物聯網 (Internet of Things, IoT) 的興起及智能車輛 (Smart Vehicle) 的發展和使用者裝置 (User Equipment) 的普及為使用者提供多樣的服務，然而，其中不乏有需要大量計算的應用程式，例如：增強/虛擬現實 (AR/VR)、線上遊戲，這些應用程式會產生巨量計算，導致使用者裝置電力的快速消耗。為此，有卸載 (Offloading)機制的提出，使用者裝置將自身的任務卸載到計算資源比較豐富的雲端伺服器(Cloud Server)、邊緣伺服器 (Edge Server) 或車輛霧 (Vehicular Fog)，以減少使用者裝置的計算量，並減少能源消耗 (Energy Consumption) 和等待時間 (Waiting Time)。
然而，在過往的論文中，大多假設伺服器不會故障 [1]，鮮少討論到伺服器會故障的問題，特別是多重伺服器故障問題。因此，本論文將考量 [1] 的架構，進一步討論雲端伺服器、邊緣伺服器、車輛霧之故障容錯設計並分析卸載延遲等效能指標。於本論文中，我們提出幾種容錯設計，並獲得其理論效能分析及最佳化之參數。理論效能分析透過模擬驗證後，不同容錯機制間之效能比較與相關系統動態探究將予以呈現與觀察，以利找出本論文所提且最為推薦之容錯設計。

The rise of the Internet of things (IoT) and the development and application of smart vehicles offer a variety of services for user equipments. However, there are many computingintensive applications, such as augmented/virtual reality (AR/VR), online games, etc.
These applications will generate massive amounts of computation and power consumption rapidly on UEs. For solving such an issue, offloading has been proposed. A UE can
offload its own tasks to the server, such as the cloud server, the edge server or the vehicular fog to reduce the computational load, power consumption, and waiting time of the UE.
However, most of past papers, e.g. [1], assumed that the server will not breakdown, and rarely discussed the problem of server failures, especially the problem of multiple-server failures. Therefore, this paper will consider the architecture of [1] to further incorporate the fault-tolerant design for cloud servers, edge servers, and the vehicle fog first and then analyze the offloading delay accordingly. In this paper, we shall propose several fault-tolerant offloading mechanisms, and obtain their performance measures and optimized parameters in a theoretical apporach. After the theoretical performance analysis is verified by simulation results, the performance comparison among different fault-tolerant offloading mechanisms and the system dynamic exploration presented and observed in order to facilitate the most recommended design of the fault-tolerant offloading proposed by this paper.

[1] B. Kar, K.-M. Shieh, Y.-C. Lai, Y.-D. Lin, and H.-W. Ferng, “Qos Violation
Probability Minimization in Federating Vehicular-Fogs with Cloud and Edge
Systems,” IEEE Trans. Veh. Technol., vol. 70, no. 12, pp. 13270–13280, 2021.
[2] X. Duan, F. Xu, and Y. Sun, “Research on Offloading Strategy in Edge Computing
of Internet of Things,” in Int. Conf. Comput. Netw. Electron. Autom. (ICCNEA),
pp. 206–210, 2020.
[3] M. Chiang and T. Zhang, “Fog and Iot: An Overview of Research Opportunities,”
IEEE Internet Things J., vol. 3, no. 6, pp. 854–864, 2016.
[4] C. Xian, Y.-H. Lu, and Z. Li, “Adaptive Computation Offloading for Energy
Conservation on Battery-Powered Systems,” in Int. Conf. Parallel Distrib. Syst.,
pp. 1–8, 2007.
[5] M. Caprolu, R. Di Pietro, F. Lombardi, and S. Raponi, “Edge Computing
Perspectives: Architectures, Technologies, and Open Security Issues,” in IEEE Int.
Conf. Edge Comput. (EDGE), pp. 116–123, 2019.
[6] N. Fernando, S. W. Loke, and W. Rahayu, “Mobile Cloud Computing: A Survey,”
Future Generation Comput. Syst., vol. 29, no. 1, pp. 84–106, 2013. Including Special
section: AIRCC-NetCoM 2009 and Special section: Clouds and Service-Oriented
Architectures.
[7] Y. Zhang, C.-Y. Wang, and H.-Y. Wei, “Parking Reservation Auction for Parked
Vehicle Assistance in Vehicular Fog Computing,” IEEE Trans. Veh. Technol.,
vol. 68, no. 4, pp. 3126–3139, 2019.
[8] Q. Fan and L. Liu, “A Survey of Challenging Issues and Approaches in Mobile
Cloud Computing,” in Int. Conf. Parallel Distrib. Comput. Appl. Technol. (PDCAT),
pp. 87–90, 2016.
[9] Z. Sanaei, S. Abolfazli, A. Gani, and R. Buyya, “Heterogeneity in Mobile Cloud
Computing: Taxonomy and Open Challenges,” IEEE Commun. Surveys Tutorials,
vol. 16, no. 1, pp. 369–392, 2014.
