Scholarlink

<p>The proposed study of this paper introduces an AI-Enhanced Quality-of-Service (QoS) model for 6G networks, which will improve the performance of CR networks functioning under heavy interference and exhausted resources. The proposed model utilizes DRL-based resource allocation with adaptive SC to combat multipath fading. Simulations show that our proposed system achieved 45% higher throughput and 38% lower latency compared to standard QoS management techniques as well as a 50% reduction in BER when the proposed model was able to dynamically vary the transmission parameters. The proposed AI-driven solution consistently maintained a Signal-to-Interference-plus-Noise Ratio (SINR) above 12&#xa0;dB in a heavily interfered environment with less than 5% packet loss in a highly congested network. Also, the model has a quality-of-service stability margin above 90% in highly dynamic environments, a significant improvement over current state-of-the-art QoS models. Official Explanation Statement of 6G results suggest that traditional QoS mechanisms may not provide sufficient support for future 6G network implementations. This research promotes the development of resilient self-optimizing wireless systems required to enable URLLC for 6G networks.</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

AI-enhanced QoS modeling in 6G networks with selection combining in fading environments and interference analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年5月19日

查看全文
  • Keshav Kaushik,
  • Gunjan Chhabra,
  • Deepak Upadhyay

摘要

The proposed study of this paper introduces an AI-Enhanced Quality-of-Service (QoS) model for 6G networks, which will improve the performance of CR networks functioning under heavy interference and exhausted resources. The proposed model utilizes DRL-based resource allocation with adaptive SC to combat multipath fading. Simulations show that our proposed system achieved 45% higher throughput and 38% lower latency compared to standard QoS management techniques as well as a 50% reduction in BER when the proposed model was able to dynamically vary the transmission parameters. The proposed AI-driven solution consistently maintained a Signal-to-Interference-plus-Noise Ratio (SINR) above 12 dB in a heavily interfered environment with less than 5% packet loss in a highly congested network. Also, the model has a quality-of-service stability margin above 90% in highly dynamic environments, a significant improvement over current state-of-the-art QoS models. Official Explanation Statement of 6G results suggest that traditional QoS mechanisms may not provide sufficient support for future 6G network implementations. This research promotes the development of resilient self-optimizing wireless systems required to enable URLLC for 6G networks.