Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
158 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Communication-Efficient Federated Learning for LEO Satellite Networks Integrated with HAPs Using Hybrid NOMA-OFDM (2401.00685v2)

Published 1 Jan 2024 in cs.LG, cs.AI, and cs.DC

Abstract: Space AI has become increasingly important and sometimes even necessary for government, businesses, and society. An active research topic under this mission is integrating federated learning (FL) with satellite communications (SatCom) so that numerous low Earth orbit (LEO) satellites can collaboratively train a machine learning model. However, the special communication environment of SatCom leads to a very slow FL training process up to days and weeks. This paper proposes NomaFedHAP, a novel FL-SatCom approach tailored to LEO satellites, that (1) utilizes high-altitude platforms (HAPs) as distributed parameter servers (PS) to enhance satellite visibility, and (2) introduces non-orthogonal multiple access (NOMA) into LEO to enable fast and bandwidth-efficient model transmissions. In addition, NomaFedHAP includes (3) a new communication topology that exploits HAPs to bridge satellites among different orbits to mitigate the Doppler shift, and (4) a new FL model aggregation scheme that optimally balances models between different orbits and shells. Moreover, we (5) derive a closed-form expression of the outage probability for satellites in near and far shells, as well as for the entire system. Our extensive simulations have validated the mathematical analysis and demonstrated the superior performance of NomaFedHAP in achieving fast and efficient FL model convergence with high accuracy as compared to the state-of-the-art.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (39)
  1. Q. Fang, Z. Zhai, S. Yu, Q. Wu, X. Gong, and X. Chen, “Olive branch learning: A topology-aware federated learning framework for space-air-ground integrated network,” IEEE Transactions on Wireless Communications, 2022.
  2. N. Pachler, I. del Portillo, E. F. Crawley, and B. G. Cameron, “An updated comparison of four low earth orbit satellite constellation systems to provide global broadband,” in IEEE International Conference on Communications Workshops.   IEEE, 2021, pp. 1–7.
  3. Z. Zhai, Q. Wu, S. Yu, R. Li, F. Zhang, and X. Chen, “FedLEO: an offloading-assisted decentralized federated learning framework for low earth orbit satellite networks,” IEEE Transactions on Mobile Computing, 2023.
  4. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-efficient learning of deep networks from decentralized data,” in Artificial intelligence and statistics.   PMLR, 2017, pp. 1273–1282.
  5. C. Xie, O. Koyejo, and I. Gupta, “Asynchronous federated optimization,” in 12t⁢h𝑡ℎ{}^{th}start_FLOATSUPERSCRIPT italic_t italic_h end_FLOATSUPERSCRIPT Wksp on Optimization for Machine Learning, 2020.
  6. H. Chen, M. Xiao, and Z. Pang, “Satellite-based computing networks with federated learning,” IEEE Wireless Communications, vol. 29, no. 1, pp. 78–84, 2022.
  7. N. Razmi, B. Matthiesen, A. Dekorsy, and P. popovski, “On-board federated learning for dense leo constellations,” in IEEE International Conference on Communications (ICC), Seoul, Southkorea, May 2022.
  8. M. Elmahallawy and T. Luo, “FedHAP: Fast federated learning for leo constellations using collaborative haps,” in 2022 14th International Conference on Wireless Communications and Signal Processing (WCSP), 2022, pp. 888–893.
  9. J. Lin, J. Xu, Y. Li, and Z. Xu, “Federated learning with dynamic aggregation based on connection density at satellites and ground stations,” in 2022 IEEE International Conference on Satellite Computing (Satellite).   IEEE, 2022, pp. 31–36.
  10. C.-Y. Chen, L.-H. Shen, K.-T. Feng, L.-L. Yang, and J.-M. Wu, “Edge selection and clustering for federated learning in optical inter-leo satellite constellation,” arXiv preprint arXiv:2303.16071, 2023.
  11. C. Wu, Y. Zhu, and F. Wang, “DSFL: Decentralized satellite federated learning for energy-aware leo constellation computing,” in 2022 IEEE International Conference on Satellite Computing (Satellite).   IEEE, 2022, pp. 25–30.
  12. M. Elmahallawy and T. Luo, “Optimizing federated learning in leo satellite constellations via intra-plane model propagation and sink satellite scheduling,” in ICC 2023-IEEE International Conference on Communications, 2023. [Online]. Available: {https://arxiv.org/abs/2302.13447}
  13. N. Razmi, B. Matthiesen, A. Dekorsy, and P. Popovski, “Ground-assisted federated learning in leo satellite constellations,” IEEE Wireless Communications Letters, 2022.
  14. ——, “Scheduling for ground-assisted federated learning in leo satellite constellations,” arXiv preprint arXiv:2206.01952, 2022.
  15. J. So, K. Hsieh, B. Arzani, S. Noghabi, S. Avestimehr, and R. Chandra, “Fedspace: An efficient federated learning framework at satellites and ground stations,” arXiv preprint arXiv:2202.01267, 2022.
  16. P. Wang, H. Li, and B. Chen, “Fl-task-aware routing and resource reservation over satellite networks,” in GLOBECOM 2022-2022 IEEE Global Communications Conference.   IEEE, 2022, pp. 2382–2387.
  17. M. Elmahallawy and T. Luo, “AsyncFLEO: Asynchronous federated learning for LEO satellite constellations with high-altitude platforms,” in 2022 IEEE International Conference on Big Data (BigData), 2022, pp. 5478–5487.
