隨著車載網路的發展，車載網路環境下對於傳輸延遲的敏感性，使得對網路設備與運算能力的需求不斷提高，若是車輛本身的運算能力不敷負荷，便須將運算任務卸載到行動邊緣運算(MEC)伺服器，以就近取得高效能和低延遲的計算服務，然而，MEC伺服器通常被安裝在基地台附近等的固定位置，通常僅能為其訊號覆蓋範圍內的車輛提供服務，因此靈活性相對較低，此外，當車輛密度因為塞車或事故而大幅度增加時，大量的運算需求可能導致MEC伺服器資源(例如：CPU與記憶體等)不足而造成響應延遲的增加，這對於講求安全性的車載網路可能會嚴重影響行車安全。
在有大量傳輸與運算需求的地區，利用飛行無人機(UAV)協助固定式MEC伺服器是很可行的解決方案，其視為移動式MEC伺服器，除了能提供邊緣運算服務，同時也能作為固定式MEC伺服器與在其傳輸範圍外車輛之間的中繼者(Relay node)，考量到UAV的數量稀少以及電力儲備有限，如何安排UAV飛行到最合適的位置，以滿足最多車輛的服務品質(QoS)需求是一個值得研究的議題。
基於上述環境與考量，本論文開發一套具QoS感知的任務卸載與UAV派遣的機制，其可根據網路情況來動態安排少數UAV飛行到對運算資源有高度需求的子區域以提供支援，並且讓車輛可自適應地選擇將任務卸載至固定式MEC伺服器或是UAV進行運算，以提高運算任務的成功率，該機制根據車輛分布，利用分群演算法將車輛分組，以群集座標、UAV座標、UAV運算能力等參數作為依據，將群集與UAV進行配對，以找到最適合派遣每架UAV的位置以提供邊緣運算的資源，此外，以具成本感知的防碰撞方法讓需要卸載至MEC伺服器的任務傳輸所受到碰撞的機率得以降低，從而滿足多數車輛的QoS需求，透過模擬實驗結果的分析，本論文提出的機制相較於現有的方法，能夠有效提升任務成功率以及減少任務平均延遲時間。

With the development of vehicular ad hoc networks (VANETs), the sensitivity of transmission delays in a VANET environment has led to increasing demand for network equipment and computing capabilities. If the vehicle lacks sufficient computing power, it will need to offload the computing tasks to an MEC (Multi-access mobile edge) server to obtain high-performance and low-latency computing services. However, MEC servers are usually installed at fixed locations near base stations and only provide services to vehicles within their signal coverage, so their flexibility is relatively low. In addition, when vehicle density increases significantly due to traffic jams or accidents, the large computing requirements may lead to insufficient MEC server resources (such as CPU and memory), resulting in increased response latency. This may seriously affect driving safety for VANETs.
In areas with large transmission and computing demands, using unmanned aerial vehicles (UAVs) to assist fixed MEC servers is a promising solution. They can be regarded as mobile MEC servers, not only providing edge computing services but also serving as relay nodes between fixed MEC servers and vehicles outside their transmission range. Considering the scarcity of UAVs and their limited power storage, how to arrange UAVs to fly to the most appropriate locations to meet the QoS (quality of service) requirements of most vehicles is an issue worth studying.
Based on the above environment and considerations, this thesis develops a QoS-aware task offloading and UAV dispatching mechanism that can dynamically deploy a few UAVs to the sub-area with high computational demands to provide support based on network conditions. Moreover, vehicles can adaptively offload tasks to either fixed MEC servers or UAVs for computation. Doing so helps improve the successful rate of computing tasks. This mechanism uses a clustering algorithm to group vehicles based on their distribution, and clusters are matched with UAVs according to cluster coordinates, UAV coordinates, and UAV computing capabilities to find optimal UAV deploy locations. In addition, the cost-aware anti-collision method reduces transmission collision probabilities of task offloading to MEC servers, thereby meeting the QoS requirements of most vehicles. Through the analysis of simulation results, the proposed mechanism can effectively improve the task successful rate and reduce the average task latency time compared with existing methods.

