Routing without source information and Traffic self-similarity

Jerry Scharf scharf at
Fri Sep 19 15:38:01 UTC 1997

boydn at said:
> Second, to what degree do you believe Internet traffic exhibits 
> self-similarity, and how does this change with varying levels of 
> traffic aggregation?  I have read papers from Bellcore and others 
> suggesting that no matter the level of aggregation (be it a single 
> Internet user or a major NAP), Internet traffic exhibits high degrees 
> of self-similarity - but more recent research does not seem to agree 
> with this. 

I think the key here is aggregation and congestion control algorithms. In the 
case of the Bellcore study, they were looking at high speed devices on LANs, 
and possibly aggregation levels in the few thousand devices (not all active) 
per line. The current OC3C pipes at the core of major networks are seeing 
aggregations orders of magniture greater in terms of concurrent active 
sessions (I remember hearing numbers approaching 10^6 over a year ago.) This 
combined with many areas of congestion and the end-to-end nature of congestion 
control makes any simple model, either statistical independence or self 
similar, suspect.

just my opinion,

More information about the NANOG mailing list