Accès libre

Research on downlink channel state information prediction technique for 5G system based on deep neural network

Jinhui Chen

Jinhui Chen

College of Information and Communication Engineering, Beijing Information Science and Technology UniversityBeijing, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Chen, Jinhui
, 
Chenxi Zhu

Chenxi Zhu

College of Information and Communication Engineering, Beijing Information Science and Technology UniversityBeijing, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Zhu, Chenxi
 et 
Zhan Xu

Zhan Xu

College of Information and Communication Engineering, Beijing Information Science and Technology UniversityBeijing, China
Recherchez cet auteur sur
Sciendo|Google Scholar
Xu, Zhan
  
19 mars 2025
Research on downlink channel state information prediction technique for 5G system based on deep neural network's Cover Image
À propos de cet article
Article précédent
Article suivant
Citez
Télécharger la couverture
Publié en ligne: 19 mars 2025
Reçu: 11 nov. 2024
Accepté: 09 févr. 2025
DOI: https://doi.org/10.2478/amns-2025-0471
Mots clés
© 2025 Jinhui Chen et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Figure 1.

Basic structure of neurons
Basic structure of neurons

Figure 2.

Convolutional neural network structure
Convolutional neural network structure

Figure 3.

Full connection layer network structure
Full connection layer network structure

Figure 4.

CSI feedback model based on deep learning
CSI feedback model based on deep learning

Figure 5.

Deep learning CSI feedback method classification
Deep learning CSI feedback method classification

Figure 6.

Structure of 3D-CsiNet network model
Structure of 3D-CsiNet network model

Figure 7.

The channel prediction is compared to the real value in the walking scenario
The channel prediction is compared to the real value in the walking scenario

Figure 8.

Channel prediction and true value of cycling scenarios
Channel prediction and true value of cycling scenarios

Figure 9.

The 3D-CsiNet model and the AR model predictive can compare the results
The 3D-CsiNet model and the AR model predictive can compare the results

Figure 10.

The channel prediction error of different SRS transmission cycles3
The channel prediction error of different SRS transmission cycles3

Figure 11.

The NMSE performance of the CSI amplitude feedback
The NMSE performance of the CSI amplitude feedback

Figure 12.

NMSE performance of different CSI phase feedback mechanisms
NMSE performance of different CSI phase feedback mechanisms
Langue:
Anglais
Périodicité:
1 fois par an
Sujets de la revue:
Sciences de la vie, Sciences de la vie, autres, Mathématiques, Mathématiques appliquées, Mathématiques générales, Physique, Physique, autres
RSS Feed de la revue