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

A mega-constellation of low-altitude earth orbit (LEO) satellites (SATs) andburgeoning unmanned aerial vehicles (UAVs) are promising enablers forhigh-speed and long-distance communications in beyond fifth-generation (5G)systems. Integrating SATs and UAVs within a non-terrestrial network (NTN), inthis article we investigate the problem of forwarding packets between twofaraway ground terminals through SAT and UAV relays using eithermillimeter-wave (mmWave) radio-frequency (RF) or free-space optical (FSO) link.Towards maximizing the communication efficiency, the real-time associationswith orbiting SATs and the moving trajectories of UAVs should be optimized withsuitable FSO/RF links, which is challenging due to the time-varying networktopology and a huge number of possible control actions. To overcome thedifficulty, we lift this problem to multi-agent deep reinforcement learning(MARL) with a novel action dimensionality reduction technique. Simulationresults corroborate that our proposed SAT-UAV integrated scheme achieves 1.99xhigher end-to-end sum throughput compared to a benchmark scheme with fixedground relays. While improving the throughput, our proposed scheme also aims toreduce the UAV control energy, yielding 2.25x higher energy efficiency than abaseline method only maximizing the throughput. Lastly, thanks to utilizinghybrid FSO/RF links, the proposed scheme achieves up to 62.56x higher peakthroughput and 21.09x higher worst-case throughput than the cases utilizingeither RF or FSO links, highlighting the importance of co-designing SAT-UAVassociations, UAV trajectories, and hybrid FSO/RF links in beyond-5G NTNs.

Integrating LEO Satellites and Multi-UAV Reinforcement Learning for Hybrid FSO/RF Non-Terrestrial Networks