隨著互聯網的興起，車聯網（Vehicular Ad Hoc Networks, VANET）作為智能交通系統的核心組成部分，正逐漸受到關注。利用無線通信技術和先進的車輛感知器，車聯網實現了汽車間及汽車與基礎設施間的即時數據交換，提升了交通系統的安全性和效率。然而，快速都市化導致車輛數量劇增，交通事故頻發，尤其是追撞事故。為解決此問題，本研究提出基於5G網路的車輛影像協作共享功能，通過無線通信和跳點通訊技術延伸車輛影像傳輸範圍，並使用強化學習選擇最佳傳輸對象，提高影像品質。此外，本文引入多接取邊緣計算（Multi-access Edge Computing, MEC）以應對車
載系統計算能力不足導致的延遲問題。MEC將計算資源部署在靠近用戶車輛的位置，減少數據傳輸延遲並降低網路頻寬需求。
本文通過多代理人強化學習架構，多代理人深度確定性策略梯度（Multi-Agent Deep Deterministic Policy Gradient,MADDPG），結合邊緣計算，預測最佳路徑並選擇最合適的協作車輛，實現最佳傳輸效率，提升整體系統的性能和可靠性。最後進行不同強化學習模型之間的效能比較，證明部署多代理人強化學習能使系統得到長期最大報酬。

With the rise of the IoT, Vehicular Ad Hoc Networks (VANET) have gradually gained attention as a core component of intelligent transportation systems. Utilizing wire
less communication technologies and advanced vehicle sensors, VANET enables real-time data exchange between vehicles and between vehicles and infrastructure, enhancing the safety and efficiency of transportation systems. However, rapid urbanization has led to a dramatic increase in the number of vehicles and frequent traffic accidents, particularly rear-end collisions. To address this issue, this study proposes a vehicle image cooperative sharing function based on 5G networks. By extending the range of vehicle image transmission through wireless communication and multi-hop transmission , and using reinforcement learning to select the best transmission targets, the quality of the images is improved.
In addition, this paper introduces Multi-access Edge Computing (MEC) to address the issues of insufficient computing ability and transmission delays in onboard systems.MEC deploys computing resources close to the user vehicles, reducing data transmissiondelays and less network bandwidth requirements.This paper employs a multi-agent reinforcement learning framework, Multi-Agent Deep Deterministic Policy Gradient (MADDPG), combining edge computing to predict optimal routes and select the most suitable cooperative vehicles, achieving optimal transmission efficiency and enhancing the overall system performance and reliability. Finally,
a performance comparison between different reinforcement learning models is conducted, demonstrating that deploying multi-agent reinforcement learning can achieve long-term
maximum rewards for the system.

參考文獻
[1] Y.-C. Chu, “Using stackelberg game and multi-agent reinforcement learning to self
organize relaying groups for real-time video sharing in vehicular networks, https://
hdl.handle.net/11296/v5u5r2,” 2023.
[2] C. S. Evangeline, V. B. Kumaravelu, and A. Joshi, “Safety and driver assistance
in vanets: an experimental approach for v2v,” in 2019 International Conference on
Communication and Electronics Systems (ICCES). IEEE, 2019, pp. 397–402.
[3] P. Gomes, C. Olaverri-Monreal, and M. Ferreira, “Making vehicles transparent
through v2v video streaming,” IEEE Transactions on Intelligent Transportation Sys
tems, vol. 13, no. 2, pp. 930–938, 2012.
[4] X. Xiang, W. Qin, and B. Xiang, “Research on a dsrc-based rear-end collision warning
model,” IEEE Transactions on Intelligent Transportation Systems, vol. 15, no. 3, pp.
1054–1065, 2014.
[5] A. M. Khodayer, A. H. Najim, N. Alkhazraji, A. H. Alkhayyat, and F. H. Abbas,
“Performance evaluation of effective cluster head selection and maintenance for lte
based vehicular ad-hoc networks,” in 2023 6th International Conference on Engi
neering Technology and its Applications (IICETA). IEEE, 2023, pp. 714–719.
[6] J. Hu, S. Chen, L. Zhao, Y. Li, J. Fang, B. Li, and Y. Shi, “Link level performance
comparison between lte v2x and dsrc,” Journal of Communications and Information
Networks, vol. 2, no. 2, pp. 101–112, 2017.
[7] Z. Deng, Z. Cai, and M. Liang, “A multi-hop vanets-assisted offloading strategy in
vehicular mobile edge computing,” IEEE Access, vol. 8, pp. 53062–53071, 2020.
[8] M. M. Hamdi, S. A. Jassim, and B. S. Abdulhakeem, “Successful delivery using
stable multi-hop clustering protocol for energy efficient highway vanets,” in 2023 7th
International Symposium on Multidisciplinary Studies and Innovative Technologies
(ISMSIT). IEEE, 2023, pp. 1–6.
[9] D. Zhang, H. Ge, T. Zhang, Y.-Y. Cui, X. Liu, and G. Mao, “New multi-hop clus
tering algorithm for vehicular ad hoc networks,” IEEE Transactions on Intelligent
Transportation Systems, vol. 20, no. 4, pp. 1517–1530, 2018.
[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, 2016.
[11] S. A. Ahmad, A. Hajisami, H. Krishnan, F. Ahmed-Zaid, and E. Moradi-Pari, “V2v
system congestion control validation and performance,” IEEE Transactions on Ve
hicular Technology, vol. 68, no. 3, pp. 2102–2110, 2019.
[12] D. K. Nayak, S. V. Reddy, and S. D. Roy, “Performance evaluation of cv2x communi
cation,” in 2022 IEEE North Karnataka Subsection Flagship International Conference
(NKCon). IEEE, 2022, pp. 1–5.
