A Next-Generation Codebook Evolution Strategy for Massive Arrays Using Deep Neurals Networks
The discrete Fourier transform (DFT)-based codebook is currently among the mostly commonly adopted codebooks for beamforming using arrays of different shapes and sizes, including the large-scale two-dimensional uniform planar array (UPA). DFT-based codevectors can be easily generated in arbitrary an...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2022-01-01
|
Series: | International Journal of Antennas and Propagation |
Online Access: | http://dx.doi.org/10.1155/2022/3837376 |
_version_ | 1811190682818183168 |
---|---|
author | Minwoo Choi Wonjin Sung |
author_facet | Minwoo Choi Wonjin Sung |
author_sort | Minwoo Choi |
collection | DOAJ |
description | The discrete Fourier transform (DFT)-based codebook is currently among the mostly commonly adopted codebooks for beamforming using arrays of different shapes and sizes, including the large-scale two-dimensional uniform planar array (UPA). DFT-based codevectors can be easily generated in arbitrary angle resolutions and apply well to millimeter-wave (mmWave) channels due to their directive nature of resulting beams. However, a fixed set of codevectors is applied regardless of the user distributions and the propagation environment, which may exhibit limited beamforming performance under certain transmission scenarios. In this paper, we propose a new way of generating a set of beamforming vectors for multiple-input multiple-output (MIMO) transmission using massive arrays under the limited feedback of the channel state information (CSI). Precoder matrix indicator (PMI) and channel quality indicator (CQI) reports from the users have become the sources for the generation of a new set of codevectors, which are autonomously determined by the deep learning (DL) module at the base station (BS). The process is operated in an iterative fashion to produce updated versions of the codebook with the reduced return of the loss function at the deep neural network (DNN). The time-varying codebook for each BS automatically reflects the characteristics of a given wireless environment to adapt to its channel and traffic conditions. The reference signal (RS) at the BS is periodically transmitted in the form of beamformed CSI-RS, thus the operation is transparent to the users of the system and no significant specification changes are necessary. A simple plug-and-play type of BS installation suffices to achieve the potential gain of the proposal, which is demonstrated by the implementation details of the DL engine and the corresponding performance simulation results. |
first_indexed | 2024-04-11T14:54:21Z |
format | Article |
id | doaj.art-dd4e1b517cfa45a2a047453d5450bb92 |
institution | Directory Open Access Journal |
issn | 1687-5877 |
language | English |
last_indexed | 2024-04-11T14:54:21Z |
publishDate | 2022-01-01 |
publisher | Hindawi Limited |
record_format | Article |
series | International Journal of Antennas and Propagation |
spelling | doaj.art-dd4e1b517cfa45a2a047453d5450bb922022-12-22T04:17:19ZengHindawi LimitedInternational Journal of Antennas and Propagation1687-58772022-01-01202210.1155/2022/3837376A Next-Generation Codebook Evolution Strategy for Massive Arrays Using Deep Neurals NetworksMinwoo Choi0Wonjin Sung1Department of Electronic EngineeringDepartment of Electronic EngineeringThe discrete Fourier transform (DFT)-based codebook is currently among the mostly commonly adopted codebooks for beamforming using arrays of different shapes and sizes, including the large-scale two-dimensional uniform planar array (UPA). DFT-based codevectors can be easily generated in arbitrary angle resolutions and apply well to millimeter-wave (mmWave) channels due to their directive nature of resulting beams. However, a fixed set of codevectors is applied regardless of the user distributions and the propagation environment, which may exhibit limited beamforming performance under certain transmission scenarios. In this paper, we propose a new way of generating a set of beamforming vectors for multiple-input multiple-output (MIMO) transmission using massive arrays under the limited feedback of the channel state information (CSI). Precoder matrix indicator (PMI) and channel quality indicator (CQI) reports from the users have become the sources for the generation of a new set of codevectors, which are autonomously determined by the deep learning (DL) module at the base station (BS). The process is operated in an iterative fashion to produce updated versions of the codebook with the reduced return of the loss function at the deep neural network (DNN). The time-varying codebook for each BS automatically reflects the characteristics of a given wireless environment to adapt to its channel and traffic conditions. The reference signal (RS) at the BS is periodically transmitted in the form of beamformed CSI-RS, thus the operation is transparent to the users of the system and no significant specification changes are necessary. A simple plug-and-play type of BS installation suffices to achieve the potential gain of the proposal, which is demonstrated by the implementation details of the DL engine and the corresponding performance simulation results.http://dx.doi.org/10.1155/2022/3837376 |
spellingShingle | Minwoo Choi Wonjin Sung A Next-Generation Codebook Evolution Strategy for Massive Arrays Using Deep Neurals Networks International Journal of Antennas and Propagation |
title | A Next-Generation Codebook Evolution Strategy for Massive Arrays Using Deep Neurals Networks |
title_full | A Next-Generation Codebook Evolution Strategy for Massive Arrays Using Deep Neurals Networks |
title_fullStr | A Next-Generation Codebook Evolution Strategy for Massive Arrays Using Deep Neurals Networks |
title_full_unstemmed | A Next-Generation Codebook Evolution Strategy for Massive Arrays Using Deep Neurals Networks |
title_short | A Next-Generation Codebook Evolution Strategy for Massive Arrays Using Deep Neurals Networks |
title_sort | next generation codebook evolution strategy for massive arrays using deep neurals networks |
url | http://dx.doi.org/10.1155/2022/3837376 |
work_keys_str_mv | AT minwoochoi anextgenerationcodebookevolutionstrategyformassivearraysusingdeepneuralsnetworks AT wonjinsung anextgenerationcodebookevolutionstrategyformassivearraysusingdeepneuralsnetworks AT minwoochoi nextgenerationcodebookevolutionstrategyformassivearraysusingdeepneuralsnetworks AT wonjinsung nextgenerationcodebookevolutionstrategyformassivearraysusingdeepneuralsnetworks |