Topology-Aware Learning for Routing In Satellite–Terrestrial Integrated Networks: A Review of Graph Neural Network and Reinforcement Learning Approaches

Satellite–Terrestrial Integrated Networks (STINs) are a key part of 5G-Advanced and new 6G non-terrestrial networks. They connect the world by combining LEO, MEO, and GEO satellite constellations with ground-based infrastructure. But routing is very hard because of highly dynamic topologies, different link characteristics, and large-scale networks. This makes traditional protocols and topology-agnostic learning methods less useful. This review analyses topology-aware learning-based routing for STINs, concentrating on Graph Neural Networks (GNNs) and hybrid GNN–Reinforcement Learning (GNN–RL) frameworks. By modelling STINs as graphs that change over time, these methods clearly show how relationships and multi-hop interactions work, which are important for routing that can grow and change. Comprehensive analyses are conducted on classical routing, non-topology-aware reinforcement learning, purely GNN-based methodologies, and hybrid GNN–RL architectures, emphasising their merits and drawbacks in dynamic satellite–terrestrial contexts. We also look at hierarchical and multi-agent extensions, as well as current datasets and evaluation methods. Finally, important open problems related to scalability, non-stationarity, and real-world use are found, and future research directions that fit with new 6G non-terrestrial network standards are laid out.

5G-advanced, 6G non-terrestrial networks, Satellite–Terrestrial Integrated Networks, GNN, RL

1. Alegre, L., Bazzan, A., & da Silva, B. (2021). Quantifying the impact of non-stationarity in reinforcement learning-based traffic signal control. PeerJ Computer Science, 7, e575. https://doi.org/10.7717/peerj-cs.575 [Google Scholar] [Crossref]

2. Chen, N., Song, Y., Cao, Y., Sun, Z., Zhao, B., Wang, M., He, D., & Peng, G. (2025). Network-layer perspectives on satellite–terrestrial integrated networks in 6G: A comprehensive review. Engineering. https://doi.org/10.1016/j.eng.2025.05.012 [Google Scholar] [Crossref]

3. Chen, Y., Cao, H., Wang, L., Chen, D., Liu, Z., Zhou, Y., & Shi, J. (2025). Deep Reinforcement Learning-Based Routing Method for Low Earth Orbit Mega-Constellation Satellite Networks with Service Function Constraints. Sensors, 25(4), 1232. https://doi.org/10.3390/s25041232 [Google Scholar] [Crossref]

4. Ekici, E., Akyildiz, I. F., & Ergin, D. (2022). Time-dependent routing in satellite networks. IEEE/ACM Transactions on Networking, 30(5), 2134–2147. [Google Scholar] [Crossref]

5. Ekici, E., Akyildiz, I. F., & Ergin, D. (2022). Time-dependent routing in satellite networks. IEEE/ACM Transactions on Networking, 30(5), 2134–2147. [Google Scholar] [Crossref]

6. Giordani, M., Polese, M., Mezzavilla, M., Rangan, S., & Zorzi, M. (2020). Toward 6G networks: Use cases and technologies. IEEE Communications Magazine, 58(3), 55–61. [Google Scholar] [Crossref]

7. Goteti, D., & Reddy, V. (2025). AI-driven routing pipeline in software-defined networks using DQL: A mini review. Frontiers in Artificial Intelligence, 8, 1685155. https://doi.org/10.3389/frai.2025.1685155. [Google Scholar] [Crossref]

8. Hu, Z., Han, C., Gerstacker, W., & Akyildiz, I. F. (2024). Tera-SpaceCom: GNN-based deep reinforcement learning for joint resource allocation and task offloading in terahertz-band space networks. arXiv preprint. https://doi.org/10.48550/arXiv.2409.07911 [Google Scholar] [Crossref]

9. Jiang, W., Zhan, Y., Xiao, X., & Sha, G. (2023). Network simulators for satellite-terrestrial integrated networks: A survey. IEEE Access, 11, 1–1. https://doi.org/10.1109/ACCESS.2023.3313229 [Google Scholar] [Crossref]

10. Kodheli, O., Lagunas, E., Maturo, N., Sharma, S. K., Shankar, B., Montoya, J. F. M., & Goussetis, G. (2021). Satellite communications in the new space era: A survey and future challenges. IEEE Communications Surveys & Tutorials, 23(1), 70–109. [Google Scholar] [Crossref]

