跳到正文
arXiv cs.AI· Yijie Bian, Wei Guo, Jie Yang, Shenghui Song, Jun Zhang, Shi Jin, Khaled B. Letaief·· 10 小时前AI 评分18

面向大规模 MIMO 的多模态环境感知波束管理:几何驱动的虚拟基站框架

Multi-Modal Environment-Aware Beam Management for Massive MIMO: A Geometry-Driven Virtual Base Station Framework

AI 导读

研究提出几何驱动的虚拟基站(VBS)框架,利用区域 3D LiDAR 点云与位置信息离线构建 VBS 数据库,通过建筑立面镜像对称建模主要反射路径,实现稀疏的传播环境描述。该框架支持在线粗信道重建与波束空间先验生成,并设计 VBS 辅助正交导频(VOP)部分波束训练方案以减少在线测量。仿真显示其在评估的随机、启发式及传统学习基线之上提升了有效频谱效率,同时在线波束测量更少。

正文 · 原文

View PDF HTML (experimental)

Abstract:High-frequency massive multiple-input multiple-output (MIMO) systems promise ultra-high data rates. However, efficient beam management remains challenging due to the prohibitive beam training overhead and intricate coordination required in multi-user MIMO (MU-MIMO) scenarios. To address these bottlenecks, environment-aware communications have emerged as a promising paradigm, leveraging site-specific knowledge to circumvent exhaustive pilot-based beam training and streamline multi-user communications. In this paper, we propose a geometry-driven framework that utilizes multi-modal environmental data, specifically regional 3D light detection and ranging (LiDAR) point clouds and location information, to construct an offline virtual base station (VBS) database. By modeling dominant reflection paths via mirror symmetry across building facades reconstructed from the point clouds, the VBS database provides a compact and sparse description of the wireless propagation environment. Given a user location, the VBS representation supports online coarse channel reconstruction and the generation of a beamspace prior. To refine the coarse estimates, we design a VBS-assisted orthogonal-pilot (VOP)-based partial beam training scheme with limited online measurements. Finally, to coordinate beam selection under inter-user interference, we develop a hierarchical dual-agent dueling double deep Q-network for coordinated beam selection (DD3QN-CBS). Simulation results show that the proposed framework improves effective spectral efficiency over the evaluated stochastic, heuristic, and conventional learning-based baselines, while achieving competitive performance with fewer online beam measurements.
Subjects: Signal Processing (eess.SP); Artificial Intelligence (cs.AI)
Cite as: arXiv:2606.26567 [eess.SP]
  (or arXiv:2606.26567v2 [eess.SP] for this version)
  https://doi.org/10.48550/arXiv.2606.26567

arXiv-issued DOI via DataCite

Submission history

From: Yijie Bian [view email]
[v1] Thu, 25 Jun 2026 03:37:20 UTC (17,816 KB)
[v2] Wed, 18 Nov 2026 06:21:06 UTC (16,485 KB)

来源:arXiv cs.AI · arxiv.org