Scholarlink

This paper examines the problem of optimizing the location of the IRS to improve efficiencies in Beyond 5G networks. In order to achieve a specific performance matrix, namely Signal-to-Interference-plus-Noise Ratio (SINR), achievable rate, latency as well as throughput, a machine learning (ML) framework is employed to optimize beamforming settings. Cross-entropy optimization is one such method utilized in the study. It has been shown to be superior to conventional approaches in reconfiguring IRS elements at optimal angles for better signal emissions. The simulation results show how the effective interference, SINR, and achievable rates improve, pointing out why the IRS should be well placed to reduce the issues in the networks built for the purposes of paving the way for the evolution of 6G networks. This paper contains results on IRS placement, beamforming optimization using machine learning methods, and the design of IRS-assisted systems with a systematic comparison with the existing systems.

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

Optimization of IRS Network Using Machine Learning for Enhanced Performance in Beyond 5G Network

  • 章节

  • 发表日期：

    2025年

查看全文
  • Kalapraveen Bagadi,
  • Visalakshi Annepu,
  • Muhsin Jaber Jweeg,
  • Moneer H. Tolephih,
  • Naga Raju Challa,
  • M. N. Mohammed,
  • Oday I. Abdullah,
  • Thamer Adnan Abdullah

摘要

This paper examines the problem of optimizing the location of the IRS to improve efficiencies in Beyond 5G networks. In order to achieve a specific performance matrix, namely Signal-to-Interference-plus-Noise Ratio (SINR), achievable rate, latency as well as throughput, a machine learning (ML) framework is employed to optimize beamforming settings. Cross-entropy optimization is one such method utilized in the study. It has been shown to be superior to conventional approaches in reconfiguring IRS elements at optimal angles for better signal emissions. The simulation results show how the effective interference, SINR, and achievable rates improve, pointing out why the IRS should be well placed to reduce the issues in the networks built for the purposes of paving the way for the evolution of 6G networks. This paper contains results on IRS placement, beamforming optimization using machine learning methods, and the design of IRS-assisted systems with a systematic comparison with the existing systems.