arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.02416cs.ITcs.LGmath.IT
收藏

对抗DDQN-based自适应多目标切换优化用于低轨道卫星网络

Dueling DDQN-Based Adaptive Multi-Objective Handover Optimization for LEO Satellite Networks

Research Center for Information Technology Innovation (CITI), Academia Sinica (AS)(信息科技创新研究中心(CITI),学术院(AS));Department of Electrical Engineering, National Taiwan Normal University (NTNU)(电气工程系,国立台湾师范大学(NTNU));Bradley Department of Electrical and Computer Engineering (ECE), Virginia Tech (VT)(电气与计算机工程系(ECE),弗吉尼亚理工大学(VT))

Po-Heng Chou, Chiapin Wang, Chung-Chi Huang, Kuan-Hao Chen

AI总结:

本文提出基于对抗DDQN的自适应多目标切换框架,用于低轨道卫星网络,在时间变化网络条件下实现吞吐量、阻塞概率和切换成本的动态权衡,仿真结果表明性能优于传统方法。

摘要:

本文提出了一种基于对抗双深度Q网络(DDQN)的自适应多目标切换框架,用于低地球轨道(LEO)卫星网络。所提出的方法在时间变化的网络条件下实现了吞吐量、阻塞概率和切换成本之间的动态权衡。仿真结果表明,所提出的方法在典型运行条件下优于传统基线方法,实现了高达10.3%的吞吐量提升和接近零的阻塞概率。

英文摘要:

In this paper, we propose a dueling double deep Q-network (DDQN)-based adaptive multi-objective handover framework for low Earth orbit (LEO) satellite networks. The proposed method enables dynamic trade-off learning among throughput, blocking probability, and switching cost under time-varying network conditions. Simulation results demonstrate that the proposed approach consistently outperforms conventional baselines, achieving up to 10.3% throughput improvement and near-zero blocking under typical operating conditions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