11. Kołakowski, R., Tomaszewski, L., Tępiński, R., & Kukliński, S. (2025). Hierarchical traffic engineering in 3D networks using QoS-aware graph-based deep reinforcement learning. Electronics, 14. https://doi.org/10.3390/electronics14051045 [Google Scholar] [Crossref]

12. Li, R., Zhu, J., Mao, Y., Shi, Y., Wang, T., & Jiang, C. (2025). Topology-aware routing for federated learning over multi-layer satellite networks. IEEE Wireless Communications and Networking Conference (WCNC), 1–6. https://doi.org/10.1109/WCNC61545.2025.10978815 [Google Scholar] [Crossref]

13. Liu, X., Han, C., Wang, J., & Akyildiz, I. F. (2023). Deep learning for non-terrestrial networks: A survey. IEEE Communications Surveys & Tutorials, 25(3), 1890–1931. [Google Scholar] [Crossref]

14. Mondragon Guadarrama, J., Branco, P., Jourdan, G.-V., Gutiérrez-Rodríguez, A., & Biswal, R. (2025). Advanced IDS: A comparative study of datasets and machine learning algorithms for network flow-based intrusion detection systems. Applied Intelligence, 55. https://doi.org/10.1007/s10489-025-06422-4 [Google Scholar] [Crossref]

15. Muzammal, S. M., Murugesan, R. K., Jhanjhi, N., Hossain, M. S., & Yassine, A. (2022). Trust and Mobility-Based Protocol for Secure Routing in Internet of Things. Sensors, 22(16), 6215. https://doi.org/10.3390/s22166215 [Google Scholar] [Crossref]

16. Roth, M. M. H., et al. (2024). Shaping rewards, shaping routes: On multi-agent deep Q-networks for routing in satellite constellation networks. DLR Technical Report. [Google Scholar] [Crossref]

17. Rusek, K., Suárez-Varela, J., Mestres, A., Barlet-Ros, P., & Cabellos-Aparicio, A. (2020). Unveiling the potential of graph neural networks for network modeling and optimization. IEEE/ACM Transactions on Networking, 28(6), 2249–2262. [Google Scholar] [Crossref]

18. Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., & Monfardini, G. (2009). The graph neural network model. IEEE Transactions on Neural Networks, 20(1), 61–80. [Google Scholar] [Crossref]

19. Veres, P. (2025). ML and Statistics-Driven Route Planning: Effective Solutions Without Maps. Logistics, 9(3), 124. https://doi.org/10.3390/logistics9030124 [Google Scholar] [Crossref]

20. Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021). A comprehensive survey on graph neural networks. IEEE Transactions on Neural Networks and Learning Systems, 32(1), 4–24. [Google Scholar] [Crossref]

21. Xiao, Z., Liu, J., Zhang, Q., & Wang, S. (2023). GNN-based routing for dynamic satellite networks. IEEE Network, 37(6), 134–141. [Google Scholar] [Crossref]

22. Xu, P., Feng, M., Zhou, J., Xiao, P., & Jiang, T. (2024). Inter-satellite routing for LEO satellite networks: A GNN and DRL integrated approach. In Proceedings of the IEEE/CIC International Conference on Communications in China (ICCC). [Google Scholar] [Crossref]

23. Zhang, Q., Wang, S., Li, Y., & Zhang, H. (2023). Learning-based routing in dynamic satellite networks: Challenges and opportunities. IEEE Network, 37(5), 122–129. [Google Scholar] [Crossref]

24. Zhu, X., et al. (2021). Reinforcement learning-based routing algorithm in satellite–terrestrial integrated networks. Conference proceedings. [Google Scholar] [Crossref]

• Assessment of the Role of Artificial Intelligence in Repositioning TVET for Economic Development in Nigeria
• Teachers’ Use of Assure Model Instructional Design on Learners’ Problem Solving Efficacy in Secondary Schools in Bungoma County, Kenya
• “E-Booksan Ang Kaalaman”: Development, Validation, and Utilization of Electronic Book in Academic Performance of Grade 9 Students in Social Studies
• Analyzing EFL University Students’ Academic Speaking Skills Through Self-Recorded Video Presentation
• Major Findings of The Study on Total Quality Management in Teachers’ Education Institutions (TEIs) In Assam – An Evaluative Study