Basic Search / Detailed Display

Author: 沈家葳
Chia-Wei Shen
Thesis Title: 車聯網聯合系統中具多重故障之容錯設計及卸載:架構、優化及分析
Offloading along with Fault Tolerance Design in the V2X-Based Federated System with Multiple Failures: Architecture, Optimization, and Analysis
Advisor: 馮輝文
Huei-Wen Ferng
Committee: 周詩梵
Shih-Fan Chou
張時中
Shi-Chung Chang
黎明富
Ming-Fu Li
Degree: 碩士
Master
Department: 電資學院 - 資訊工程系
Department of Computer Science and Information Engineering
Thesis Publication Year: 2023
Graduation Academic Year: 111
Language: 中文
Pages: 117
Keywords (in Chinese): 工作卸載設備故障車載網路服務品質違反機率最佳化容錯
Keywords (in other languages): Offloading, Device Failure, V2X, Quality of Service Violation Probability, Optimization, Fault Tolerance
Reference times: Clicks: 259Downloads: 0
Share:
School Collection Retrieve National Library Collection Retrieve Error Report

車聯網 (Vehicle-to-Everything, V2X) 是5G 無線技術提供的服務之一。V2X 中的數據流量(Data Flow)需要通信和計算,而工作卸載(Task Offloading)預期為解決V2X計算的有效方法。目前,多數的卸載研究討論在演算法以及平均降低延遲之上,並無對設備可能故障進行較深入的討論及提出有效的容錯(Fault Tolerance)解決方法。因此,本碩士論文在保證車輛服務的服務品質(Quality of Service, QoS)的同時,亦考慮設備具潛在故障,以達到更周延的考量與卸載之設計。首先,本碩士論文參考[1]之二層卸載架構,亦即將路側設備(Road Side Unit, RSU) 和基地台(gNodeB, gNB) 的聯合卸載架構做適度擴充,加入鄰近車輛(Nearby Vehicles),同時讓gNB由多個伺服器(Mutiple Servers)組成;此外,提出上述三種設備潛在故障出現時的容錯方法。最後,以最小化QoS違反機率(QoS violation probability)下,透過最佳化問題(Optimization Problem Formulation)形成找到最佳工作卸載路徑機率來最小化平均封包延遲等效能。為了優化gNB之多個伺服器效能,伺服器間的負載平衡(Load Balancing)設計也納入考量,工作延遲可近一步優化,而透過模擬以及驗證過後的分析結果,我們不僅呈現所提出之聯合卸載架構較[1]之架構可有效提升整體系統的QoS以及降低工作的封包平均延遲外,更能展現對潛在伺服器故障之容錯能力,而三種卸載容錯設計之系統動態(System Dynamics)也充分被探討,以推薦最佳之卸載容錯設計。


Vehicle-to-everything (V2X) is one of the services provided by the 5th generation (5G) mobile communication system. Data flows in V2X require communication and computing and task offloading is expected to be an effective approach to solve the V2X computing. Up to now, most offloading research merely discusses algorithm design and average delay reduction without conducting in-depth issues, e.g., possible device failures, thus proposing effective fault tolerance solutions. Therefore, this thesis considers the potential device failures to achieve a more thoughtful consideration on the offloading design while ensuring the quality of service (QoS) requested vehicles by vehicles. First of all, this thesis will modify the two-layer offloading architecture proposed by [1], i.e., the federated offloading architecture composed of road side unit (RSU) and gNodeB (gNB), to further incorporate the nearby vehicles to form the three-layer federated offloading architecture and allow the gNB to be supported by multiple servers. In addition, we shall propose the fault tolerance for the after mentioned three kinds of devices with potential failures. Lastly, the optimization problem is formulated to find the probability of each task offloading path by minimizing the QoS violation probability, to minimize the performance measure such as the average task delay. In order to optimize the performance of the multiple servers of gNB, a load balancing design among servers is further taken into consideration, reaching the optimized task delay. Via simulations and the validated analytical results, we not only demonstrate that our proposed federated offloading architecture outperforms the architecture proposed by [1] for effectively improving the QoS of the overall system and reducing the average task delay but also exhibit excellent capability of fault tolerance to potential server failures. Consequently, the system dynamics of the three fault-tolerance designs for offloading are fully examined to reveal the best fault-tolerant design among the three proposed solutions.

