In the future, the beyond 5G (B5G) the sixth generation (6G) systems will further penetrate the vertical industry applications, such as the mission-critical Internet-of-Things (MC-IoT) and autonomous vehicles. These emerging services that have stringent quality-of-service (QoS) requirements will bring unprecedented challenges. Accordingly, ultra-reliable and low-latency communication (URLLC) has been considered as one of the important application scenarios of B5G and 6G communications. Driven by recent breakthroughs in the area of deep learning, combining deep learning algorithms with theoretical principles of wireless communications has been considered as a promising way of developing enabling technologies for B5G and 6G systems. However, implementing deep learning in URLLC is not straightforward. Most of the widely applied deep learning algorithms are data-driven, but models in wireless networks are helpful for predicting and optimizing the QoS and resource utilization efficiency. In this talk, I will introduce a multi-level framework that enables user intelligence, edge intelligence and network intelligence for URLLC. The basic idea is to combine model-based and data-driven methods in B5G and 6G systems.
Changyang She received the B.Eng. degree in Honors College (formerly School of Advanced Engineering) of Beihang University (BUAA), Beijing, China in 2012, and Ph.D. degree in School of Electronics and Information Engineering of BUAA in 2017. From July 2017 to March 2018, he worked as a postdoctoral research fellow in Singapore University of Technology and Design. Since March 2018, he has worked as a postdoctoral research associate in the University of Sydney. His research interests include ultra-reliable and low-latency communications, mobile edge computing, tactile internet, mission-critical internet-of-things, and deep learning in wireless communications.