EUVIMEDEUVIMED entdecken
Crossref

Decision Transformers for RIS-Assisted Systems With Diffusion Model-Based Channel Acquisition

Jie Zhang, Yiyang Ni, Jun Li, Guangji Chen, Zhe Wang, Long Shi, Shi Jin, Wen Chen, H. Vincent Poor

IEEE Transactions on Wireless Communications · 2026 · 25 · 17542-17558

DOI: 10.1109/twc.2026.3692586 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Wireless Communications, 2026. Verfasst von Jie Zhang und 8 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Jiangsu Province, Natural Science Foundation of Jiangsu Provincial Excellent Young Scientist.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reconfigurable intelligent surfaces (RISs) have been recognized as a revolutionary technology for future wireless networks. However, RIS-assisted communications have to continuously tune phase-shifts relying on accurate channel state information (CSI) that is generally difficult to obtain due to the large number of RIS channels. The joint design of CSI acquisition and subsection RIS phase-shifts remains a significant challenge in dynamic environments. In this paper, we propose a diffusion-enhanced decision Transformer (DEDT) framework consisting of a diffusion model (DM) designed for efficient CSI acquisition and a decision Transformer (DT) utilized for phase-shift optimizations. Specifically, we first propose a novel DM mechanism, i.e., conditional imputation based on denoising diffusion probabilistic model, for rapidly acquiring real-time full CSI by exploiting the spatial correlations inherent in wireless channels. Then, we optimize beamforming schemes based on the DT architecture, which pre-trains on historical environments to establish a robust policy model. Next, we incorporate a fine-tuning mechanism to ensure rapid beamforming adaptation to new environments, eliminating the retraining process that is imperative in conventional reinforcement learning (RL) methods. Simulation results demonstrate that DEDT can enhance efficiency and adaptability of RIS-aided communications with fluctuating channel conditions compared to state-of-the-art RL methods.

Förderung

  • National Natural Science Foundation of China
  • Natural Science Foundation of Jiangsu Province
  • Natural Science Foundation of Jiangsu Provincial Excellent Young Scientist
  • Jiangsu Provincial Key Research and Development Program
  • Shanghai Kewei
  • Open Research Fund of the National Mobile Communications Research Laboratory, Southeast University
  • Innovation Grant from Princeton NextG

Zitieren

APA

Zhang, J., Ni, Y., Li, J., Chen, G., Wang, Z., Shi, L., Jin, S., Chen, W., & Poor, H. V. (2026). Decision Transformers for RIS-Assisted Systems With Diffusion Model-Based Channel Acquisition. IEEE Transactions on Wireless Communications, 25, 17542-17558. https://doi.org/10.1109/twc.2026.3692586

Vancouver

Zhang J, Ni Y, Li J, Chen G, Wang Z, Shi L, et al. Decision Transformers for RIS-Assisted Systems With Diffusion Model-Based Channel Acquisition. IEEE Transactions on Wireless Communications. 2026;25:17542-17558. doi:10.1109/twc.2026.3692586

BibTeX
@article{Zhang2026,
  author = {Zhang, Jie and Ni, Yiyang and Li, Jun and Chen, Guangji and Wang, Zhe and Shi, Long and Jin, Shi and Chen, Wen and Poor, H. Vincent},
  title = {Decision Transformers for RIS-Assisted Systems With Diffusion Model-Based Channel Acquisition},
  journal = {IEEE Transactions on Wireless Communications},
  year = {2026},
  volume = {25},
  pages = {17542--17558},
  doi = {10.1109/twc.2026.3692586}
}
Kostenlos starten →