Comprehensive review on ML-based RIS-enhanced IoT systems: basics, research progress and future challenges

Sree Krishna Das; Fatma Benkhelifa; Yao Sun; Hanaa Abumarshoud; Qammer H. Abbasi; Muhammad Ali Imran; Lina Mohjazi

doi:10.1016/j.comnet.2023.109581

Comprehensive review on ML-based RIS-enhanced IoT systems: basics, research progress and future challenges

Sree Krishna Das, Fatma Benkhelifa, Yao Sun, Hanaa Abumarshoud, Qammer H. Abbasi, Muhammad Ali Imran, Lina Mohjazi

Research output: Contribution to journal › Article › peer-review

37 Citations (Scopus)

Abstract

Sixth generation (6G) internet of things (IoT) networks will modernize the applications and satisfy user demands through implementing smart and automated systems. Intelligence-based infrastructure, also called reconfigurable intelligent surfaces (RISs), have been introduced as a potential technology striving to improve system performance in terms of data rate, latency, reliability, availability, and connectivity. A huge amount of cost-effective passive components are included in RISs to interact with the impinging electromagnetic waves in a smart way. However, there are still some challenges in RIS system, such as finding the optimal configurations for a large number of RIS components. In this paper, we first provide a complete outline of the advancement of RISs along with machine learning (ML) algorithms and overview the working regulations as well as spectrum allocation in intelligent IoT systems. Also, we discuss the integration of different ML techniques in the context of RIS, including deep reinforcement learning (DRL), federated learning (FL), and FL-deep deterministic policy gradient (FL-DDPG) techniques which are utilized to design the radio propagation atmosphere without using pilot signals or channel state information (CSI). Additionally, in dynamic intelligent IoT networks, the application of existing integrated ML solutions to technical issues like user movement and random variations of wireless channels are surveyed. Finally, we present the main challenges and future directions in integrating RISs and other prominent methods to be applied in upcoming IoT networks.

Original language	English
Article number	109581
Number of pages	39
Journal	Computer Networks
Volume	224
Early online date	23 Jan 2023
DOIs	https://doi.org/10.1016/j.comnet.2023.109581
Publication status	Published - Apr 2023

Funder

Qammer H. Abbasi (Senior Member, IEEE) is currently a Reader with the James Watt School of Engineering, University of Glasgow, Glasgow, U.K.; the Deputy Head of the Communication Sensing and Imaging Group; the Program Director of the Dual Ph.D. Degree; the Deputy Theme Lead for quantum and nanotechnology with the University's Advance Research Centre; the Co-Manager of the RF and Terahertz Laboratory; and the Lead for healthcare and the Internet of Things use cases with the Scotland 5G Center Urban testbed. He has a grant portfolio of 6M and contributed to more than 350 leading international technical journal and peer-reviewed conference papers, and ten books. He is a Committee Member of the IEEE APS Young Professional, the IEEE 1906.1.1 Standard on Nano Communication, the IEEE APS/SC WG P145, the IET Antenna & Propagation, and Healthcare Network. Dr. Abbasi was a recipient of several recognitions for his research, including the URSI Young Scientist Award, the U.K. Exceptional Talent Endorsement by the Royal Academy of Engineering, the National Talent Pool Award by Pakistan, the International Young Scientist Award by NSFC China, the National Interest Waiver by USA, the University Research Excellence Award from TAMUQ in two consecutive years, the Reward for Excellence from the University of Glasgow, the Research Culture Award from the University of Glasgow, seven best paper awards, the Most Downloaded Paper in the IEEE Transactions on Terahertz Science and Technology, the Cover of MDPI Journal twice, and the Best Representative Image of an Outcome by QNRF. In addition, his work received media coverage by Analog IC Tips, Microwaves & RF Newsletters, Vertical News, Pakistan Dawn News, BBC, Scotland TV, Chinese News, and many other media houses. He is the Chair of the IEEE AP/MTT Scotland Joint Chapter and was the Chair of the IEEE Young Professional Affinity Group. He is currently an Associate Editor for the IEEE Journal of Electromagnetics, RF and Microwaves in Medicine and Biology, IEEE Sensors Journal, IEEE Internet of Things Journal, and IEEE Open Journal of Antennas and Propagation; a Senior Editor for IoT and Sensors Networks Section (Frontiers); and acted as a guest editor for numerous special issues in top-notch journals. He has been a member of the technical program committees of several IEEE flagship conferences; a technical reviewer for several IEEE and top-notch journals; acted as the TPC Chair and the Executive Chair for the Fourth, Fifth, and Sixth International UCET Conference in 2019, 2020, and 2021; and the EAI Bodynets 2021 General Co-Chair. He serves regularly as a Reviewer for EPSRC, MRC, and international funding bodies; an organizer for conferences, special sessions, and workshops; a TPC member for several IEEE flagship conferences; and a Reviewer for Wiley & Sons books, Springer, IET books, IEEE conferences, and more than 30 leading journals, including Nature.

Publisher Copyright:
© 2023 Elsevier B.V.

