引用本文:陈永,康婕.玻尔兹曼优化Q-learning的高速铁路越区切换控制算法[J].控制理论与应用,2025,42(4):688~694.[点击复制]
CHEN Yong,KANG Jie.Boltzmann optimized Q-learning algorithm for high-speed railway handover control[J].Control Theory & Applications,2025,42(4):688~694.[点击复制]
玻尔兹曼优化Q-learning的高速铁路越区切换控制算法
Boltzmann optimized Q-learning algorithm for high-speed railway handover control
摘要点击 2  全文点击 0  投稿时间:2023-12-23  修订日期:2025-02-04
查看全文  查看/发表评论  下载PDF阅读器
DOI编号  10.7641/CTA.2024.30825
  2025,42(4):688-694
中文关键词  越区切换  5G-R  Q-learning算法  玻尔兹曼优化策略
英文关键词  handover  5G-R  Q-learning algorithm  Boltzmann optimize strategy
基金项目  国家自然科学基金项目(62462043,61963023),兰州交通大学重点研发项目(ZDYF2304)资助.
作者单位E-mail
陈永* 兰州交通大学电子与信息工程学院 edukeylab@126.com 
康婕 兰州交通大学电子与信息工程学院  
中文摘要
      针对5G-R高速铁路越区切换使用固定切换阈值,且忽略了同频干扰、乒乓切换等的影响,导致越区切换成 功率低的问题,提出了一种玻尔兹曼优化Q-learning的越区切换控制算法.首先,设计了以列车位置–动作为索引 的Q表,并综合考虑乒乓切换、误码率等构建Q-learning算法回报函数;然后,提出玻尔兹曼搜索策略优化动作选择, 以提高切换算法收敛性能;最后,综合考虑基站同频干扰的影响进行Q表更新,得到切换判决参数,从而控制切换执 行. 仿真结果表明:改进算法在不同运行速度和不同运行场景下,较传统算法能有效提高切换成功率,且满足无线 通信服务质量QoS的要求.
英文摘要
      Aiming at the problem of using a fixed handover threshold for 5G-R high-speed railway cross section han dover and ignoring the effects of same frequency interference and ping-pong handover, which leads to a low success rate of cross section handover, a cross section handover control algorithm based on Boltzmann optimized Q-learning is proposed. Firstly, a Q-table with train position action as the index was designed, and a Q-learning algorithm return function was con structed by comprehensively considering ping pong handover, bit error rate, and other factors. Then, a Boltzmann search strategy is proposed to optimize action selection and improve the convergence performance of the handover algorithm. Finally, taking into account the impact of co frequency interference of base stations, the Q-table is updated to obtain the handover decision parameters, thereby controlling the handover execution. The simulation results show that the improved algorithm can effectively enhance the handover success rate compared to traditional algorithms under different operating speeds and scenarios, and meet the Quality of Service (QoS) requirements of wireless communication systems.