EUVIMEDEUVIMED entdecken
Crossref

Enhancing Reliability in AI-Based CSI Prediction: A Proxy-Based Performance Monitoring Approach

Chengyong Jiang, Jiajia Guo, Chao-Kai Wen, Shi Jin

IEEE Transactions on Communications · 2025-04 · 73 (4) · 2602-2615

DOI: 10.1109/tcomm.2024.3475274 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Communications, 2025-04. Verfasst von Chengyong Jiang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 40 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, in part by the Key Technologies R&D Program of Jiangsu under.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Artificial intelligence (AI)-based channel state information (CSI) prediction, aimed at enhancing CSI accuracy and reducing overhead, has shown significant advancements over traditional model-based prediction methods. Despite these advantages, its practical deployment has been hindered by unreliable prediction performance due to AI instability. This study introduces a reliable AI-based CSI prediction framework by implementing a proxy-based performance monitoring mechanism. Specifically, we deploy a lightweight proxy at the user equipment (UE), trained via knowledge distillation to accommodate the UE’s limited capacities. This proxy mimics the output of the CSI prediction network at the base station (BS) side, enabling the UE to monitor the accuracy of the predicted CSI and prevent undesirable outcomes. To overcome the deployment challenges in operational systems, we detail the practical implementation procedures of our proposed method, covering both offline training and online operation phases. Simulation results show that our proxy-based monitor can achieve over 90% consistency with the CSI prediction network at the BS side and avoid over 85% of unsatisfactory prediction outcomes under various practical considerations, demonstrating remarkable generalization capabilities across different configurations.

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • in part by the Key Technologies R&D Program of Jiangsu under
  • Fundamental Research Funds for the Central Universities
  • and by the Guangdong Basic and Applied Basic Research Foundation
  • Google

Zitieren

APA

Jiang, C., Guo, J., Wen, C., & Jin, S. (2025). Enhancing Reliability in AI-Based CSI Prediction: A Proxy-Based Performance Monitoring Approach. IEEE Transactions on Communications, 73(4), 2602-2615. https://doi.org/10.1109/tcomm.2024.3475274

Vancouver

Jiang C, Guo J, Wen C, Jin S. Enhancing Reliability in AI-Based CSI Prediction: A Proxy-Based Performance Monitoring Approach. IEEE Transactions on Communications. 2025;73(4):2602-2615. doi:10.1109/tcomm.2024.3475274

BibTeX
@article{Jiang2025,
  author = {Jiang, Chengyong and Guo, Jiajia and Wen, Chao-Kai and Jin, Shi},
  title = {Enhancing Reliability in AI-Based CSI Prediction: A Proxy-Based Performance Monitoring Approach},
  journal = {IEEE Transactions on Communications},
  year = {2025},
  volume = {73},
  number = {4},
  pages = {2602--2615},
  doi = {10.1109/tcomm.2024.3475274}
}
Kostenlos starten →