Scholarlink

<p>Efficient packet routing is essential to manage the vast data generated by Internet of Things (IoT) devices, which can strain network performance. Traditional Mobile Ad hoc Network (MANET) routing protocols rely on neighbour information for network views but discard routing history after packet delivery, limiting their efficiency. This research introduces a Machine Learning (ML)-based routing approach that leverages historical routing decisions to train predictive models, enabling nodes to make intelligent routing choices. We evaluate Decision Trees (DT), Support Vector Machines (SVM), and Artificial Neural Networks (ANN) as alternatives to conventional routing protocols, such as Ad hoc On-demand Distance Vector (AODV). Simulation results in an IoT-connected smart city scenario show that our approach reduces control message overhead by up to 73%, improving network efficiency by optimizing load distribution, energy consumption, and packet delay. These results demonstrate the potential of ML-driven routing to significantly extend the operational lifetime of IoT networks compared to traditional methods.</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

Machine Learning Based Routing Protocol (MLBRP) for Mobile Internet of Things Networks

  • 期刊论文

  • 发表日期：

    2025年6月18日

查看全文
  • Nour El Houda Larouci,
  • Somia Sahraoui,
  • Abdelhamid Djeffal

摘要

Efficient packet routing is essential to manage the vast data generated by Internet of Things (IoT) devices, which can strain network performance. Traditional Mobile Ad hoc Network (MANET) routing protocols rely on neighbour information for network views but discard routing history after packet delivery, limiting their efficiency. This research introduces a Machine Learning (ML)-based routing approach that leverages historical routing decisions to train predictive models, enabling nodes to make intelligent routing choices. We evaluate Decision Trees (DT), Support Vector Machines (SVM), and Artificial Neural Networks (ANN) as alternatives to conventional routing protocols, such as Ad hoc On-demand Distance Vector (AODV). Simulation results in an IoT-connected smart city scenario show that our approach reduces control message overhead by up to 73%, improving network efficiency by optimizing load distribution, energy consumption, and packet delay. These results demonstrate the potential of ML-driven routing to significantly extend the operational lifetime of IoT networks compared to traditional methods.