論文審定書 i
誌謝 ii
摘要 iii
Abstract v
目錄 vii
圖次 ix
表次 xi
第一章 緒論 1
1.1簡介 1
1.2研究動機 2
1.3論文貢獻與架構 3
第二章 研究背景 4
2.1車載網路 4
2.2行動邊緣運算 6
2.3飛行無人機 8
第三章 相關文獻探討 10
第四章 問題定義 14
第五章 研究方法 21
5.1 車輛分群模組 22
5.2 UAV配對與派遣模組 24
5.3 傳輸與防碰撞模組 26
5.4 DUDTO設計理念 30
第六章 實驗結果與分析 31
6.1模擬環境與參數設定 31
6.2固定MSM任務比例下的效能評估 35
6.3 MSM任務比例之影響 41
6.4 DUDTO權重設定之影響 46
第七章 結論及未來展望 51
7.1結論 51
7.2未來展望 51
參考文獻 53

[1] M. A. Al-shareeda, M. A. Alazzawi, M. Anbar, S. Manickam, and A. K. Al-Ani, “A comprehensive survey on vehicular ad hoc networks (vanets),” International Conference on Advanced Computer Applications, 2021, pp. 156-160.
[2] M. Ahmed, M. A. Mirza, S. Raza, H. Ahmad, F. Xu, W. U. Khan, Q. Lin, and Z. Han, “Vehicular communication network enabled CAV data offloading: A review,” IEEE Transactions on Intelligent Transportation Systems, 2023.
[3] M. J. N. Mahi, S. Chaki, S. Ahmed, M. Biswas, M. S. Kaiser, M. S. Islam, M. Sookhak, A. Barros, and M. Whaiduzzaman, “A review on VANET research: Perspective of recent emerging technologies,” IEEE Access, vol. 10, pp. 65760-65783, 2022.
[4] M. B. Kokare and D. Kakkar, “A survey on clustering algorithms for cluster-head selection in VANET,” Second International Conference on Electronics and Sustainable Communication Systems, 2021, pp. 992-996.
[5] ESTI GS MEC 002 (2016), “Mobile Edge Computing (MEC) Technical RequirementsV1.1.1.”[Online].Avaliable:http://www.etsi.org/deliver/etsi_gs/ME C/001_099/002/01.01.01_60/gs_MEC002v010101p.pdf
[6] J. Lansky, S. Ali, A. M. Rahmani, M. S. Yousefpoor, E. Yousefpoor, F. Khan, and M. Hosseinzadeh, “Reinforcement learning-based routing protocols in flying ad hoc networks (FANET): A review,” Mathematics, vol. 10, no. 16, p. 3017, 2022.
[7] O. S. Oubbati, M. Atiquzzaman, P. Lorenz, M. H. Tareque, and M. S. Hossain, “Routing in flying ad hoc networks: Survey, constraints, and future challenge perspectives,” IEEE Access, vol. 7, pp. 81057-81105, 2019.
[8] B. Li, Z. Fei, and Y. Zhang, “UAV communications for 5G and beyond: Recent advances and future trends,” IEEE Internet of Things Journal, vol. 6, no. 2, pp. 2241-2263, 2018.
[9] J. Xiong, H. Guo, and J. Liu, “Task offloading in UAV-aided edge computing: Bit allocation and trajectory optimization,” IEEE Communications Letters, vol. 23, no. 3, pp. 538-541, 2019.
[10] F. Zhou, Y. Wu, H. Sun, and Z. Chu, “UAV-enabled mobile edge computing: Offloading optimization and trajectory design,” IEEE International Conference on Communications, 2018, pp. 1-6.
[11] H. Mei, K. Wang, D. Zhou, and K. Yang, “Joint trajectory-task-cache optimization in UAV-enabled mobile edge networks for cyber-physical system,” IEEE Access, vol. 7, pp. 156476-156488, 2019.
[12] Z. Yang, S. Bi, and Y. J. A. Zhang, “Dynamic offloading and trajectory control for UAV-enabled mobile edge computing system with energy harvesting devices,” IEEE Transactions on Wireless Communications, vol. 21, no. 12, pp. 10515-10528, 2022.
[13] R. Khalid, Z. Shah, M. Naeem, A. Ali, A. Al-Fuqaha, and W. Ejaz, “Computational efficiency maximization for UAV-assisted MEC networks with energy harvesting in disaster scenarios,” IEEE Internet of Things Journal, vol. 11, no. 5, pp. 9004-9018, 2023.
[14] H. Wang, H. Ke, and W. Sun, “Unmanned-aerial-vehicle-assisted computation offloading for mobile edge computing based on deep reinforcement learning,” IEEE Access, vol. 8, pp. 180784-180798, 2020.
[15] L. Zhang, Z. Y. Zhang, L. Min, C. Tang, H. Y. Zhang, Y. H. Wang, and P. Cai, “Task offloading and trajectory control for UAV-assisted mobile edge computing using deep reinforcement learning,” IEEE Access, vol. 9, pp. 53708-53719, 2021.
