FL-task-aware routing and resource reservation over satellite networks

P Wang, H Li, B Chen - GLOBECOM 2022-2022 IEEE Global …, 2022 - ieeexplore.ieee.org
Earth observation satellites using asynchronous ground-assisted federated learning (FL)
can avoid transmitting massive raw image data to ground. However, current FL approach …

FedLEO: An offloading-assisted decentralized federated learning framework for low earth orbit satellite networks

Z Zhai, Q Wu, S Yu, R Li, F Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Low Earth orbit (LEO) satellites enable complex Earth observation tasks (eg, remote sensing
and cooperative monitoring) by leveraging large-scale satellite-generated Earth imageries …

Fedspace: An efficient federated learning framework at satellites and ground stations

J So, K Hsieh, B Arzani, S Noghabi… - arXiv preprint arXiv …, 2022 - arxiv.org
Large-scale deployments of low Earth orbit (LEO) satellites collect massive amount of Earth
imageries and sensor data, which can empower machine learning (ML) to address global …

Federated learning with dynamic aggregation based on connection density at satellites and ground stations

J Lin, J Xu, Y Li, Z Xu - 2022 IEEE International Conference on …, 2022 - ieeexplore.ieee.org
Earth observation images collected by low earth orbit (LEO) satellites can enhance the
capability of machine learning to solve some global problems: eg, climate change, disease …

Communication-Efficient Satellite-Ground Federated Learning through Progressive Weight Quantization

C Yang, J Yuan, Y Wu, Q Sun, A Zhou… - IEEE Transactions …, 2024 - ieeexplore.ieee.org
Large constellations of Low Earth Orbit (LEO) satellites have been launched for Earth
observation and satellite-ground communication, which collect massive imagery and sensor …

SatFed: A Resource-Efficient LEO Satellite-Assisted Heterogeneous Federated Learning Framework

Y Zhang, Z Lin, Z Chen, Z Fang, W Zhu, X Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
Traditional federated learning (FL) frameworks rely heavily on terrestrial networks, where
coverage limitations and increasing bandwidth congestion significantly hinder model …

CDMR: Effective computing-dependent multi-path routing strategies in satellite and terrestrial integrated networks

C Wang, Z Ren, W Cheng… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
With the development of science and technology, Satellite and Terrestrial Integrated
Network (STIN) can effectively make up for the defects in the terrestrial network coverage …

Throughput-optimal joint routing and scheduling for low-earth-orbit satellite networks

O Kondrateva, H Döbler, H Sparka… - 2018 14th Annual …, 2018 - ieeexplore.ieee.org
When optimizing communication patterns in wireless networks, routing and link scheduling
cannot be handled separately but must be addressed jointly. Various linear programming …

Connection-density-aware satellite-ground federated learning via asynchronous dynamic aggregation

Z Xu, M Jin, J Lin, Y Liu, J Xu, Z Xiong, H Cai - Future Generation Computer …, 2024 - Elsevier
With the development of space technology, the use of satellites for Earth observation is
becoming more and more common. Among them, low-earth orbit (LEO) satellites have …

Optimizing federated learning in LEO satellite constellations via intra-plane model propagation and sink satellite scheduling

M Elmahallawy, T Luo - ICC 2023-IEEE International …, 2023 - ieeexplore.ieee.org
The advances in satellite technology developments have recently seen a large number of
small satellites being launched into space on Low Earth orbit (LEO) to collect massive data …