EUVIMEDEUVIMED entdecken
Crossref

Computation Offloading and Quantization Schemes for Federated Satellite-Ground Graph Networks

Yongkang Gong, Dongxiao Yu, Xiuzhen Cheng, Chau Yuen, Mehdi Bennis, Mérouane Debbah

IEEE Transactions on Wireless Communications · 2024-10 · 23 (10) · 14140-14154

DOI: 10.1109/twc.2024.3409691 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2024-10. Verfasst von Yongkang Gong und 5 weiteren Autor:innen. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: Shandong Provincial Postdoctoral Science Foundation, Major Basic Research Program of Shandong Provincial Natural Science Foundation, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Satellite-Ground integrated networks (SGINs) are regarded as promising network architecture, which can provide global coverage, large broadband and mega access services for massive terrestrial users. Furthermore, it is beneficial to reducing network congestion, releasing network resources and achieving computation offloading functions. However, the SGIN graph structure is time-varying and highly complex, lack of fixed node orders or reference nodes, which result in dynamic multi-modal features. Hence, we consider a SGIN directed graph model to minimize the total latency while improving the model prediction accuracy, and then perform the computation offloading and quantization schemes. Specifically, we envision a spatial graph convolutional neural network framework to adapt to the dynamic SGIN graph nodes and size, and then propose a centrally deep reinforcement learning aided multi-node federated learning (CDRFL) framework to optimize the CPU cycle frequency, transmission bandwidth and the number of quantization bits to accelerate the convergence round. Extensive theoretical analyses verify the graph permutation property between SGIN graph structure and optimization problems, and demonstrate the upper bound of quantization error via massive mathematical derivation. Finally, the experimental results indicate that the proposed CDRFL framework outperforms some existing benchmarks with reference to FL convergence analysis, average latency and transmission energy consumption for all independent identically distribution (IID) and non-IID data.

Förderung

  • Shandong Provincial Postdoctoral Science Foundation
  • Major Basic Research Program of Shandong Provincial Natural Science Foundation
  • National Natural Science Foundation of China
  • Qingdao Municipal Science and Technology Bureau

Zitieren

APA

Gong, Y., Yu, D., Cheng, X., Yuen, C., Bennis, M., & Debbah, M. (2024). Computation Offloading and Quantization Schemes for Federated Satellite-Ground Graph Networks. IEEE Transactions on Wireless Communications, 23(10), 14140-14154. https://doi.org/10.1109/twc.2024.3409691

Vancouver

Gong Y, Yu D, Cheng X, Yuen C, Bennis M, Debbah M. Computation Offloading and Quantization Schemes for Federated Satellite-Ground Graph Networks. IEEE Transactions on Wireless Communications. 2024;23(10):14140-14154. doi:10.1109/twc.2024.3409691

BibTeX
@article{Gong2024,
  author = {Gong, Yongkang and Yu, Dongxiao and Cheng, Xiuzhen and Yuen, Chau and Bennis, Mehdi and Debbah, Mérouane},
  title = {Computation Offloading and Quantization Schemes for Federated Satellite-Ground Graph Networks},
  journal = {IEEE Transactions on Wireless Communications},
  year = {2024},
  volume = {23},
  number = {10},
  pages = {14140--14154},
  doi = {10.1109/twc.2024.3409691}
}
Kostenlos starten →