[icnrg] Comments on "draft-choi-icnrg-aiot-02"
Chonggang Wang <Chonggang.Wang@InterDigital.com> Mon, 20 April 2020 00:30 UTC
Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 7E3EC3A0A8B for <email@example.com>; Sun, 19 Apr 2020 17:30:33 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Status: No, score=-0.189 tagged_above=-999 required=5 tests=[DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, HTML_MESSAGE=0.001, SPF_PASS=-0.001, T_REMOTE_IMAGE=0.01, URIBL_BLOCKED=0.001] autolearn=ham autolearn_force=no
Authentication-Results: ietfa.amsl.com (amavisd-new); dkim=pass (1024-bit key) header.d=interdigital.com
Received: from mail.ietf.org ([188.8.131.52]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id imUK0VF3i_6g for <firstname.lastname@example.org>; Sun, 19 Apr 2020 17:30:27 -0700 (PDT)
Received: from NAM12-DM6-obe.outbound.protection.outlook.com (mail-dm6nam12on2102.outbound.protection.outlook.com [184.108.40.206]) (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 4E2FE3A0A88 for <email@example.com>; Sun, 19 Apr 2020 17:30:26 -0700 (PDT)
ARC-Seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=mh2Q1zaHr1ZaawByoBYGRXeUynAHaCjN9v0h1kIlWpHcwkI9iRBDkUZGicz4defJEB6r7mLeKlhvrfBaStWBv88TSk4pSbK5bN96U89Plgi8pqH3tHIwTQnJ17Ju5lDA4kywgwycAoYe1hYIEJW2OuRBZykDNJUyzRDmCcimQo0xeHhgkcD7IqAstgi2vnoG8iY/kLE5oL4omSKiJ2j3NNJCzvcmw0TqGlUBdFuM5jq/zqCkpYZr2C0DGtGIVHe28Xo+juGLGXI3/HN2F+Jiu7EI/NxmIhzmJNenFJm58829BQwH8YPvunKm54t31xs2z/gvyxH4lgATuqIRvXs5yQ==
ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector9901; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=VzCoG3NjBI+AcamtNcqDLqg97QNtgQdkFsJV/91EElA=; b=eRVDkmg/TKH3JsK/EMx0pGBu8504GVGxT7JPMsizZpyU95yKLl80hQgZEHfgDW793bMvmn9vccYaNoFy/7Z4fbwv0qmlj0kpEgCebgafbjjS9D9WsYe0nQS4Fv3YunM5mY1GDH7dbrHbg3q/I7uLsylMRus7V7QBsrT+InzgZGyYyXzxlfkD5lyr+gQznM3eUnIk8bGYjAufuE5wJR9+19ak5cQRKojpTSMea9KOyfYMghzNb+pYyLmxC8jlT5bZvwxvNIFER3yLSFTUKvSevXlSbNWptHQAnVxUxHLxPiJUekHfAVJSfl33WlKhhp9x60wNeFLh+VeT2gLBDOV4rA==
ARC-Authentication-Results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=interdigital.com; dmarc=pass action=none header.from=interdigital.com; dkim=pass header.d=interdigital.com; arc=none
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=interdigital.com; s=selector1; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=VzCoG3NjBI+AcamtNcqDLqg97QNtgQdkFsJV/91EElA=; b=XCUGnOhvXxerJUQN1jwzguTwC5VtEdigVeXH+pcP7a2uZkAEiagiP1npSafxTP4v2sq3VWWhHVQFIuDevcmt5pYC0jnng9P4laW7vMTZvOE3sdsuN5H1grH21JSjyPlU+ZvD4SHdZz9+znDT3/4ME5HqJvifzG5jAlkgKYWyPeM=
Received: from MN2PR10MB3485.namprd10.prod.outlook.com (2603:10b6:208:10e::24) by MN2PR10MB3341.namprd10.prod.outlook.com (2603:10b6:208:12f::32) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.20.2921.25; Mon, 20 Apr 2020 00:30:23 +0000
Received: from MN2PR10MB3485.namprd10.prod.outlook.com ([fe80::9172:c59:670a:2d60]) by MN2PR10MB3485.namprd10.prod.outlook.com ([fe80::9172:c59:670a:2d60%7]) with mapi id 15.20.2921.027; Mon, 20 Apr 2020 00:30:23 +0000
From: Chonggang Wang <Chonggang.Wang@InterDigital.com>
To: ICNRG <firstname.lastname@example.org>
Thread-Topic: Comments on "draft-choi-icnrg-aiot-02"
Date: Mon, 20 Apr 2020 00:30:22 +0000
authentication-results: spf=none (sender IP is ) smtp.mailfrom=Chonggang.Wang@InterDigital.com;
x-forefront-antispam-report: CIP:255.255.255.255; CTRY:; LANG:en; SCL:1; SRV:; IPV:NLI; SFV:NSPM; H:MN2PR10MB3485.namprd10.prod.outlook.com; PTR:; CAT:NONE; SFTY:; SFS:(10019020)(4636009)(396003)(39830400003)(136003)(346002)(376002)(366004)(76116006)(66476007)(64756008)(66446008)(66946007)(5660300002)(66574012)(66556008)(9326002)(8676002)(81156014)(8936002)(6916009)(7696005)(71200400001)(52536014)(186003)(9686003)(26005)(966005)(316002)(33656002)(55016002)(86362001)(478600001)(6506007)(2906002)(85282002); DIR:OUT; SFP:1102;
received-spf: None (protection.outlook.com: InterDigital.com does not designate permitted sender hosts)
