汽車移動物聯網技術(簡稱：車聯網)是因應自動駕駛而發展的重要技術，目前第三代合作夥伴計劃(the Third Generation Partnership Project，3GPP)與Wi-Fi聯盟(Wi-Fi Alliance，WFA)兩大通訊標準組織正積極研究相關技術。由於兩組織所訂定的標準擁有各自的特色，再加上車輛高速移動與拓撲快速變化的特性，在各自傳輸資源有限的狀態下，車輛該如何抉擇通訊界面將是未來需要解決的問題。
然而將車輛分散於兩種通訊界面中，傳輸資源也會因為每一輛車與中心設備(AP、Evolved Node B(eNodeB)…等)建立連線所需的控制訊息而佔據多數資源，因此該如何設計資料傳輸路徑，使得有些車輛可以不用與中心設備建立連線，而是透過鄰近車輛幫忙轉送，以降低車輛與中心設備所建立的連線數將是重要議題之一。
本論文所設計的演算法根據系統效能與車輛所給予的資訊，判斷車輛該選擇何種通訊介面，以及如何將車輛分群，以提高資料傳送成功率與有效降低連線數。

Vehicular communication is a technology developed to support autonomous driving. Recently, the two major communication standards organization, Third Generation Partnership Project (3GPP) and Wi-Fi Alliance (WFA), are actively studying related technologies. However, each of the two standards has its own characteristics, along with some features such as high mobility of vehicles, frequent topology changes and limited transmission resources. Consequently, how to select the communication interface will be the problem that we should solve in the future.
However, even if we disperse the vehicles into two different communication interface, the control signaling overhead caused by the connections between vehicles and the central equipment will exhaust the transmission resources. Therefore, the issue of designing a proper transmission model will be important. In other words, we aim to reduce the number of connections between the vehicle and the central equipment, achieved by forcing the vehicle to transmit data via its neighbor.
According to information given by vehicles and environment condition of the system, we proposed an algorithm that decides which communication interface the vehicle should choose, as well as a vehicle clustering method, in order to improve packet delivery ratio and reduce the number of connections efficiently.

[1] X. Wang, S. Mao and M. X. Gong, "An Overview of 3GPP Cellular Vehicle-to-Everything Standards," GetMobile: Mobile Comp. and Comm., vol. 21, no. 3, pp. 19-25, 2017.
[2] 3GPP, "Evolved Universal Terrestrial Radio Access (E-UTRA); Physical layer procedures (v14.3.0, Release 14)," 3GPP, Tech. Rep. 36.213, Jun. 2017.
[3] Qualcomm, "5G NR based C-V2X," 2018. [Online]. Available: https://www.qualcomm.com/media/documents/files/5g-nr-based-c-v2x-presentation.pdf. [Accessed 3 6 2019].
[4] J. Gozalvez and R. Molina-Masegosa , "LTE-V for Sidelink 5G V2X Vehicular Communications," IEEE Vehicular Technology Magazine, vol. 12, no. 4, pp. 30-39, Dec. 2017.
[5] Y. Jeon, S. Kuk and H. Kim, "Reducing Message Collisions in Sensing-Based Semi-Persistent Scheduling (SPS) by Using Reselection Lookaheads in Cellular V2X," Sensors, vol. 18, no. 12, 2018.
[6] 3GPP, "Study on enhancement of 3GPP Support for 5G V2X Services," 3GPP, Tech. Rep. 22.886, Dec. 2018.
[7] [Online]. Available: https://www.3gpp.org/ftp/Information/presentations/presentations_2018/2018_10_17_tokyo/presentations/2018_1017_3GPP%20Summit_07_5GAA_FLAMENT.pdf. [Accessed 29 6 2019].

