Satellite Federated Edge Learning: Architecture Design and Convergence Analysis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909157390548992 |
|---|---|
| author | Shi, Yuanming Zeng, Li Zhu, Jingyang Zhou, Yong Jiang, Chunxiao Letaief, Khaled B. |
| author_facet | Shi, Yuanming Zeng, Li Zhu, Jingyang Zhou, Yong Jiang, Chunxiao Letaief, Khaled B. |
| contents | The proliferation of low-earth-orbit (LEO) satellite networks leads to the generation of vast volumes of remote sensing data which is traditionally transferred to the ground server for centralized processing, raising privacy and bandwidth concerns. Federated edge learning (FEEL), as a distributed machine learning approach, has the potential to address these challenges by sharing only model parameters instead of raw data. Although promising, the dynamics of LEO networks, characterized by the high mobility of satellites and short ground-to-satellite link (GSL) duration, pose unique challenges for FEEL. Notably, frequent model transmission between the satellites and ground incurs prolonged waiting time and large transmission latency. This paper introduces a novel FEEL algorithm, named FEDMEGA, tailored to LEO mega-constellation networks. By integrating inter-satellite links (ISL) for intra-orbit model aggregation, the proposed algorithm significantly reduces the usage of low data rate and intermittent GSL. Our proposed method includes a ring all-reduce based intra-orbit aggregation mechanism, coupled with a network flow-based transmission scheme for global model aggregation, which enhances transmission efficiency. Theoretical convergence analysis is provided to characterize the algorithm performance. Extensive simulations show that our FEDMEGA algorithm outperforms existing satellite FEEL algorithms, exhibiting an approximate 30% improvement in convergence rate. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_01875 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Satellite Federated Edge Learning: Architecture Design and Convergence Analysis Shi, Yuanming Zeng, Li Zhu, Jingyang Zhou, Yong Jiang, Chunxiao Letaief, Khaled B. Signal Processing Distributed, Parallel, and Cluster Computing Information Theory Machine Learning The proliferation of low-earth-orbit (LEO) satellite networks leads to the generation of vast volumes of remote sensing data which is traditionally transferred to the ground server for centralized processing, raising privacy and bandwidth concerns. Federated edge learning (FEEL), as a distributed machine learning approach, has the potential to address these challenges by sharing only model parameters instead of raw data. Although promising, the dynamics of LEO networks, characterized by the high mobility of satellites and short ground-to-satellite link (GSL) duration, pose unique challenges for FEEL. Notably, frequent model transmission between the satellites and ground incurs prolonged waiting time and large transmission latency. This paper introduces a novel FEEL algorithm, named FEDMEGA, tailored to LEO mega-constellation networks. By integrating inter-satellite links (ISL) for intra-orbit model aggregation, the proposed algorithm significantly reduces the usage of low data rate and intermittent GSL. Our proposed method includes a ring all-reduce based intra-orbit aggregation mechanism, coupled with a network flow-based transmission scheme for global model aggregation, which enhances transmission efficiency. Theoretical convergence analysis is provided to characterize the algorithm performance. Extensive simulations show that our FEDMEGA algorithm outperforms existing satellite FEEL algorithms, exhibiting an approximate 30% improvement in convergence rate. |
| title | Satellite Federated Edge Learning: Architecture Design and Convergence Analysis |
| topic | Signal Processing Distributed, Parallel, and Cluster Computing Information Theory Machine Learning |
| url | https://arxiv.org/abs/2404.01875 |