Content-Type: multipart/alternative; boundary="_000_MN2PR10MB34856D5B64595F00F6414F0EF8D40MN2PR10MB3485namp_"
X-MS-Exchange-CrossTenant-originalarrivaltime: 20 Apr 2020 00:30:22.9471 (UTC)
Subject: [icnrg] Comments on "draft-choi-icnrg-aiot-02"
List-Id: Information-Centric Networking research group discussion list <icnrg.irtf.org>
List-Unsubscribe: <https://www.irtf.org/mailman/options/icnrg>, <mailto:email@example.com?subject=unsubscribe>
List-Subscribe: <https://www.irtf.org/mailman/listinfo/icnrg>, <mailto:firstname.lastname@example.org?subject=subscribe>
X-List-Received-Date: Mon, 20 Apr 2020 00:30:34 -0000
Hello Authors, We have reviewed your document on "Requirements and Challenges for User-level Service Managements of IoT Network by utilizing Artificial Intelligence", which introduces a very interesting area. We would like to provide below our comments. General Comments: 1. So is there any link to ICN technologies from this draft? 2. The draft has a lot of text (which is good) but makes it very hard to understand the main points. So it would be nice to have a clear Conclusion section to help the reader. * Example: In the Abstract it says "This document intends to present a right direction to empower AI in IoT ...". In which section is this done? 3. This document introduced quite a lot terms such as IoT device, IoT object, edge device, IoT gateway, IoT server, IoT data, IoT context, IoT service, IoT service environment, etc. Would the authors consider defining these terms in the way to avoid any potential confusion and help develop the requirements/challenges of AI/ML for IoT. 4. It will be helpful to add appropriate references as needed to Section 1 - Section 5. 5. The focus of this document seems to be on the use case and requirements of using AI/ML for IoT, which is good. On the other hand, it will be beneficial to add some discussion on challenges and/or pitfalls when applying AI/ML for IoT since AI/ML is not a panacea for all IoT applications. 6. Editorial: The formatting seems to have many issues (e.g. Table of Contents, indenting of lines, pagination, line breaks, etc.) even in the txt version (which is surprising) Detailed Comments: 7. on pp.3, "Many IoT sensors and devices can connect to an IoT service environment where IoT objects cannot interoperate with each other and can interact with different applications." - This sentence could be rephased, especially on why "where IoT objects cannot interoperate with each other and can interact with different applications". 8. on pp.3, "...context-aware IoT..." - It's not clear about the meaning of context-aware IoT. Also, what would be the context information? 9. on pp.4, "Most IoT applications can operate in two modes. One is a simple monitoring mode and the other is an abnormal mode for rapid processing." - Wonder why the abnormal mode has not been described in the same paragraph. In addition, an IoT application does not have to report data to an IoT server periodically; instead, it can wait for a request from the IoT server, then sends a response. Wonder why this data collection mode has not been mentioned/considered in this document. 10. on pp.5, "When an abnormal situation occurs, IoT sensor should investigate whether it noticed normal operations and notified the IoT service operator." - Wonder how the IoT sensor will do which kind of investigation. 11. on pp.5, "...Mobile IoT traffic can cause some errors ..." - It's not the traffic which cause some errors, but the communication link which cause errors to IoT traffic. 12. on pp.6, "If the signal strength of the IoT device with a power limit is not so strong, the reception quality of the IoT server may not be sufficient to obtain the measurement data." - Usually, there is no direct one-hop wireless (or wired) link between an IoT device and an IoT server (especially the IoT server in cloud). As such, "the reception quality of the IoT server" is not affected by IoT device's signal strength. 