隨著物聯網不斷地發展，車輛將逐漸轉型為聯網之車輛，不僅讓車輛聯網的頻寬面臨考驗，道路交通情形也會變得壅塞，這使得駕駛員花費更多的時間與精力。因此，本論文將採用霧運算(Fog Computing)，來偵測道路的壅塞程度，以適當給予車輛重新路由的策略，並且根據即時車流量的多寡來自動調整紅綠燈信號，在每一次紅綠燈階段結束後，會再根據車流量的多寡重新計算下一個階段的綠燈時間，這個方法稱為ATLC (Adaptive Traffic Light Control)，以儘可能讓每一輛車輛可以減少行駛時間與等待時間。另外，特別再針對類似上下班尖峰時期的車流情況做考量；車流量會有集中於某一條道路上且具有較固定的方向性，基於 ATLC 做進一步改良，此對主幹道上的車流做更進一步設計的方法稱為 AR-ATLC (Arterial Road Adaptive Traffic Light Control)，其使用相鄰紅綠燈的階段時間與多層級的參數自動化調整配置，讓主幹道上的相鄰紅綠燈可以有相互聯動的機制。透過模擬驗證，AR-ATLC對於道路行駛狀態可以較ATLC有較佳之表現且與文獻上之相近方法 TLC-CDT[1]有相當之行駛時間與等待時間，但 AR-ATLC 僅需較低之時間複雜度，因此，AR-ATLC 較 TLC-CDT 更利於實際車輛聯網系統之需求。

With the development of the Internet of things (IoT), vehicles will be gradually transformed into connected vehicles, causing not only some issues of bandwidth of the network connecting vehicles but also congested traffic. Therefore, drivers need spending more time in traveling. Towards alleviating such a problem, this thesis will propose a mechanism adopting the fog computing to detect the congestion level of the road, thus giving a re-routing strategy to drivers. Allocating adaptive traffic light signals according to the real-time traffic flow forms the first proposed mechanism called the adaptive traffic light control (ATLC) mechanism. According to the volume of traffic flow again, the duration of the next phase for ATLC will be re-calculated when reaching the end of the traffic light phase. Therefore, each vehicle can reduce its travel time and waiting time as much as possible. Additionally, we would like to further focus on the rush hour situation with the congested traffic on a specific road. Considering the concept of the arterial road, the second proposed mechanism called the arterial road ATLC (AR-ATLC) mechanism is then designed based on ATLC. AR-ATLC determines the parameter of the traffic light by referring to the parameters of the adjacent traffic lights with multi-stage parameter adjustment. Explicitly, the adjacent traffic lights on the arterial road can work jointly. According to the simulation results obtained, AR-ATLC spends less time than ATLC and reaches the comparable performance as TLC-CDT[1]. Undoubtedly, AR-ATLC will suit the actual network of vehicles better than TLC-CDT.

[1] Z. Cao, S. Jiang, J. Zhang, and H. Guo, “A unified framework for vehicle rerouting and traffic light control to reduce traffic congestion,” IEEE Transactions on Intelligent Transportation Systems, vol. 18, no. 7, pp. 1958–1973, Jul. 2017.
[2] Y. Gu, L. X. Cai, M. Pan, L. Song, and Z. Han, “Exploiting the stable fixture matching game for content sharing in D2Dbased LTEV2X communications,” in Proc. IEEE Global Communications Conference (GLOBECOM), pp. 1–6, Dec. 2016.
[3] P. Chouhan, G. Kaushal, and U. Prajapat, “Comparative study MANET and VANET,” International Journal of Engineering and Computer Science, vol. 5, no. 4, pp. 16079–16083, Apr. 2016.
[4] Statista, “Worldwide Connected car shipments 2023.” Available: https:// www.statista.com/ statistics/ 743400/ estimatedconnectedcarshipmentsglobally/, Apr. 06 2020. [Online]. [Accessed Aug. 24, 2020].
