Scholarlink

<p>Wireless Sensor Networks (WSNs) play a vital role in bridging the physical and digital worlds, but they encounter significant challenges when handling large volumes of data. Overloading of WSNs often leads to issues such as congestion, delay, and packet loss, causing inefficiencies and information loss. Additionally, congestion increases energy consumption, shortening the overall lifespan of the network. To overcome these challenges and achieve efficient routing in WSNs, we propose an Entropy-based Softmax-Regressed and Tanimoto Reweight Grey Wolf Optimizer (ESRTRGWO) approach. This method focuses on two key processes: route path establishment and congestion-aware MIMO routing (CAR). First, the residual energy of each node is calculated and evaluated through entropy-based softmax regression (ESR). Then, the optimal routing path is selected using the TRGWO method, which considers both energy efficiency and network congestion. Performance evaluations demonstrate that the proposed ESRTRGWO approach significantly outperforms existing methods, offering improved routing efficiency, reduced congestion, and enhanced energy utilization.</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

Grey wolf optimizer with softmax-regressed and tanimoto reweight for AI-ML-based wireless sensor network routing

  • 期刊论文

  • 发表日期：

    2025年2月27日

查看全文
  • Satheesh Kumar D,
  • Satheesh Kumar N,
  • Divya R,
  • Sampath Kumar S

摘要

Wireless Sensor Networks (WSNs) play a vital role in bridging the physical and digital worlds, but they encounter significant challenges when handling large volumes of data. Overloading of WSNs often leads to issues such as congestion, delay, and packet loss, causing inefficiencies and information loss. Additionally, congestion increases energy consumption, shortening the overall lifespan of the network. To overcome these challenges and achieve efficient routing in WSNs, we propose an Entropy-based Softmax-Regressed and Tanimoto Reweight Grey Wolf Optimizer (ESRTRGWO) approach. This method focuses on two key processes: route path establishment and congestion-aware MIMO routing (CAR). First, the residual energy of each node is calculated and evaluated through entropy-based softmax regression (ESR). Then, the optimal routing path is selected using the TRGWO method, which considers both energy efficiency and network congestion. Performance evaluations demonstrate that the proposed ESRTRGWO approach significantly outperforms existing methods, offering improved routing efficiency, reduced congestion, and enhanced energy utilization.