Scholarlink

Our study puts forth an innovative solution for energy optimization in 5G networks through a combination of reinforcement learning (RL) and Built-In Self-Test (BIST) architectures. Our proposed RL model adapts power levels and operational states based on changing network demands and conditions, all while prioritizing minimal energy usage and high service quality. Initial results demonstrate a marked increase in energy efficiency compared to conventional methods, leading to reduced energy consumption and improved network adaptability and resilience. This study lays the groundwork for practical applications of energy-optimized network operations.

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

Reinforcement Learning for Energy Efficiency in 5G Networks with Built-In Self-Test Architecture

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Suhas B. Shirol,
  • S. Ramakrishna,
  • Rajashekar B. Shettar

摘要

Our study puts forth an innovative solution for energy optimization in 5G networks through a combination of reinforcement learning (RL) and Built-In Self-Test (BIST) architectures. Our proposed RL model adapts power levels and operational states based on changing network demands and conditions, all while prioritizing minimal energy usage and high service quality. Initial results demonstrate a marked increase in energy efficiency compared to conventional methods, leading to reduced energy consumption and improved network adaptability and resilience. This study lays the groundwork for practical applications of energy-optimized network operations.