Publications-Theses
Article View/Open
Publication Export
-
題名 以軟體定義網路為基礎的智慧交通控制平台
SDN based Smart Traffic Control Platform作者 林庭寬
Lin, Ting-Kuan貢獻者 張宏慶
Jang, Hung-Chin
林庭寬
Lin, Ting-Kuan關鍵詞 軟體定義網路
物聯網
智慧交通
Software Defined Networking (SDN)
Internet of Things (IoT)日期 2018 上傳時間 5-Sep-2019 16:14:02 (UTC+8) 摘要 隨著物聯網技術高度發展，相關應用也愈來愈廣泛及多元，Gartner 預測到 2020 年，透過物聯網(IoT)相連的裝置將高達 260 億台，其中又以汽車物聯 網的成長速率最快。物聯網的概念是將每個可以聯網的裝置進行連接，彼此之 間共享資訊，以達到資訊共享的目的，並為資料分析與機器學習應用開創新的 應用領域。本篇論文以現行建置在各大路口的紅綠燈為基礎，在紅綠燈上安裝 必要的物聯網裝置，針對上下班時段或因交通事故所造成的交通壅塞狀況，以 及假日節慶可能湧現的大量車潮，提出一個「以軟體定義網路為基礎的智慧交 通控制平台」。在網路管理部份，我們擬藉助軟體定義網路(Software Defined Networking，SDN)監控、設定與管理的優勢，應用於紅綠燈號誌管理，以期 達到動態調節紅燈與綠燈時脈，紓解車流量，降低平均行車時間的目的。系統 整體架構分為交通資訊的中控端，即 SDN 的控制平面(control plane)，與靠 近駕駛人的紅綠燈端，亦即SDN的資料平面(data plane)。控制平面直接和雲 端模組連接，負責計算及監測大範圍區域中紅綠燈與車流量的狀態，當車流量 大時啟動協同管理模式，將許多小區域的紅綠燈群組起來並做協調。資料平面 和霧計算模組連接，主要針對小區域中的紅綠燈做時脈調控。紅綠燈上的物聯 網裝置負責蒐集道路上車輛的行車資訊，透過軟體定義網路為基礎的智慧交通 控制平台，結合無線通訊、軟體定義網路及雲與霧計算等技術，並透過提出的 演算法達到紅綠燈自適應調配的目標，進而紓解壅塞的車流，減少平均行車時間。在智慧交通控制平台中，實驗結果顯示所提出的紅綠燈號誌演算法，可有 效降低行車時間最高達79.7%，且在100公尺x 100公尺的模擬地圖中，隨著車 輛數由 100 輛車增加到 600 輛車，能有效減少等待紅燈的時間，相對縮短了整 段路程所需要的行車時間。當單位面積車輛數增加時，愈能顯示該演算法所發 揮的效益。
With the trend of the rapid development of the Internet of Things (IoT), therelated applications are becoming more and more diverse. Gartner predicted that by 2020, there are up to 26 billion devices connected via the IoT devices. Among these, one major part is the automotive IoT devices. The concept of the IoT is to connect every device that can be connected, share information, to achieve the purpose of information sharing, and open up new application areas for data analysis and machine learning. This research is based on the assumption that there are IoT devices embedded in the traffic lights at road intersections. An "SDN Based Smart Traffic Control Platform" is proposed for the traffic congestion which is caused by traffic accidents or a large number of traffic flows that may arise during holiday festivals. In the part of network management, we apply Software Defined Networking (SDN) to traffic light management based on its underlying advantages like monitoring, setting, and management, to dynamically adjust the timing of stop light and thus reduce the average travel time. The system structure consists of the central control of the traffic, which is the control plane of the SDN, and the traffic lights close to the vehicles, which is the data plane of the SDN. The IoT devices on the traffic lights are responsible for collecting information from the vehicles. This kind of information is exchanged through IoT devices and SDN.In summary, this research proposed an "SDN Based Smart Traffic Control Platform" that combines wireless communication, software-defined networking, and other relevant technologies together with the proposed algorithm to effectively relieve traffic congestion and reduce average travel time. Experiment results show that the proposed algorithm is able to reduce the moving time up to 79.7%. With the number of vehicles increased from 100 to 600 on an 100m x 100m simulating environment, the waiting time for red lights can be largely reduced.