Learning and Management for Internet of Things: Accounting for Adaptivity and Scalability

Tianyi Chen, Sergio Barbarossa, Xin Wang, Georgios B Giannakis, Zhi-Li Zhang

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Internet of Things (IoT) envisions an intelligent infrastructure of networked smart devices offering task-specific monitoring and control services. The unique features of IoT include extreme heterogeneity, massive number of devices, and unpredictable dynamics partially due to human interaction. These call for foundational innovations in network design and management. Ideally, it should allow efficient adaptation to changing environments, and low-cost implementation scalable to a massive number of devices, subject to stringent latency constraints. To this end, the overarching goal of this paper is to outline a unified framework for online learning and management policies in IoT through joint advances in communication, networking, learning, and optimization. From the network architecture vantage point, the unified framework leverages a promising fog architecture that enables smart devices to have proximity access to cloud functionalities at the network edge, along the cloud-to-things continuum. From the algorithmic perspective, key innovations target online approaches adaptive to different degrees of nonstationarity in IoT dynamics, and their scalable model-free implementation under limited feedback that motivates blind or bandit approaches. The proposed framework aspires to offer a stepping stone that leads to systematic designs and analysis of task-specific learning and management schemes for IoT, along with a host of new research directions to build on.

Original languageEnglish (US)
Article number8648462
Pages (from-to)778-796
Number of pages19
JournalProceedings of the IEEE
Volume107
Issue number4
DOIs
StatePublished - Apr 2019

Fingerprint

Scalability
Innovation
Fog
Network architecture
Internet of things
Feedback
Monitoring
Communication
Costs

Keywords

  • Internet of Things (IoT)
  • mobile edge computing (MEC)
  • network resource allocation
  • online learning
  • stochastic optimization

Cite this

Learning and Management for Internet of Things : Accounting for Adaptivity and Scalability. / Chen, Tianyi; Barbarossa, Sergio; Wang, Xin; Giannakis, Georgios B; Zhang, Zhi-Li.

In: Proceedings of the IEEE, Vol. 107, No. 4, 8648462, 04.2019, p. 778-796.

Research output: Contribution to journalArticle

@article{ed76ab4e7d56406a9ff6a2a1a4b5d8d7,
title = "Learning and Management for Internet of Things: Accounting for Adaptivity and Scalability",
abstract = "Internet of Things (IoT) envisions an intelligent infrastructure of networked smart devices offering task-specific monitoring and control services. The unique features of IoT include extreme heterogeneity, massive number of devices, and unpredictable dynamics partially due to human interaction. These call for foundational innovations in network design and management. Ideally, it should allow efficient adaptation to changing environments, and low-cost implementation scalable to a massive number of devices, subject to stringent latency constraints. To this end, the overarching goal of this paper is to outline a unified framework for online learning and management policies in IoT through joint advances in communication, networking, learning, and optimization. From the network architecture vantage point, the unified framework leverages a promising fog architecture that enables smart devices to have proximity access to cloud functionalities at the network edge, along the cloud-to-things continuum. From the algorithmic perspective, key innovations target online approaches adaptive to different degrees of nonstationarity in IoT dynamics, and their scalable model-free implementation under limited feedback that motivates blind or bandit approaches. The proposed framework aspires to offer a stepping stone that leads to systematic designs and analysis of task-specific learning and management schemes for IoT, along with a host of new research directions to build on.",
keywords = "Internet of Things (IoT), mobile edge computing (MEC), network resource allocation, online learning, stochastic optimization",
author = "Tianyi Chen and Sergio Barbarossa and Xin Wang and Giannakis, {Georgios B} and Zhi-Li Zhang",
year = "2019",
month = "4",
doi = "10.1109/JPROC.2019.2896243",
language = "English (US)",
volume = "107",
pages = "778--796",
journal = "Proceedings of the IEEE",
issn = "0018-9219",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Learning and Management for Internet of Things

T2 - Accounting for Adaptivity and Scalability

AU - Chen, Tianyi

AU - Barbarossa, Sergio

AU - Wang, Xin

AU - Giannakis, Georgios B

AU - Zhang, Zhi-Li

PY - 2019/4

Y1 - 2019/4

N2 - Internet of Things (IoT) envisions an intelligent infrastructure of networked smart devices offering task-specific monitoring and control services. The unique features of IoT include extreme heterogeneity, massive number of devices, and unpredictable dynamics partially due to human interaction. These call for foundational innovations in network design and management. Ideally, it should allow efficient adaptation to changing environments, and low-cost implementation scalable to a massive number of devices, subject to stringent latency constraints. To this end, the overarching goal of this paper is to outline a unified framework for online learning and management policies in IoT through joint advances in communication, networking, learning, and optimization. From the network architecture vantage point, the unified framework leverages a promising fog architecture that enables smart devices to have proximity access to cloud functionalities at the network edge, along the cloud-to-things continuum. From the algorithmic perspective, key innovations target online approaches adaptive to different degrees of nonstationarity in IoT dynamics, and their scalable model-free implementation under limited feedback that motivates blind or bandit approaches. The proposed framework aspires to offer a stepping stone that leads to systematic designs and analysis of task-specific learning and management schemes for IoT, along with a host of new research directions to build on.

AB - Internet of Things (IoT) envisions an intelligent infrastructure of networked smart devices offering task-specific monitoring and control services. The unique features of IoT include extreme heterogeneity, massive number of devices, and unpredictable dynamics partially due to human interaction. These call for foundational innovations in network design and management. Ideally, it should allow efficient adaptation to changing environments, and low-cost implementation scalable to a massive number of devices, subject to stringent latency constraints. To this end, the overarching goal of this paper is to outline a unified framework for online learning and management policies in IoT through joint advances in communication, networking, learning, and optimization. From the network architecture vantage point, the unified framework leverages a promising fog architecture that enables smart devices to have proximity access to cloud functionalities at the network edge, along the cloud-to-things continuum. From the algorithmic perspective, key innovations target online approaches adaptive to different degrees of nonstationarity in IoT dynamics, and their scalable model-free implementation under limited feedback that motivates blind or bandit approaches. The proposed framework aspires to offer a stepping stone that leads to systematic designs and analysis of task-specific learning and management schemes for IoT, along with a host of new research directions to build on.

KW - Internet of Things (IoT)

KW - mobile edge computing (MEC)

KW - network resource allocation

KW - online learning

KW - stochastic optimization

UR - http://www.scopus.com/inward/record.url?scp=85063804937&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063804937&partnerID=8YFLogxK

U2 - 10.1109/JPROC.2019.2896243

DO - 10.1109/JPROC.2019.2896243

M3 - Article

AN - SCOPUS:85063804937

VL - 107

SP - 778

EP - 796

JO - Proceedings of the IEEE

JF - Proceedings of the IEEE

SN - 0018-9219

IS - 4

M1 - 8648462

ER -