Scholarlink

<p>The development of 6G communication systems presents major obstacles for an effective network model, primarily due to the elevated costs and complexities associated with measurements across various scenarios and frequency ranges. Predictive channel modeling has surfaced as a viable and practical approach to tackle these issues. This research introduces an innovative framework, the Feedforward convolutional graph attention network with Groupers and Moray Eels (FCAGME), which is integrated with a gated recurrent unit. This framework is specifically designed to capture both spatial and temporal dependencies within the frequency domain. As a result, it facilitates accurate predictions of unknown frequency band characteristics by utilizing insights derived from existing channel measurements. Furthermore, this approach incorporates a Groupers and Moray Eels optimization algorithm to refine the parameters of FCAGME, thereby enhancing training stability and efficiently optimizing loss and error parameters. The proposed methodology demonstrates exceptional performance, achieving a channel prediction rate of 97.8%, an accuracy of 98.6%, a frequency prediction rate of 65&#xa0;MHz, a mean squared error of 0.015, a mean absolute error of 0.009, and a root mean squared error of 0.132, surpassing the performance of current methods. In summary, the FCAGME framework provides a precise, stable, and efficient solution for predictive channel modeling in 6G 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

Optimized feedforward convolutional graph attention-based frequency domain predictive channel model for 6G wireless MIMO communications

  • 期刊论文

  • 发表日期：

    2025年11月18日

查看全文
  • Ranjitham Govindasamy,
  • Debarati Sen,
  • Jamuna Rani Muthu,
  • Sathish Kumar Nagarajan

摘要

The development of 6G communication systems presents major obstacles for an effective network model, primarily due to the elevated costs and complexities associated with measurements across various scenarios and frequency ranges. Predictive channel modeling has surfaced as a viable and practical approach to tackle these issues. This research introduces an innovative framework, the Feedforward convolutional graph attention network with Groupers and Moray Eels (FCAGME), which is integrated with a gated recurrent unit. This framework is specifically designed to capture both spatial and temporal dependencies within the frequency domain. As a result, it facilitates accurate predictions of unknown frequency band characteristics by utilizing insights derived from existing channel measurements. Furthermore, this approach incorporates a Groupers and Moray Eels optimization algorithm to refine the parameters of FCAGME, thereby enhancing training stability and efficiently optimizing loss and error parameters. The proposed methodology demonstrates exceptional performance, achieving a channel prediction rate of 97.8%, an accuracy of 98.6%, a frequency prediction rate of 65 MHz, a mean squared error of 0.015, a mean absolute error of 0.009, and a root mean squared error of 0.132, surpassing the performance of current methods. In summary, the FCAGME framework provides a precise, stable, and efficient solution for predictive channel modeling in 6G systems.