Scholarlink

<p>The rising scenario of Internet of Things (IoT)-enabled wireless networks has led to several issues in terms of network efficiency, scalability, and energy consumption. Many times, conventional energy management techniques are unable to fit the dynamic and complicated character of contemporary IoT devices. So, the given paper introduces a hybrid deep learning (DL) framework meant to improve energy efficiency in IoT-enabled wireless networks. Using convolutional and recurrent neural network (CRNN), the proposed method dynamically optimizes resource allocation, forecasts energy consumption patterns, and improves energy harvesting tactics employing sustainable sources. The framework guarantees best performance by optimal selection of cluster heads (CH) with the help of Krill herd optimization algorithm (KHO). Extensive simulations confirm that as the number of nodes increases, the energy consumption of the proposed model decreases, eventually reaching a value of 52% lower and achieves the highest accuracy on taking different number of nodes i.e. by taking 100 nodes the accuracy is 91.89% along with 0.0309&#xa0;J of energy consumption, by taking 200 nodes the accuracy is 92.47% along with 0.0824&#xa0;J of energy consumption and by taking 100 nodes the accuracy is 93.34% along with 0.0793&#xa0;J of energy consumption.</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

CRNN-KHO: hybrid deep learning optimization framework for enhancing energy efficiency in IoT-enabled wireless networks

  • 期刊论文

  • 发表日期：

    2025年10月29日

查看全文
  • Bhimaraya Patil,
  • Kuldeep Singh,
  • Rohini Ganapathi,
  • Deepak Suresh Asudani,
  • Krishan Dutt Sharma,
  • Nidhi Sindhwani,
  • Ekta Singh

摘要

The rising scenario of Internet of Things (IoT)-enabled wireless networks has led to several issues in terms of network efficiency, scalability, and energy consumption. Many times, conventional energy management techniques are unable to fit the dynamic and complicated character of contemporary IoT devices. So, the given paper introduces a hybrid deep learning (DL) framework meant to improve energy efficiency in IoT-enabled wireless networks. Using convolutional and recurrent neural network (CRNN), the proposed method dynamically optimizes resource allocation, forecasts energy consumption patterns, and improves energy harvesting tactics employing sustainable sources. The framework guarantees best performance by optimal selection of cluster heads (CH) with the help of Krill herd optimization algorithm (KHO). Extensive simulations confirm that as the number of nodes increases, the energy consumption of the proposed model decreases, eventually reaching a value of 52% lower and achieves the highest accuracy on taking different number of nodes i.e. by taking 100 nodes the accuracy is 91.89% along with 0.0309 J of energy consumption, by taking 200 nodes the accuracy is 92.47% along with 0.0824 J of energy consumption and by taking 100 nodes the accuracy is 93.34% along with 0.0793 J of energy consumption.