[Irtf-rr] Re: question about multipath routing applicability and internet traffic pattern

[Jing Shen]

Dear Mr. MAHRAMIAN MEHRAN,

Thank you very much for comment.

The work has been finished and we resort to a method named 
"proactive multipath routing" to route according to traffic 
characteristics. With that method we try to route according to
traffic characteristics. And, simulation shows it could improve 
network performance significantly. The paper related is accepted
by QofIS'02 which will be held in Oct.16.

I have read the paper by Jin Cao and Cleverland, in which they state
traffic shows traffic in high speed network tend to be Possion
arrival. In contrast, steve claimed it do follow the way of Self-similar 
when he analyze his observation( You can find his message on ippm list).

The result seems contradictable but with our observation on ZJU-Net,
the bandwidth consumed do shows self-similar.( The ZJU-Net is 
a network consist by 10Mbps--100Mbps--1Gbps Ethernet and all of 
those in ZJU use it to transmit text, audio, video, software etc.)

So, what I conclude is : it still "self-similar" but there do exist
something behind our eyes. 

Regards



> 
> Dear Mr. Jing Shen
> 
> Although I am new in this field, but I think that we need a uniform network
> to guarantee QoS and make sure about loop free paths during multipath
> routing.
> Your results may differ from previous papers, because of self-similar
> traffic that you may have applied to your network. I have already received a
> message from one of my friends that claims that high bandwidth traffics are
> not necessarily self similar. You may work more on the statistical model of
> your traffic.
> 
> Mehran Mahramian Moallem
> Amirkabir University of Technology
> Tehran, Iran
> 
> This is a reply to the message below :
> 
> > Hi,
> 
> I want to make clear some problems while doing with multipath routing.
> 
> At current time routing is done with unipath ( including ECMP on it), while
> in some ISP network
> network optimization is done according to the traffic pattern derived from
> observation.
> it is found such methodology works fine in current network environment ( Am
> i right with current situation? )
> 
> But TE asks us to make full use of network resource and improve the
> network's adapting ability
> to bursty traffic. Although overprovision is adopted to deal with such
> requirements, it is not the
> least cost solution ( I think). But as we simulate some of the multipath
> routing method for
> intradomain routing, under uniform traffic pattern multipath always shows
> bad congestion
> delivery capacity. :-(
> 
> My questions raise with such experience is :
> 
> 1. How is the network traffic distributed when considering edge-to-edge
> connections ? What about aggregation?
>    what I want to make clear is : how non_uniformility is ? what is the flow
> level properties ?
> 
> 2. Is it reasonable to simulate a network with only a subset of node
> exchange traffic? How could
>    load sensitive routing affect the traffic distibution over the network?
> is there any paper on it?
> 
> I found i lost in the jungle as our experiments shows different result
> showed by some papers I read.
> Would you please give some help?
> 
> great thanks to each word you give.
> 
> Regards
> 
> Jing Shen

-- 
Jing Shen

State Key Lab of CAD&CG
ZheJiang University(YuQuan)
HangZhou, Z.J. 310027
P.R.China

Tel: +86-571-87932423

Email: jshen@cad.zju.edu.cn

**********************************************************************
* The SunShine of life is made up of very little beams which is      *
*  bright all the time                                               *
**********************************************************************