English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Space AI has become increasingly important and sometimes even necessary forgovernment, businesses, and society. An active research topic under thismission is integrating federated learning (FL) with satellite communications(SatCom) so that numerous low Earth orbit (LEO) satellites can collaborativelytrain a machine learning model. However, the special communication environmentof SatCom leads to a very slow FL training process up to days and weeks. Thispaper proposes NomaFedHAP, a novel FL-SatCom approach tailored to LEOsatellites, that (1) utilizes high-altitude platforms (HAPs) as distributedparameter servers (PS) to enhance satellite visibility, and (2) introducesnon-orthogonal multiple access (NOMA) into LEO to enable fast andbandwidth-efficient model transmissions. In addition, NomaFedHAP includes (3) anew communication topology that exploits HAPs to bridge satellites amongdifferent orbits to mitigate the Doppler shift, and (4) a new FL modelaggregation scheme that optimally balances models between different orbits andshells. Moreover, we (5) derive a closed-form expression of the outageprobability for satellites in near and far shells, as well as for the entiresystem. Our extensive simulations have validated the mathematical analysis anddemonstrated the superior performance of NomaFedHAP in achieving fast andefficient FL model convergence with high accuracy as compared to thestate-of-the-art.

Communication-Efficient Federated Learning for LEO Constellations Integrated with HAPs Using Hybrid NOMA-OFDM