論文指導教授推薦書 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . i 考試委員審定書 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ii 中文摘要 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iii 英文摘要 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iv 誌謝 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vi 目錄 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vii 表目錄 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xi 圖目錄 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . xii 第一章、緒論 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.1 研究背景 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.2 車聯網之介紹 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.3 最大加權匹配 (Maximum Weight Matching, MWM) 演算法 . . . . . . 4 1.4 工作任務卸載 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.5 研究動機 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 1.6 論文組織 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 第二章、相關文獻回顧 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.1 降低計算能耗之相關文獻 . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.2 降低任務延遲之相關文獻 . . . . . . . . . . . . . . . . . . . . . . . . . 9 2.3 工作任務卸載之相關文獻 . . . . . . . . . . . . . . . . . . . . . . . . . 10 2.4 卸載失敗或伺服器故障之相關文獻 . . . . . . . . . . . . . . . . . . . 11 2.5 與相近論文之比較與貢獻 . . . . . . . . . . . . . . . . . . . . . . . . . 11 第三章、機制設計 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13 3.1 問題描述 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 3.2 環境架構與模型 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 14 3.2.1 FID 方法設計 . . . . . . . . . . . . . . . . . . . . . . . . . . . 16 3.2.2 PRD 方法設計 . . . . . . . . . . . . . . . . . . . . . . . . . . . 20 3.2.3 SDP 方法設計 . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 3.2.4 剩餘空間配對 (Remaining Space Matching, RSM) 演算法 . . . 30 第四章、系統效能分析 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 33 4.1 服務品質違反機率分析 . . . . . . . . . . . . . . . . . . . . . . . . . . 33 4.1.1 FID 之服務品質違反機率分析 . . . . . . . . . . . . . . . . . . 37 4.1.2 PRD 之服務品質違反機率分析 . . . . . . . . . . . . . . . . . . 40 4.1.3 SDP 之服務品質違反機率分析 . . . . . . . . . . . . . . . . . . 45 4.2 平均工作延遲時間分析 . . . . . . . . . . . . . . . . . . . . . . . . . . 49 4.2.1 FID 之平均工作延遲時間分析 . . . . . . . . . . . . . . . . . . 50 4.2.2 PRD 之平均工作延遲時間分析 . . . . . . . . . . . . . . . . . . 52 4.2.3 SDP 之平均工作延遲時間分析 . . . . . . . . . . . . . . . . . . 54 4.3 工作丟棄機率分析 . . . . . . . . . . . . . . . . . . . . . . . . . . . . 56 4.3.1 NF 之工作丟棄機率分析 . . . . . . . . . . . . . . . . . . . . . 57 4.3.2 FID 之工作丟棄機率分析 . . . . . . . . . . . . . . . . . . . . . 57 4.3.3 PRD 之工作丟棄機率分析 . . . . . . . . . . . . . . . . . . . . 58 4.4 平均服務時間暫停時間分析 . . . . . . . . . . . . . . . . . . . . . . . 59 4.4.1 FID 之平均服務時間暫停時間分析 . . . . . . . . . . . . . . . 60 4.4.2 PRD 之平均服務時間暫停時間分析 . . . . . . . . . . . . . . . 61 第五章、模擬結果數值討論與分析 . . . . . . . . . . . . . . . . . . . . . . . . 