請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/96367完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 廖婉君 | zh_TW |
| dc.contributor.advisor | Wan jiun Liao | en |
| dc.contributor.author | 王梓旭 | zh_TW |
| dc.contributor.author | Tzu Hsu Wang | en |
| dc.date.accessioned | 2025-02-13T16:08:38Z | - |
| dc.date.available | 2025-02-14 | - |
| dc.date.copyright | 2025-02-13 | - |
| dc.date.issued | 2024 | - |
| dc.date.submitted | 2025-01-24 | - |
| dc.identifier.citation | [1] X. Chen, C. Xu, M. Wang, Z. Wu, S. Yang, L. Zhong, and G.-M. Muntean. A uni versal transcoding and transmission method for livecast with networked multi-agen reinforcement learning. In IEEE INFOCOM 2021-IEEE Conference on Compute Communications, pages 1–10. IEEE, 2021.
[2] M. M. Gost, I. Leyva-Mayorga, A. Pérez-Neira, M. Á. Vázquez, B. Soret, an M. Moretti. Edge computing and communication for energy-efficient earth surveil lance with leo satellites. In 2022 IEEE International Conference on Communication Workshops (ICC Workshops), pages 556–561. IEEE, 2022. [3] Q. He, C. Zhang, X. Ma, and J. Liu. Fog-based transcoding for crowdsourced vide livecast. IEEE Communications Magazine, 55(4):28–33, 2017. [4] B. Hofmann-Wellenhof, H. Lichtenegger, J. Collins, B. Hofmann-Wellenhof H. Lichtenegger, and J. Collins. Transformation of GPS results. Global Positionin System: Theory and Practice, pages 279–307, 2001. [5] C. Li, Y. Zhang, R. Xie, X. Hao, and T. Huang. Integrating edge computing into lo earth orbit satellite networks: Architecture and prototype. Ieee Access, 9:39126 39137, 2021. [6] Z. Luo, Z. Wang, J. Chen, M. Hu, Y. Zhou, T. Z. Fu, and D. Wu. Crowdsr: En abling high-quality video ingest in crowdsourced livecast via super-resolution. I Proceedings of the 31st ACM Workshop on Network and Operating Systems Suppor for Digital Audio and Video, pages 90–97, 2021. [7] V. Mnih, K. Kavukcuoglu, D. Silver, A. Graves, I. Antonoglou, D. Wierstra, an M. Riedmiller. Playing atari with deep reinforcement learning. arXiv preprin arXiv:1312.5602, 2013. [8] K. Spiteri, R. Urgaonkar, and R. K. Sitaraman. Bola: Near-optimal bitrate adaptatio for online videos. IEEE/ACM transactions on networking, 28(4):1698–1711, 2020. [9] Y. Su, Y. Liu, Y. Zhou, J. Yuan, H. Cao, and J. Shi. Broadband leo satellite com munications: Architectures and key technologies. IEEE Wireless Communications 26(2):55–61, 2019. [10] F. Wang, J. Liu, C. Zhang, L. Sun, and K. Hwang. Intelligent edge learning fo personalized crowdsourced livecast: Challenges, opportunities, and solutions. IEE Network, 35(1):170–176, 2021. [11] F. Wang, C. Zhang, J. Liu, Y. Zhu, H. Pang, L. Sun, et al. Intelligent edge assisted crowdcast with deep reinforcement learning for personalized qoe. In IEE INFOCOM 2019-IEEE Conference on Computer Communications, pages 910–918. IEEE, 2019. [12] S. Wang and Q. Li. Satellite computing: Vision and challenges. IEEE Internet o Things Journal, 2023. [13] Y. Yang, M. Xu, D. Wang, and Y. Wang. Towards energy-efficient routing in satellit networks. IEEE Journal on Selected Areas in Communications, 34(12):3869–3886 2016. [14] Q. Zeng, Y. Zhuang, J. Hai, Q. Pan, Z. Yin, Q. Chen, and J. Liang. Challenges of live cast computing network: A contemporary survey. In 2023 International Conferenc on Networking and Network Applications (NaNA), pages 690–697. IEEE, 2023. [15] C. Zhang, J. Liu, and H. Wang. Cloud-assisted crowdsourced livecast. AC Transactions on Multimedia Computing, Communications, and Application (TOMM), 13(3s):1–22, 2017. [16] R. Zhang, C. Yang, X. Wang, T. Huang, C. Wu, J. Liu, and L. Sun. Practical cloud edge scheduling for large-scale crowdsourced live streaming. IEEE Transactions o Parallel and Distributed Systems, 34(7):2055–2071, 2023. [17] W. Zhang, Z. Xu, F. Wang, and J. Liu. Proffler: Towards collaborative and scalabl edge-assisted crowdsourced livecast. IEEE