Re: [Idnet] Intelligence-Defined Network Architecture and Call for Interests

[Pedro Martinez-Julia <[e-mail]>]

On Fri, Mar 31, 2017 at 06:12:19AM +0200, Laurent Ciavaglia wrote:
> Hello,
> 
> A couple of suggestions:
>     -Why not raise this point / request in various WGs (e.g. in the OPS
> Area) and RGs (e.g. MAPRG, NMRG).
>     -Why not work with the IETF meeting NOC to collect data sets?

Dear Laurent and others,

The main reason I did not consider to request it within/through the IETF
is that I do not know how it would be addressed, so I cannot help in any
aspect. Since I somehow know (have experience with) the process required
to get access to information from operators, I encouraged it.

That said, and considering that operators did not demonstrate interest
on this topic, I request the list that if somebody knows how to address
this request within/through the IETF, please let us know so we can work
together to get it done as best as possible. It would mean a lot for the
network research and engineering community, inside and outside IETF, so
it is worth to try.

Also, please, consider that any kind of data would be worth having. Even
if anonymization breaks something or most of it, since it would be much
more useful than synthetic data. Remember that this is about AI, so the
proposed models and algorithms should also work with adulterated data to
some extent. They would be later validated and tuned using better data
will less (or none) adulteration.

To sum up, any real information is worth to have, regardless of it being
adulterated, filtered, or anything. If anybody knows some way of getting
it or has some examples, please point us to them, as others have already
done, or give us some "easy" guide of how to get the access to it. Thank
you very much.

> BR, Laurent.

Regards,
Pedro

-- 
Pedro Martinez-Julia
Network Science and Convergence Device Technology Laboratory
Network System Research Institute
National Institute of Information and Communications Technology (NICT)
4-2-1, Nukui-Kitamachi, Koganei, Tokyo 184-8795, Japan
Email: [e-mail]
---------------------------------------------------------
*** Entia non sunt multiplicanda praeter necessitatem ***