DPC-CNN Algorithm for Multiuser Hybrid Precoding With Dynamic Structure

This paper presents a dynamic partially connected (DPC) structure-based convolutional neural network (CNN) hybrid precoding with multi-user optimization algorithm. In the proposed algorithm, a multi-output CNN framework is constructed to simultaneously optimize the phase shifter and switch precoders...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:IEEE transactions on green communications and networking Ročník 8; číslo 4; s. 1361 - 1370
Hlavní autori: Liu, Fulai, Duan, Zhuoyao, Zhang, Lijie, Shi, Baozhu, Liu, Yubiao, Du, Ruiyan
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Piscataway IEEE 01.12.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Predmet:
Algorithms
Artificial neural networks
Constraints
convolutional neural network
Convolutional neural networks
dynamic structure
Heuristic algorithms
Hybrid precoding
massive-wave MIMO
MIMO communication
Neural networks
Phase shifters
Precoding
Radio frequency
Real time
Switches
Vectors
ISSN:2473-2400, 2473-2400
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:This paper presents a dynamic partially connected (DPC) structure-based convolutional neural network (CNN) hybrid precoding with multi-user optimization algorithm. In the proposed algorithm, a multi-output CNN framework is constructed to simultaneously optimize the phase shifter and switch precoders, including custom 'Out' layer, deep neural network (DNN)-based analog phase shifter subnetwork, namely DNN-Fps, and DNN-based switch subnetwork, called DNN-Fs. Specifically, the DNN-Fps is designed to obtain the vectorized phase shifter precoder with constant modulus constraint. The DNN-Fs is utilized to output the vectorized switch precoder with the binary constraint. The 'Out' layer is defined to obtain the vectorized analog precoder with constant modulus and binary constraints. Moreover, to further improve the real-time performance of hybrid precoding, a dynamic pruning technique is applied to remove the redundant parameters for the DPC-CNN model. Finally, the DPC-CNN is trained using the loss function with the residual between the vectorized analog precoders of the fully connected (FC) and DPC structures. Theoretical analyses and simulation experiments show that compared to the FC and partially connected structures, the proposed DPC-CNN hybrid precoding algorithm can achieve a balance between spectral efficiency and energy efficiency with less execution time.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2473-2400
2473-2400
DOI:10.1109/TGCN.2024.3376571