13. on pp.6, "However, in an abnormal state, IoT devices need a high bandwidth, up to several tens of megabits/sec, in order to identify actual events and investigate accurate status information." - It's not clear why an abnormal state would cause high bandwidth. 14. on pp. 7, "More than a billion IoT devices are expected to connect to smartphones, tablets, wearables, and vehicles" - Wonder what would be the use case an IoT device connects to a wearable. In most cases, wearables as IoT devices connects to smartphones, tablets, and/or vehicles. 15. on pp.7, "Therefore, IoT services are targeted at mobile applications" - Wonder why IoT services are limited to mobile applications. Besides, 6.1 has smart home use case, which is not too much mobile case. 16. on pp.8, "The common property of IoT applications and services is that they require fast analytics rather than later analytics with piled data" - Batch processing/analytics on data at rest is also applicable to many IoT applications without ream-time requirements. 17. on pp.9, "Artificial intelligence technologies have been shown promising in many areas, including IoT." - This sentence has no any problem, but it's expected that subsequent sentences/paragraphs on the same page would elaborate why AI is promising for IoT. 18. on pp.11, "...controlling data collection and delivery for each of them has become impossible..." - "become impossible" is not very accurate here. We could say "become challenging", but it is not impossible. 19. on pp.11, "...it is impossible to deliver energy to many IoT devices simultaneously..." - Wonder what "to deliver energy to many IoT devices" really mean. 20. Section 4.3 Requirements are not clear * Example: Training AI/ML algorithm (section 4.3.1) gives some good examples but no clear Requirement Section 5.1 should be updated to give some clear indication of how the listed techniques (e.g. Naïve Bayes) apply specifically to IoT. Otherwise suggest just to briefly mention and then provide references for these techniques 21. The title of 5.1.1 to 5.1.4 has "for IoT", but the content of each of these 4 subsections does not talk too much on "IoT". 22. on pp.19 (5.2), Will edge computing, decentralized AI/ML and federated learning be considered here as well? For example, federated learning can protect data privacy, which is quite critical and needed for many IoT domains such as smart health. I would suggest adding "edge intelligence" and "federated learning" to 5.2. I can provide some texts if it helps. 23. Should there be a mention of TinyML (e.g., https://www.tinyml.org/summit/ ) in Section 5.2? 24. on pp.21, "...the IoT and the other network-related devices can use their computing resources ..." - In many place before page #21, IoT devices are said to be constrained, but here it is powerful and can even share its computing resources to other devices. 25. Security Considerations section seems to be missing from the draft. Best regards, CG Chonggang (CG) Wang Principal Engineer | InterDigital T: (610) 878.5731 E: Chonggang.Wang@InterDigital.com<mailto:Chonggang.Wang@InterDigital.com> [Banner] [Banner]<https://www.interdigital.com/white_papers/streaming-media-report-> ABI - Streaming Media Report<https://www.interdigital.com/white_papers/streaming-media-report-> This e-mail is intended only for the use of the individual or entity to which it is addressed, and may contain information that is privileged, confidential and/or otherwise protected from disclosure to anyone other than its intended recipient. Unintended transmission shall not constitute waiver of any privilege or confidentiality obligation. If you received this communication in error, please do not review, copy or distribute it, notify me immediately by email, and delete the original message and any attachments. Unless expressly stated in this e-mail, nothing in this message or any attachment should be construed as a digital or electronic signature.
- [icnrg] Comments on "draft-choi-icnrg-aiot-02" Chonggang Wang