Call for Papers

As one of the new communication scenarios in the 5th Generation (5G) mobile communications, Ultra-Reliable and Low-Latency Communications (URLLC) is crucial for enabling a wide range of emerging applications, including industry automation, intelligent transportation, telemedicine, Tactile Internet, Virtual/Augmented Reality (VR/AR) and Meta Universe. According to the requirements in 5G standards, to support emerging mission-critical applications, the End-to-End (E2E) delay cannot exceed 1 ms and the packet loss probability should be 10^-5 ~10^-7. Compared with the existing cellular networks, the delay and reliability require significant improvements by at least two orders of magnitude for 5G networks. This capability gap cannot be fully resolved by the 5G New Radio (NR), i.e., the physical-layer technology for 5G, even though the transmission delay in Radio Access Networks (RANs) achieves the 1 ms target. Transmission delay contributes a small fraction of the E2E delay. Stochastic delays in upper networking layers, such as queuing delay, processing delay, and access delay, remain key bottlenecks for achieving URLLC. Beyond 5G systems or so-called Sixth Generation (6G) systems should guarantee the E2E delay bound with high reliability.

In addition to the latency and reliability requirements, some other Key Performance Indicators (KPIs) should also be taken into account, including Spectrum Efficiency, throughput, Energy Efficiency, Age of Information, jitter, round-trip delay, network availability, and security. To meet diverse KPI requirements, a new trend of developing communication networks is to integrating domain knowledge in wireless communications, information theory, and networking into deep learning. Considering that deep learning algorithm suffers from low learning efficiency in terms of computing efficiency and sample efficiency, the domain knowledge has the potential to improve the learning efficiency significantly. The combination of human intelligence (domain knowledge) and artificial intelligence (machine learning algorithms) will be critical for achieving URLLC in 6G.

To enable intelligent URLLC in 6G, we seek original and high quality submissions related to the core area of this Special Issue (SI). Topics of interest include, but are not limited to, the following subjects, all in the context of intelligent URLLC:

• Constrained deep/reinforcement learning for diverse Quality-of-Service guarantee in URLLC
• Distributed learning/graph neural networks for network management of URLLC
• Few-shot learning for URLLC in dynamic wireless networks
• Fundamental limits, performance analysis, theoretic approaches for intelligent URLLC
• Prediction and communication co-design for long-distance URLLC
• Learning to optimize finite blocklength communications for factory automation
• Intelligent URLLC for better Quality-of-Experience in digital twin/meta universe
• Real-world deployments, experiments, prototypes, and testbeds for intelligent URLLC

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.

Important Dates

Manuscript Submission Deadline: 15 August 2022
Initial Decision Date: 1 October 2022
Revised Manuscript Due: 1 November 2022
Final Decision Date: 1 December 2022
Final Manuscript Due: 1 February 2023
Publication Date: April 2023

Guest Editors

Changyang She
The University of Sydney, Sydney, Australia  

Trung Q. Duong
Queen’s University Belfast, Belfast, UK  

Tony Q.S. Quek
Singapore University of Technology and Design, Singapore 

Harish Viswanathan
Nokia Bell Labs, New Jersey, USA  

David Lopez-Perez
Huawei Technologies, France