研究生: |
桑翊軒 Sang, Yi-Hsuan |
---|---|
論文名稱: |
基於深度強化學習的6G衛星網路換手策略 Hanover Strategy for 6G Satellite Networks Based on Deep Reinforcement Learning |
指導教授: |
蔡明哲
Tsai, Ming-Jer |
口試委員: |
郭桐惟
Kuo, Tung-Wei 郭建志 Kuo, Jian-Jhih |
學位類別: |
碩士 Master |
系所名稱: |
電機資訊學院 - 資訊工程學系 Computer Science |
論文出版年: | 2024 |
畢業學年度: | 112 |
語文別: | 英文 |
論文頁數: | 27 |
中文關鍵詞: | 頻道利用效率 、低地球軌道衛星網路 、強化學習 、衛星換手 、6G換手 |
外文關鍵詞: | Channel utilization efficiency, LEO satellite network, Reinforcement learning, satellite handover, 6G handover |
相關次數: | 點閱:3 下載:0 |
分享至: |
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
在現代移動通信網絡中,低地球軌道(LEO)衛星在實現全球個人通訊方面起著至
關重要的作用。由於這些衛星在太空中的密集部署,地球上任何地方的用戶都可以
同時被多個衛星覆蓋。因為衛星的移動速度比大多數移動使用者(即使是乘坐商業
飛機的使用者)要快得多,這導致了大量的衛星切換,進而造成巨大的負擔。用戶
在只從其視角觀察到衛星的特定訊息時,需要為衛星頻道而苦苦掙扎。因此,需要
一個全面的衛星換手策略來有效平衡衛星負載並防止網路堵塞。該策略應確保網路
保持高效和可靠,盡量減少超載的風險。此外,必須盡可能降低訊號消耗,以保持
最佳性能並減少不必要的數據流量。通過實施這樣的策略,網路可以在高需求下為
用戶提供無縫和一致的服務。
In modern mobile communication networks, Low Earth Orbit (LEO) satellites play a crucial role in enabling global personal communication. Due to the dense deployment of these satellites in space, users located anywhere on the planet can be covered by multiple satellites simultaneously. Since the satellites travel at higher speeds than most mobile users, even those in a commercial jet, this results in a large number of satellite handovers, which can cause a heavy, leading to significant signaling burden. Otherwise, users need to struggle for satellite channels while they only observe specific information about satellites from their viewpoint. Thus, a comprehensive satellite handover strategy is required to effectively balance the satellite load and prevent network congestion. This strategy should ensure that the network remains efficient and reliable, minimizing the risk of overloads. Additionally, the signaling overhead must be kept as low as possible to maintain optimal performance and reduce unnecessary data traffic. By implementing such a strategy, the network can provide seamless and consistent service to users, even under high demand.
1] A. A. Siddiqi, Sputnik and the Soviet Space Challenge. University Press of Florida, 2003.
[2] 3GPP, “3GPP TS 22.261: Service requirements for the 5G system;
Stage 1,” 3rd Generation Partnership Project (3GPP), Tech. Rep., 2018,
https://www.3gpp.org/DynaReport/22261.htm.
[3] J. R. Wertz and W. J. Larson, Space Mission Analysis and Design. Springer Science Business Media, 1999.
[4] P. Chitre and F. Yegenoglu, “Next-generation satellite networks: Ar- chitectures and implementations,” IEEE Commun. Mag., vol. 37, no. 3, pp. 30–36, 1999.
[5] A. Jamalipour and T. Tung, “The role of satellites in global it: Trends and implications,,” IEEE Pers. Commun., vol. 8, no. 3, pp. 5–11, 2001.
[6] Y. Su et al., “A survey of handover management in low earth orbit (leo) satellite networks,” Wireless Personal Communications, vol. 111, no. 4, pp. 2141–2161,
2020.
[7] 3GPP, “Technical specification group radio access network; evolved
universal terrestrial radio access (e-utra); radio resource control (rrc); protocol specification,” 3rd Generation Partnership Project (3GPP), Tech. Rep. TS 36.331, version 16.0.0, 2020,https://www.3gpp.org/ftp/Specs/archive/36series/36.331/36331 − g60.zip.
[8] R. Xie et al., “Handover management in leo satellite networks: A survey,” IEEECommunications Surveys Tutorials, vol. 22, no. 4, pp.2472–2496, 2020.
[9] Q. Zhang et al., “Load balancing in leo satellite networks with inter-satellite links,”IEEE Transactions on Communications, vol. 47, no. 5, pp. 717–728, 1999.
[10] T. W. Shuxin He and S. Wang, “Load-aware satellite handover strategy based on multi-agent reinforcement learning,” 2020.26
[11] V. Mnih et al., “Asynchronous methods for deep reinforcement learning,” in Proceed-ings of the 33rd International Conference on Machine Learning (ICML), 2016, pp.1928–1937.
[12] R. S. Sutton and A. G. Barto, Reinforcement Learning: An Introduction. MIT Press,2018