Scholarlink

This paper tackles the issue of reducing beamforming switching time while ensuring Quality of Service (QoS) in 6G Vehicle-to-Everything (V2X) communication systems. We introduce a Deep Reinforcement Learning (DRL) framework employing Proximal Policy Optimization (PPO) to optimize base station beamforming switching times, thereby improving communication efficiency and reliability for connected vehicles. By reducing switching time and maintaining QoS, our solution improves overall network performance, representing a notable advancement for autonomous and connected vehicle systems. Our findings demonstrate that PPO is a promising approach for enhancing V2X communication, optimizing network performance, and maintaining consistent QoS, setting the stage for future research in complex vehicular networks.

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

DRL Framework for Minimizing Beam Switching Time and Maintaining QoS in 6G-V2X Base Stations

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Ali Belgacem,
  • Abbas Bradai

摘要

This paper tackles the issue of reducing beamforming switching time while ensuring Quality of Service (QoS) in 6G Vehicle-to-Everything (V2X) communication systems. We introduce a Deep Reinforcement Learning (DRL) framework employing Proximal Policy Optimization (PPO) to optimize base station beamforming switching times, thereby improving communication efficiency and reliability for connected vehicles. By reducing switching time and maintaining QoS, our solution improves overall network performance, representing a notable advancement for autonomous and connected vehicle systems. Our findings demonstrate that PPO is a promising approach for enhancing V2X communication, optimizing network performance, and maintaining consistent QoS, setting the stage for future research in complex vehicular networks.