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

doi:10.12142/ZTECOM.202303008

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

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

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

CHENG Lei, QIN Shuang, FENG Gang. Learning-Based Admission Control for Low-Earth-Orbit Satellite Communication Networks[J]. ZTE Communications, 2023, 21(3): 54-62.

Figures/Tables 10

Figure 1 Basic mobility scenario of low-earth-orbit (LEO) satellite communication system

Figure 2 Simplified mobility model of low-earth-orbit (LEO) satellite communication system

Figure 3 Illustration of multi-priority service threshold-based channel reservation strategy

Table 1 Simulation parameters

Parameter	Value
Number of services $s$	3
Number of beam cell channels	100
Average call duration parameter $u$	1/30 s
Call arrival rate ratio $p 1 : ? p 2 : ? p 3$	0.2:0.3:0.5
Decision period $T Δ$	5 s
Maximum number of calls $N$	50
Balance factor $α 0$ , $? α 1$	0.4, 0.6
Balance factor $β 1$ , $? β 2$ , $? β 3$	0.2, 0.3, 0.5
FCR normalized fixed threshold setting	[0.73, 0.75, 0.82, 0.85, 0.86, 1]
HPFCR normalized fixed threshold setting	[0.73, 0.75, 0.73, 0.85, 0.73, 1]
DCR normalized initial threshold setting	[0.73, 0.75, 0.82, 0.85, 0.86, 1]
Number of periods played	20 000 $T Δ$
Total call arrival rate $λ$	2–25 calls/s

Table 1 Simulation parameters

Parameter	Value
Number of services $s$	3
Number of beam cell channels	100
Average call duration parameter $u$	1/30 s
Call arrival rate ratio $p 1 : ? p 2 : ? p 3$	0.2:0.3:0.5
Decision period $T Δ$	5 s
Maximum number of calls $N$	50
Balance factor $α 0$ , $? α 1$	0.4, 0.6
Balance factor $β 1$ , $? β 2$ , $? β 3$	0.2, 0.3, 0.5
FCR normalized fixed threshold setting	[0.73, 0.75, 0.82, 0.85, 0.86, 1]
HPFCR normalized fixed threshold setting	[0.73, 0.75, 0.73, 0.85, 0.73, 1]
DCR normalized initial threshold setting	[0.73, 0.75, 0.82, 0.85, 0.86, 1]
Number of periods played	20 000 $T Δ$
Total call arrival rate $λ$	2–25 calls/s

Table 2 AC algorithm parameters

Parameter	Value
Discount factor $γ$	0.99
Learning rate of policy $α a c t o r$	0.002
Learning rate of value function $α c r i t i c$	0.005
Action selection variance $σ$	0.05

Table 2 AC algorithm parameters

Parameter	Value
Discount factor $γ$	0.99
Learning rate of policy $α a c t o r$	0.002
Learning rate of value function $α c r i t i c$	0.005
Action selection variance $σ$	0.05

