Preprint
Aug 2026
LEO-Aware DRL Meta-Scheduler for 5G Non-Terrestrial Network Slicing
This paper proposes a deep reinforcement learning (DRL) meta-scheduler for twin-timescale resource allocation, which enforces isolation without inducing the broadband slice starvation characteristic of standard maximum-CQI heuristics, establishing a robust foundation for 6G O-RAN NTN resource allocation.
Víctor Vilchez, T. P. C. de Andrade, Edward Hinojosa et al.
· 0 citations