Scholarlink

<p>Wireless Sensor Networks (WSNs) play a critical role in IoT-based smart city systems, yet their performance is often affected by energy limitations, communication delays, and dynamic data conditions. To address these challenges, this paper presents a Cell Attention–based Self-Guided Deep Clustering Network optimized with the Emperor Penguin Optimizer (CASGDCNet-EPO) for IoT-WSN performance prediction. The model first estimates WSN and Internet behavior using a Cell Attention Network and subsequently integrates these outputs through a Self-Guided Deep Clustering framework. The loss function is optimized using EPO to improve prediction accuracy and stability. Simulation results demonstrate that CASGDCNet-EPO achieves reliable performance prediction with improved throughput, reduced latency, lower energy consumption, and minimized packet loss. The proposed approach provides an effective mechanism for enhancing communication reliability in IoT-driven smart city environments.</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

Performance prediction for IoT and WSN-based smart city applications using cell attention-based self-guided deep clustering network and an improved emperor penguin optimizer

  • 期刊论文

  • 发表日期：

    2026年1月12日

查看全文
  • Sudheer Nidamanuri,
  • P. Raju,
  • Balasubbareddy Mallala,
  • J Rajasekhar

摘要

Wireless Sensor Networks (WSNs) play a critical role in IoT-based smart city systems, yet their performance is often affected by energy limitations, communication delays, and dynamic data conditions. To address these challenges, this paper presents a Cell Attention–based Self-Guided Deep Clustering Network optimized with the Emperor Penguin Optimizer (CASGDCNet-EPO) for IoT-WSN performance prediction. The model first estimates WSN and Internet behavior using a Cell Attention Network and subsequently integrates these outputs through a Self-Guided Deep Clustering framework. The loss function is optimized using EPO to improve prediction accuracy and stability. Simulation results demonstrate that CASGDCNet-EPO achieves reliable performance prediction with improved throughput, reduced latency, lower energy consumption, and minimized packet loss. The proposed approach provides an effective mechanism for enhancing communication reliability in IoT-driven smart city environments.