IEEE International Mediterranean Conference on Communications and Networking
8–11 July 2024 // Madrid, Spain

WS-01: Workshop on scalable, efficient, and optimized model-based AI/ML solutions for 6G networks

WS-01: Workshop on scalable, efficient, and optimized model-based AI/ML solutions for 6G networks


Mobile communications have transformed our lives and will continue to provide universal access to education, health, security, and much more. With 5G underway, the interest of the scientific and industrial communities has already begun to focus on the future 6G communication networks. However, the stringent requirements not met by 5G (latency, reliability, data, and energy) and the new and critical use cases that will be required can be seen as new challenges for 6G. In the architectural domain, there is a need for full integration and interoperation between satellite, airborne, and terrestrial network components, brought together for the first time in a unique, dynamically adaptive network infrastructure, referred to as the 3D network. Within this architecture, the evolution of mobile communications requires a combination of several innovative and complementary advances at the PHY, MAC, and RMM. These include sensing and context awareness, new waveforms and interference management, advanced MIMO techniques, RIS, and holographic radio. Undoubtedly, achieving these challenging requirements requires a paradigm shift.

Artificial Intelligence (AI) and Machine Learning (ML) have been successfully applied to solve many problems in engineering (e.g., computer vision). For this reason, their application to wireless communication problems has attracted considerable attention in recent years. It is envisaged that 6G communication networks will be the first generation of networks with native AI. However, a purely data-driven approach has significant limitations due to its resource constraints, high complexity, and black-box nature. AI/ML must be developed for wireless communications with the characteristics and features of these networks in mind. This idea refers to the combination of physical modeling based on numerical simulations or mathematical models with methods based on AI. The success of AI in many areas of science has led to the belief that this technology has the potential to replace traditional mathematical or simulation-based approaches to science that start from first principles. Bridging both worlds is crucial for the next generation of communication systems: combining classical mathematical and numerical techniques with AI methods. A key reason for the importance of this combination is that AI methods are powerful, but at the same time, they benefit significantly from domain knowledge in the form of physical models.

Topics of Interest

This special session will provide a forum for sharing multidisciplinary contributions to developing model-based AI solutions for future 6G networks that provide considerable advances at PHY, MAC, and RRM layers. In this context, we seek to assemble crosscutting and high-quality original research papers on topics including, but not limited to:

  • Model-based AI beamforming and mMIMO solutions for 6G networks
  • New model-based AI waveforms for 6G networks
  • In-band full-duplex solutions for 6G networks aided by model-based AI
  • PHY/MAC/RRM algorithms for RIS solutions using model-based AI
  • PHY/MAC/RRM sensing algorithms using model-based AI
  • Non-coherent communications for 6G networks aided by model-based AI
  • Energy efficient PHY/MAC/RRM model-based AI algorithms for 6G
  • Model-based AI algorithms for 6G cognitive radio networks
  • Robust AI solutions for constrained and dynamic RRM in 6G
  • Model-based AI solutions for routing and network management
  • AI solutions for mobility management in multilayer 6G networks

Important Dates

  • Workshop Paper Submission Deadline: 5 April 2024
  • Paper Acceptance Notification: 14 May 2024
  • Camera Ready: 1 June 2024

Submission Link

Workshop Chairs

  • Eneko Iradier, University of the Basque Country, Spain
  • Thang X. Vu, University of Luxembourg, Luxembourg
  • Adrian Kliks, Poznan University of Technology, Poland
  • Marco di Renzo, University Paris-Saclay, France