Scholarlink

This paper examines the application of deep-Q learning (DQL) to improve performance in UAV/IRS-assisted non-orthogonal cognitive radio (CR) systems. Taking advantage of the flexible deployment of UAVs and intelligent reflecting surfaces (IRS), signal transmission between the ground base station (SGBS) and the destination users is assisted by UAV/IRS in the secondary network. The total system capacity is considered a primary metric and is presented in simulation results to highlight the outperformance of the proposed method when considering the influence of different system parameters. Finally, this work highlights the potential of DQL in enabling intelligent and efficient operation of next-generation UAV/IRS-assisted NOMA-CR communication 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

Deep-Q Learning-Based Performance Enhancement in UAV/IRS-Aided NOMA Cognitive Radio Systems

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Anh Le-Thi,
  • Ton Nguyen-Quy,
  • Thuc Kieu-Xuan,
  • My Binh Nguyen-Thi,
  • Hong Nguyen-Thi

摘要

This paper examines the application of deep-Q learning (DQL) to improve performance in UAV/IRS-assisted non-orthogonal cognitive radio (CR) systems. Taking advantage of the flexible deployment of UAVs and intelligent reflecting surfaces (IRS), signal transmission between the ground base station (SGBS) and the destination users is assisted by UAV/IRS in the secondary network. The total system capacity is considered a primary metric and is presented in simulation results to highlight the outperformance of the proposed method when considering the influence of different system parameters. Finally, this work highlights the potential of DQL in enabling intelligent and efficient operation of next-generation UAV/IRS-assisted NOMA-CR communication networks.