arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2607.22217eess.SP

用于具有数据缩减的 D-MIMO 室内定位的深度可分离卷积神经网络

Depthwise Separable CNN for D-MIMO Indoor Localization with Data Reduction

Georgios Mystriotis, Rodney Martinez Alonso, Achiel Colpaert, Sofie Pollin

首次发表
浏览论文内容

中文总结 AI 辅助

研究针对 D-MIMO 室内定位中传容量瓶颈问题,提出轻量级分布式 ML 框架,在网络边缘进行 CSI 特征提取与缩减,传输低维特征至中央单元估计位置,可减少中传流量 100 倍,保持误差 8.5 毫米,提供可扩展定位蓝图。

中文摘要 AI 辅助

使用分布式多输入多输出(D-MIMO)和机器学习(ML)的室内定位可实现亚厘米级精度,但在开放无线接入网络(O-RAN)架构中传输原始信道状态信息(CSI)时面临中传容量瓶颈。为解决此问题,我们提出了一个轻量级的分布式 ML 框架,将初始处理转移到网络边缘。通过在分布式单元(DU)上作为 dApp 部署本地化模型,每个模型仅需 1.39MB 内存和 1.96MFLOPs,系统在边缘执行 CSI 特征提取和缩减。缩减后的低维特征被传输到中央单元(CU),在那里部署另一个 dApp 进行位置估计。在高密度数据集上评估,该框架将中传流量减少 100 倍,同时保持平均误差 8.5 毫米,即使部署的无线单元(RU)减半,为实际 D-MIMO 定位提供了可扩展蓝图。

英文摘要

Indoor localization using Distributed Multiple-Input Multiple-Output (D-MIMO) and machine learning (ML) achieves sub-centimeter accuracy but faces midhaul capacity bottlenecks when transmitting raw Channel State Information (CSI) in Open Radio Access Networks (O-RAN) architectures. To address this, we propose a lightweight, distributed ML framework that shifts initial processing to the network edge. By deploying localized models as dApps on Distributed Units (DUs), each requiring just 1.39 MB of memory and 1.96 MFLOPs, the system performs CSI feature extraction and reduction on the edge. The reduced low-dimensional features are transmitted to the Central Unit (CU), where another dApp is deployed for location estimation. Evaluated on a high-density dataset, this framework reduces midhaul traffic by 100x while maintaining an average error of 8.5 mm, even with half the deployed Radio Units (RUs), providing a scalable blueprint for practical D-MIMO localization.

补充信息

↑