EUVIMEDEUVIMED entdecken
Crossref

Full Cascaded CSI Acquisition for RIS-Assisted Cognitive Radio Systems by Deep Learning

Zhong Tian, Fan Cheng, Zhengchuan Chen, Min Wang, Chaowei Tang, Dapeng O. Wu, Tony Q. S. Quek

IEEE Transactions on Wireless Communications · 2026 · 25 · 17649-17665

DOI: 10.1109/twc.2026.3692246 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2026. Verfasst von Zhong Tian und 6 weiteren Autor:innen. Die Arbeit nennt 47 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Natural Science Foundation of Chongqing, China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The reconfigurable intelligent surface (RIS)-aided cognitive radio (CR) system holds significant promise for enhancing spectrum utilization. However, its practical implementation hinges critically on accurate channel state information (CSI). Obtaining full cascaded CSI in RIS-aided CR systems with the cross interference between multiple cascaded channels is challenging. To fill this gap, we propose the deep learning-based channel acquisition schemes for the users in static scenario and mobile scenario, respectively. In static scenario, we propose a novel deep neural network (DNN)-based channel estimation scheme named dual output parameter estimation (DOPE). This scheme achieves remarkable normalized mean square error (NMSE) performance in CSI estimation while significantly reducing the required pilot overhead. In mobile scenario, we propose a channel prediction scheme with hybrid recurrent neural network (RNN) and Transformer (HRT-CP). This scheme utilizes RNN to extract dynamic and static features of cascaded channels, and introduces Transformer’s powerful parallel processing capability to efficiently predict dynamic features. By combining static and dynamic features appropriately, the HRT-CP scheme has predicted the future cascaded CSI accurately, and mitigated the error accumulation phenomenon effectively. The simulation results under both near-field and far-field channel models demonstrate that our proposed schemes provide significant gains on NMSE performance compared to other benchmarks.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Natural Science Foundation of Chongqing, China
  • Key Laboratory of Cognitive Radio and Information Processing, Ministry of Education
  • Opening Fund of the National Key Laboratory of Multi-Domain Data Collaborative Processing and Control
  • Postdoctoral Fellowship Program of China Postdoctoral Science Foundation
  • Project funded by China Postdoctoral Science Foundation
  • Xiaomi Young Talents Program

Zitieren

APA

Tian, Z., Cheng, F., Chen, Z., Wang, M., Tang, C., Wu, D. O., & Quek, T. Q. S. (2026). Full Cascaded CSI Acquisition for RIS-Assisted Cognitive Radio Systems by Deep Learning. IEEE Transactions on Wireless Communications, 25, 17649-17665. https://doi.org/10.1109/twc.2026.3692246

Vancouver

Tian Z, Cheng F, Chen Z, Wang M, Tang C, Wu DO, et al. Full Cascaded CSI Acquisition for RIS-Assisted Cognitive Radio Systems by Deep Learning. IEEE Transactions on Wireless Communications. 2026;25:17649-17665. doi:10.1109/twc.2026.3692246

BibTeX
@article{Tian2026,
  author = {Tian, Zhong and Cheng, Fan and Chen, Zhengchuan and Wang, Min and Tang, Chaowei and Wu, Dapeng O. and Quek, Tony Q. S.},
  title = {Full Cascaded CSI Acquisition for RIS-Assisted Cognitive Radio Systems by Deep Learning},
  journal = {IEEE Transactions on Wireless Communications},
  year = {2026},
  volume = {25},
  pages = {17649--17665},
  doi = {10.1109/twc.2026.3692246}
}
Kostenlos starten →