Scholarlink

This thesis proposes an innovative system framework for vehicular communication utilizing Reconfigurable Intelligent Surfaces (RIS) to support millimeter-wave (mmWave) scenarios, addressing the high transmission rate demands of 6G communication. Due to significant path loss in mmWave propagation, RIS is introduced to enhance coverage and communication rates. Additionally, the thesis employs a deep learning-based Graph Neural Network (GNN) algorithm to optimize beamforming at the base station and phase shift matrices at the RIS, bypassing complex channel estimation processes. Simulation results demonstrate that the proposed algorithm exhibits excellent performance and generalization capabilities, enabling rapid response in vehicular communication scenarios.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Research on RIS Assisted Vehicle Communication Method Based on Deep Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Hua Tan,
  • Chenguang He,
  • Dezhi Li

摘要

This thesis proposes an innovative system framework for vehicular communication utilizing Reconfigurable Intelligent Surfaces (RIS) to support millimeter-wave (mmWave) scenarios, addressing the high transmission rate demands of 6G communication. Due to significant path loss in mmWave propagation, RIS is introduced to enhance coverage and communication rates. Additionally, the thesis employs a deep learning-based Graph Neural Network (GNN) algorithm to optimize beamforming at the base station and phase shift matrices at the RIS, bypassing complex channel estimation processes. Simulation results demonstrate that the proposed algorithm exhibits excellent performance and generalization capabilities, enabling rapid response in vehicular communication scenarios.