Article Details

Abstract

To address the challenges of rapid topology changes, unstable link conditions, and the difficulty of simultaneously guaranteeing multi-service Quality of Service (QoS) in low-Earth-orbit satellite networks, this paper studies an intelligent routing optimization method for multi-service scenarios. First, link state awareness is achieved through the HELLO message mechanism, to acquire information on link delay, bandwidth utilization, and congestion. Second, a Graph Neural Network (GNN) is employed to extract state representations of network topology and link features. On this basis, a Deep Q-Network (DQN) is introduced for routing decisions, and multi-objective QoS constraints are integrated into the reward function to achieve differentiated optimization for diverse service requirements. Simulation results demonstrate that the proposed method outperforms existing approaches in terms of average end-to-end delay, throughput, and packet loss rate, and can effectively enhance transmission efficiency and service quality of Low-Earth-Orbit satellite networks in dynamic environments.

Keywords

Low-Earth-Orbit satellite network; multi-service QoS; Graph Neural Networks; Deep Reinforcement Learning

References

1. [1] Lan Song Research on Resource Allocation and Reliability Based on Deep Reinforcement Learning in Satellite Communication [D]. Nanjing: Nanjing University of Information Science and Technology, 2023
2. [2] Li C C，Zhang Y S，Cui Z X，et al. An Overview of Low Earth Orbit Satellite Routing Algorithms [C]//2023 International Wireless Communications and Mobile Computing (IWCMC)，2023：866-870.
3. [3] Wei Debin, Cao Yu, Yang Li, etc A routing strategy for LEO satellite networks based on spatiotemporal hierarchy [J]. Acta Aeronautica Sinica, 2023, 44 (16): 204-214
4. [4] Li Peng, Zhao Xiang, Hu Jianping, etc QoS routing algorithm for LEO satellite constellation based on regional partitioning [J]. Telemetry and Remote Control, 2022, 43 (2): 17-24
5. [5] Zhang X H，Zhang J H，Si W J，et al. Dynamic Weight Adjusting Deep Q-Networks for Real-Time Environmental Adaptation [C]//2024 IEEE International Conference on Knowledge Graph (ICKG)，2024：500-507.
6. [6] Xu P，Feng M J，Zhou J X，et al. Inter-satellite Routing for LEO Satellite Networks: A GNN and DRL Integrated Approach [C]//2024 IEEE/CIC International Conference on Communications in China (ICCC)，2024：1346-1351.
7. [7] Zhang Guangwei Research on Power Allocation and Optimization Algorithm for Satellite Communication System Based on Graph Neural Network [D]. Beijing: Beijing University of Posts and Telecommunications, 2024
8. [8] Zhang S B，Liu A J，Han C，et al. Graph Neural Network and Reinforcement Learning Based Routing for Mega Leo Satellite Constellations [C]//2023 9th International Conference on Computer and Communications (ICCC)，2023：1-6.
9. [9] Wang Chaowei, Du Jianan, Wang Cheng, etc Hybrid Routing Algorithm Based on Service Scheduling in Software Defined Satellite Networks [J]. Acta Sinica, 2024, 52 (5): 1506-1515
10. [10] Liang Chao, Yang Li, Pan Chengsheng, etc Multi QoS Constrained Routing Algorithm for Satellite Network Dynamic Resource Graph [J]. Acta Aeronautica Sinica, 2023, 44 (1): 257-267

About the authors

Xu Xiangyang (1967-), male, Han ethnicity, from Shijiazhuang, Hebei Province, associate professor, master's degree, research interests: IP networks, multimedia communication, network security, satellite communication; Gu Yu (2000-), female, Han ethnicity, from Shijiazhuang, Hebei Province, currently pursuing a master's degree in satellite communication; Jiang Huili (2000-), female, Han ethnicity, from Tai'an, Shandong, currently pursuing a master's degree in satellite communication; Dong Jianao (2000-), male, Han ethnicity, from Nanyang, Henan Province, is currently pursuing a master's degree in satellite communication.