  18. L. Wu and J. Zhang, “Fedgsm: Efficient federated learning for leo constellations with gradient staleness mitigation,” arXiv preprint arXiv:2304.08537, 2023.
  19. M. Elmahallawy and T. Luo, “One-shot federated learning for LEO constellations that reduces convergence time from days to 90 minutes,” in 2023 24th IEEE International Conference on Mobile Data Management (MDM), 2023, pp. 45–54.
  20. M. Elmahallawy, T. Luo, and M. I. Ibrahem, “Secure and efficient federated learning in LEO constellations using decentralized key generation and on-orbit model aggregation,” in GLOBECOM 2023-2023 IEEE Global Communications Conference, 2023. [Online]. Available: {https://arxiv.org/abs/2302.13447}
  21. M. El-Mahallawy, A. S. TagEldien, and S. S. Elagooz, “Performance enhancement of underwater acoustic ofdm communication systems,” Wireless Personal Communications, vol. 108, pp. 2047–2057, 2019.
  22. C. Gamal, K. An, X. Li, V. G. Menon, G. Ragesh, M. M. Fouda, and B. M. ElHalawany, “Performance of hybrid satellite-uav noma systems,” in ICC 2022-IEEE International Conference on Communications.   IEEE, 2022, pp. 189–194.
  23. X. Yan, H. Xiao, K. An, G. Zheng, and S. Chatzinotas, “Ergodic capacity of noma-based uplink satellite networks with randomly deployed users,” IEEE Systems Journal, vol. 14, no. 3, pp. 3343–3350, 2020.
  24. A. Alsharoa and M.-S. Alouini, “Improvement of the global connectivity using integrated satellite-airborne-terrestrial networks with resource optimization,” IEEE Transactions on Wireless Communications, vol. 19, no. 8, pp. 5088–5100, 2020.
  25. Z. Jia, M. Sheng, J. Li, D. Zhou, and Z. Han, “Joint hap access and leo satellite backhaul in 6g: Matching game-based approaches,” IEEE Journal on Selected Areas in Communications, vol. 39, no. 4, pp. 1147–1159, 2020.
  26. Y. Xing, F. Hsieh, A. Ghosh, and T. S. Rappaport, “High altitude platform stations (haps): Architecture and system performance,” in 2021 IEEE 93rd Vehicular Technology Conference (VTC2021-Spring).   IEEE, 2021, pp. 1–6.
  27. F. Hsieh, F. Jardel, E. Visotsky, F. Vook, A. Ghosh, and B. Picha, “Uav-based multi-cell haps communication: System design and performance evaluation,” in GLOBECOM 2020-2020 IEEE Global Communications Conference.   IEEE, 2020, pp. 1–6.
  28. GSMA, “High altitude platform systems: Towers in the skies,” Technical report, GSMA, 2021.
  29. G. K. Kurt, M. G. Khoshkholgh, S. Alfattani, A. Ibrahim, T. S. Darwish, M. S. Alam, H. Yanikomeroglu, and A. Yongacoglu, “A vision and framework for the high altitude platform station (haps) networks of the future,” IEEE Communications Surveys & Tutorials, vol. 23, no. 2, pp. 729–779, 2021.
  30. J. Marriott, B. Tezel, Z. Liu, and N. E. Stier-Moses, “Trajectory optimization of solar-powered high-altitude long endurance aircraft,” in 2020 6th International Conference on Control, Automation and Robotics (ICCAR).   IEEE, 2020, pp. 473–481.
  31. M. Aldababsa, M. Toka, S. Gökçeli, G. K. Kurt, and O. Kucur, “A tutorial on nonorthogonal multiple access for 5g and beyond,” Wireless communications and mobile computing, vol. 2018, 2018.
  32. V. Bankey, P. K. Upadhyay, and D. B. d. Costa, “Physical layer security in hybrid satellite-terrestrial relay networks,” in Physical Layer Security.   Springer, 2021, pp. 1–28.
  33. W. Van Assche, “Ordinary special functions,” in Encyclopedia of Mathematical Physics, J.-P. Françoise, G. L. Naber, and T. S. Tsun, Eds.   Oxford: Academic Press, 2006, pp. 637–645. [Online]. Available: https://www.sciencedirect.com/science/article/pii/B0125126662003953
  34. X. Li, K. Huang, W. Yang, S. Wang, and Z. Zhang, “On the convergence of fedavg on non-iid data,” in International Conference on Learning Representations, 2020. [Online]. Available: https://openreview.net/forum?id=HJxNAnVtDS
  35. M. Ribero, H. Vikalo, and G. De Veciana, “Federated learning under intermittent client availability and time-varying communication constraints,” IEEE Journal of Selected Topics in Signal Processing, vol. 17, no. 1, pp. 98–111, 2022.
  36. J. G. Walker, “Satellite constellations,” Journal of the British Interplanetary Society, vol. 37, p. 559, 1984.
  37. L. Deng, “The mnist database of handwritten digit images for machine learning research,” IEEE Signal Processing Magazine, vol. 29, no. 6, pp. 141–142, 2012.
  38. A. Krizhevsky, V. Nair, and G. Hinton, “Cifar-10 (canadian institute for advanced research),” URL http://www. cs. toronto. edu/kriz/cifar. html, vol. 5, no. 4, p. 1, 2010.
  39. I. Demir, K. Koperski, D. Lindenbaum, G. Pang, J. Huang, S. Basu, F. Hughes, D. Tuia, and R. Raskar, “Deepglobe 2018: A challenge to parse the earth through satellite images,” in Computer Vision and Pattern Recognition (CVPR) Workshops, June 2018.
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets