Scholarlink

<p>Energy replenishment in Wireless Sensor Networks (WSNs) is essential to maintain continuous operation, especially when sensors have limited battery capacity. This study proposes a novel Multilayer Edge Spherical Convolutional Neural Network with Stereoscopic Scalable Quantum Adaptive Causal Decision CNN (S2QACDCNN-HSO) for efficient sequence scheduling and trajectory planning in mobile charging systems. The framework integrates Spherical CNNs with Edge Attention Networks to optimize sensor scheduling and uses a quantum-enhanced convolutional network combined with Adaptive Causal Decision Transformers (ACDT) for dynamic path optimization under obstacle and energy constraints. The Hyperbolic Sine Optimizer (HSO) adaptively tunes model parameters, improving convergence speed and reducing computational cost. Simulation results show that S2QACDCNN-HSO improves sensor lifespan by 18.7% reduces data processing latency by 17.2%, and increases charging efficiency by 25.3% compared with existing deep learning–based WSN approaches. Statistical evaluation confirms that the proposed model achieves the highest accuracy (99.8%), with significant reductions in energy consumption and trajectory deviation. Overall, the framework offers a scalable and energy-efficient solution for real-time mobile charging and adaptive trajectory control in WSNs.</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

Sequence scheduling and trajectory planning in WSNs using multilayer edge spherical CNN and optimized stereoscopic scalable quantum adaptive causal decision CNN

  • 期刊论文

  • 发表日期：

    2026年2月5日

查看全文
  • Mohamadh Shoukath Ali,
  • Chelliah Srinivasan,
  • Aparajita Mohanty,
  • Dharmesh Dhabliya

摘要

Energy replenishment in Wireless Sensor Networks (WSNs) is essential to maintain continuous operation, especially when sensors have limited battery capacity. This study proposes a novel Multilayer Edge Spherical Convolutional Neural Network with Stereoscopic Scalable Quantum Adaptive Causal Decision CNN (S2QACDCNN-HSO) for efficient sequence scheduling and trajectory planning in mobile charging systems. The framework integrates Spherical CNNs with Edge Attention Networks to optimize sensor scheduling and uses a quantum-enhanced convolutional network combined with Adaptive Causal Decision Transformers (ACDT) for dynamic path optimization under obstacle and energy constraints. The Hyperbolic Sine Optimizer (HSO) adaptively tunes model parameters, improving convergence speed and reducing computational cost. Simulation results show that S2QACDCNN-HSO improves sensor lifespan by 18.7% reduces data processing latency by 17.2%, and increases charging efficiency by 25.3% compared with existing deep learning–based WSN approaches. Statistical evaluation confirms that the proposed model achieves the highest accuracy (99.8%), with significant reductions in energy consumption and trajectory deviation. Overall, the framework offers a scalable and energy-efficient solution for real-time mobile charging and adaptive trajectory control in WSNs.