Re: [Idnet] IETF99 for applying AI/ML into network management: Follow-up

Pedro Martinez-Julia <> Thu, 27 July 2017 02:16 UTC

Return-Path: <>
Received: from localhost (localhost []) by (Postfix) with ESMTP id DF869131F9E for <>; Wed, 26 Jul 2017 19:16:28 -0700 (PDT)
X-Virus-Scanned: amavisd-new at
X-Spam-Flag: NO
X-Spam-Score: -4.201
X-Spam-Status: No, score=-4.201 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, RCVD_IN_DNSWL_MED=-2.3, RP_MATCHES_RCVD=-0.001, SPF_PASS=-0.001, URIBL_BLOCKED=0.001] autolearn=ham autolearn_force=no
Received: from ([]) by localhost ( []) (amavisd-new, port 10024) with ESMTP id Q8sUjl62A4Nu for <>; Wed, 26 Jul 2017 19:16:26 -0700 (PDT)
Received: from ( [IPv6:2001:df0:232:300::2]) by (Postfix) with ESMTP id 3AD44131C86 for <>; Wed, 26 Jul 2017 19:16:26 -0700 (PDT)
Received: from ( []) by with ESMTP id v6R2GMsb072940; Thu, 27 Jul 2017 11:16:22 +0900 (JST)
Received: from ( []) by with ESMTP id v6R2GMgC072937; Thu, 27 Jul 2017 11:16:22 +0900 (JST)
Received: from spectre (unknown []) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by (NICT Mail Spool Server1) with ESMTPS id 73408B794; Thu, 27 Jul 2017 11:16:22 +0900 (JST)
Date: Thu, 27 Jul 2017 11:16:22 +0900
From: Pedro Martinez-Julia <>
To: yanshen <>
Cc: "" <>
Message-ID: <20170727021622.GD18300@spectre>
References: <> <20170720171907.GF15832@spectre> <> <20170721091729.GJ15832@spectre> <> <20170724085956.GI18300@spectre> <> <20170726002417.GZ18300@spectre> <>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <>
User-Agent: Mutt/1.8.3 (2017-05-23)
X-Virus-Scanned: clamav-milter 0.98.7 at zenith2
X-Virus-Status: Clean
Archived-At: <>
Subject: Re: [Idnet] IETF99 for applying AI/ML into network management: Follow-up
X-Mailman-Version: 2.1.22
Precedence: list
List-Id: "The IDNet \(Intelligence-Defined Network\) " <>
List-Unsubscribe: <>, <>
List-Archive: <>
List-Post: <>
List-Help: <>
List-Subscribe: <>, <>
X-List-Received-Date: Thu, 27 Jul 2017 02:16:29 -0000

Dear Yanshen,

Thanks for your comments, please find my reply in-line.

On Thu, Jul 27, 2017 at 01:54:58AM +0000, yanshen wrote:
> > For me that depends on the algorithmic representation. We have two types of
> > variables:
> > 
> > - Measurable and controllable variables, such as the load of a resource
> >   managed by the solution, which can be known and can be altered by some
> >   decision of such solution (increase/decrease the amount of resources).
> > 
> > - Measurable but non-controllable, which are outside the control of the
> >   solution. They can be known and used to take decisions but cannot be
> >   altered (directly or indirectly) by the solution. A simple example can
> >   be found in the occurrence of some event that can affect to a system,
> >   such as the number of attendees to a baseball match. The management
> >   solution cannot control such variable but uses it to determine the
> >   amount of network resources assigned to the network of the stadium.
> I have a similar thought. I try to divide the variables into objective
> and subjective (may corresponding to your controllable and
> non-controllable. Perhaps a little different). 
> 	- The objective data means that we can capture, input or measure it
> 	periodically from any source (whatever it is). This class of data
> 	needs to be focused and formatted, including the context and format
> 	and so on. One of the cases is QoS value which I just mentioned. 
> 	- The subjective data means that it is imported into the machine
> 	(AI/Brain/Knowledge system) temporarily or irregularly. This class
> 	of data may be high-level and diversity. The solution for them I
> 	think should be pushed to application layer. It is not our dishes.
> 	Another thought is that we should try to obtain more subjective data
> 	by objective way, for example, we should try to change the way of
> 	obtaining the "reward" feedback from "user randomly report" to
> 	"periodically capture". Unless such, it should not be included into
> 	our consideration. 
> I think it is significant to combine our two dimensions into one. Of
> course other dimensions may also considerable.

They are different aspects and, of course, they must be combined. My
classification is based on the "control theory", which clearly states
what a controlled variable means and the strict definition of the loop
closure (closed-loop controller), which implies to check such variables
and confirm they are changed according to the intended objective after
some change/s is/are applied to the controlled environment.

On the other hand, your view is more practical in terms of the scope of
the information in relation to the AI algorithm and its needs. It would
be good to simplify/unify both dimensions but also to simplify/unify the
differences within them. I mean that it would be probably a good option
to consider any kind of data homogeneously. I am using a simple ontology
to resolve such problem, so we could probably use it and a corresponding
YANG model, as I proposed in my other message, to achieve such unified
view. Please, let me know your thoughts. Thank you very much.


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
*** Entia non sunt multiplicanda praeter necessitatem ***