Optimizing Covertness in NOMA: A GAN-Based Approach for Composite Power Distribution Design
IEEE Communications Letters · 2026 · 30 · 218-222
DOI: 10.1109/lcomm.2025.3630580 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Communications Letters, 2026. Verfasst von Xueqin Yang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 6 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: National Natural Science Foundation for Distinguished Young Scholar, National Natural Science Foundation of China, Youth Innovation Team of Shaanxi Universities.
Abstract (Originalsprache)
This letter focuses on downlink non-orthogonal multiple access (NOMA) covert communication systems over quasi-static Rayleigh fading channels, considering multi-slot transmission scenarios with partial eavesdropper channel state information (CSI). Our objective is to jointly maximize covert transmission rate and detection error probability by adopting a random transmit power distribution scheme to find the optimal composite power distribution. To address this high-dimensional, non-convex optimization problem, we propose POWER-GAN, an optimization framework built on generative adversarial networks (GANs). Building on this framework, we design a dynamic distribution combination algorithm for generating the optimal composite power distribution that effectively addresses the aforementioned objective. Additionally, we design a moment-matching performance comparison algorithm that compares the performance of a composite distribution with its moment-matched single distribution across different power ratios. Simulation results show that the proposed method achieves near-optimal performance under both perfect and imperfect CSI, demonstrating that POWER-GAN’s learnable CSI mechanism effectively compensates for channel information imperfectness and provides significant performance advantages.
Förderung
- National Natural Science Foundation for Distinguished Young Scholar
- National Natural Science Foundation of China
- Youth Innovation Team of Shaanxi Universities
- Key Research and Development Projects of Shaanxi Province
Zitieren
APA
Yang, X., Li, Z., Fan, X., Shang, Y., & Chu, H. (2026). Optimizing Covertness in NOMA: A GAN-Based Approach for Composite Power Distribution Design. IEEE Communications Letters, 30, 218-222. https://doi.org/10.1109/lcomm.2025.3630580
Vancouver
Yang X, Li Z, Fan X, Shang Y, Chu H. Optimizing Covertness in NOMA: A GAN-Based Approach for Composite Power Distribution Design. IEEE Communications Letters. 2026;30:218-222. doi:10.1109/lcomm.2025.3630580
BibTeX
@article{Yang2026,
author = {Yang, Xueqin and Li, Zan and Fan, Xiaomin and Shang, Yu and Chu, Hongyun},
title = {Optimizing Covertness in NOMA: A GAN-Based Approach for Composite Power Distribution Design},
journal = {IEEE Communications Letters},
year = {2026},
volume = {30},
pages = {218--222},
doi = {10.1109/lcomm.2025.3630580}
}
EUVIMED