Keywords

6G
Deep learning
IoT
Machine learning
Reconfigurable intelligent surface
Resource management

ASJC Scopus subject areas

Computer Networks and Communications

Access to Document

10.1016/j.comnet.2023.109581

Cite this

@article{79b45f4aec2842939e30e9bbb3007a95,

title = "Comprehensive review on ML-based RIS-enhanced IoT systems: basics, research progress and future challenges",

abstract = "Sixth generation (6G) internet of things (IoT) networks will modernize the applications and satisfy user demands through implementing smart and automated systems. Intelligence-based infrastructure, also called reconfigurable intelligent surfaces (RISs), have been introduced as a potential technology striving to improve system performance in terms of data rate, latency, reliability, availability, and connectivity. A huge amount of cost-effective passive components are included in RISs to interact with the impinging electromagnetic waves in a smart way. However, there are still some challenges in RIS system, such as finding the optimal configurations for a large number of RIS components. In this paper, we first provide a complete outline of the advancement of RISs along with machine learning (ML) algorithms and overview the working regulations as well as spectrum allocation in intelligent IoT systems. Also, we discuss the integration of different ML techniques in the context of RIS, including deep reinforcement learning (DRL), federated learning (FL), and FL-deep deterministic policy gradient (FL-DDPG) techniques which are utilized to design the radio propagation atmosphere without using pilot signals or channel state information (CSI). Additionally, in dynamic intelligent IoT networks, the application of existing integrated ML solutions to technical issues like user movement and random variations of wireless channels are surveyed. Finally, we present the main challenges and future directions in integrating RISs and other prominent methods to be applied in upcoming IoT networks.",

keywords = "6G, Deep learning, IoT, Machine learning, Reconfigurable intelligent surface, Resource management",

author = "Das, {Sree Krishna} and Fatma Benkhelifa and Yao Sun and Hanaa Abumarshoud and Abbasi, {Qammer H.} and Imran, {Muhammad Ali} and Lina Mohjazi",

year = "2023",

month = apr,

doi = "10.1016/j.comnet.2023.109581",

language = "English",

volume = "224",

journal = "Computer Networks",

issn = "1389-1286",

publisher = "Elsevier",

}

TY - JOUR

T1 - Comprehensive review on ML-based RIS-enhanced IoT systems

T2 - basics, research progress and future challenges

AU - Das, Sree Krishna

AU - Benkhelifa, Fatma

AU - Sun, Yao

AU - Abumarshoud, Hanaa

AU - Abbasi, Qammer H.

AU - Imran, Muhammad Ali

AU - Mohjazi, Lina

PY - 2023/4

Y1 - 2023/4

N2 - Sixth generation (6G) internet of things (IoT) networks will modernize the applications and satisfy user demands through implementing smart and automated systems. Intelligence-based infrastructure, also called reconfigurable intelligent surfaces (RISs), have been introduced as a potential technology striving to improve system performance in terms of data rate, latency, reliability, availability, and connectivity. A huge amount of cost-effective passive components are included in RISs to interact with the impinging electromagnetic waves in a smart way. However, there are still some challenges in RIS system, such as finding the optimal configurations for a large number of RIS components. In this paper, we first provide a complete outline of the advancement of RISs along with machine learning (ML) algorithms and overview the working regulations as well as spectrum allocation in intelligent IoT systems. Also, we discuss the integration of different ML techniques in the context of RIS, including deep reinforcement learning (DRL), federated learning (FL), and FL-deep deterministic policy gradient (FL-DDPG) techniques which are utilized to design the radio propagation atmosphere without using pilot signals or channel state information (CSI). Additionally, in dynamic intelligent IoT networks, the application of existing integrated ML solutions to technical issues like user movement and random variations of wireless channels are surveyed. Finally, we present the main challenges and future directions in integrating RISs and other prominent methods to be applied in upcoming IoT networks.

AB - Sixth generation (6G) internet of things (IoT) networks will modernize the applications and satisfy user demands through implementing smart and automated systems. Intelligence-based infrastructure, also called reconfigurable intelligent surfaces (RISs), have been introduced as a potential technology striving to improve system performance in terms of data rate, latency, reliability, availability, and connectivity. A huge amount of cost-effective passive components are included in RISs to interact with the impinging electromagnetic waves in a smart way. However, there are still some challenges in RIS system, such as finding the optimal configurations for a large number of RIS components. In this paper, we first provide a complete outline of the advancement of RISs along with machine learning (ML) algorithms and overview the working regulations as well as spectrum allocation in intelligent IoT systems. Also, we discuss the integration of different ML techniques in the context of RIS, including deep reinforcement learning (DRL), federated learning (FL), and FL-deep deterministic policy gradient (FL-DDPG) techniques which are utilized to design the radio propagation atmosphere without using pilot signals or channel state information (CSI). Additionally, in dynamic intelligent IoT networks, the application of existing integrated ML solutions to technical issues like user movement and random variations of wireless channels are surveyed. Finally, we present the main challenges and future directions in integrating RISs and other prominent methods to be applied in upcoming IoT networks.

KW - 6G

KW - Deep learning

KW - IoT

KW - Machine learning

KW - Reconfigurable intelligent surface

KW - Resource management

UR - http://www.scopus.com/inward/record.url?scp=85147855656&partnerID=8YFLogxK

U2 - 10.1016/j.comnet.2023.109581

DO - 10.1016/j.comnet.2023.109581

M3 - Article

AN - SCOPUS:85147855656

SN - 1389-1286

VL - 224

JO - Computer Networks

JF - Computer Networks

M1 - 109581

ER -

Comprehensive review on ML-based RIS-enhanced IoT systems: basics, research progress and future challenges

Abstract

Funder

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this