[5] S. Zeadally, R. Hunt, Y.S. Chen, A. Irwin, and A. Hassan, “Vehicular ad hoc networks (VANETs): Status, results, and challenges,” Telecommunication Systems, vol. 50, no. 4, pp. 217–241, Dec. 2010.
[6] B. Xia, F. Kong, J. Zhou, X. Tang, and H. Gong, “A delaytolerant data transmission scheme for internet of vehicles based on software defined cloudfog networks,” IEEE Access, vol. 8, pp. 65911–65922, Mar. 2020.
[7] L. Morgan, “USA Today The effects of traffic congestion.” Available: https: //traveltips.usatoday.com/effects-traffic-congestion-61043.html, Feb. 08, 2017. [Online]. [Accessed Aug. 24, 2020].
[8] W. KIRKLAND, “INRIX Congestion costs each american nearly 100 hours, $1,400 a year.” Available: https://inrix.com/press-releases/ 2019-traffic-scorecard-us/, Mar. 09 2020. [Online]. [Accessed Aug. 24, 2020].
[9] P. Bielaczyc, J. Woodburn, A. Szczotka, and P. Pajdowski, “The impact of alternative fuels on fuel consumption and exhaust emissions of greenhouse gases from vehicles featuring si engines,” Energy Procedia, vol. 66, pp. 21–24, Feb. 2015.
[10] Z. Xiao, Z. Xiao, D. Wang, and X. Li, “An intelligent traffic light control approach for reducing vehicles CO2 emissions in VANET,” in Proc. International Conference on Fuzzy Systems and Knowledge Discovery (FSKD), pp. 2070–2075, Aug. 2015.
[11] P. Salvo, F. Cuomo, A. Baiocchi, and A. Bragagnini, “Road side unit coverage extension for data dissemination in VANETs,” in Proc. Annual Conference on Wireless OnDemand Network Systems and Services (WONS), pp. 47–50, Jan. 2012.
[12] J. Zhang, F.Y. Wang, K. Wang, W.H. Lin, X. Xu, and C. Chen, “Datadriven intelligent transportation systems: A survey,” IEEE Transactions on Intelligent Transportation Systems, vol. 12, no. 4, pp. 1624–1639, Dec. 2011.
[13] 中華智慧運輸協會, “中華智慧運輸協會 關於協會甚麼是ITS.” Available: http://www.its-taiwan.org.tw/ch/a-2.asp. [Accessed Aug. 24, 2020].
[14] K. Saharan and A. Kumar, “Fog in comparison to cloud: A survey,” International Journal of Computer Applications, vol. 122, no. 3, Jul. 2015.
[15] A. V. Dastjerdi and R. Buyya, “Fog computing: Helping the internet of things realize its potential,” Computer, vol. 49, no. 8, pp. 112–116, Aug. 2016.
[16] F. Bonomi, R. Milito, J. Zhu, and S. Addepalli, “Fog computing and its role in the internet of things,” in Proc. Edition of the MCC Workshop on Mobile Cloud Computing, pp. 13–16, Aug. 2012.
[17] N. K. Giang, V. Leung, and R. Lea, “On developing smart transportation applications in fog computing paradigm,” in Proc. ACM Symposium on Development and Analysis of Intelligent Vehicular Networks and Applications, pp. 91–98, Nov. 2016.
[18] M. Deruyck, W. Joseph, B. Lannoo, D. Colle, and L. Martens, “Designing energyefficient wireless access networks: LTE and LTEAdvanced,” IEEE Internet Computing, vol. 17, no. 5, pp. 39–45, Jan. 2013.
[19] C. Huang, R. Lu, and K.K. R. Choo, “Vehicular fog computing: Architecture, use case, and security and forensic challenges,” IEEE Communications Magazine, vol. 55, no. 11, pp. 105–111, Nov. 2017.
[20] J. Grover, A. Jain, S. Singhal, and A. Yadav, “Realtime VANET applications using fog computing,” in Proc. International Conference on Smart System, Innovations and Computing, pp. 683–691, Jan. 2018.
