Scholarlink

<p>In today's technological landscape, Wireless Sensor Networks (WSNs) are crucial for a wide range of advanced applications, where nodes are strategically deployed within their respective domains. A key challenge in WSN deployment is extending network lifetime while ensuring optimal coverage and minimal energy consumption. Recent works have explored sensor placement using swarm intelligence and heuristic-based strategies. However, these approaches often suffer from local optima, slow convergence, and inefficient energy utilization during repositioning. Moreover, techniques that overlook spatial topology struggle to maintain coverage consistency as node density changes. To solve these issues, this research proposes a novel hybrid approach that integrates Delaunay Triangulation and Glowworm Swarm Optimization algorithm (DT-GSOA) with a 1D-Convolutional Neural Network (1D-CNN), termed 1D-CNN_DT-GSOA. This approach aims to optimize sensor placement to reduce energy consumption by minimizing the distance required to reach the optimal positions. This approach ensures comprehensive and persistent coverage within the WSN. By implementing an optimal radius strategy, the model conserves the energy of sensor nodes. By leveraging the GSOA, 1D-CNN, and the DT cell structure, this solution effectively maximizes coverage, improves network lifetime, and minimizes energy consumption. The optimal sensing radius is determined using the DT cell structure, and the GSOA guides sensors to converge towards the centroid of this structure for optimal placement. The 1D-CNN_DT-GSOA approach demonstrates impressive performance, achieving 96% energy efficiency, a throughput of 400 kbps, a network lifetime of 1100&#xa0;s, an end-to-end delay of 0.6&#xa0;s, and a coverage rate of 96.3%.</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

Optimizing energy efficiency and coverage in wireless sensor networks using Delaunay Triangulation and glowworm swarm optimization

  • 期刊论文

  • 发表日期：

    2025年10月30日

查看全文
  • Senthil Perumal,
  • J. Vijayaraj,
  • D. Prabakar

摘要

In today's technological landscape, Wireless Sensor Networks (WSNs) are crucial for a wide range of advanced applications, where nodes are strategically deployed within their respective domains. A key challenge in WSN deployment is extending network lifetime while ensuring optimal coverage and minimal energy consumption. Recent works have explored sensor placement using swarm intelligence and heuristic-based strategies. However, these approaches often suffer from local optima, slow convergence, and inefficient energy utilization during repositioning. Moreover, techniques that overlook spatial topology struggle to maintain coverage consistency as node density changes. To solve these issues, this research proposes a novel hybrid approach that integrates Delaunay Triangulation and Glowworm Swarm Optimization algorithm (DT-GSOA) with a 1D-Convolutional Neural Network (1D-CNN), termed 1D-CNN_DT-GSOA. This approach aims to optimize sensor placement to reduce energy consumption by minimizing the distance required to reach the optimal positions. This approach ensures comprehensive and persistent coverage within the WSN. By implementing an optimal radius strategy, the model conserves the energy of sensor nodes. By leveraging the GSOA, 1D-CNN, and the DT cell structure, this solution effectively maximizes coverage, improves network lifetime, and minimizes energy consumption. The optimal sensing radius is determined using the DT cell structure, and the GSOA guides sensors to converge towards the centroid of this structure for optimal placement. The 1D-CNN_DT-GSOA approach demonstrates impressive performance, achieving 96% energy efficiency, a throughput of 400 kbps, a network lifetime of 1100 s, an end-to-end delay of 0.6 s, and a coverage rate of 96.3%.