[13] M. A. Palash and D. Wijesekera, “Adaptive traffic signal control using cv2x,” in 2023
IEEE 98th Vehicular Technology Conference (VTC2023-Fall). IEEE, 2023, pp. 1–7.
[14] Y. Tang, N. Cheng, W. Wu, M. Wang, Y. Dai, and X. Shen, “Delay-minimization
routing for heterogeneous vanets with machine learning based mobility prediction,”
IEEE Transactions on Vehicular Technology, vol. 68, no. 4, pp. 3967–3979, 2019.
[15] J. He, L. Cai, J. Pan, and P. Cheng, “Delay analysis and routing for two-dimensional
vanets using carry-and-forward mechanism,” IEEE Transactions on Mobile Comput
ing, vol. 16, no. 7, pp. 1830–1841, 2016.
[16] Y. Su, H. Cai, and J. Shi, “An improved realistic mobility model and mechanism
for vanet based on sumo and ns3 collaborative simulations,” in 2014 20th IEEE
International Conference on Parallel and Distributed Systems (ICPADS). IEEE,
2014, pp. 900–905.
[17] C.-M. Huang, M.-S. Chiang, D.-T. Dao, W.-L. Su, S. Xu, and H. Zhou, “V2v data
offloading for cellular network based on the software defined network (sdn) inside
mobile edge computing (mec) architecture,” IEEE Access, vol. 6, pp. 17741–17755,
2018.
[18] F. Liu, J. Chen, Q. Zhang, and B. Li, “Online mec offloading for v2v networks,”
IEEE Transactions on Mobile Computing, vol. 22, no. 10, pp. 6097–6109, 2022.
[19] Y. Wang, X. Hu, L. Guo, and Z. Yao, “Research on v2i/v2v hybrid multi-hop edge
computing offloading algorithm in iov environment,” in 2020 IEEE 5th International
Conference on Intelligent Transportation Engineering (ICITE). IEEE, 2020, pp.
336–340.
[20] K. Wang, X. Wang, X. Liu, and A. Jolfaei, “Task offloading strategy based on rein
forcement learning computing in edge computing architecture of internet of vehicles,”
IEEE Access, vol. 8, pp. 173779–173789, 2020.
[21] H. Wang, T. Lv, Z. Lin, and J. Zeng, “Energy-delay minimization of task migration
based on game theory in mec-assisted vehicular networks,” IEEE Transactions on
Vehicular Technology, vol. 71, no. 8, pp. 8175–8188, 2022.
[22] L. Luo, L. Sheng, H. Yu, and G. Sun, “Intersection-based v2x routing via rein
forcement learning in vehicular ad hoc networks,” IEEE Transactions on Intelligent
Transportation Systems, vol. 23, no. 6, pp. 5446–5459, 2021.
[23] J. Huang, J. Peng, H. Xiang, L. Li, and Y. Yang, “Hybrid spectrum access for v2v
heterogeneous networks with deep reinforcement learning,” in 2022 14th International
Conference on Wireless Communications and Signal Processing (WCSP). IEEE,
2022, pp. 1091–1095.
[24] S.-H. Wu, R.-H. Hwang, C.-Y. Wang, and C.-H. Chou, “Deep reinforcement learning
based resource allocation for 5g v2v groupcast communications,” in 2023 Interna
tional Conference on Computing, Networking and Communications (ICNC). IEEE,
2023, pp. 1–6.
[25] X. Zhang, M. Peng, S. Yan, and Y. Sun, “Deep-reinforcement-learning-based mode
selection and resource allocation for cellular v2x communications,” IEEE Internet of
Things Journal, vol. 7, no. 7, pp. 6380–6391, 2019.
[26] T. Li, K. Zhu, N. C. Luong, D. Niyato, Q. Wu, Y. Zhang, and B. Chen, “Applications
of multi-agent reinforcement learning in future internet: A comprehensive survey,”
IEEE Communications Surveys & Tutorials, vol. 24, no. 2, pp. 1240–1279, 2022.
[27] C. Lu, Z. Wang, W. Ding, G. Li, S. Liu, and L. Cheng, “Marvel: Multi-agent rein
forcement learning for vanet delay minimization,” China Communications, vol. 18,
no. 6, pp. 1–11, 2021.
[28] O. Urmonov, H. Aliev, and H. Kim, “Multi-agent deep reinforcement learning for
enhancement of distributed resource allocation in vehicular network,” IEEE Systems
Journal, vol. 17, no. 1, pp. 491–502, 2022.
[29] N. Hammami and K. K. Nguyen, “Multi-agent actor-critic for cooperative resource
allocation in vehicular networks,” in 2022 14th IFIP Wireless and Mobile Networking
Conference (WMNC). IEEE, 2022, pp. 93–100.
[30] T. Lyu, H. Xu, F. Liu, M. Li, L. Li, and Z. Han, “Two layer stackelberg game
based resource allocation in cloud-network convergence service computing,” IEEE
Transactions on Cognitive Communications and Networking, 2024.
[31] X. Chen, L. Jiao, W. Li, and X. Fu, “Efficient multi-user computation offloading
for mobile-edge cloud computing,” IEEE/ACM transactions on networking, vol. 24,
no. 5, pp. 2795–2808, 2015.
[32] S.-W. Kim, B. Qin, Z. J. Chong, X. Shen, W. Liu, M. H. Ang, E. Frazzoli, and
D. Rus, “Multivehicle cooperative driving using cooperative perception: Design and
experimental validation,” IEEE Transactions on Intelligent Transportation Systems,
vol. 16, no. 2, pp. 663–680, 2014.