摘要
海洋物联网的发展对超密集低轨卫星网络的通信质量提出了更高要求,传统固定规则切换策略难以适应低轨卫星的高速运动,易导致频繁切换。参考第一期星链计划进行星座建模,提出一种基于多智能体深度强化学习的智能卫星切换策略,通过构建分层决策架构将传统阈值判决与强化学习优化相结合,利用多终端协同机制实现资源协调,考虑载噪比、仰角和剩余服务时间等多维指标,设计综合奖励函数引导智能体学习最优切换策略。仿真结果表明,在超密集星座环境下,该策略平均接入成功率可达92.4%,较传统方法提升13%以上,且在高负载场景仍保持77.6%的稳定性能。虽然切换频率有所上升,但通过主切换有效保障了通信的连续,为解决海洋物联网间歇性连接问题提供了创新的解决方案。
The development of the maritime Internet of things(IoT)imposes higher demands on the communication quality of ultra-dense low Earth orbit(LEO)satellite networks.Traditional fixed-rule handover strategies struggle to adapt to the high-speed motion of LEO satellites,often leading to frequent handovers.This study,referencing the first phase of the Starlink project for constellation modeling,proposes an intelligent handover strategy based on multi-agent deep reinforcement learning.A hierarchical decision-making architecture is constructed to combine traditional threshold-based decision-making with reinforcement learning optimization.Leveraging a multi-terminal collaboration mechanism,it achieves global resource coordination.Multi-dimensional metrics,including carrier-to-noise ratio,elevation angle,and remaining service time,are comprehensively considered to design a comprehensive reward function that guides the agents to learn the optimal handover strategy.Simulation results demonstrate that in an ultra-dense constellation environment,this strategy achieves an average access success rate of 92.4%,an improvement of over 13%compared to traditional methods.Furthermore,it maintains stable performance of 77.6%even under high-load scenarios.Although the handover frequency increases,the continuity of communication is effectively ensured through primary handovers.This provides a novel solution to address the intermittent connectivity issues in the maritime IoT.
作者
葛富源
张申虎
闫实
GE Fuyuan;ZHANG Shenhu;YAN Shi(School of Information and Communication Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China)
出处
《南京邮电大学学报(自然科学版)》
北大核心
2026年第1期56-65,共10页
Journal of Nanjing University of Posts and Telecommunications(Natural Science Edition)
基金
国家自然科学基金联合基金重点项目(U21A20444)
国家自然科学基金(62371067)资助项目。
关键词
超密集低轨卫星网络
切换策略
星座建模
多智能体深度强化学习
ultra-dense low Earth orbit(LEO)satellite networks
handover strategy
constellation modeling
multi-agent deep reinforcement learning