63 5.1 模擬與分析之間的驗證 . . . . . . . . . . . . . . . . . . . . . . . . . . 63 5.2 設計模型討論 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 65 5.3 不同任務封包抵達率討論 . . . . . . . . . . . . . . . . . . . . . . . . . 67 5.4 不同基地台服務速率討論 . . . . . . . . . . . . . . . . . . . . . . . . . 69 5.5 不同的路側設備服務速率討論 . . . . . . . . . . . . . . . . . . . . . . 72 5.6 不同的鄰近車輛服務速率討論 . . . . . . . . . . . . . . . . . . . . . . 74 5.7 不同的任務延遲門檻 η 討論 . . . . . . . . . . . . . . . . . . . . . . . 76 5.8 不同的故障門檻 ω 討論 . . . . . . . . . . . . . . . . . . . . . . . . . . 79 5.9 不同的鄰近車輛分布參數討論 . . . . . . . . . . . . . . . . . . . . . . 81 第六章、結論 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 84 參考文獻 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 85 附錄 A:QoS violation probability . . . . . . . . . . . . . . . . . . . . . . . . 90 A.1 三個節點串聯佇列之服務品質違反機率 . . . . . . . . . . . . . . . . . 90 A.2 四個節點串聯佇列之服務品質違反機率 . . . . . . . . . . . . . . . . . 91 A.2.1 包含 M/M/1 之節點模型討論 . . . . . . . . . . . . . . . . . . . 91 A.2.2 包含 M/M/C 之節點模型討論 . . . . . . . . . . . . . . . . . . 92 A.3 五個節點串聯佇列之服務品質違反機率 . . . . . . . . . . . . . . . . . 94 附錄 B:次梯度搜尋 (Sub-Gradient Search, SGS) 演算法 . . . . . . . . . . . . . 97 附錄 C:各個機制平均工作延遲 . . . . . . . . . . . . . . . . . . . . . . . . . . 99 D.1 NF(No Failure) 各路徑之平均工作延遲推導 . . . . . . . . . . . . . . . 99 D.2 FID 各路徑之平均工作延遲推導 . . . . . . . . . . . . . . . . . . . . . 100 D.3 PRD 各路徑之平均工作延遲推導 . . . . . . . . . . . . . . . . . . . . . 100 D.4 SDP 各路徑之平均工作延遲推導 . . . . . . . . . . . . . . . . . . . . . 102

[1] R.-H. Hwang, M. M. Islam, M. A. Tanvir, M. S. Hossain, and Y.-D. Lin, “Communication and Computation Offloading for 5G V2X: Modeling and Optimization,” in Proc. GLOBECOM 2020 - 2020 IEEE Global Communications Conference, pp. 1–6, Jan. 2020.
[2] Y. Hu, T. Cui, X. Huang, and Q. Chen, “Task Offloading Based on Lyapunov Optimization for MEC-assisted Platooning,” in Proc. 2019 11th International Conference on Wireless Communications and Signal Processing (WCSP), pp. 1–5, Dec. 2019.
[3] F. Ding, Z. Ma, Z. Li, R. Su, D. Zhang, and H. Zhu, “A Terminal-Oriented Distributed Traffic Flow Splitting Strategy for Multi-Service of V2X Networks,” Electronics, vol. 8, no. 6, Apr. 2019.
[4] Z. Ning, X. Wang, J. J. P. C. Rodrigues, and F. Xia, “Joint Computation Offloading, Power Allocation, and Channel Assignment for 5G-Enabled Traffic Management Systems,” IEEE Transactions on Industrial Informatics, vol. 15, no. 5, pp. 3058– 3067, Jan. 2019.
[5] Z. Zhou, F. Xiong, C. Xu, Y. He, and S. Mumtaz, “Energy-Efficient Vehicular Heterogeneous Networks for Green Cities,” IEEE Transactions on Industrial Informatics, vol. 14, no. 4, pp. 1522–1531, Nov. 2018.
[6] D. Xu, Y. Li, X. Chen, J. Li, P. Hui, S. Chen, and J. Crowcroft, “A Survey of Opportunistic Offloading,” IEEE Communications Surveys and Tutorials, vol. 20, no. 3, pp. 2198–2236, Feb. 2018.
