請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/101562完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 魏宏宇 | zh_TW |
| dc.contributor.advisor | Hung-Yu Wei | en |
| dc.contributor.author | 李語婕 | zh_TW |
| dc.contributor.author | Yu-Chieh Lee | en |
| dc.date.accessioned | 2026-02-11T16:22:47Z | - |
| dc.date.available | 2026-02-12 | - |
| dc.date.copyright | 2026-02-11 | - |
| dc.date.issued | 2025 | - |
| dc.date.submitted | 2025-11-20 | - |
| dc.identifier.citation | [1] I. U. of Railways. (2023) Frmcs: Future railway mobile communication system. [Online]. Available: https://uic.org/rail-system/telecoms-signalling/frmcs#UGFA-Report-technical-aspects
[2] FRMCS Functional Working Group, “Future railway mobile communication system user requirements specification,” pp. 1–120, 2019. [3] R. He, B. Ai, Z. Zhong, M. Yang, R. Chen, J. Ding, Z. Ma, G. Sun, and C. Liu, “5g for railways: Next generation railway dedicated communications,” IEEE Communications Magazine, vol. 60, no. 12, pp. 130–136, 2022. [4] Z. Cao, Y. Qin, L. Jia, Z. Xie, Y. Gao, Y. Wang, P. Li, and Z. Yu, “Railway intrusion detection based on machine vision: A survey, challenges, and perspectives,” IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 7, pp. 6427–6448, 2024. [5] ETSI, “Mobile edge computing (mec); framework and reference architecture,” ETSI, DGS MEC, vol. 3, pp. 1–18, 2016. [6] J. Sheng, X. Cai, Q. Li, C. Wu, B. Ai, Y. Wang, M. Kadoch, and P. Yu, “Space-airground integrated network development and applications in high-speed railways: A survey,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 8, pp. 10 066–10 085, 2022. [7] H.-T. Chen, Y. Chiang, and H.-Y. Wei, “Edge computing resource management for cross-camera video analytics: Workload and model adaptation,” IEEE Access, vol. 12, pp. 12 098–12 109, 2024. [8] S. S. Sefati, A. U. Haq, Nidhi, R. Craciunescu, S. Halunga, A. Mihovska, and O. Fratu, “A comprehensive survey on resource management in 6g network based on internet of things,” IEEE Access, vol. 12, pp. 113 741–113 784, 2024. [9] Q. Zhang, C. Zhang, J. Zhao, D. Wang, and W. Xu, “Dynamic resource allocation for multi-access edge computing in urban rail transit,” IEEE Transactions on Vehicular Technology, vol. 74, no. 2, pp. 3296–3310, 2025. [10] W. Wu, H. Song, M. Zhou, X. Song, and H. Dong, “Game based task offloading in cyber-physical systems for high-speed railway with dynamic latency and energy cost,” IEEE Transactions on Industrial Cyber-Physical Systems, vol. 2, pp. 292–302, 2024. [11] J. Xu, B. Ai, L. Chen, Y. Cui, and N. Wang, “Deep reinforcement learning for computation and communication resource allocation in multiaccess mec assisted railway iot networks,” IEEE Transactions on Intelligent Transportation Systems, vol. 23, no. 12, pp. 23 797–23 808, 2022. [12] T. Gong, L. Zhu, F. R. Yu, and T. Tang, “Train-to-edge cooperative intelligence for obstacle intrusion detection in rail transit,” IEEE Transactions on Vehicular Technology, vol. 73, no. 6, pp. 7669–7680, 2024. [13] L. Zhu, Y. Liang, and Y. Li, “Toward optimal train control: An edge computing approach with adaptive computation offloading,” IEEE Internet of Things Journal, vol. 12, no. 8, pp. 10 601–10 612, 2025. [14] J. Zhao, L. He, D. Zhang, and X. Gao, “A tp-ddpg algorithm based on cache assistance for task offloading in urban rail transit,” IEEE Transactions on Vehicular Technology, vol. 72, no. 8, pp. 10 671–10 681, 2023. [15] Q. Guo, Z. Xu, J. Yuan, and Y. Wei, “Cloud-edge collaboration-based task offloading strategy in railway iot for intelligent detection,” Wireless Networks, vol. 31, no. 2, pp. 1361–1376, 2025. [16] L. Zhu, S. Lin, F. R. Yu, and Y. Li, “Collaborative computing optimization in trainedge-cloud-based smart train systems using risk-sensitive reinforcement learning,”IEEE Transactions on Vehicular Technology, vol. 73, no. 3, pp. 3129–3141, 2024. [17] L. Zhu, T. Gong, S. Wei, and F. R. Yu, “Collaborative train and edge computing in edge intelligence based train autonomous operation control systems,” IEEE Transactions on Intelligent Transportation Systems, vol. 25, no. 9, pp. 11 991–12 004, 