CA‐PPO: Collision‐Aware Reinforcement Learning for Grant‐Free NOMA in Wireless Federated Learning
IET Networks · 2026-01 · 15 (1)
DOI: 10.1049/ntw2.70028 ↗Kurz gefasst
Fachartikel in der Zeitschrift IET Networks, online erschienen am 12.05.2026. Verfasst von Emmanuel Atebawone und 5 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
This paper proposes a collision‐aware proximal policy optimisation (CA‐PPO) framework for adaptive resource management in grant‐free nonorthogonal multiple access (GF‐NOMA) enabled wireless federated learning systems. Unlike conventional approaches that rely on static clustering or grant‐based access, CA‐PPO dynamically coordinates device clustering and transmit‐power allocation under stochastic channel conditions, random‐access collisions and successive interference cancelation (SIC) constraints. The proposed framework employs a hybrid discrete–continuous actor–critic architecture with a collision‐aware reward that jointly captures decoding success, energy consumption, latency and retransmissions. CA‐PPO enables scalable and reliable aggregation in ultradense IoT deployments by improving participation stability and reducing communication overhead. Simulation results demonstrate that the proposed approach accelerates convergence by approximately 16%, reduces per‐device energy consumption by up to 25% and sustains high device participation under dense connectivity. These findings highlight the potential of learning‐driven network‐aware resource optimisation for next‐generation wireless federated learning systems.
Zitieren
APA
Atebawone, E., Agyekum, K. O. O., Gadze, J. D., Opare, K. A., Antwi, O. A., & Akromond, R. (2026). CA‐PPO: Collision‐Aware Reinforcement Learning for Grant‐Free NOMA in Wireless Federated Learning. IET Networks, 15(1). https://doi.org/10.1049/ntw2.70028
Vancouver
Atebawone E, Agyekum KOO, Gadze JD, Opare KA, Antwi OA, Akromond R. CA‐PPO: Collision‐Aware Reinforcement Learning for Grant‐Free NOMA in Wireless Federated Learning. IET Networks. 2026;15(1). doi:10.1049/ntw2.70028
BibTeX
@article{Atebawone2026,
author = {Atebawone, Emmanuel and Agyekum, Kwame Opuni‐Boachie Obour and Gadze, James Dzisi and Opare, Kwasi Adu‐Boahen and Antwi, Owusu Agyeman and Akromond, Robert},
title = {CA‐PPO: Collision‐Aware Reinforcement Learning for Grant‐Free NOMA in Wireless Federated Learning},
journal = {IET Networks},
year = {2026},
volume = {15},
number = {1},
doi = {10.1049/ntw2.70028}
}
EUVIMED