Skip to main content
Publications lead hero image abstract pattern


Publication Date

Manuscript Submission Deadline

Special Issue

Call for Papers

Nowadays, researchers have started to conceptualize 6G with the vision of connecting everything, transmission over mmWave and THz, and integrating sensing, communication, computation, and control functionalities. To support such network evolution, the deployment of small and even tiny cells is further densified overlaying with the existing macro cellular networks. The resultant technical and network complexity puts considerable pressure on energy efficiency and sustainability.

Artificial intelligence (AI) and machine learning techniques have great potential to tackle the energy efficiency challenges in the future green 6G. AI methodologies, e.g., deep learning, federated learning and reinforcement learning, can be explored for the design and optimization of 6G architecture and network orchestration in a cost-efficient manner. By learning the complex network topology and the varying traffic pattern, AI could tame network complexity for the design of 6G air interfaces. The diversified 6G enabling applications, such as smart cities, smart grid, autonomous vehicles, and industrial automation, will make AI more far-reaching and essential in energy savings. On the other hand, AI and machine learning techniques usually demand high computation and communication. This may pose a significant challenge for the design and implementation of both machine learning algorithms and future 6G systems in an energy-efficient way. One advantage is that 6G's Gb-level transmission rate will possibly bring a radical paradigm shift for AI toward ubiquitous AI, taking advantage of distributed machine learning and edge intelligence.

Thus, the convergence of AI and 6G will potentially overcome the defect of network complexity and find a path toward a sustainable ecosystem. However, limited research efforts have been made and few studies can be found regarding the convergence of 6G and AI from an energy-efficiency perspective. Challenges still remain untouched on how to tailor AI on edge nodes and systematically work for a green 6G and how 6G networks will support AI. This Special Issue (SI) aims to bring together researchers from academia and industry to explore recent advances and state-of-the-art on the convergence of AI and 6G integrated design and optimization. Possible topics include, but are not limited to:

AI empowered green 6G:

  • Green communication and networking for AI enabled 6G
  • AI-based channel estimation and prediction in 6G
  • AI empowered energy-efficient scheduling and resource management for 6G
  • Energy-efficient AI enabled 6G network orchestration
  • Green hardware, software and platforms for AI enabled 6G networks
  • AI methods managing performance, scalability and complexity in 6G
  • Hardware-aware communication in Green 6G
  • New AI-based energy harvesting and management technologies
  • AI-based self-optimizing transmitters and receivers for Green 6G
  • AI driving green computation offloading
  • Innovative AI and Green 6G-enabled usage applications
  • Breakthrough theories, concepts and technologies for integrated AI and Green 6G
  • New performance metrics and evaluation criteria for AI-enabled Green 6G

6G supporting green AI:

  • Novel 6G architectures for green AI
  • New concepts, models and frameworks for supporting green AI
  • Distributed machine learning in 6G
  • Communication-efficient machine learning in 6G (e.g., federated learning, deep reinforcement learning, deep learning)
  • Deep learning algorithm and operation supported by 6G
  • New AI applications driven by 6G
  • Security and privacy issues in AI-based green communication technologies
  • AI methods for different hardware constraints in 6G
  • Testbed, experiments and standards supporting green AI

Submission Guidelines

Manuscripts should conform to the standard format as indicated in the “Information for Authors” section of the Paper Submission Guidelines.

All manuscripts to be considered for publication must be submitted by the deadline through Manuscript Central. Select “November 2021/AI and 6G Convergence: An Energy-Efficiency Perspective” from the drop-down menu of Topic titles.

Important Dates

Manuscript Submission Deadline: 15 April 2021
Initial Decision Notification: 15 June 2021
Revised Manuscript Due: 15 July 2021
Final Decision Notification: 15 August 2021
Final Manuscript Due: 30 August 2021
Publication Date: November 2021

Guest Editors

Yan Zhang
University of Oslo, Norway

Melike Erol-Kantarci
University of Ottawa, Canada

Wen Sun
Northwestern Polytechnical University, China

Yueyue Dai
Nanyang Technological University, Singapore

Jakob Hoydis
Nokia Bell Labs, France

M. Cenk Gursoy
Syracuse University, USA