[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

RE: e2e measurements


I think that you could find interesting our research presented at PAM2002:
In this paper we presented technique to correlate network-centric QoS
measurements with a perceived QoE (QoE from end-user perspective).

Please, do not hesitate to contact me for any additional information.


-----Original Message-----
From: Ayyasamy, Senthilkumar (UMKC-Student) [mailto:saq66@umkc.edu]
Sent: Sunday, March 31, 2002 9:41 PM
To: psamp@ops.ietf.org
Subject: e2e measurements

Hi all,
These are questions out of curiosity though might not fit with the psamp
1)I am was always wondering about e2e peformance measurement since it is
difficult to measure ..This is extremely important at times of  service
degradation in the network and hence a strong need for e2e service
assesement.On random browsing about ways various ISP's  measurement
strategies,they tend to describe and measure service from a network view .Is
their any research on e2e measurements.
2)Are the selection of  internet performance metrics done from end-user
perspective (from which cutomers know what performance to expect).Does
netscope take end-user persecptive while selecting a metric ?
3) This is a question more related to psamp & e2e measurement.Its a well
known fact that TCP packets can give e2e measurement  and hence can be
useful to study the service degradation from end user's persecptive.Also,TCP
give us lot of avenues for aggregation (packet size + time stamp pushes me
to think of various levels of granularity in aggregation).My question is
*will these details give me a clear picture of service quality from a
customer point of view ( unlike a network persecpctive )*
4) Is there ways to measure overbooking by service providers.I know there is
a way using ping but will not work for high-speed links and also mostly
concentrate on round trip than one way (which will be more useful)
5) which gives more info on e2e details ( packet measurements or flow
measurements) ..psamp or ipfix :-)
Thanks in advance ,
rzǧuƠz)嬱z湡hȞ+孆^Šݺ{.n+尉"	^)j瑩azgmnrj岷!硶l_?+-ljj

to unsubscribe send a message to psamp-request@ops.ietf.org with
the word 'unsubscribe' in a single line as the message text body.
archive: <http://ops.ietf.org/lists/psamp/>