[7] F. P. Rezha and S. Y. Shin, “Performance Analysis of ISA100.11a Under Interference From an IEEE 802.11b Wireless Network,” IEEE Transactions on Industrial Informatics, vol. 10, no. 2, pp. 919–927, Feb. 2014
[8] R. Iyengar and B. Sikdar, “A Queueing Model for Polled Service in WiMAX/IEEE
802.16 Networks,” IEEE Transactions on Communications, vol. 60, no. 7, pp. 1777–
1781, May 2012.
[9] K. Kim, S. Koo, and J.-W. Choi, “Analysis on Path Rerouting Algorithm based on V2X Communication for Traffic Flow Improvement,” in Proc. 2020 International
Conference on Information and Communication Technology Convergence (ICTC),
pp. 251–254, Dec. 2020.
[10] K. Abboud, H. A. Omar, and W. Zhuang, “Interworking of DSRC and Cellular
Network Technologies for V2X Communications: A Survey,” IEEE Transactions
on Vehicular Technology, vol. 65, no. 12, pp. 9457–9470, Jul. 2016.
[11] X. Hu, S. Xu, L. Wang, Y. Wang, Z. Liu, L. Xu, Y. Li, and W. Wang, “A Joint
Power and Bandwidth Allocation Method based on Deep Reinforcement Learning
for V2V Communications in 5G,” China Communications, vol. 18, no. 7, pp. 25–35,
Jul. 2021.
[12] S. Chen, J. Hu, Y. Shi, Y. Peng, J. Fang, R. Zhao, and L. Zhao, “Vehicle-to-Everything (V2X) Services Supported by LTE-Based Systems and 5G,” IEEE Communications Standards Magazine, vol. 1, no. 2, pp. 70–76, Jul. 2017.
[13] T. Deinlein, M. Roshdi, T. Nan, T. Heyn, A. Djanatliev, and R. German, “On the
Impact of Priority-based MAC Layer Scheduling in 5G V2N Multi-Application
Scenarios,” in Proc. 2021 13th IFIP Wireless and Mobile Networking Conference
(WMNC), pp. 63–70, Dec. 2021.
[14] J. Kwon and H. Park, “Reliable Data Dissemination Strategy based on Systematic Network Coding in V2I Networks,” in Proc. 2019 International Conference on Information and Communication Technology Convergence (ICTC), pp. 744–746, Dec. 2019.
[15] R. Hasan and R. Hasan, “Towards a Threat Model and Privacy Analysis for V2P
in 5G Networks,” in Proc. 2021 IEEE 4th 5G World Forum (5GWF), pp. 383–387,
Nov. 2021.
[16] G. Im, J. B. Kim, J. G. Ryu, and S. K. Park, “Downlink link-level Simulator
designs for 3GPP Rel. 16 NR Non-Terrestrial Networks,” in 2022 27th Asia Pacific
Conference on Communications (APCC), pp. 647–648, Nov. 2022.
[17] H. Halabian, I. Lambadaris, and C.-H. Lung, “Optimal Server Assignment in
Multi-server Parallel Queueing Systems With Random Connectivities and Random Service
Failures,” in Proc. 2012 IEEE International Conference on Communications (ICC),
pp. 1219–1224, Nov. 2012.
[18] J. Tang and W. Lang, “Multi-user Efficient Computing Task Offloading and Resource Optimization,” in Proc. 2021 6th International Conference on Intelligent Computing
and Signal Processing (ICSP), pp. 15–19, Apr. 2021.
[19] A. Belogaev, A. Elokhin, A. Krasilov, E. Khorov, and I. F. Akyildiz, “Cost-Effective V2X Task Offloading in MEC-Assisted Intelligent Transportation Systems,” IEEE Access, vol. 8, pp. 169010–169023, Sep. 2020.
