基于GCNet的毫米波波束选择算法

李雨泽; 李心安

doi:10.13756/j.gtxyj.2023.06.009

您当前的位置：

首页 >

文章列表页 >

基于GCNet的毫米波波束选择算法

无线通信技术 | 更新时间：2023-12-07

- 基于GCNet的毫米波波束选择算法
- Beam Selection Algorithm in Millimeter Wave based on GCNet
- 光通信研究 2023年第6期页码：72-76
- 作者机构：
  
  重庆邮电大学　a.通信与信息工程学院；b.新一代宽带移动通信重点实验室，重庆　400065
- 作者简介：
  
  李雨泽，硕士。Email：975120972@qq.com
- 基金信息：
  
  国家科技重大专项资助项目(2018ZX03001026-002)
- DOI：10.13756/j.gtxyj.2023.06.009
  中图分类号： TN928
- 纸质出版日期：2023-12-10，
  
  收稿日期：2022-09-08，
  
  修回日期：2022-10-08，
扫描看全文
李雨泽，李心安.基于GCNet的毫米波波束选择算法[J].光通信研究，2023(6):72-76.

Li Y Z, Li X A. Beam Selection Algorithm in Millimeter Wave based on GCNet [J]. Study on Optical Communications, 2023(6):72-76.
李雨泽，李心安.基于GCNet的毫米波波束选择算法[J].光通信研究，2023(6):72-76. DOI： 10.13756/j.gtxyj.2023.06.009.

Li Y Z, Li X A. Beam Selection Algorithm in Millimeter Wave based on GCNet [J]. Study on Optical Communications, 2023(6):72-76. DOI： 10.13756/j.gtxyj.2023.06.009.

摘要

在车辆到基础设施（V2I）通信中，毫米波波束宽度窄、设备移动性高，有效的毫米波波束选择是一项关键而又富有挑战性的任务。针对波束搜索过程开销大的问题，文章提出了一种基于雷达和位置信息的毫米波波束选择算法。所提算法使用Top-

分类度量在激光雷达数据和波束跟踪通道数据集上训练神经网络结构，并且使用全局上下文网络（GCNet）模型预测最佳波束对。仿真结果表明，所提算法性能在分类识别准确率上有明显提升，与此同时，仅需搜索5个波束便能接近穷举搜索的性能，大大减少了波束搜索开销。

Abstract

In the vehicle to infrastructure communication

the millimeter wave beam width is narrow and user equipment mobility is high. Therefore

effective millimeter wave beam selection is a key and challenging task. Aiming at the problem of high overhead in the beam search process

this paper proposes a millimeter-wave beam selection algorithm based on radar and location information. The proposed algorithm trains a neural network structure on the lidar and beam tracking channel datasets using the Top-

classification metric. It also predicts the best beam pair using the Global Context Net (GCNet) model. The simulation results show that the performance of the proposed algorithm is significantly improved in the classification and recognition accuracy. At the same time

it only needs to search 5 beams to approach the performance of the exhaustive search

which greatly reduces the beam search overhead.

关键词

毫米波波束选择机器学习神经网络GCNet

Keywords

millimeter wavebeam selectionmachine learningneural networkGCNet

references

Choi J, Va V, Gonzalez-Prelcic N, et al. Millimeter-wave Vehicular Communication to Support Massive Automotive Sensing[J]. IEEE Communications Magazine, 2016, 54(12): 160-167.

Va V, Choi J, Heath R W. The Impact of Beamwidth on Temporal Channel Variation in Vehicular Channels and Its Implications[J]. IEEE Transactions on Vehicular Technology, 2017, 66(6): 5014-5029.

Wei L L, Li Q, Wu G. Initial Access Techniques for 5G NR: Omni/beam SYNC and RACH Designs[C]//2018 International Conference on Computing, Networking and Communications (ICNC). Maui, HI, USA: IEEE, 2018: 249-253.

Hur S, Kim T, Love D J, et al.Millimeter Wave Beamforming for Wireless Backhaul and Access in Small Cell Networks[J]. IEEE Transactions on Communications, 2013, 61(10): 4391-4403.

侯嘉智, 梁晶, 刘高路. 基于机器学习的波束搜索算法设计[J]. 光通信研究, 2020(4): 62-67.

Hou J Z, Liang J, Liu G L. A Beam Search Algorithm based on Machine Learning [J]. Study on Optical Communications, 2020(4):62-67.

Klautau A, Batista P, González-Prelcic N, et al. 5G MIMO Data for Machine Learning: Application to Beam-selection Using Deep Learning[C]//2018 Information Theory and Applications Workshop (ITA). San Diego, CA, USA: IEEE, 2018: 8503086.

Wang Y Y, Klautau A, Ribero M, et al. Mmwave Vehicular Beam Training with Situational Awareness by Machine Learning[C]//2018 IEEE Globecom Workshops (GC Wkshps). Abu Dhabi, United Arab Emirates: IEEE, 2018: 8644288.

Klautau A, González-Prelcic N, Heath R W. LIDAR Data for Deep Learning-based mmWave Beam-selection[J]. IEEE Wireless Communications Letters, 2019, 8(3): 909-912.

Dias M, Klautau A, González-Prelcic N, et al. Position and LIDAR-aided mmWave Beam Selection Using Deep Learning[C]//2019 IEEE 20th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC). Cannes, France: IEEE, 2019: 8815569.

Mashhadi M B, Jankowski M, Tung T Y, et al. Federated mmWave Beam Selection Utilizing LIDAR Data[J]. IEEE Wireless Communications Letters, 2021, 10(10): 2269-2273.

Zecchin M, Mashhadi M B, Jankowski M, et al. LIDAR and Position-aided mmWave Beam Selection with Non-local CNNs and Curriculum Training[J]. IEEE Transactions on Vehicular Technology, 2022, 71(3): 2979-2990.

Cao Y, Xu J R, Lin S, et al. Gcnet: Non-local Networks Meet Squeeze-excitation Networks and Beyond[C]//2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). Seoul, Korea (South): IEEE, 2019: 00246.

更多指标>

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

深度学习在光纤通信系统损伤补偿中的应用

基于神经网络的编码压扩联合峰均比降低技术

光纤分布式传感系统在变电站维护中的应用

迁移学习辅助基于机器学习的传输质量评估

基于机器学习的调制格式识别算法研究