[21] Y. Xiao and Chao Zhu, “Vehicular fog computing: Vision and challenges,” in Proc. IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops), pp. 6–9, Mar. 2017.
[22] J. GarcíaNieto, E. Alba, and A. C. Olivera, “Swarm intelligence for traffic light scheduling: Application to real urban areas,” Engineering Applications of Artificial Intelligence, vol. 25, no. 2, pp. 274–283, Mar. 2012.
[23] M. Firdous, F. U. Din Iqbal, N. Ghafoor, N. K. Qureshi, and N. Naseer, “Traffic light control system for fourway intersection and tcrossing using fuzzy logic,” in Proc. IEEE International Conference on Artificial Intelligence and Computer Applications (ICAICA), pp. 178–182, Mar. 2019.
[24] J. Pan, I. S. Popa, and C. Borcea, “DIVERT: A distributed vehicular traffic rerouting system for congestion avoidance,” IEEE Transactions on Mobile Computing, vol. 16, no. 1, pp. 58–72, Jan. 2017.
[25] M. Rezaei, H. Noori, D. Rahbari, and M. Nickray, “ReFOCUS: A hybrid fogcloud based intelligent traffic rerouting system,” in Proc. IEEE International Conference on KnowledgeBased Engineering and Innovation (KBEI), pp. 0992–0998, Dec. 2017.
[26] D. H. Widyantoro and M. D. Enjat Munajat, “Fuzzy traffic congestion model based on speed and density of vehicle,” in 2014 International Conference of Advanced Informatics: Concept, Theory and Application (ICAICTA), pp. 321–325, Aug. 2014.
[27] R. Bauza, J. Gozalvez, and J. SanchezSoriano, “Road traffic congestion detection through cooperative vehicletovehicle communications,” in IEEE Local Computer Network Conference, pp. 606–612, Oct. 2010.
[28] Risald, A. E. Mirino, and Suyoto, “Best routes selection using Dijkstra and FloydWarshall algorithm,” in Proc. International Conference on Information Communication Technology and System (ICTS), pp. 155–158, Oct. 2017.
[29] J. Pan, I. S. Popa, K. Zeitouni, and C. Borcea, “Proactive vehicular traffic rerouting for lower travel time,” IEEE Transactions on vehicular technology, vol. 62, no. 8, pp. 3551–3568, Oct. 2013.
[30] J. Hainmueller and Y. Xu, “Ebalance: A stata package for entropy balancing,” Journal of Statistical Software, vol. 54, no. 7, Sep. 2013.
[31] A. Vogel, I. Oremović, R. Šimić, and E. Ivanjko, “Fuzzy traffic light control based on phase urgency,” in Proc. International Symposium ELMAR, pp. 9–14, Sep. 2019.
[32] Q. Wu, F. He, and X. Fan, “The intelligent control system of traffic light based on fog computing,” Chinese Journal of Electronics, vol. 27, no. 6, pp. 1265–1270, Nov. 2018.
[33] M. Behrisch, L. Bieker, J. Erdmann, and D. Krajzewicz, “SUMO–simulation of urban mobility: An overview,” in Proc. International Conference on Advances in System Simulation, Oct. 2011.
[34] A. Wegener, M. Piórkowski, M. Raya, H. Hellbrück, S. Fischer, and J.P. Hubaux, “TraCI: An interface for coupling road traffic and network simulators,” in Proc. Communications and Networking Simulation Symposium, pp. 155––163, Apr. 2008.
[35] M. Haklay and P. Weber, “Openstreetmap: Usergenerated street maps,” IEEE Pervasive Computing, vol. 7, no. 4, pp. 12–18, Oct. 2008.
[36] N. Vandaele, T. Van Woensel, and A. Verbruggen, “A queueing based traffic flow model,” Transportation Research Part D: Transport and Environment, vol. 5, no. 2, pp. 121–135, Mar. 2000.
[37] M. Keller, S. Hausberger, C. Matzer, P. Wüthrich, and B. Notter, “HBEFA version 3.3,” Background documentation, Berne, vol. 12, Apr. 2017.