Hyppää sisältöön
    • FI
    • ENG
  • FI
  • /
  • EN
OuluREPO – Oulun yliopiston julkaisuarkisto / University of Oulu repository
Näytä viite 
  •   OuluREPO etusivu
  • Oulun yliopisto
  • Avoin saatavuus
  • Näytä viite
  •   OuluREPO etusivu
  • Oulun yliopisto
  • Avoin saatavuus
  • Näytä viite
JavaScript is disabled for your browser. Some features of this site may not work without it.

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

Gong, Yongkang; Yu, Dongxiao; Cheng, Xiuzhen; Yuen, Chau; Bennis, Mehdi; Debbah, Merouane (2024-06-12)

 
Avaa tiedosto
nbnfioulu-202503101925.pdf (6.310Mt)
Lataukset: 

URL:
https://doi.org/10.1109/TWC.2024.3409691

Gong, Yongkang
Yu, Dongxiao
Cheng, Xiuzhen
Yuen, Chau
Bennis, Mehdi
Debbah, Merouane
IEEE
12.06.2024

Y. Gong, D. Yu, X. Cheng, C. Yuen, M. Bennis and M. Debbah, "Computation Offloading and Quantization Schemes for Federated Satellite-Ground Graph Networks," in IEEE Transactions on Wireless Communications, vol. 23, no. 10, pp. 14140-14154, Oct. 2024, doi: 10.1109/TWC.2024.3409691

https://rightsstatements.org/vocab/InC/1.0/
© 2024 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists,or reuse of any copyrighted component of this work in other works.
https://rightsstatements.org/vocab/InC/1.0/
doi:https://doi.org/10.1109/TWC.2024.3409691
Näytä kaikki kuvailutiedot
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi:oulu-202503101925
Tiivistelmä
Abstract

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.
Kokoelmat
  • Avoin saatavuus [38865]
oulurepo@oulu.fiOulun yliopiston kirjastoOuluCRISLaturiMuuntaja
SaavutettavuusselosteTietosuojailmoitusYlläpidon kirjautuminen
 

Selaa kokoelmaa

NimekkeetTekijätJulkaisuajatAsiasanatUusimmatSivukartta

Omat tiedot

Kirjaudu sisäänRekisteröidy
oulurepo@oulu.fiOulun yliopiston kirjastoOuluCRISLaturiMuuntaja
SaavutettavuusselosteTietosuojailmoitusYlläpidon kirjautuminen