[Nrg-l] NRG tomorrow @2pm

Niky Riga inki at cs.bu.edu
Tue Jun 14 09:57:57 EDT 2005

Tomorrow Vijay is going to present a paper from SIGMETRICS 2005; he just 
came back really excited:-) The paper is titled

"Fundamental Bounds on the Accuracy of Network Performance Measurements"

 The meeting will take place tomorrow (Wednesday 6/15) at the grad 
lounge at 2:00pm.
 The abstract follows.

One more thing about the time of NRG. It would be more convinient for 
me, e.g. I would be able to attend, if we move the time to 4-5pm. I 
understand that this might be too late for some of you so please let me 
know what you think. Notice that the time won't change for tomorrow's NRG.



This paper considers the basic problem of "how accurate can we make 
Internet performance measurements". The answer is somewhat 
counterintuitive in that there are bounds on the accuracy of such 
measurements, no matter how many probes we can use in a given time 
interval, and thus arises a type of Heisenberg inequality describing the 
bounds in our knowledge of the performance of a network. The results stem 
from the fact that we cannot make independent measurements of a system's 
performance: all such measures are correlated, and these correlations 
reduce the efficacy of measurements. The degree of correlation is also 
strongly dependent on system load. The result has important practical 
implications that reach beyond the design of Internet measurements, into 
the design of network protocols.

More information about the Nrg-l mailing list