arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.00752cs.NIcs.AIcs.CVcs.LGeess.IV
收藏

面向毫米波通信的基于点云的主动链路质量预测

Point Cloud-based Proactive Link Quality Prediction for Millimeter-wave Communications

Tokyo Institute of Technology(东京工业大学);NTT Corporation(日本电报电话公司)

Shoki Ohta, Takayuki Nishio, Riichi Kudo, Kahoko Takahashi, Hisashi Nagata

AI总结:

针对毫米波链路受行人遮挡且图像预测存在隐私风险的问题,提出基于点云的主动链路质量预测方法,并在60 GHz室内实验中证明其精度可比或优于图像方法。

摘要:

本研究证明了基于点云的毫米波(mmWave)通信主动链路质量预测的可行性。已有研究提出了基于机器学习的方法,利用深度图像时间序列预测未来时段的接收信号强度,以缓解毫米波通信中行人对视距(LOS)路径的遮挡。然而,由于相机图像可能包含敏感信息,这些基于图像的方法因隐私问题而适用性有限。本研究提出了一种基于点云的毫米波链路质量预测方法,并通过实验证明其可行性。点云将三维(3D)空间表示为点的集合,比相机图像更稀疏,且更不容易包含敏感信息。此外,点云提供三维位置和运动信息,这对于理解涉及行人的无线电传播环境是必要的。本研究设计了毫米波链路质量预测方法,并开展了真实室内实验;在该场景中,人体遮挡导致链路质量显著波动。实验使用市售的基于 IEEE 802.11ad 的 60 GHz 无线局域网设备,并使用 Kinect v2 RGB-D 相机和 Velodyne VLP-16 光探测与测距(LiDAR)设备采集点云。实验结果表明,所提方法能够预测由行人遮挡 LOS 路径引起的未来毫米波接收信号强度和吞吐量大幅衰减,其准确率与基于图像的预测方法相当或更优。因此,本文基于点云的方法可作为基于图像方法的可行替代方案。

英文摘要:

This study demonstrates the feasibility of point cloud-based proactive link quality prediction for millimeter-wave (mmWave) communications. Previous studies have proposed machine learning-based methods to predict received signal strength for future time periods using time series of depth images to mitigate the line-of-sight (LOS) path blockage by pedestrians in mmWave communication. However, these image-based methods have limited applicability due to privacy concerns as camera images may contain sensitive information. This study proposes a point cloud-based method for mmWave link quality prediction and demonstrates its feasibility through experiments. Point clouds represent three-dimensional (3D) spaces as a set of points and are sparser and less likely to contain sensitive information than camera images. Additionally, point clouds provide 3D position and motion information, which is necessary for understanding the radio propagation environment involving pedestrians. This study designs the mmWave link quality prediction method and conducts realistic indoor experiments, where the link quality fluctuates significantly due to human blockage, using commercially available IEEE 802.11ad-based 60 GHz wireless LAN devices and Kinect v2 RGB-D camera and Velodyne VLP-16 light detection and ranging (LiDAR) for point cloud acquisition. The experimental results showed that our proposed method can predict future large attenuation of mmWave received signal strength and throughput induced by the LOS path blockage by pedestrians with comparable or superior accuracy to image-based prediction methods. Hence, our point cloud-based method can serve as a viable alternative to image-based methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