[16] X. Du, X. Li, N. Zhao, and X. Wang, “A joint trajectory and computation offloading scheme for UAV-MEC networks via multi-agent deep reinforcement learning,” IEEE International Conference on Communications, 2023, pp. 5438-5443.
[17] K. Xiang and Y. He, “UAV-assisted MEC system considering UAV trajectory and task offloading strategy,” IEEE International Conference on Communications, 2023, pp. 4677-4682.
[18] J. Zhang, J. Gao, F. Ye, and Y. Li, “Energy-saving algorithm of UAVs in task offloading of UAV-assisted mobile edge computing,” IEEE USNC-URSI Radio Science Meeting, 2022, pp. 102-103.
[19] Z. Liu, J. Qi, Y. Shen, K. Ma, and X. Guan, “Maximizing energy efficiency in UAV-assisted NOMA-MEC networks,” IEEE Internet of Things Journal, vol. 10, no. 24, pp. 22208-22222, 2023.
[20] D. Wang, J. Tian, H. Zhang, and D. Wu, “Task offloading and trajectory scheduling for UAV-enabled MEC networks: An optimal transport theory perspective,” IEEE Wireless Communications Letters, vol. 11, no. 1, pp. 150-154, 2021.
[21] Y. Ding, W. Lu, Y. Zhang, Y. Feng, B. Li, and Y. Gao, “Energy consumption minimization for secure UAV-enabled MEC networks against active eavesdropping,” IEEE Vehicular Technology Conference, 2023, pp. 1-5.
[22] J. Wang, D. Feng, J. Zhu, and H. Huang, “Vehicular computation offloading in UAV-enabled MEC systems,” IEEE International Conference on Computer Supported Cooperative Work in Design, 2022, pp. 1071-1076.
[23] G. Wu, Q. Liu, J. Xu, Y. Miao, and M. Pustišek, “Energy efficient task caching and offloading in UAV-enabled crowd management,” IEEE Sensors Journal, vol. 22, no. 18, pp. 17565-17572, 2022.
[24] Y. C. Wang and S. W. Yeh, “E-DSR: energy-efficient routing for sensors with diverse sensing rates,” International Journal of Ad Hoc and Ubiquitous Computing, vol. 34, no. 4, pp. 233-248, 2020.
[25] Z. Chen, Y. Guo, J. Hao, and Y. Du, “Energy Efficient UAV Trajectory Design for Hovering-Flying Data Collection,” IEEE Globecom Workshops, 2022, pp. 886-890.
[26] Y. C. Wang and C. T. Chu, “Efficient resource scheduling and dispatch of mobile cell sites to improve 5G performance,” IEEE Vehicular Technology Conference, 2022, pp. 1-5.
[27] H. W. Kuhn, “The Hungarian method for the assignment problem,” Naval Research Logistics Quarterly, vol. 2, no. 1‐2, pp. 83-97, 1955.
[28] M. M. Azari, G. Geraci, A. Garcia-Rodriguez, and S. Pollin, “UAV-to-UAV communications in cellular networks,” IEEE Transactions on Wireless Communications, vol. 19, no. 9, pp. 6130-6144, 2020.
[29] Veins. [Online]. Available: https://veins.car2x.org/
[30] SUMO - Simulation of Urban Mobility. [Online]. Available: https://eclipse.dev/sumo/
[31] OMNeT++ Discrete Event Simulator. [Online]. Available: https://omnetpp.org/
[32] OpenStreetMap. [Online]. Available: https://www.openstreetmap.org/
[33] D. Rico and P. Merino, “A survey of end-to-end solutions for reliable low-latency communications in 5G networks,” IEEE Access, vol. 8, pp. 192808-192834, 2020.
[34] M. H. C. Garcia, A. Molina-Galan, M. Boban, J. Gozalvez, B. Coll-Perales, T. Şahin, and A. Kousaridas, “A tutorial on 5G NR V2X communications,” IEEE Communications Surveys & Tutorials, vol. 23, no. 3, pp. 1972-2026, 2021.
[35] C. Singhal, S. Rafiei, and K. Brunnström, “Real-time live-video streaming in delay-critical application: remote-controlled moving platform,” IEEE Vehicular Technology Conference, 2023, pp. 1-7.
[36] Y. C. Wang and K. C. Chen, “Efficient path planning for a mobile sink to reliably gather data from sensors with diverse sensing rates and limited buffers,” IEEE Transactions on Mobile Computing, vol. 18, no. 7, pp. 1527-1540, 2018.