參考文獻 [1] M. S. Ahmed and A. R. Cook, “Analysis of Freeway Traffic Time-Series Data by Using Box–Jenkins Techniques,” Transp. Res. Rec., no. 722, pp. 1– 9, 1979.[2] Flavio Bonomi, Rodolfo Milito, Jiang Zhu, Sateesh Addepalli, Cisco Systems Inc.,” Fog Computing and Its Role in the Internet of Things,” Aug. 2012.[3] Christos Bouras, Anastasia Kollia and Andreas Papazois, "SDN & NFV in 5G: Advancements and Challenges", 20th Conference on Innovations in Clouds, Internet and Networks (ICIN) , 2017.[4] Yi Cao, Jinhua Guo, Yue Wu, “SDN Enabled Content Distribution in Vehicular Networks,” Innovative Computing Technology (INTECH), 2014 Fourth International Conference on, IEEE 164-169, Electronic ISBN: 978- 1-4799-4233-6.[5] Yuan-Yuan Chen, Yisheng Lv, Zhenjiang Li, and Fei-Yue Wang, “Long Short-Term Memory Model for Traffic Congestion Prediction with Online Open Data,” IEEE 19th International Conference on Intelligent Transportation System, 2016.[6] Cisco White Paper, “Fog Computing and the Internet of Things: Extend the Cloud to Where the ThingsAre” ,https://www.cisco.com/c/dam/en_us/solutions/trends/iot/docs/comput ing-overview.pdf, Printed in USA, 2015.[7] Tej Tharang Dandala, Vallidevi Krishnamurthy, Rajan Alwan, "Internet of Vehicles (IoV) for Traffic Management" International Conference on Computer, Communication and Signal Processing (ICCCSP), 2017.[8] Beying Deng and Xufeng Zhang, "Car Networking Application in Vehicle Safety", IEEE Workshop on Advanced Research and Technology in Industry Applications (WARTIA), 2014.[9] Bilal Ghazal, Khaled ElKhatib, Khaled Chahine, "Smart Traffic Light Control System", Third International Conference on Electrical, Electronics, Computer Engineering and their Applications (EECEA), 2016.[10] Sushant Gautam, Aryasupurna Timalsina, Sumana Manandhar and Aditi Gajurel,”Real Time-Based Smart Traffic Light System with its Simulation using 8051 Microcontroller”, KEC Conference, At Kathmandu,Nepal,Volume 1st,September 2018[11] Jehn-Ruey Jiang, Hsin-Wen Huang, Ji-Hau Liao, and Szu-Yuan Chen, “Extending Dijkstra’s Shortest Path Algorithm for Software Defined Networking,” Department of Computer Science and Information Engineering, National Central University Jhongli City, Taiwan, September 2014, Conference: 2014 16th Asia-Pacific Network Operations and Management Symposium (APNOMS).[12] Ievgeniia Kuzminvkh, "Development of Traffic Light Control Algorithm in Smart Municipal Network", 13th International Conference on Modern Problems of Radio Engineering, Telecommunications and Computer Science (TCSET), 2016.[13] Héctor Jalil Desirena Lopez, Mario Siller, Iván Huerta, "Internet of vehicles: Cloud and Fog Computing Approaches", IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI),2017.