Re: [nmrg] Follow-up Network AI Challenge
"Liushucheng (Will Liu)" <liushucheng@huawei.com> Fri, 11 October 2019 06:34 UTC
Return-Path: <liushucheng@huawei.com>
X-Original-To: nmrg@ietfa.amsl.com
Delivered-To: nmrg@ietfa.amsl.com
Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 7BA4C1200F7 for <nmrg@ietfa.amsl.com>; Thu, 10 Oct 2019 23:34:30 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -4.19
X-Spam-Level:
X-Spam-Status: No, score=-4.19 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, HTML_MESSAGE=0.001, RCVD_IN_DNSWL_MED=-2.3, SPF_PASS=-0.001, T_KAM_HTML_FONT_INVALID=0.01] 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 EMKl-McMQ7ZN for <nmrg@ietfa.amsl.com>; Thu, 10 Oct 2019 23:34:27 -0700 (PDT)
Received: from huawei.com (szxga01-in.huawei.com [45.249.212.187]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id D87681200F4 for <nmrg@irtf.org>; Thu, 10 Oct 2019 23:34:26 -0700 (PDT)
Received: from DGGEML401-HUB.china.huawei.com (unknown [172.30.72.57]) by Forcepoint Email with ESMTP id B5686EE90373E8F9C5AC; Fri, 11 Oct 2019 14:34:22 +0800 (CST)
Received: from DGGEML529-MBX.china.huawei.com ([169.254.6.197]) by DGGEML401-HUB.china.huawei.com ([fe80::89ed:853e:30a9:2a79%31]) with mapi id 14.03.0439.000; Fri, 11 Oct 2019 14:34:18 +0800
From: "Liushucheng (Will Liu)" <liushucheng@huawei.com>
To: Jérôme François <jerome.francois@inria.fr>, "nmrg@irtf.org" <nmrg@irtf.org>
Thread-Topic: [nmrg] Follow-up Network AI Challenge
Thread-Index: AQHVf2DX0dVeiRZYlkm2Dpw/0D3FDadU+qHQ
Date: Fri, 11 Oct 2019 06:34:17 +0000
Message-ID: <C9B5F12337F6F841B35C404CF0554ACB8C016864@dggeml529-mbx.china.huawei.com>
References: <b725873b-4bb3-95aa-9fba-2a2a41c410ae@inria.fr>
In-Reply-To: <b725873b-4bb3-95aa-9fba-2a2a41c410ae@inria.fr>
Accept-Language: zh-CN, en-US
Content-Language: zh-CN
X-MS-Has-Attach:
X-MS-TNEF-Correlator:
x-originating-ip: [10.40.19.185]
Content-Type: multipart/alternative; boundary="_000_C9B5F12337F6F841B35C404CF0554ACB8C016864dggeml529mbxchi_"
MIME-Version: 1.0
X-CFilter-Loop: Reflected
Archived-At: <https://mailarchive.ietf.org/arch/msg/nmrg/6LG1u-JEr5RI7TFSpeOOMuvQd3Q>
Subject: Re: [nmrg] Follow-up Network AI Challenge
X-BeenThere: nmrg@irtf.org
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Network Management Research Group discussion list <nmrg.irtf.org>
List-Unsubscribe: <https://www.irtf.org/mailman/options/nmrg>, <mailto:nmrg-request@irtf.org?subject=unsubscribe>
List-Archive: <https://mailarchive.ietf.org/arch/browse/nmrg/>
List-Post: <mailto:nmrg@irtf.org>
List-Help: <mailto:nmrg-request@irtf.org?subject=help>
List-Subscribe: <https://www.irtf.org/mailman/listinfo/nmrg>, <mailto:nmrg-request@irtf.org?subject=subscribe>
X-List-Received-Date: Fri, 11 Oct 2019 06:34:30 -0000
Hi Jerome, Very detailed and useful info. Thanks for the efforts! Sorry that due to time conflict I missed the meeting. My comments below inline. Regards, | 致礼! Will LIU | 刘树成 From: nmrg [mailto:nmrg-bounces@irtf.org] On Behalf Of Jér?me Fran?ois Sent: Thursday, October 10, 2019 7:49 PM To: nmrg@irtf.org Subject: [nmrg] Follow-up Network AI Challenge Dear all, Here are the minutes of the last telco on AI challenge: - discussion on the different work-items and some addings (publication of the cahllenge to conferences, possibilities to have two phase with a final stage in a conference/hackhathon, use of kaggle) [Will] Given the status of this work. I prefer one single work-items to describe the gap analysis and challenging. - presentation of potential use cases to develop for the challenge: routing, traffic analysis, intent interpretation [Will] Agree. Use cases specific to IETF/IRTF aspects will be critical to trigger the work here, especially those that attached to some IETF existing work such as YANG, SR, and intent as well. - need a platform to perform the challenge (pure data-based validation as kaggle vs validating with running experiment in network simulator/emulator) [Will] This might be bit difficult currently for standalone platform for IETF/IRTF, we may try to cooperate with some of existing work in industry, such as LN acumos. - General Comments: -- need to check how other communities propose challenge and what are the outcomes -- open question: what will be the outcome of the challenge? only a ranking of algorithm? What could be useful for NMRG activities then? -- IBN - AI challenge: can be at the different stage of the IBN pipeline, need to understand the requirements of each stage [Will] AI and IBN are related, but the overlapping is not a must. AI may be even wider than IBN, which could help most of the policy and decision in IETF scope. To follow the activity (with more details about use cases and discussions): https://pad.inria.fr/p/g.D1sMHS8qEcwsc2iq$np_TuYkekVkbtLyVZYr_netaichallenge To continue: - we are looking for volunteers to investigate the feasability and the potential outcomes of some uses (either those proposed or other ones). So please raise your hand if you're interested. - to setup a follow-up telco you fill out the following doodle: https://doodle.com/poll/34ecz66ptmugec86 Best regards jerome
- [nmrg] Follow-up Network AI Challenge Jérôme François
- Re: [nmrg] Follow-up Network AI Challenge Liushucheng (Will Liu)
- Re: [nmrg] Follow-up Network AI Challenge Abdelkader Lahmadi
- Re: [nmrg] Follow-up Network AI Challenge Jérôme François