Name
Title | ||
|---|---|---|
Deep Learning Assisted Hybrid Precoding with Dynamic Subarrays in mmWave MU-MIMO System |
Abstract | ||
|---|---|---|
In millimeter wave communication, analog-digital hybrid precoding is used to decrease hardware complexity and energy consumption. The performance and hardware complexity of hybrid precoding can be compromised by using sub-connected architecture further, but it also brings about the problem of high computational complexity. To tackle this issue, a multiuser hybrid precoding framework based on deep learning is proposed in this paper. Specifically, two deep neural networks (DNN), which can be connected by the transformation matrix, are constructed to maximize the effective channel gain, thus maximizing the sum rate of multiuser. Simulation results exhibit that the DNN-based framework achieves better performance while maintaining low computational complexity compared with the traditional method in hybrid precoding. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/ICCC49849.2020.9238917 | 2020 IEEE/CIC International Conference on Communications in China (ICCC) |
Keywords | DocType | ISSN |
massive MU-MIMO,deep learning,dynamic subarrays,millimeter wave | Conference | 2377-8644 |
ISBN | Citations | PageRank |
978-1-7281-7328-3 | 0 | 0.34 |
References | Authors | |
9 | 2 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jing Jiang | 1 | 0 | 0.34 |
| Yun Yang | 2 | 76 | 9.80 |