Scholarlink

<p>Energy consumption has become a critical challenge in next-generation wireless communication systems, particularly with the rise of Ultra-Dense Networks (UDNs) in fifth-generation (5G) architectures. While UDNs improve coverage and capacity through dense deployment of Small Cell Base stations (SBSs) alongside Macro Base Stations (MBSs), they also introduce substantial power demands especially from underutilized SBSs during periods of low traffic. To address this inefficiency, a novel Predictive Energy Aware BS Sleeping (PEAS) model is proposed that dynamically adapts SBS operational states based on real-time traffic patterns. The PEAS framework integrates Bidirectional LSTM-based traffic prediction with a convexified, multi-objective Grasshopper Optimization Algorithm (GOA) to optimize energy consumption while maintaining Quality of Service (QoS). The system supports four adaptive SBS modes and incorporates penalties for frequent transitions and prediction uncertainty, making it resilient to both short- and long-term traffic fluctuations. Simulation results of the proposed model achieves a 26–27% improvement in energy efficiency and a 22% gain in spectral efficiency, outperforming conventional methods and state-of-the-art deep reinforcement learning and heuristic optimization approaches.</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

Energy-efficient adaptive sleep mode control in cellular networks using grasshopper optimization and Traffic-aware QoS management

  • 期刊论文

  • 发表日期：

    2026年2月16日

查看全文
  • Nilakshee Rajule,
  • Mithra Venkatesan,
  • Radhika Menon,
  • Anju Kulkarni,
  • Rajeshree Raut

摘要

Energy consumption has become a critical challenge in next-generation wireless communication systems, particularly with the rise of Ultra-Dense Networks (UDNs) in fifth-generation (5G) architectures. While UDNs improve coverage and capacity through dense deployment of Small Cell Base stations (SBSs) alongside Macro Base Stations (MBSs), they also introduce substantial power demands especially from underutilized SBSs during periods of low traffic. To address this inefficiency, a novel Predictive Energy Aware BS Sleeping (PEAS) model is proposed that dynamically adapts SBS operational states based on real-time traffic patterns. The PEAS framework integrates Bidirectional LSTM-based traffic prediction with a convexified, multi-objective Grasshopper Optimization Algorithm (GOA) to optimize energy consumption while maintaining Quality of Service (QoS). The system supports four adaptive SBS modes and incorporates penalties for frequent transitions and prediction uncertainty, making it resilient to both short- and long-term traffic fluctuations. Simulation results of the proposed model achieves a 26–27% improvement in energy efficiency and a 22% gain in spectral efficiency, outperforming conventional methods and state-of-the-art deep reinforcement learning and heuristic optimization approaches.