Ultra-Reliable and Low-Latency Communications in 6G: Challenges, Solutions, and Future Directions

In the future, 6th-generation networks, ultra-reliable and low-latency communications (URLLC) will lay the foundation for emerging mission-critical applications that have stringent requirements on end-to-end delay and reliability. Nevertheless, applications in different vertical industries have unique requirements on top of latency and reliability, such as global connectivity, high mobility, and low jitter. Since these key performance indicators have not been addressed in the 5th-generation (5G) communication systems, 5G systems are not ready for URLLC. In this chapter, we first identify promising technologies to fulfill these requirements and summarize corresponding new research challenges. To address these challenges, we investigate design methodologies in wireless artificial intelligence and put forward a multi-level architecture that enables device intelligence, edge intelligence, and cloud intelligence for URLLC. The basic idea is to merge theoretical models and real-world data in analyzing the latency and reliability and training deep neural networks (DNNs). Considering that the computing capacity at each user and each mobile edge computing server is limited, federated learning is applied to improve the learning efficiency. Furthermore, meta-learning is adopted in the architecture to increase the generalization ability of DNNs in nonstationary networks. Finally, we provide some experimental and simulation results and discuss some future directions.