Scholarlink

<p>In modern wireless networks, routing performance is significantly affected by congestion and malicious node behavior. This study proposes an Intelligent Flooding-Based Routing framework named HLDFP, which integrates machine learning-based traffic classification with a Horned Lizard Optimization strategy for adaptive path selection. The proposed method first monitors network traffic characteristics to identify congested and malicious nodes using a lightweight neural classification module, followed by elimination of unreliable nodes from the routing process. Subsequently, an optimized flooding mechanism is applied where route selection is guided by the Horned Lizard optimization algorithm to identify the most efficient and secure transmission path. The proposed HLDFP is implemented in an NS-3 simulation environment and evaluated under varying node densities. Experimental results demonstrate that the proposed model achieves a communication delay of 2.8&#xa0;s, throughput of 1100&#xa0;Kbps, and packet drop rate of 0.02%, outperforming traditional flooding and intelligent routing approaches. These results confirm that integrating learning-based decision-making with optimization-driven routing significantly enhances network performance and reliability.</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

HLDFP: machine learning and horned lizard optimized flooding routing for wireless networks

  • 期刊论文

  • 发表日期：

    2026年6月30日

查看全文
  • S. Mary Evanchalin,
  • R. Ravi

摘要

In modern wireless networks, routing performance is significantly affected by congestion and malicious node behavior. This study proposes an Intelligent Flooding-Based Routing framework named HLDFP, which integrates machine learning-based traffic classification with a Horned Lizard Optimization strategy for adaptive path selection. The proposed method first monitors network traffic characteristics to identify congested and malicious nodes using a lightweight neural classification module, followed by elimination of unreliable nodes from the routing process. Subsequently, an optimized flooding mechanism is applied where route selection is guided by the Horned Lizard optimization algorithm to identify the most efficient and secure transmission path. The proposed HLDFP is implemented in an NS-3 simulation environment and evaluated under varying node densities. Experimental results demonstrate that the proposed model achieves a communication delay of 2.8 s, throughput of 1100 Kbps, and packet drop rate of 0.02%, outperforming traditional flooding and intelligent routing approaches. These results confirm that integrating learning-based decision-making with optimization-driven routing significantly enhances network performance and reliability.