Scholarlink

<p>An array of sensing nodes that are used to monitor, record, and organize the environmental conditions they have collected in one location is called Wireless Sensor Network (WSN). Here, the challenges regarding energy consumption during routing of data transmission. To overcome this issue, this paper proposes an Optimized Explicit Feature Interaction-Aware Graph Neural Network based Efficient Energy Management in Wireless Sensor Networks (OEFIA-GNN-EEM-WSN). The data is transmitted through cluster nodes in WSN for selecting the cluster head (CH) and the data is transmitted to a single point called Base Station (BS). During data transmission, the energy efficiency management in WSN is conserved using Explicit Feature Interaction-Aware Graph Neural Network (EFIA-GNN). Then termite life cycle optimizer (TLCO) is considered to improve the EFIA-GNN weight parameters. The OEFIA-GNN-EEM-WSN approach is implemented in MATLAB platform. The OEFIA-GNN-EEM-WSN method attains high throughput of 20.28%, 28.22%, 29.27% and 18.26%, 13.22%, and 21.27% low delay rate compared to the existing techniques: Deep learning for distributed data mining models based on LSTM for energy-efficient WSN (DL-LSTM-DDM-WSN), Machine Learning Techniques for Energy-Efficient and Secure Information Dissemination in Heterogeneous WSN (EESI-WSN-ML), and Hybrid particle swarm optimization dependent energy-efficient cluster-based routing in WSN (EEC-HPSO-WSN) in the Internet of Things respectively.</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 energy management in wireless sensor networks based on optimized explicit feature interaction-aware graph neural network

  • 期刊论文

  • 发表日期：

    2025年3月7日

查看全文
  • G. Senthilkumar,
  • R. Naveenkumar,
  • S. Rajeshkannan,
  • S. Rama Sree

摘要

An array of sensing nodes that are used to monitor, record, and organize the environmental conditions they have collected in one location is called Wireless Sensor Network (WSN). Here, the challenges regarding energy consumption during routing of data transmission. To overcome this issue, this paper proposes an Optimized Explicit Feature Interaction-Aware Graph Neural Network based Efficient Energy Management in Wireless Sensor Networks (OEFIA-GNN-EEM-WSN). The data is transmitted through cluster nodes in WSN for selecting the cluster head (CH) and the data is transmitted to a single point called Base Station (BS). During data transmission, the energy efficiency management in WSN is conserved using Explicit Feature Interaction-Aware Graph Neural Network (EFIA-GNN). Then termite life cycle optimizer (TLCO) is considered to improve the EFIA-GNN weight parameters. The OEFIA-GNN-EEM-WSN approach is implemented in MATLAB platform. The OEFIA-GNN-EEM-WSN method attains high throughput of 20.28%, 28.22%, 29.27% and 18.26%, 13.22%, and 21.27% low delay rate compared to the existing techniques: Deep learning for distributed data mining models based on LSTM for energy-efficient WSN (DL-LSTM-DDM-WSN), Machine Learning Techniques for Energy-Efficient and Secure Information Dissemination in Heterogeneous WSN (EESI-WSN-ML), and Hybrid particle swarm optimization dependent energy-efficient cluster-based routing in WSN (EEC-HPSO-WSN) in the Internet of Things respectively.