Internet of Things Journal, 2023. [18] Y. Zheng, D. Wu, Y. Ke, C. Yang, M. Chen, and G. Zhang. Online cloud transcodin and distribution for crowdsourced live game video streaming. IEEE Transactions o Circuits and Systems for Video Technology, 27(8):1777–1789, 2016. [19] Y. Zhu, J. Liu, Z. Wang, and C. Zhang. When cloud meets uncertain crowd: A auction approach for crowdsourced livecast transcoding. In Proceedings of the 25t ACM international conference on Multimedia, pages 1372–1380, 2017. [20] X. Zou, R. Xie, Q. Tang, and T. Huang. Joint transmission and transcoding in com puting power networks for livecast: A quantum-inspired optimization approach. I 2024 IEEE Wireless Communications and Networking Conference (WCNC), page 1–6. IEEE, 2024. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/96367 | - |
| dc.description.abstract | 在眾包直播中，觀眾端的觀看環境和對使用者體驗和偏好有異質性，導致如何符合成本效益地優化觀眾使用者體驗成了前所未有的挑戰。透過低軌衛星進行傳輸有望成為一個解決方案。然而，衛星的移動性、計算資源以及能源限制也成為了一大考驗。因此，本文提出資源分配的解決方案。基於直播主、衛星網路和觀眾的大量實時信息做出智能決策。而考慮到在這種背景下的過高計算複雜性，我們提出搭配深度強化學習的解決方案，能夠自動學習最合適的觀眾調度和轉碼選擇策略。 | zh_TW |
| dc.description.abstract | In crowdsourced live streaming, the diverse viewing environments and user experience preferences present significant challenges in cost-effectively optimizing audience experience. Transmission via low Earth orbit (LEO) satellites shows promise but also faces challenges due to mobility, computing resources, and energy constraints. This paper proposes a resource allocation solution. By leveraging real-time information from broadcasters, satellite networks, and viewers, we aim to meet user experience demands while minimizing system costs. Given the high computational complexity, we incorporate deep reinforcement learning (DRL) to automatically learn optimal strategies for viewer scheduling and transcoding selection. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2025-02-13T16:08:37Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2025-02-13T16:08:38Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | Acknowledgements i
摘要 ii Abstract iii Contents iv List of Figures vi List of Tables vii Chapter 1 Introduction 1 1.1 Crowdsourced Live Streaming 1 1.2 LEO Satellite Networks 4 Chapter 2 Related work 7 2.1 Crowdsourced live streaming 7 2.1.1 Cloud Based Method 7 2.1.2 Edge-assisted Method 7 2.1.3 End-assisted Method 8 2.2 Satellite Edge Computing 9 2.3 Challenge and Motivation 9 Chapter 3 System Model 12 3.1 Satellite Model 12 3.2 Transcoding Model 15 3.3 Communication Model 15 3.4 Computation Model 17 3.5 QoE Model 18 3.6 Energy Model 19 3.6.1 Energy Absorption Model 19 3.6.2 Energy Consumption Model 19 Chapter 4 Problem Formulation 21 Chapter 5 Proposed Method 23 5.1 DRL Model Design 27 5.1.1 State 28 5.1.2 Action 29 5.1.3 Reward Design 30 5.1.4 Training Process 30 5.2 Path Finding 31 Chapter 6 Experiment Results 33 Chapter 7 Conclusion 39 References 40 | - |
| dc.language.iso | en | - |
| dc.title | 低軌道衛星網絡中基於深度強化學習的衛星輔助群眾外包直播 | zh_TW |
| dc.title | LEO-assisted Crowdsourced Livecast with Deep Reinforcement Learning on Satellite Networks | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 113-1 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 郭耀煌;林宗男;陳俊良 | zh_TW |
| dc.contributor.oralexamcommittee | Yau-Hwang Kuo;Tsung-Nan Lin;Jiann-Liang Chen | en |
| dc.subject.keyword | 低軌道衛星,衛星邊緣運算,眾包直播,深度強化學習, | zh_TW |
| dc.subject.keyword | Low Earth Orbit,Satellite Edge Computing,Crowdsourced Livecast,Deep Reinforcement Learning, | en |
| dc.relation.page | 42 | - |
| dc.identifier.doi | 10.6342/NTU202500030 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2025-01-25 | - |
| dc.contributor.author-college | 電機資訊學院 | - |
| dc.contributor.author-dept | 電機工程學系 | - |
| dc.date.embargo-lift | N/A | - |
| 顯示於系所單位： | 電機工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-113-1.pdf 目前未授權公開取用 | 5.38 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。