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

Pedro Martinez-Julia <pedro@nict.go.jp> Fri, 21 July 2017 09:17 UTC

Return-Path: <pedro@nict.go.jp>
X-Original-To: idnet@ietfa.amsl.com
Delivered-To: idnet@ietfa.amsl.com
Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 7CD2A129AAD for <idnet@ietfa.amsl.com>; Fri, 21 Jul 2017 02:17:48 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -4.201
X-Spam-Level:
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 mail.ietf.org ([4.31.198.44]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id vEESM8Cev-Vb for <idnet@ietfa.amsl.com>; Fri, 21 Jul 2017 02:17:46 -0700 (PDT)
Received: from ns1.nict.go.jp (ns1.nict.go.jp [IPv6:2001:df0:232:300::1]) by ietfa.amsl.com (Postfix) with ESMTP id 97902126557 for <idnet@ietf.org>; Fri, 21 Jul 2017 02:17:46 -0700 (PDT)
Received: from gw1.nict.go.jp (gw1.nict.go.jp [133.243.18.250]) by ns1.nict.go.jp with ESMTP id v6L9Hftt016334; Fri, 21 Jul 2017 18:17:41 +0900 (JST)
Received: from mail1.nict.go.jp (mail1.nict.go.jp [133.243.18.14]) by gw1.nict.go.jp with ESMTP id v6L9HfnR016330; Fri, 21 Jul 2017 18:17:41 +0900 (JST)
Received: from spectre (ssh1.nict.go.jp [133.243.3.49]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail1.nict.go.jp (NICT Mail Spool Server1) with ESMTPS id B3780B664; Fri, 21 Jul 2017 18:17:40 +0900 (JST)
Date: Fri, 21 Jul 2017 18:17:30 +0900
From: Pedro Martinez-Julia <pedro@nict.go.jp>
To: yanshen <yanshen@huawei.com>
Cc: "idnet@ietf.org" <idnet@ietf.org>
Message-ID: <20170721091729.GJ15832@spectre>
References: <015d4fb0-496a-a9a0-e8c5-7fcf6c52caee@inria.fr> <20170720171907.GF15832@spectre> <6AE399511121AB42A34ACEF7BF25B4D29783BD@DGGEMM505-MBS.china.huawei.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <6AE399511121AB42A34ACEF7BF25B4D29783BD@DGGEMM505-MBS.china.huawei.com>
User-Agent: Mutt/1.8.3 (2017-05-23)
X-Virus-Scanned: clamav-milter 0.98.7 at zenith1
X-Virus-Status: Clean
Archived-At: <https://mailarchive.ietf.org/arch/msg/idnet/cR6ouNTpv-2GGyCWwzYmaJhLtHU>
Subject: Re: [Idnet] IETF99 for applying AI/ML into network management: Follow-up
X-BeenThere: idnet@ietf.org
X-Mailman-Version: 2.1.22
Precedence: list
List-Id: "The IDNet \(Intelligence-Defined Network\) " <idnet.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/options/idnet>, <mailto:idnet-request@ietf.org?subject=unsubscribe>
List-Archive: <https://mailarchive.ietf.org/arch/browse/idnet/>
List-Post: <mailto:idnet@ietf.org>
List-Help: <mailto:idnet-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/idnet>, <mailto:idnet-request@ietf.org?subject=subscribe>
X-List-Received-Date: Fri, 21 Jul 2017 09:17:48 -0000

Dear Yanshen,

Please find my reply below.

On Fri, Jul 21, 2017 at 08:52:33AM +0000, yanshen wrote:
> Dear Pedro,
> 
> Thanks for your hints. Please find some hints from my side.
> 
> I am not sure whether you means that there should be an "interface" or
> an "entity" between the other source data and control loop?

I'm sorry, I mean that, by definition, a "closed control loop" intends
to maintain a particular variable within some defined values by reading
it and enforcing the necessary actions to affect it. Any external data
cannot be considered as such variable so they cannot be part of the
closed control loop. However, it can be used to help controlling other
variables, but it must be clearly defined how the external data is
integrated and derived into the changes to the other variable.

> BTW, have you ever obtain some achievement about such point that can
> be shared?

My results are trivial and do not shed any light to this issue and I do
not try to fit external data into the closed control loop, I just use it
to complement the control of the "load" variable.

> I think that since NMRG may be a probably choice, it is better to
> explore via this thread. 

So let's go that way.

> Thanks for reading. 
> 
> Regards,
> 
> Yansen

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: pedro@nict.go.jp
---------------------------------------------------------
*** Entia non sunt multiplicanda praeter necessitatem ***