研究人员开发了一种新的自适应多目标切换框架，用于LEO卫星网络，该框架利用了Dueling Double Deep Q-Network (DDQN)。该框架旨在根据不断变化的網絡状况，动态平衡吞吐量、阻塞概率和切换成本。模拟结果表明，这种基于DDQN的方法优于现有方法，吞吐量最高可提高10.3%，同时保持接近零的阻塞率。 AI
影响 这项研究通过优化切换过程，有望实现更高效的卫星通信。
排序理由 这是一篇发表在arXiv上的研究论文，详细介绍了一种用于卫星网络的新框架。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2605.02416v1 Announce Type: cross Abstract: In this paper, we propose a dueling double deep Q-network (DDQN)-based adaptive multi-objective handover framework for LEO satellite networks. The proposed method enables dynamic trade-off learning among throughput, blocking proba…
In this paper, we propose a dueling double deep Q-network (DDQN)-based adaptive multi-objective handover framework for LEO satellite networks. The proposed method enables dynamic trade-off learning among throughput, blocking probability, and switching cost under time-varying netw…
In this paper, we propose a dueling double deep Q-network (DDQN)-based adaptive multi-objective handover framework for LEO satellite networks. The proposed method enables dynamic trade-off learning among throughput, blocking probability, and switching cost under time-varying netw…