2024. [18] Q. Guo, Z. Xu, J. Yuan, and Y. Wei, “Computation offloading strategy for detection task in railway iot with integrated sensing, storage, and computing,” Electronics, vol. 13, no. 15, p. 2982, 2024. [19] W. Wu, H. Song, H. Wang, and H. Dong, “Potential game based task offloading in the high-speed railway with reinforcement learning,” IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 11, pp. 12 671–12 685, 2023. [20] L. Li, Y. Niu, S. Mao, B. Ai, Z. Zhong, N. Wang, and Y. Chen, “Resource allocation and computation offloading in a millimeter-wave train-ground network,” IEEE Transactions on Vehicular Technology, vol. 71, no. 10, pp. 10 615–10 630, 2022. [21] Y. Fang, M. Li, F. R. Yu, P. Si, R. Yang, C. Gao, and Y. Sun, “Parallel offloading and resource optimization for multi-hop ad hoc network-enabled cbtc with mobile edge computing,” IEEE Transactions on Vehicular Technology, vol. 73, no. 2, pp. 2684–2698, 2024. [22] K. Boutiba, M. Bagaa, and A. Ksentini, “Radio link failure prediction in 5g networks,”in 2021 IEEE Global Communications Conference (GLOBECOM), 2021, pp. 1–6. [23] S. Aktaş, H. Alemdar, and S. Ergüt, “Towards 5g and beyond radio link diagnosis: Radio link failure prediction by using historical weather, link parameters,” Computers and Electrical Engineering, vol. 99, p. 107742, 2022. [24] K. Hasan, K. Papry, T. Trappenberg, and I. Haque, “A generalized gnn-transformerbased radio link failure prediction framework in 5g ran,” IEEE Transactions on Machine Learning in Communications and Networking, pp. 1–1, 2025. [25] K. Danilchenko, N. Lazmi, and M. Segal, “Online learning framework for radio link failure prediction in fanets,” in 2023 18th Conference on Computer Science and Intelligence Systems (FedCSIS), 2023, pp. 41–48. [26] S. Vigneshwaran, P. Vignesh, R. Anuradha, and N. Sathishkumar, “5g radio link failure prediction using quantum machine learning,” in 2023 International Conference on Quantum Technologies, Communications, Computing, Hardware and Embedded Systems Security (iQ-CCHESS), 2023, pp. 1–5. [27] T. Gong, L. Zhu, F. R. Yu, and T. Tang, “Edge intelligence in intelligent transportation systems: A survey,” IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 9, pp. 8919–8944, 2023. [28] IEEE standard for edge/fog manageability and orchestration, IEEE standard 1935-2023, 2023. [29] T.-Y. Chen, Y. Chiang, J.-H. Wu, H.-T. Chen, C.-C. Chen, and H.-Y. Wei, “Ieee p1935 edge/fog manageability and orchestration: Standard and usage example,” in 2023 IEEE International Conference on Edge Computing and Communications (EDGE), 2023, pp. 96–103. [30] D. Reis, J. Kupec, J. Hong, and A. Daoudi, “Real-time flying object detection with yolov8,” arXiv preprint arXiv:2305.09972, 2023. [31] S.-S. Yang, “Radio link failure prediction and adaptive band locking for reliable 5g non-standalone dual-radio networks,” Master’s thesis, Department of Electrical Engineering, National Taiwan University, 2025. [32] T. C. Government, “Taipei metro station-wise hourly entry and exit statistics,” https://data.taipei/dataset/detail?id=63f31c7e-7fc3-418b-bd82-b95158755b4d, 2024, accessed: 2025-03-05. [33] Ultralytics, “Ultralytics yolo docs,” https://docs.ultralytics.com/, 2023, accessed: 2025-02-20. [34] Ultralytics, “Ultralytics,” https://github.com/ultralytics/ultralytics, 2022, accessed: 2025-02-20. [35] P. Zhu, L. Wen, D. Du, X. Bian, H. Fan, Q. Hu, and H. Ling, “Detection and tracking meet drones challenge,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 44, no. 11, pp. 7380–7399, 2021. [36] VisDrone, “Visdrone-dataset,” https://github.com/VisDrone/VisDrone-Dataset, 2019, accessed: 2025-02-14. [37] Prometheus, “Prometheus,” https://github.com/prometheus/prometheus, 2012, accessed: 2025-03-01. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/101562 | - |
| dc.description.abstract | 在5G鐵路通訊系統以及對營運效率和安全性至關重要的各種新興應用情境中，實現視訊偵測的低端到端延遲至關重要。邊緣運算雖具發展潛力，但也帶來了嚴峻挑戰，特別是在受限且動態條件下的高效資源管理問題。此外，鐵路環境固有的高移動性，經常導致不穩定的通訊品質，這是一個關鍵挑戰，可透過無線鏈路故障(RLF)預測模型來主動應對。儘管邊緣運算中的資源管理與RLF預測兩個領域各自存在大量研究，但這兩個關鍵領域在很大程度上仍未整合。再者，既有的資源管理研究常假設為單支線的鐵路系統，從而限制了所提出解決方案在現實多支線環境中的實際適用性和通用性。為了解決這些限制，我們提出了一種新穎的混合式-GGA方法，該方法利用RLF預測結果來動態決定鐵路邊緣運算中的資源分配和任務卸載策略，旨在優化每個時段的整體系統效能。我們的方法透過涵蓋五種不同情境的全面模擬進行評估，並使用真實世界數據集。實證結果突顯了RLF預測的顯著影響，並證明了所提出方法在不同鐵路支線和運作情境下相較於基準方法的卓越效能，從而驗證了其穩健性和通用性。 | zh_TW |