Figure 4 O(t) with varying λ

Figure 5 Channel utilization with varying λ

Figure 6 Average call success rate with varying λ

Figure 7 O(t) with change frequency varying

Figure 8 Value function with time varying

References 17

1	LIU J J, SHI Y P, FADLULLAH Z M, et al. Space-air-ground integrated network: a survey [J]. IEEE communications surveys & tutorials, 2018, 20(4): 2714–2741. DOI: 10.1109/COMST.2018.2841996 DOI URL
2	DING R, CHEN T T, LIU L, et al. 5G integrated satellite communication systems: architectures, air interface, and standardization [C]//International Conference on Wireless Communications and Signal Processing (WCSP). IEEE, 2020: 702–707. DOI: 10.1109/WCSP49889.2020.9299757 DOI URL
3	DENG R Q, DI B Y, ZHANG H L, et al. Ultra-dense LEO satellite constellation design for global coverage in terrestrial-satellite networks [C]//Global Communications Conference. IEEE, 2021: 1–6. DOI: 10.1109/GLOBECOM42002.2020.9322362 DOI URL
4	DUAN C F, DUAN R Q, FENG J, et al. A novel channel allocation strategy in low earth orbit satellite networks [C]//6th International Conference on Computer and Communications (ICCC). IEEE, 2021: 8–13. DOI: 10.1109/ICCC51575.2020.9345173 DOI URL
5	ZHOU J, YE X G, PAN Y, et al. Dynamic channel reservation scheme based on priorities in LEO satellite systems [J]. Journal of systems engineering and electronics, 2015, 26(1): 1–9. DOI: 10.1109/JSEE.2015.00001 DOI URL
6	LI Z W, XIE Z C, LIANG X W. Dynamic channel reservation strategy based on DQN algorithm for multi-service LEO satellite communication system [J]. IEEE wireless communications letters, 2021, 10(4): 770–774. DOI: 10.1109/LWC.2020.3043073 DOI URL
7	MARAL G, RESTREPO J, DEL RE E, et al. Performance analysis for a guaranteed handover service in an LEO constellation with a “satellite-fixed cell” system [J]. IEEE transactions on vehicular technology, 1998, 47(4): 1200–1214. DOI: 10.1109/25.728509 DOI URL
8	WANG X L, WANG X X. The research of channel reservation strategy in LEO satellite network [C]//11th International Conference on Dependable, Autonomic and Secure Computing. IEEE, 2014: 590–594. DOI: 10.1109/DASC.2013.131 DOI URL
9	BOUKHATEM L, GAITI D, PUJOLLE G. A channel reservation algorithm for handover issues in LEO satellite systems based on a satellite-fixed cell coverage [C]//IEEE VTS 53rd Vehicular Technology Conference. IEEE, 2001: 2975–2979. DOI: 10.1109/VETECS.2001.944147 DOI URL
10	BEYLOT A L, BOUMERDASSI S. Adaptive channel reservation schemes in multitraffic LEO satellite systems [C]//IEEE Global Telecommunications Conference. IEEE, 2002: 2740–2743. DOI: 10.1109/GLOCOM.2001.966272 DOI URL
11	ZOU Q Y, ZHU L D. Dynamic channel allocation strategy of satellite communication systems based on grey prediction [C]//International Symposium on Networks, Computers and Communications (ISNCC). IEEE, 2019: 1–5. DOI: 10.1109/ISNCC.2019.8909122 DOI URL
12	CHATTERJEE S, SAHA J, BANERJEE S, et al. Neighbour Location Based Channel Reservation scheme for LEO Satellite communication [C]//International Conference on Communications, Devices and Intelligent Systems (CODIS). IEEE, 2012: 73–76. DOI: 10.1109/CODIS.2012.6422139 DOI URL
13	RAHMAN M, WALINGO T, TAKAWIRA F. Adaptive handover scheme for LEO satellite communication system [C]//Proceedings of AFRICON. IEEE, 2015: 1–5. DOI: 10.1109/AFRCON.2015.7332051 DOI URL
14	CHEN L M, GUO Q, WANG H Y. A handover management scheme based on adaptive probabilistic resource reservation for multimedia LEO satellite networks [C]//WASE International Conference on Information Engineering. IEEE, 2010: 255–259. DOI: 10.1109/ICIE.2010.67 DOI URL
15	LIU S J, HU X, WANG W D. Deep reinforcement learning based dynamic channel allocation algorithm in multibeam satellite systems [J]. IEEE access, 2018, 6: 15733–15742. DOI: 10.1109/ACCESS.2018.2809581 DOI URL
16	CHOWDHURY P K, ATIQUZZAMAN M, IVANCIC W. Handover schemes in satellite networks: state-of-the-art and future research directions [J]. IEEE communications surveys & tutorials, 2006, 8(4): 2–14. DOI: 10.1109/COMST.2006.283818 DOI URL
17	BHATNAGAR S, SUTTON R S, GHAVAMZADEH M, et al. Natural actor‑critic algorithms [J]. Automatica, 2009, 45(11): 2471–2482. DOI: 10.1016/j.automatica.2009.07.008 DOI URL

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

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 17

Related Articles 1

Recommended Articles

Metrics