Authors: Yang Cao, Shao-Yu Lien, Ying-Chang Liang, Dusit Niyato, Xuemin, Shen

Published on: February 07, 2024

Impact Score: 8.45

Arxiv code: Arxiv:2402.04865

Summary

• What is new: A multi-time-scale deep reinforcement learning scheme for radio resource optimization in non-terrestrial networks using LEO satellites and user equipment.
• Why this is important: The challenge of optimizing resources in LEO satellite networks within a short duration due to limited computing capabilities.
• What the research proposes: Developed a scheme where the user equipment collaborates with the LEO satellite to perform decision-making tasks with different control cycles, ensuring performance convergence.
• Results: The scheme successfully balanced transmission performance and computational complexity in simulations.

Technical Details

Technological frameworks used: Multi-time-scale deep reinforcement learning (DRL)

Models used: nan

Data used: nan

Potential Impact

Telecommunications, satellite communication companies, and global internet service providers could benefit or face disruption.

Want to implement this idea in a business?

We have generated a startup concept here: SkyOptiNet.