Scholarlink

<p>Wireless networks face significant challenges in achieving optimal routing while minimizing energy consumption and preventing packet collisions. This paper proposes an intelligent hybrid framework that integrates fuzzy logic-based adaptive clustering with machine learning (ML)-driven collision avoidance to enhance network efficiency and stability. The proposed model employs fuzzy logic to enable cluster head selection and network organization based on uncertain parameters such as signal strength, transmission distance, and residual energy. By incorporating an adaptive clustering mechanism, the network achieves flexible and self-organizing routing structures. Furthermore, ML algorithms leverage historical collision records and real-time link-state information to predict and prevent collision incidents, thereby improving data transmission reliability. The routing protocol dynamically adapts to network conditions to ensure energy-efficient paths without compromising data quality. Experimental evaluations demonstrate that the proposed framework significantly reduces energy consumption, minimizes collision occurrences, and extends network lifetime compared to conventional routing protocols. This approach offers a scalable and intelligent solution for modern wireless communication 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

Fuzzy logic adaptive clustering with ML-based collision avoidance for wireless networks

  • 期刊论文

  • 发表日期：

    2026年1月27日

查看全文
  • S Vimalnath,
  • B Deepalakshmi

摘要

Wireless networks face significant challenges in achieving optimal routing while minimizing energy consumption and preventing packet collisions. This paper proposes an intelligent hybrid framework that integrates fuzzy logic-based adaptive clustering with machine learning (ML)-driven collision avoidance to enhance network efficiency and stability. The proposed model employs fuzzy logic to enable cluster head selection and network organization based on uncertain parameters such as signal strength, transmission distance, and residual energy. By incorporating an adaptive clustering mechanism, the network achieves flexible and self-organizing routing structures. Furthermore, ML algorithms leverage historical collision records and real-time link-state information to predict and prevent collision incidents, thereby improving data transmission reliability. The routing protocol dynamically adapts to network conditions to ensure energy-efficient paths without compromising data quality. Experimental evaluations demonstrate that the proposed framework significantly reduces energy consumption, minimizes collision occurrences, and extends network lifetime compared to conventional routing protocols. This approach offers a scalable and intelligent solution for modern wireless communication systems.