Scholarlink

<p>Wireless Sensor Networks (WSNs) are a vital technology for data collection in inaccessible and remote regions, offering applications across healthcare, environmental monitoring and industrial automation. Sensor nodes have limited energy resources, which poses significant challenges to WSN longevity and efficiency. This paper introduces an innovative approach to improve energy efficiency in WSNs by integrating Chaotic Particle Swarm Optimization (CPSO) for cluster head selection and employing an Attention-Based Recurrent Neural Network (RNN) for data routing. In WSNs, nodes are organized into clusters and the selection of a Cluster Head (CH) greatly influences network performance and energy consumption. To enhance this decision-making process, Chaotic Particle Swarm Optimization is introduced. CPSO seeks to optimize CH selection by considering chaotic behavior and swarm intelligence, resulting in robust and adaptive cluster head decisions. Furthermore, an Attention-Based RNN routing strategy is introduced. This intelligent routing mechanism optimizes the routing of data packets throughout the network, promoting energy efficiency while preserving data integrity and accuracy. Attention mechanisms enable the RNN to focus on crucial information and make informed routing decisions. A significant contribution of this research is the synergy of CPSO for CH selection and an Attention-Based RNN for routing, promising to extend the operational lifespan of WSNs and improve their overall efficiency. By incorporating chaos-based optimization and attention-driven routing, this approach offers a comprehensive solution for addressing the energy constraints in WSNs.</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

Efficient cluster head selection and routing in wireless sensor networks using CPSO and Attention-based RNN

  • 期刊论文

  • 发表日期：

    2025年9月19日

查看全文
  • R. Dinesh,
  • D. Venkata Srihari Babu,
  • V. Arun Antony,
  • Uma Reddy

摘要

Wireless Sensor Networks (WSNs) are a vital technology for data collection in inaccessible and remote regions, offering applications across healthcare, environmental monitoring and industrial automation. Sensor nodes have limited energy resources, which poses significant challenges to WSN longevity and efficiency. This paper introduces an innovative approach to improve energy efficiency in WSNs by integrating Chaotic Particle Swarm Optimization (CPSO) for cluster head selection and employing an Attention-Based Recurrent Neural Network (RNN) for data routing. In WSNs, nodes are organized into clusters and the selection of a Cluster Head (CH) greatly influences network performance and energy consumption. To enhance this decision-making process, Chaotic Particle Swarm Optimization is introduced. CPSO seeks to optimize CH selection by considering chaotic behavior and swarm intelligence, resulting in robust and adaptive cluster head decisions. Furthermore, an Attention-Based RNN routing strategy is introduced. This intelligent routing mechanism optimizes the routing of data packets throughout the network, promoting energy efficiency while preserving data integrity and accuracy. Attention mechanisms enable the RNN to focus on crucial information and make informed routing decisions. A significant contribution of this research is the synergy of CPSO for CH selection and an Attention-Based RNN for routing, promising to extend the operational lifespan of WSNs and improve their overall efficiency. By incorporating chaos-based optimization and attention-driven routing, this approach offers a comprehensive solution for addressing the energy constraints in WSNs.