Scholarlink

<p>The majority of Wireless Sensor Networks (WSNs) are made up of energy- and cost-efficient detecting nodes. Traditional wireless sensor networks encounter serious problems, including latency, network failure, and congestion, since they rely on individual base stations (BSs) to gather data from the whole network. Sensor nodes adjacent to the base station will use more energy because of excessive energy consumption and energy-hole constraints, affecting the network's life. Understanding the best place for mobile sink nodes can help alleviate this issue by lowering energy usage and extending the network's lifespan. In this paper, utilizing a deep learning-based energy prediction and neighbour cell score model, we build and construct an efficient method to locate mobile receivers using distance, expected energy, and fairness variables. Furthermore, a Deep Maximum Output Network (DMN) calculates the desired power. However, the minimum length, maximum residual energy, complete normalized right, maximum network lifespan, and maximum normalized throughput for our suggested neighbor-based cell scoring with Deep Maxout Network are 137.364, 30.903, 64.426, and 60.613, 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

A novel mobile sink placement in wireless sensor network using deep maxout network based energy prediction with adjacent cell score

  • 期刊论文

  • 发表日期：

    2025年10月6日

查看全文
  • U. Nilabar Nisha,
  • A. Manikandan,
  • C. Venkataramanan,
  • J. Ashok

摘要

The majority of Wireless Sensor Networks (WSNs) are made up of energy- and cost-efficient detecting nodes. Traditional wireless sensor networks encounter serious problems, including latency, network failure, and congestion, since they rely on individual base stations (BSs) to gather data from the whole network. Sensor nodes adjacent to the base station will use more energy because of excessive energy consumption and energy-hole constraints, affecting the network's life. Understanding the best place for mobile sink nodes can help alleviate this issue by lowering energy usage and extending the network's lifespan. In this paper, utilizing a deep learning-based energy prediction and neighbour cell score model, we build and construct an efficient method to locate mobile receivers using distance, expected energy, and fairness variables. Furthermore, a Deep Maximum Output Network (DMN) calculates the desired power. However, the minimum length, maximum residual energy, complete normalized right, maximum network lifespan, and maximum normalized throughput for our suggested neighbor-based cell scoring with Deep Maxout Network are 137.364, 30.903, 64.426, and 60.613, respectively.