Khaf, Sadia et Kaddoum, Georges.
2026.
« Federated hierarchical reinforcement learning for resilient spectrum sharing in 6G non-terrestrial networks ».
IEEE Open Journal of the Communications Society.
(Sous presse)
Prévisualisation |
PDF
Kaddoum-G-2026-33771.pdf - Version publiée Licence d'utilisation : Creative Commons CC BY-NC-ND. Télécharger (4MB) | Prévisualisation |
Résumé
High-altitude platform stations (HAPS) offer a pragmatic backbone for extending 6G non-terrestrial networks (NTNs) into dense urban cores, sparsely connected remote regions, and disaster-stricken areas. In these environments, cognitive radio networks (CRNs) must arbitrate spectrum access without trusting all agents or relying on intact terrestrial backhaul. Accordingly, in the present study, we propose a federated hierarchical reinforcement learning (F-HRL) framework where secondary users (SUs) cooperatively access primary users’ (PUs) spectrum, ground next-generation Node Bs (gNBs) and uncrewed aerial vehicles (UAVs) enforce trust-aware scheduling, while HAPS coordinators perform Byzantine-resilient aggregation using satellite backhaul. Area-specific reward shaping allows the same policy stack to prioritize spectral efficiency in urban deployments, coverage in remote regions, and rapid recovery after infrastructure loss. We benchmark F-HRL against non-cognitive baselines, simple heuristics, and the hierarchical deep reinforcement learning framework across the following three key scenarios over 5 000 decision steps: nominal spectrum sharing, disaster recovery with a gNB outage, and adversarial environments with malicious SUs. Experimental results demonstrate that F-HRL achieves a nearly 8-fold higher spectrum efficiency than the non-cognitive operation, maintains 86% SU quality-of-service (QoS) satisfaction with a Jain fairness index of 0.950, and sustains over 95% of nominal throughput during infrastructure failures. Under attack conditions with 25% compromised agents, trust-weighted aggregation successfully isolates malicious updates while preserving legitimate throughput. These findings demonstrate that HAPS-centric F-HRL provides adaptive, secure, and resilient spectrum management for future NTN deployments.
| Type de document: | Article publié dans une revue, révisé par les pairs |
|---|---|
| Chercheur(-euse): | Chercheur(-euse) Kaddoum, Georges |
| Affiliation: | Génie électrique |
| Date de dépôt: | 03 juin 2026 18:19 |
| Dernière modification: | 12 juin 2026 23:08 |
| URI: | https://espace2.etsmtl.ca/id/eprint/33771 |
Actions (Authentification requise)
 |
Dernière vérification avant le dépôt |