EUVIMEDEUVIMED entdecken
Crossref

Optimized Federated Reinforcement Learning for Latency and Energy Minimization in Dynamic Satellite-Ground Graph Networks

Jiaen Zhou, Yafei Zhao, Yongkang Gong, Ronghui Zhang, Jingjing Wang, Shijie Zhang, Mugen Peng

IEEE Transactions on Vehicular Technology · 2026-08 · 75 (8) · 16970-16982

DOI: 10.1109/tvt.2026.3672860 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Vehicular Technology, 2026-08. Verfasst von Jiaen Zhou und 6 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben. Gefördert von: National Natural Science Foundation of China, BUPT Excellent Ph.D. Students Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Satellite–ground integrated networks (SGIN) represent a novel architectural paradigm that enables seamless spatiotemporal coverage, high-throughput data dissemination, and distributed computation offloading. By reducing end-to-end latency and alleviating resource contention, SGIN support efficient and adaptive task scheduling across heterogeneous network entities. However, the dynamic and time-varying topology of SGIN results in complex, multi-modal graph structures, posing significant challenges for unified representation, modeling, and optimization over space and time. To address these issues, we construct a graph-based model of the SGIN to jointly minimize total network latency and improve energy efficiency. A graph neural network (GNN)-based graph learning approach is developed to capture the dynamic features of satellite nodes. We further introduce a federated reinforcement learning framework to jointly optimize CPU cycle frequency, quantization bit allocation, and transmission power. This framework enhances convergence speed while preserving data privacy. Additionally, a transaction verification mechanism is integrated to illustrate the task execution process and demonstrate graph permutation invariance between the generative model and optimization objectives. Extensive simulations validate that the proposed algorithm achiveves about 20% lower latency and 25% lower energy consumption than baselines.

Förderung

  • National Natural Science Foundation of China
  • BUPT Excellent Ph.D. Students Foundation

Zitieren

APA

Zhou, J., Zhao, Y., Gong, Y., Zhang, R., Wang, J., Zhang, S., & Peng, M. (2026). Optimized Federated Reinforcement Learning for Latency and Energy Minimization in Dynamic Satellite-Ground Graph Networks. IEEE Transactions on Vehicular Technology, 75(8), 16970-16982. https://doi.org/10.1109/tvt.2026.3672860

Vancouver

Zhou J, Zhao Y, Gong Y, Zhang R, Wang J, Zhang S, et al. Optimized Federated Reinforcement Learning for Latency and Energy Minimization in Dynamic Satellite-Ground Graph Networks. IEEE Transactions on Vehicular Technology. 2026;75(8):16970-16982. doi:10.1109/tvt.2026.3672860

BibTeX
@article{Zhou2026,
  author = {Zhou, Jiaen and Zhao, Yafei and Gong, Yongkang and Zhang, Ronghui and Wang, Jingjing and Zhang, Shijie and Peng, Mugen},
  title = {Optimized Federated Reinforcement Learning for Latency and Energy Minimization in Dynamic Satellite-Ground Graph Networks},
  journal = {IEEE Transactions on Vehicular Technology},
  year = {2026},
  volume = {75},
  number = {8},
  pages = {16970--16982},
  doi = {10.1109/tvt.2026.3672860}
}
Kostenlos starten →