Scholarlink

<p>This research evaluates the performance of a compact, lightweight, dual-band switched-beam antenna designed for 5G sub-6&#xa0;GHz communications, operating at 0.7&#xa0;GHz and 2.6&#xa0;GHz. The antenna structure integrates grooves and parasitic features to improve bandwidth performance. Three machine learning models, decision tree, random forest, and XGBoost, are utilized to optimize seven critical dimensional parameters for the achievement of broadband operation. The model is trained using 244 samples collected from 305 simulated datasets designed by CST Microwave Studio to replicate an extensive selection of conditions, targeting resonance frequencies and corresponding bandwidths. Beam steering is achieved with the incorporation of a short-circuit mechanism, allowing the antenna to guide its main beam in two directions across both frequency bands. The proposed design attains bandwidths of 21.65&#xa0;MHz at 0.63&#xa0;GHz and 192.89&#xa0;MHz at 2.48&#xa0;GHz, representing enhancements of 11.52&#xa0;MHz (113.72%) and 128.72&#xa0;MHz (200.59%), respectively, in comparison with the conventional reference antenna. The design was evaluated using simulation and empirical measurement, demonstrating significant concordance and affirming the antenna’s efficacy in beam switching and wideband dual-band functionality. Its simple structure, compact dimensions, and machine learning performance provide a promising alternative for next-generation wireless systems.</p>

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

Performance evaluation of a machine learning-driven dual broadband antenna with beam steering for 5G sub-6 GHz applications

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年1月6日

查看全文
  • Pichaya Chaipanya,
  • Nuchanart Santalunai,
  • Samran Santalunai

摘要

This research evaluates the performance of a compact, lightweight, dual-band switched-beam antenna designed for 5G sub-6 GHz communications, operating at 0.7 GHz and 2.6 GHz. The antenna structure integrates grooves and parasitic features to improve bandwidth performance. Three machine learning models, decision tree, random forest, and XGBoost, are utilized to optimize seven critical dimensional parameters for the achievement of broadband operation. The model is trained using 244 samples collected from 305 simulated datasets designed by CST Microwave Studio to replicate an extensive selection of conditions, targeting resonance frequencies and corresponding bandwidths. Beam steering is achieved with the incorporation of a short-circuit mechanism, allowing the antenna to guide its main beam in two directions across both frequency bands. The proposed design attains bandwidths of 21.65 MHz at 0.63 GHz and 192.89 MHz at 2.48 GHz, representing enhancements of 11.52 MHz (113.72%) and 128.72 MHz (200.59%), respectively, in comparison with the conventional reference antenna. The design was evaluated using simulation and empirical measurement, demonstrating significant concordance and affirming the antenna’s efficacy in beam switching and wideband dual-band functionality. Its simple structure, compact dimensions, and machine learning performance provide a promising alternative for next-generation wireless systems.