[10] K. Xiao, Z. Gao, Q. Wang, and Y. Yang, “A Heuristic Algorithm Based on Resource
Requirements Forecasting for Server Placement in Edge Computing,” in IEEE/ACM
Symp. Edge Comput. (SEC), pp. 354–355, 2018.
[11] H. Li, G. Shou, Y. Hu, and Z. Guo, “Mobile Edge Computing: Progress and
Challenges,” in IEEE Int. Conf. Mobile Cloud Comput. Services Eng. (MobileCloud),
pp. 83–84, 2016.
[12] M. ETSI, Multi-access Edge Computing (MEC); Framework and Reference
Architecture, vol. 3. 2022.
[13] K. Sehla, T. M. T. Nguyen, G. Pujolle, and P. B. Velloso, “Resource Allocation
Modes in C-V2X: From LTE-V2X to 5G-V2X,” IEEE Internet Things J., vol. 9,
no. 11, pp. 8291–8314, 2022.
[14] Y. Lai, F. Yang, L. Zhang, and Z. Lin, “Distributed Public Vehicle System Based on
Fog Nodes and Vehicular Sensing,” IEEE Access, vol. 6, pp. 22011–22024, 2018.
[15] Y. Li, H. Li, G. Xu, T. Xiang, and R. Lu, “Practical Privacy-Preserving Federated
Learning in Vehicular Fog Computing,” IEEE Trans. Veh. Technol., vol. 71, no. 5,
pp. 4692–4705, 2022.
[16] 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.
[17] A. Waheed, M. A. Shah, S. M. Mohsin, A. Khan, C. Maple, S. Aslam, and
S. Shamshirband, “A Comprehensive Review of Computing Paradigms, Enabling
Computation Offloading and Task Execution in Vehicular Networks,” IEEE Access,
vol. 10, pp. 3580–3600, 2022.
[18] J. Xie, Y. Jia, Z. Chen, Z. Nan, and L. Liang, “Efficient Task Completion for Parallel
Offloading in Vehicular Fog Computing,” China Commun., vol. 16, no. 11, pp. 42–
55, 2019.
[19] Y. Jang, J. Na, S. Jeong, and J. Kang, “Energy-Efficient Task Offloading for
Vehicular Edge Computing: Joint Optimization of Offloading and Bit Allocation,”
in IEEE Veh. Technol. Conf. (VTC2020-Spring), pp. 1–5, 2020.
[20] G. Yang, L. Hou, X. He, D. He, S. Chan, and M. Guizani, “Offloading Time
Optimization via Markov Decision Process in Mobile-Edge Computing,” IEEE Internet Things J., vol. 8, no. 4, pp. 2483–2493, 2021.
[21] Y. Zhang, X. Dong, and Y. Zhao, “Decentralized Computation Offloading over
Wireless-Powered Mobile-Edge Computing Networks,” in IEEE Int. Conf. Artificial Intell. Information Syst. (ICAIIS), pp. 137–140, 2020.
[22] R.-H. Hwang, Y.-C. Lai, and Y.-D. Lin, “Offloading Optimization with Delay
Distribution in the 3-tier Federated Cloud, Edge, and Fog Systems,” 2021.
[23] C. Ren, G. Zhang, X. Gu, and Y. Li, “Computing Offloading in Vehicular Edge
Computing Networks: Full or Partial Offloading?,” in IEEE Inf. Technol. Mechatron.
Eng. Conf. (ITOEC), vol. 6, pp. 693–698, 2022.
[24] 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
IEEE Global Commun. Conf., pp. 1–6, 2020.
[25] Z. Liu, P. Dai, H. Xing, Z. Yu, and W. Zhang, “A distributed algorithm for task
offloading in vehicular networks with hybrid fog/cloud computing,” IEEE Transactions on Systems, Man, and Cybernetics: Systems, vol. 52, no. 7, pp. 4388–4401,
2022.
[26] H. Wu, “Performance Modeling of Delayed Offloading in Mobile Wireless
Environments with Failures,” IEEE Commun. Lett., vol. 22, no. 11, pp. 2334–2337,
2018.
[27] Q.-u.-A. Mastoi, A. Lakhan, F. A. Khan, and Q. H. Abbasi, “Dynamic Content and
Failure Aware Task Offloading in Heterogeneous Mobile Cloud Networks,” in Int.
Conf. Adv. Emerging Comput. Technol. (AECT), pp. 1–6, 2020.
[28] P. S and R. Manivasakan, “Performance Analysis of Delayed Offloading Model with
Intermittent Failure Using Balking,” in IEEE Int. Conf. Innovation Technol. (INOCON), pp. 1–5, 2020.
[29] S. Mondal, C. Chowdhury, S. Roy, S. K. Deb, and S. Neogy, “Crash Failure Immune
Offloading Framework,” in IEEE Int. Conf. Adv. Netw. Telecommun. Syst. (ANTS),
pp. 1–6, 2016.
[30] J. M. T. Donald Gross, John F. Shortle, Fundamentals of Queueing Theory, Fourth
Edition. Wiley, 2008.