PulseAugur
实时 07:12:51

Dueling DDQN optimizes LEO satellite network handovers, boosting throughput by 10.3%

Researchers have developed a new adaptive multi-objective handover framework for LEO satellite networks utilizing a dueling double deep Q-network (DDQN). This framework is designed to dynamically balance throughput, blocking probability, and switching costs in response to changing network conditions. Simulations indicate that this DDQN-based approach surpasses existing methods, offering up to a 10.3% increase in throughput and maintaining near-zero blocking rates. AI

影响 This research could lead to more efficient satellite communication by optimizing handover processes.

排序理由 This is a research paper published on arXiv detailing a new framework for satellite networks.

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

Dueling DDQN optimizes LEO satellite network handovers, boosting throughput by 10.3%

报道来源 [3]

  1. arXiv cs.LG TIER_1 English(EN) · Po-Heng Chou, Chiapin Wang, Chung-Chi Huang, Kuan-Hao Chen ·

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

    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…

  2. arXiv cs.LG TIER_1 English(EN) · Kuan-Hao Chen ·

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

    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…

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

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

    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…