[8] D. Jiang and L. Delgrossi, "IEEE 802.11p: Towards an International Standard for Wireless Access in Vehicular Environments," in VTC Spring 2008 - IEEE Vehicular Technology Conference, Singapore, Singapore, 2008.
[9] [Online]. Available: https://www.2cm.com.tw/2cm/zh-tw/tech/F27AA1FE62104269B31D2D9B97E4AB31. [Accessed 6 6 2019].
[10] C. Song, "Performance analysis of the IEEE 802.11p multichannel MAC protocol," Sensors, vol. 17, no. 12, 2017.
[11] [Online]. Available: https://www.auto-talks.com/technology/dsrc-vs-c-v2x-2/. [Accessed 25 6 2019].
[12] I. DOTCOM, "Note 1: Machine learning categories ," 9 Feb. 2018. [Online]. Available: http://www.fossreview.com/2018/02/note-1-machine-learning-categories.html. [Accessed 12 Jul. 2018].
[13] H. Ye and G. Y. Li, "Deep Reinforcement Learning for Resource Allocation in V2V Communications," in 2018 IEEE International Conference on Communications (ICC), Kansas City, MO, USA, 2018.
[14] L. A. Zadeh, "Processes, Outline of a New Approach to the Analysis of Complex Systems and Decision," IEEE Transactions on Systems, Man, and Cybernetics, Vols. SMC-3, no. 1, pp. 28 - 44, 1973.
[15] B. Li, M. S. Mirhashemi, X. Laurent and J. Gao, "Wireless Access for Vehicular Environments," 2010. [Online]. Available: http://www.mehrpouyan.info/Projects/Group%205.pdf. [Accessed 15 6 2019].
[16] K. Bilstrup, E. Uhlemann, E. G. Strom and U. Bilstrup, "Evaluation of the IEEE 802.11p MAC Method for Vehicle-to-Vehicle Communication," in 2008 IEEE 68th Vehicular Technology Conference, Calgary, BC, Canada, 2008.
[17] H. Seo, K.-D. Lee, S. Yasukawa, Y. Peng and P. Sartori, "LTE evolution for vehicle-to-everything services," IEEE Communications Magazine, vol. 54, no. 6, pp. 22 - 28, June 2016.
[18] G. Araniti, C. Campolo, M. Condoluci, A. Iera and A. Molinaro, "LTE for vehicular networking: a survey," IEEE Communications Magazine, vol. 51, no. 5, pp. 148 - 157, May 2013.
[19] S. S. Salihin, L. A. Nissirat, R. M. Noor and I. Ahmedy, "Handover Schemes for Vehicular Ad-Hoc Networks Over Long Term Evolution Advanced: A Survey," in 2018 International Conference on Computational Approach in Smart Systems Design and Applications (ICASSDA), Kuching, Malaysia, October 2018.
[20] S. Cao, X. Tao and Y. Hou, "Joint handover decision to relieve ping-pong effect in V2X communication," in 2015 International Conference on Connected Vehicles and Expo (ICCVE), Shenzhen, China, Oct. 2015.
[21] A. Gharsallah, N. Omheni, K. Ghanmi, F. Zarai and M. Neji, "A Seamless Mobility Mechanism for V2V Communications," in 2017 IEEE/ACS 14th International Conference on Computer Systems and Applications (AICCSA), Hammamet, Tunisia, March 2018.
[22] Xu, Yubin; Li, Limin; Soong, Boon-Hee; Li, Cheng, "Fuzzy Q-learning based vertical handoff control for vehicular heterogeneous wireless network," in 2014 IEEE International Conference on Communications (ICC), Sydney, NSW, Australia, 2014.
[23] H. Ye, L. Liang, G. Y. Li, J. Kim, L. Lu and M. Wu, "Machine Learning for Vehicular Networks: Recent Advances and Application Examples," IEEE Vehicular Technology Magazine, vol. 13, no. 2, pp. 94-101, 2018.

[24] C. Wu, T. Yoshinaga, X. Chen, L. Zhang and Y. Ji, "Cluster-Based Content Distribution Integrating LTE and IEEE 802.11p with Fuzzy Logic and Q-Learning," IEEE Computational Intelligence Magazine, vol. 13, no. 1, pp. 41 - 50, Feb 2018.
[25] G. Deng, F. Li and L. Wang, "Cooperative downloading in VANETs-LTE heterogeneous network based on Named Data," in 2016 IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), San Francisco, CA, USA, 2016.
[26] D. Garg and D. Nagpal, "Vehicular Handover Approach Based On LTE In," International Journal for Research in Applied Science & Engineering Technology (IJRASET), vol. 4, no. 5, 2016.
[27] E. Skondras, A. Michalas, A. Sgora and D. D. Vergados, "A Vertical Handover management scheme for VANET Cloud Computing systems," in 2017 IEEE Symposium on Computers and Communications (ISCC), Heraklion, Greece, 2017.
[28] G. e. m. Zhioua, H. Labiod, N. Tabbane and S. Tabbane, "FQGwS: A gateway selection algorithm in a hybrid clustered VANET LTE-advanced network: Complexity and performances," in 2014 International Conference on Computing, Networking and Communications (ICNC), Honolulu, HI, USA, 2014.
[29] E. Ndashimye, N. I. Sarkar and S. K. Ray, "A mobility-aware network selection method for vehicle-to-infrastructure communication over LTE-A multi-tier networks," in 2017 International Conference on Information Networking (ICOIN), Da Nang, Vietnam, 2017.
[30] M. A. Togou, A. Hafid and P. K. Sahu, "A stable minimum velocity CDS-based virtual backbone for VANET in city environment," in 39th Annual IEEE Conference on Local Computer Networks, Edmonton, AB, Canada, Sept. 2014.

[31] [Online]. Available: https://medium.com/%E9%9B%9E%E9%9B%9E%E8%88%87%E5%85%94%E5%85%94%E7%9A%84%E5%B7%A5%E7%A8%8B%E4%B8%96%E7%95%8C/%E6%A9%9F%E5%99%A8%E5%AD%B8%E7%BF%92-ml-note-reinforcement-learning-%E5%BC%B7%E5%8C%96%E5%AD%B8%E7%BF%92-dqn-%E5%AF%A6%E4%BD%9Catari-game-7f9185f. [Accessed 24 6 2019].
[32] A. Bazzi, B. M. Masini, A. Zanella and I. Thibault, "On the Performance of IEEE 802.11p and LTE-V2V for the Cooperative Awareness of Connected Vehicles," IEEE Transactions on Vehicular Technology, vol. 66, no. 11, pp. 10419 - 10432, 2017.