| dc.description.abstract | In the context of 5G-enabled railway communication systems and emerging applications critical for operational efficiency and safety, achieving low end-to-end latency for video detection is essential. While promising, edge computing introduces significant challenges, especially concerning efficient resource management under constrained and dynamic conditions. Furthermore, the inherent high mobility of railway environments frequently results in unstable communication quality, a critical challenge that can be proactively addressed through Radio Link Failure (RLF) prediction models. Despite extensive individual research on resource management in edge computing and on RLF prediction, these two crucial areas largely remain unintegrated. Moreover, prior work in resource management frequently assumes single-branch railway systems, thereby limiting the practical applicability and generality of proposed solutions in realistic multi-branch environments. To address these limitations, we propose a novel Hybrid-GGA approach which leverages RLF prediction results to dynamically determine resource allocation and task offloading strategies for railway edge computing, with the objective of optimizing overall system performance in each timeslot. Our method is evaluated through comprehensive simulations across five distinct scenarios, utilizing a real-world dataset. The empirical results highlight the significant impact of RLF prediction and demonstrate the proposed method's superior effectiveness compared to baselines across diverse railway branches and operational scenarios, thereby validating its robustness and generality. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2026-02-11T16:22:47Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2026-02-11T16:22:47Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 口試委員會審定書 i
誌謝 ii 摘要 iii Abstract iv Contents vi List of Figures viii List of Tables ix Chapter 1. Introduction 1 1.1 Background and Challenges 1 1.2 Motivation and Our Proposal 2 1.3 Contributions 3 1.4 Organizations 4 Chapter 2. Related Work 5 2.1 Resource Allocation and Task Offloading in Edge Computing 7 2.2 Multi-branch-awareness in HSR Scenario 8 2.3 RLF-awareness 9 2.4 Summary 10 Chapter 3. System Model 11 3.1 System Architecture 11 3.2 Wireless Throughput Model 15 3.3 Latency Model 17 3.4 Performance Model 18 Chapter 4. Problem Formulation 19 4.1 Main Problem Formulation 20 4.2 Step1: Prediction 21 4.2.1 RLF Prediction 21 4.2.2 Occupancy and Resource Status Prediction 22 4.3 Step2: Resource Allocation and Task Offloading 23 4.3.1 Greedy-based Method 23 4.3.2 GA-based Method 24 4.3.3 Hybrid-GGA Method 24 Chapter 5. Evaluation 29 5.1 Simulation Settings 29 5.2 Performance Comparison 32 Chapter 6. Conclusion 41 Bibliography 43 | - |
| dc.language.iso | en | - |
| dc.subject | 邊緣運算 | - |
| dc.subject | 無線鏈路故障預測 | - |
| dc.subject | 資源分配 | - |
| dc.subject | 任務卸載 | - |
| dc.subject | 鐵路通訊系統 | - |
| dc.subject | Edge Computing | - |
| dc.subject | RLF Prediction | - |
| dc.subject | Resource Allocation | - |
| dc.subject | Task Offloading | - |
| dc.subject | Railway Communication System | - |
| dc.title | 具鐵路系統無線鏈路故障預測之最佳化邊緣運算資源分配 | zh_TW |
| dc.title | Optimized Edge Computing Resource Allocation with RLF Prediction in Railway System | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 114-1 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 沈上翔;王志宇 | zh_TW |
| dc.contributor.oralexamcommittee | Shan-Hsiang Shen;Chih-Yu Wang | en |
| dc.subject.keyword | 邊緣運算,無線鏈路故障預測資源分配任務卸載鐵路通訊系統 | zh_TW |
| dc.subject.keyword | Edge Computing,RLF PredictionResource AllocationTask OffloadingRailway Communication System | en |
| dc.relation.page | 47 | - |
| dc.identifier.doi | 10.6342/NTU202501590 | - |
| dc.rights.note | 未授權 | - |
| dc.date.accepted | 2025-11-21 | - |
| 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-114-1.pdf 未授權公開取用 | 2.7 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。