TY - JOUR
T1 - A Tutorial on Ultrareliable and Low-Latency Communications in 6G
T2 - Integrating Domain Knowledge into Deep Learning
AU - She, Changyang
AU - Sun, Chengjian
AU - Gu, Zhouyou
AU - Li, Yonghui
AU - Yang, Chenyang
AU - Poor, H. Vincent
AU - Vucetic, Branka
N1 - Funding Information:
Manuscript received September 13, 2020; accepted January 7, 2021. Date of current version March 3, 2021. The work of Changyang She was supported by the Australian Research Council Discovery Early Career Research Award under Grant DE210100415. The work of Yonghui Li was supported by the Australian Research Council under Grant DP190101988 and Grant DP210103410. The work of Branka Vucetic was supported by the Australian Research Council Laureate Fellowship under Grant FL160100032. (Corresponding author: Yonghui Li.) Changyang She, Zhouyou Gu, Yonghui Li, and Branka Vucetic are with the School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW 2006, Australia (e-mail: shechangyang@gmail.com; zhouyou.gu@sydney.edu.au; yonghui.li@sydney.edu.au; branka.vucetic@sydney.edu.au). Chengjian Sun and Chenyang Yang are with the School of Electronics and Information Engineering, Beihang University, Beijing 100191, China (e-mail: sunchengjian@buaa.edu.cn; cyyang@buaa.edu.cn). H. Vincent Poor is with the Department of Electrical Engineering, Princeton University, Princeton, NJ 08544 USA (e-mail: poor@princeton.edu).
Funding Information:
Dr. She was a recipient of the Australian Research Council Discovery Early Career Research Award.
Funding Information:
received the Ph.D. degree in electrical engi- neering from Beihang University, Beijing, China, in 1997. She has been a Full Professor with Beihang University since 1999. She has pub- lished over 300 articles in the fields of machine learning for wireless communica- tions, energy-efficient resource allocation, ultrareliable and low-latency communication (URLLC), wireless caching, interference management, and so on. She was supported by the First Teaching and Research Award Program for Outstanding Young Teachers of Higher Education Institutions by the Ministry of Education of China. Her recent research interests lie in mobile/wireless AI, wireless virtual reality (VR), and URLLCs.
Publisher Copyright:
© 1963-2012 IEEE.
PY - 2021/3
Y1 - 2021/3
N2 - As one of the key communication scenarios in the fifth-generation and also the sixth-generation (6G) mobile communication networks, ultrareliable and low-latency communications (URLLCs) will be central for the development of various emerging mission-critical applications. State-of-the-art mobile communication systems do not fulfill the end-to-end delay and overall reliability requirements of URLLCs. In particular, a holistic framework that takes into account latency, reliability, availability, scalability, and decision-making under uncertainty is lacking. Driven by recent breakthroughs in deep neural networks, deep learning algorithms have been considered as promising ways of developing enabling technologies for URLLCs in future 6G networks. This tutorial illustrates how domain knowledge (models, analytical tools, and optimization frameworks) of communications and networking can be integrated into different kinds of deep learning algorithms for URLLCs. We first provide some background of URLLCs and review promising network architectures and deep learning frameworks for 6G. To better illustrate how to improve learning algorithms with domain knowledge, we revisit model-based analytical tools and cross-layer optimization frameworks for URLLCs. Following this, we examine the potential of applying supervised/unsupervised deep learning and deep reinforcement learning in URLLCs and summarize related open problems. Finally, we provide simulation and experimental results to validate the effectiveness of different learning algorithms and discuss future directions.
AB - As one of the key communication scenarios in the fifth-generation and also the sixth-generation (6G) mobile communication networks, ultrareliable and low-latency communications (URLLCs) will be central for the development of various emerging mission-critical applications. State-of-the-art mobile communication systems do not fulfill the end-to-end delay and overall reliability requirements of URLLCs. In particular, a holistic framework that takes into account latency, reliability, availability, scalability, and decision-making under uncertainty is lacking. Driven by recent breakthroughs in deep neural networks, deep learning algorithms have been considered as promising ways of developing enabling technologies for URLLCs in future 6G networks. This tutorial illustrates how domain knowledge (models, analytical tools, and optimization frameworks) of communications and networking can be integrated into different kinds of deep learning algorithms for URLLCs. We first provide some background of URLLCs and review promising network architectures and deep learning frameworks for 6G. To better illustrate how to improve learning algorithms with domain knowledge, we revisit model-based analytical tools and cross-layer optimization frameworks for URLLCs. Following this, we examine the potential of applying supervised/unsupervised deep learning and deep reinforcement learning in URLLCs and summarize related open problems. Finally, we provide simulation and experimental results to validate the effectiveness of different learning algorithms and discuss future directions.
KW - Cross-layer optimization
KW - deep reinforcement learning (DRL)
KW - sixth generation (6G)
KW - supervised deep learning
KW - ultrareliable and low-latency communications (URLLCs)
KW - unsupervised deep learning
UR - http://www.scopus.com/inward/record.url?scp=85102377757&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85102377757&partnerID=8YFLogxK
U2 - 10.1109/JPROC.2021.3053601
DO - 10.1109/JPROC.2021.3053601
M3 - Article
AN - SCOPUS:85102377757
SN - 0018-9219
VL - 109
SP - 204
EP - 246
JO - Proceedings of the Institute of Radio Engineers
JF - Proceedings of the Institute of Radio Engineers
IS - 3
M1 - 9369424
ER -