Future sixth-generation (6G) wireless networks are envisaged to revolutionize the way how everything is connected, by offering a plethora of diverse smart applications over a ubiquitous, unified, self-sustainable, and fully intelligent platform. The rapidly changing wireless networks are evolving towards unleashing intelligence and software-defined functionalities, in which artificial intelligence (AI) will be the driving force that controls, optimizes, and configures all elements in the network. However, through this revolutionary process, radio environments remain unlikely amenable to control. Specifically, until recently, system designers are tailoring the network components, including transmitter/receiver design, protocols, algorithms, etc., in a way that enables these components to efficiently operate in random wireless environments.
Corresponding to the breakthrough advancements in hardware technologies, reconfigurable intelligent surface (RIS) has emerged as a revolutionary energy and spectrally efficient technology, which is capable of offering a programmable control over the wireless environment. Specifically, the unique structure of an intelligent surface, which constitutes a number of metasurfaces, is artificially engineered in order to allow full manipulation of the incident electromagnetic (EM) waves. At the macroscopic level, metasurfaces exhibit unique EM properties, such as customized permittivity and permeability levels, and negative refraction. Consequently, this enables metasurfaces to realize unprecedented features when interacting with impinging EM waves, including wave focusing, absorption, scattering, and polarization, in a way that enhances the performance of wireless systems in terms of coverage, rate, etc. It is worth mentioning that metasurfaces leverage these unique abilities without any limitation on their operating frequency.
This newly emerged technology will essentially require the development of a novel, tractable and adaptive model, known as Reconfigurable Intelligent Surface (RIS), to cope with its unique electromagnetic nature. In order to perform the required functionalities in the RIS, it is necessary to integrate network controllers with RISs in order to support real-time adaptivity of RIS functionalities. In light of this, it is foreseen that the implementation of RIS in future wireless networks would require a high and sophisticated level of coordination and optimization. Therefore, it is envisioned that AI will be an indispensable tool for realizing software-defined intelligent surfaces in future 6G networks. Specifically, besides on-demand network optimization, AI is expected to cope with the high computational complexity associated with RIS real-time programming, controlling, and planning. This new era of AI-empowered metasurfaces opens up new horizons and research directions, including learning mechanisms, knowledge management, and data analytics techniques, to name a few.
The purpose of this special issue is to address fundamental and practical challenges for the efficient design of AI-empowered RIS, proposing new efficient protocols and techniques. More specifically, this special issue will bring together leading researchers and developers from both industry and academia to present their views on the current trends and challenges, addressing various concerns related to AI-empowered RIS. The papers will be peer-reviewed by at least three independent experts and will be selected on the basis of their quality and relevance to the theme of this special issue.
Architecture design and algorithms of AI-RIS enabled wireless networks.
Physical layer security in AI-RIS enabled wireless networks.
AI-RIS enabled UAV networks.
AI-RIS enabled vehicular networks.
AI-RIS enabled integrated satellite-air-ground networks.
Energy efficient schemes for AI-RIS enabled wireless networks.
Performance analysis and optimization of AI-RIS enabled wireless networks.
AI-RIS enabled fog and mobile edge computing.
Multi-user schemes in AI-RIS enabled wireless networks.
Information security, privacy, and trust in AI-RIS enabled wireless networks.
Crowdsourcing in AI-RIS enabled wireless networks.
Centralized and distributed machine learning in AI-RIS enabled wireless networks.
Integration of RISs with THz communication, multiple access techniques, and optical communications.
The submitted papers should be original, not published or currently under review for publications in any other journal. Submitted Articles have no page limits and can be any of the following types: technical, tutorial, survey, overview, magazine, letter, or commentary. Also, authors are allowed to submit multiple articles to the same issue.
Prof. Paul D Yoo, Department of Computer Science and Information Systems, University of London, London WC1E 7HX, United Kingdom.
Prof. Meiling Li, Institute of Digital Media and Communications, Taiyuan University of Science and Technology, Taiyuan 030024, China.
Prof. Sanjeev Gurugopinath, Department of ECE, PES University, BSK III Stage, Bengaluru - 560085, India.
Prof. Sami Muhaidat, Center for Cyber-Physical Systems, Khalifa University, UAE, and also with Carleton University, Ottawa, ON K1S 5B6, Canada.
Dr. Lina Bariah, Center for Cyber-Physical Systems, Khalifa University, UAE.