InfoComm'03 named&nbsp; "<A href="http://einstein.seas.upenn.edu/mnlab/paper/split_hops-report.pdf">Achieving Near-Optimal Traffic Engineering Solutions for Current OSPF/IS-IS Networks</A>", it is stated that</P>
<P>only 15% BW overprovisioning is needed to guarantee as low as 3ms e2e delay requirement. </P>
<P>My question is:</P>
<P>1) a network optimization result &nbsp;with both network topology, routing path&nbsp;preassumed&nbsp; reliable?&nbsp; How could we consider routing path changes when link BW is overprovisioned?</P>
<P>2) what's the state of link BW in current backbone network ? is there more than 15% BW idled? </P>
<P>Thanks in advance.</P>
<P>&nbsp;</P>
<P>&nbsp;</P><BR><BR>Jing Shen<BR><BR>State Key Lab of CAD&amp;CG<BR>ZheJiang University(YuQuan)<BR>HangZhou, ZheJiang Province 310027<BR>P.R.China
<P><BR>
<HR SIZE=1>
<B>Do You Yahoo!?</B><BR><A href="http://ad.cn.doubleclick.net/clk;5313999;7930402;p?http://www.ibm.com/cn/promotion/pc/netvista_a30/index.shtml">"¸ü¶à¾ªÏ²£¬Í¬Ñù¾«²Ê£¬NetVista A30 ÈÈÂô"</A></BLOCKQUOTE><BR><BR>Jing Shen<br><br>State Key Lab of CAD&amp;CG<br>ZheJiang University(YuQuan)<br>HangZhou, ZheJiang Province 310027<br>P.R.China<p><br><hr size=1><b>Do You Yahoo!?</b><br>
<a href="http://ad.cn.doubleclick.net/clk;5313999;7930402;p?http://www.ibm.com/cn/promotion/pc/netvista_a30/index.shtml">"¸ü¶à¾ªÏ²£¬Í¬Ñù¾«²Ê£¬NetVista A30 ÈÈÂô"</a>