Virtualizing AI at the Distributed Edge towards Intelligent IoT Applications

Several Internet of Things (IoT) applications are booming which rely on advanced artificial intelligence (AI) and, in particular, machine learning (ML) algorithms to assist the users and make decisions on their behalf in a large variety of contexts, such as smart homes, smart cities, smart factories. Although the traditional approach is to deploy such compute-intensive algorithms into the centralized cloud, the recent proliferation of low-cost, AI-powered microcontrollers and consumer devices paves the way for having the intelligence pervasively spread along the cloud-to-things continuum. The take off of such a promising vision may be hurdled by the resource constraints of IoT devices and by the heterogeneity of (mostly proprietary) AI-embedded software and hardware platforms. In this paper, we propose a solution for the AI distributed deployment at the deep edge, which lays its foundation in the IoT virtualization concept. We design a virtualization layer hosted at the network edge that is in charge of the semantic description of AI-embedded IoT devices, and, hence, it can expose as well as augment their cognitive capabilities in order to feed intelligent IoT applications. The proposal has been mainly devised with the twofold aim of (i) relieving the pressure on constrained devices that are solicited by multiple parties interested in accessing their generated data and inference, and (ii) and targeting interoperability among AI-powered platforms. A Proof-of-Concept (PoC) is provided to showcase the viability and advantages of the proposed solution.

[1]  Nirwan Ansari,et al.  EdgeIoT: Mobile Edge Computing for the Internet of Things , 2016, IEEE Communications Magazine.

[2]  Mianxiong Dong,et al.  Learning IoT in Edge: Deep Learning for the Internet of Things with Edge Computing , 2018, IEEE Network.

[3]  Zhisheng Niu,et al.  Edge Learning with Timeliness Constraints: Challenges and Solutions , 2020, IEEE Communications Magazine.

[4]  Vermesan Ovidiu,et al.  Internet of Things Strategic Research and Innovation Agenda , 2014 .

[5]  Marko Jurmu,et al.  6G White Paper on Edge Intelligence , 2020, ArXiv.

[6]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[7]  Xu Chen,et al.  Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing , 2019, Proceedings of the IEEE.

[8]  Prashant Shenoy,et al.  AI on the Edge: Rethinking AI-based IoT Applications Using Specialized Edge Architectures , 2020, ArXiv.

[9]  Minh-Tu Cao,et al.  Survey on performance of deep learning models for detecting road damages using multiple dashcam image resources , 2020, Adv. Eng. Informatics.

[10]  Aman Jantan,et al.  State-of-the-art in artificial neural network applications: A survey , 2018, Heliyon.

[11]  Dong-Kyu Choi,et al.  IoT-Based Resource Control for In-Vehicle Infotainment Services: Design and Experimentation , 2019, Sensors.

[12]  Raffaele Giaffreda.  iCore: A Cognitive Management Framework for the Internet of Things , 2013, Future Internet Assembly.

[13]  Michael Weyrich,et al.  Reference Architectures for the Internet of Things , 2016, IEEE Software.

[14]  Antonio Iera,et al.  SDN&NFV contribution to IoT objects virtualization , 2019, Comput. Networks.

[15]  Maximilian Lam,et al.  Benchmarking TinyML Systems: Challenges and Direction , 2020, ArXiv.

[16]  Nirwan Ansari,et al.  On cost aware cloudlet placement for mobile edge computing , 2019, IEEE/CAA Journal of Automatica Sinica.

[17]  Huayong Yang,et al.  A smart surface inspection system using faster R-CNN in cloud-edge computing environment , 2020, Adv. Eng. Informatics.

[18]  Kerry L. Taylor,et al.  Semantics for the Internet of Things: Early Progress and Back to the Future , 2019 .

[19]  Costin Badica,et al.  Rule-Based Distributed and Agent Systems , 2011, RuleML Europe.

[20]  Antonio F. Skarmeta,et al.  TinyML-Enabled Frugal Smart Objects: Challenges and Opportunities , 2020, IEEE Circuits and Systems Magazine.

[21]  Giancarlo Fortino,et al.  Agent-based Internet of Things: State-of-the-art and research challenges , 2020, Future Gener. Comput. Syst..

[22]  Kashif Sharif,et al.  IoT Virtualization: A Survey of Software Definition & Function Virtualization Techniques for Internet of Things , 2019, ArXiv.

[23]  Luigi Atzori,et al.  The Virtual Object as a Major Element of the Internet of Things: A Survey , 2016, IEEE Communications Surveys & Tutorials.

[24]  Carsten Bormann,et al.  CoAP: An Application Protocol for Billions of Tiny Internet Nodes , 2012, IEEE Internet Computing.

[25]  Edgar Ramos,et al.  Distributing Intelligence to the Edge and Beyond [Research Frontier] , 2019, IEEE Computational Intelligence Magazine.

[26]  Antonio Iera,et al.  Optimal Placement of Social Digital Twins in Edge IoT Networks , 2020, Sensors.

[27]  Xiaofei Wang,et al.  Convergence of Edge Computing and Deep Learning: A Comprehensive Survey , 2019, IEEE Communications Surveys & Tutorials.

[28]  Jukka Riekki,et al.  Semantic Reasoning for Context-Aware Internet of Things Applications , 2016, IEEE Internet of Things Journal.

[29]  Tarik Taleb,et al.  On Multi-Access Edge Computing: A Survey of the Emerging 5G Network Edge Cloud Architecture and Orchestration , 2017, IEEE Communications Surveys & Tutorials.