ZTE Communications ›› 2023, Vol. 21 ›› Issue (3): 54-62.DOI: 10.12142/ZTECOM.202303008

• Research Papers • Previous Articles     Next Articles

Learning-Based Admission Control for Low-Earth-Orbit Satellite Communication Networks

CHENG Lei, QIN Shuang(), FENG Gang   

  1. University of Electronic Science and Technology of China, Chengdu 611731, China
  • Received:2022-07-22 Online:2023-09-21 Published:2023-03-22
  • About author:CHENG Lei received her BS degree in communication engineering from University of Electronic Science and Technology of China (UESTC) in 2019. She now is pursuing her PhD degree at the National Key Laboratory of Wireless Communications, UESTC. Her research interests include resource management and network control in space-air-ground/satellite-terrestrial integrated networks by using optimization theory and machine learning techniques.|QIN Shuang (blueqs@uestc.edu.cn) received his BS degree in electronic information science and technology and PhD degree in communication and information system from University of Electronic Science and Technology of China (UESTC) in 2006 and 2012, respectively. He is currently a professor with the National Key Laboratory of Wireless Communications, UESTC. His research interests include wireless and mobile networks.|FENG Gang received his BE and ME degrees in electronic engineering from University of Electronic Science and Technology of China (UESTC) in 1986 and 1989, respectively, and PhD degree in information engineering from The Chinese University of Hong Kong, China in 1998. He joined the School of Electric and Electronic Engineering, Nanyang Technological University, Singapore in December 2000 as an assistant professor and became an associate professor in October 2005. He is currently a professor with the National Laboratory of Wireless Communications, UESTC. He has extensive research experience and has published widely on wireless networking. His research interests include next generation mobile networks, mobile cloud computing, and AI-enabled wireless networking. He has received the IEEE ComSoc TAOS Best Paper Award and the ICC Best Paper Award in 2019. A number of his papers have been highly cited.
  • Supported by:
    the ZTE Industry?University?Institute Cooperation Funds

Abstract:

Satellite communications has been regarded as an indispensable technology for future mobile networks to provide extremely high data rates, ultra-reliability, and ubiquitous coverage. However, the high dynamics caused by the fast movement of low-earth-orbit (LEO) satellites bring huge challenges in designing and optimizing satellite communication systems. Especially, admission control, deciding which users with diversified service requirements are allowed to access the network with limited resources, is of paramount importance to improve network resource utilization and meet the service quality requirements of users. In this paper, we propose a dynamic channel reservation strategy based on the Actor-Critic algorithm (AC-DCRS) to perform intelligent admission control in satellite networks. By carefully designing the long-term reward function and dynamically adjusting the reserved channel threshold, AC-DCRS reaches a long-run optimal access policy for both new calls and handover calls with different service priorities. Numerical results show that our proposed AC-DCRS outperforms traditional channel reservation strategies in terms of overall access failure probability, the average call success rate, and channel utilization under various dynamic traffic conditions.

Key words: satellite communications, admission control, dynamic channel reservation, actor-critic