Call for Papers

The augmentation of system degrees of freedom as we transition from one network generation to the next not only raises the likelihood of failures but also adds complexity to the responsibilities of human operators. This intricacy is especially evident in tasks involving real-time monitoring and fine-tuning, crucial for upholding 6G stringent service level agreements for e.g., immersive Holographic Type Communications (HTC) and industry 5.0. The response to this escalating complexity is the imperative artificial intelligence (AI)-driven automation of networks. The essence lies in the virtualization of network functions within the Radio Access Network (RAN) Edge Cloud continuum, where AI-driven agents seamlessly handle resource allocation, scaling, and dynamic placement of architectural components. This smooth orchestration, facilitated by a programmable infrastructure, empowers network operators to craft automation workflows tailored to the heterogeneity of workloads. In this respect, Intent-Based Networking (IBN) stands out as a pivotal approach in the realm of 6G network automation. By aligning network operations with specific intents such as enhancing energy efficiency or reducing latency, IBN streamlines both operations and resource allocation. The dynamic translation of high-level intents into specific network configurations using repurposed Generative AI models allows network administrators to automate lower-level tasks. On the other hand, standardization processes, such as defining protocol flows, come into play. This intricate task involves sequencing messages, procedures, and interactions among different network elements to ensure seamless communication and interoperability. Notably, standardization bodies like 3GPP invest significant effort in manually refining protocol flows to underpin reliability and efficiency. With the advent of AI-driven 6G networks, a paradigm shift emerges, wherein thanks to multi-agent communication, optimal and resource-efficient protocols can be discovered on-the-fly. This challenge is especially pertinent in mitigating conflicting decisions among competing network functions. Having said that, ethical considerations drive efforts towards enhancing transparency, interpretability, and fairness of these AI-based components. Exploring eXplainable AI (XAI) and neuro-symbolic (NeSy) AI strategies that navigate the intricate balance between explainability and performance become pivotal. 

This special issue aims at gathering the recent advances in AI for future 6G networks. It will focus on, but will not be limited to, the following topics of interest:

• Generative AI for 6G networks.
• Neuro-Symbolic AI integration in 6G.
• Multi-agent protocol learning for 6G.
• Multi-agent communication for collaborative 6G.
• Advances in explainable and human-centred AI for 6G networks.
• Advances in AI for 6G Open RAN.
• Advances in AI for optical and time-sensitive networking.
• Advances in Federated Learning for 6G
• Advances in Deep Reinforcement Learning for 6G.
• Distributed Data and knowledge distillation for 6G.
• Sustainable AI for 6G.
• AI integration in future-proof 6G PoCs.

Submission Guidelines 

Manuscripts should conform to the standard format indicated in the Manuscript Submission Guidelines on the IEEE Networking Letters website. Please, check these guidelines carefully before submitting since submissions not complying with them will be administratively rejected without review.

All manuscripts to be considered for publication must be submitted by the deadline through the Author Portal. Select the "IEEE Networking Letters Special Issue on "Advances in AI for 6G Networks" topic from the drop-down menu at the time of submission.

Important Dates

Manuscript Submission Deadline: 31 July 2024
First Round of Decision Notification: 31 August 2024
Final Decision: 30 September 2024
Final Manuscript Due: 15 October 2024
Target Publication Date: Fourth Quarter 2024

Guest Editors

Hatim Chergui (Lead Guest Editor)
i2CAT Foundation, Barcelona, Spain

Kamel Tourki
Airbus Defence and Space, France

Jun Wu
Shanghai Jiao Tong University, China