.png){kind=icon}
.png){kind=icon}
Return
An RTDNN-Based Hybrid Precoding and Combining Joint Optimization Algorithm for MUPC-MIMO Systems
.png){kind=icon}
PRE
AI
DOI：10.1109/TGCN.2025.3559308.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
To achieve a satisfactory balance between energy efficiency (EE) and spectral efficiency (SE) for hybrid precoding and combining (HPC), this paper presents a two-stage joint optimization HPC algorithm based on residual deep neural network (DNN) for multi-user partially connected (MUPC) structure, namely RTDNN algorithm. In the proposed algorithm, a two-stage framework is designed to optimize analog and digital coders at the transmitter and receiver simultaneously, which can effectively preserve coupling relationship of coders between the transmitter and receiver. Specially, the RTDNN architecture is mainly divided into two stage networks, which includes analog stage and digital stage networks. The analog stage network is developed to obtain the optimal analog precoder and combiner simultaneously. On this basis, the digital stage network is constructed to solve the digital precoder and combiner concurrently. To further improve the prediction accuracy of RTDNN-based HPC, residual modules are adopted into the developed two stage networks. Moreover, the proposed RTDNN is trained with unsupervised learning. Simulation results show that the EE of the proposed algorithm is at least enhanced by 0.6 bits/Hz/J with satisfactory SE than other methods.
Keywords:
Partially connected structure
mmWave
hybrid precoding and combining
energy efficiency
residual module
Journal
I
IF:
6.7
Papers:
1.3K
Citations:
4.3K
View more organizations