[20] M. ETSI, “Multi-access Edge Computing (MEC); Framework and Reference Architecture,” vol. 3, 2022
[21] P. Kolios, V. Friderikos, and K. Papadaki, “Ultra Low Energy Store-Carry and Forward Relaying within the Cell,” in Proc. 2009 IEEE 70th Vehicular Technology Conference Fall, pp. 1–5, Jan. 2009.
[22] C. Zheng, D. Feng, S. Zhang, X.-G. Xia, G. Qian, and G. Y. Li, “V2X-Enabled
Energy-Efficient Transmission in Cellular Networks,” in Proc. 2018 10th International Conference on Wireless Communications and Signal Processing (WCSP),
pp. 1–6, Dec. 2018.
[23] L. Feng, Y. Zhou, T. Liu, X. Que, P. Yu, T. Hong, and X. Qiu, “Energy-Efficient
Offloading for Mission-Critical IoT Services Using EVT-Embedded Intelligent Learning,” IEEE Transactions on Green Communications and Networking, vol. 5, no. 3,
pp. 1179–1190, Apr. 2021.
[24] S. Kittipiyakul and T. Javidi, “Delay-Optimal Server Allocation in Multiqueue Multiserver Systems With Time-Varying Connectivities,” IEEE Transactions on Information Theory, vol. 55, no. 5, pp. 2319–2333, Apr. 2009.
[25] H. Al-Zubaidy, I. Lambadaris, and I. Viniotis, “Optimal Resource Scheduling
in Wireless Multiservice Systems with Random Channel Connectivity,” in Proc.
GLOBECOM 2009 - 2009 IEEE Global Telecommunications Conference, pp. 1–8,
Mar. 2009.
[26] M. Gong and S. Ahn, “Computation Offloading- Based Task Scheduling in the Vehicular Communication Environment for Computation-Intensive Vehicular Tasks,”
in Proc. 2020 International Conference on Artificial Intelligence in Information and
Communication (ICAIIC), pp. 534–537, Apr. 2020.
[27] H. Zhang, Q. Zhang, and X. Du, “Toward Vehicle-Assisted Cloud Computing
for Smartphones,” IEEE Transactions on Vehicular Technology, vol. 64, no. 12,
pp. 5610–5618, Sep. 2015.
[28] W. Zhang, Z. Zhang, and H.-C. Chao, “Cooperative Fog Computing for Dealing
with Big Data in the Internet of Vehicles: Architecture and Hierarchical Resource
Management,” IEEE Communications Magazine, vol. 55, no. 12, pp. 60–67, Dec.
2017.
[29] M. Chen, S. Guo, K. Liu, X. Liao, and B. Xiao, “Robust Computation Offloading and Resource Scheduling in Cloudlet-Based Mobile Cloud Computing,” IEEE
Transactions on Mobile Computing, vol. 20, no. 5, pp. 2025–2040, Feb. 2021.
[30] H. Wu, “Performance Modeling of Delayed Offloading in Mobile Wireless Environments With Failures,” IEEE Communications Letters, vol. 22, no. 11, pp. 2334–2337, Aug. 2018.
[31] 江岳亭, “在雲、邊緣、使用者裝置聯合系統中考慮邊緣伺服器故障之卸載:設計、分析與最佳化,” 國立臺灣科技大學碩士論文, 2021.
[32] H. Wu, “Performance Modeling of Delayed Offloading in Mobile Wireless
Environments With Failures,” IEEE Communications Letters, vol. 22, no. 11,
pp. 2334–2337, Aug. 2018.
[33] R.-H. Hwang, Y.-C. Lai, and Y.-D. Lin, “Offloading Optimization with Delay
Constraint in the 3-tier Federated Cloud, Edge, and Fog Systems,” in Proc. 2021
IEEE Global Communications Conference (GLOBECOM), pp. 1–6, Feb. 2021.

無法下載圖示 Full text public date 2026/02/15 (Intranet public)
Full text public date 2026/02/15 (Internet public)
Full text public date 2026/02/15 (National library)
QR CODE