[14]Frank Po-Chen Lin, Zsehong Tsai, “Hierarchial Edge-Cloud SDNController System with Optimal Adaptive Resource Allocation for Load-Balancing”, IEEE Systems Journal, 12 February 2019.[15] Ivan Stojmenovic and Sheng Wen, “The Fog Computing Paradigm:Scenarios and Security Issues,” 2014 Federated Conference on ComputerScience and Information Systems (FedCSIS), Oct. 2014.[16] M. Van Der Voort, M. Dougherty and S. Watson, ‘Combining Kohonen Maps with ARIMA Time Series Models to Forecast Traffic Flow,’Transport. Res. C: Emerging Technol., 1996, 4, (5), pp. 307–318.[17] B. M. Williams and L. A. Hoel, "Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis andEmpirical Results," J. Transp. Eng., vol. 129, no. 6, pp. 664–672, 2003.[18] Yu Xiao and Chao Zhu "Vehicular Fog computing: Vision and Challenges"IEEE International Conference on Pervasive Computing andCommunications Workshops (PerCom Workshops), 2017.[19] Wenchao Xu, Haibo Zhou, Nan Cheng, "Internet of Vehicles in Big Data Era" IEEE/CAA Journal of Automatica Sinica (Volume: 5, Issue: 1) , Jan.2018.[20] Kai Xiong, Supeng Leng, Jie Hu, Xiaosha Chen, Kun Yang, “SmartNetwork Slicing for Vehicular Fog-RANs,” IEEE Transcations on VehiclarTechnology, 19 February 2019.[21] Shun-Ren Yang, Yu-Ju Su, Yao-Yuan Chang, Hui-Nien Hung, “Short-TermTraffic Prediction for Edge Computing-Enhanced Autonomous and Connected Cars,” IEEE Transcations on Vehicular Technology, 13 February 2019.[22] Zheng Zhao, Weihai Chen, Xingming Wu, Peter C. Y. Chen, Jingmeng Liu, “LSTM Network: A Deep Learning Approach for Short-Term Traffic Forecast,” IET Intelligent Transport System Volume 11, Issue 2, March 2017.[23] Shaokun Zhang, Zejian Kang, Zhemin Zhang, Congren Lin, Cheng Wang, Jonathan Li, “A Hybrid Model for Foreasting Traffic Flow: Using Layerwise Structure and Markov Transition Matrix,” IEEE Access, 22 February 2019.[24] “SDN和OpenFlow介紹”, http://www.just4coding.com/blog/2016/12/31/introducing- openflow/,Retrieved Date July 25, 2018[25] “剖析交換器Pipeline關鍵流程看懂SDN網路封包轉發處理,深入 OpenFlow 協定 詳解 Flow Table 比對機制”,http://www.netadmin.com.tw/article_print.aspx?sn=1610070003, RetrievedDate July 25, 2018[26] “實戰錄 | 絕對乾貨!SDN controller Ryu 答疑解惑”,https://read01.com/z3KeQO.html#.W1hTyS33Wi4, Retrieved Date July 25,2018[27] 陳一昌、張開國、張仲杰、何志宏、邱素文、徐國鈞、石家豪、蔣封文、吳悅慈、莊捷媚, “都市交通號誌全動態控制邏輯模式之研究(IV) -網路路口實例研究,” 96-10-3311,MOTC-IOT-95-SDB001, 交通部運輸 研究所，中華民國 96 年 3 月。 描述 碩士
國立政治大學
資訊科學系
104753016資料來源 http://thesis.lib.nccu.edu.tw/record/#G0104753016 資料類型 thesis dc.contributor.advisor 張宏慶 zh_TW dc.contributor.advisor Jang, Hung-Chin en_US dc.contributor.author (Authors) 林庭寬 zh_TW dc.contributor.author (Authors) Lin, Ting-Kuan en_US dc.creator (作者) 林庭寬 zh_TW dc.creator (作者) Lin, Ting-Kuan en_US dc.date (日期) 2018 en_US dc.date.accessioned 5-Sep-2019 16:14:02 (UTC+8) - dc.date.available 5-Sep-2019 16:14:02 (UTC+8) - dc.date.issued (上傳時間) 5-Sep-2019 16:14:02 (UTC+8) - dc.identifier (Other Identifiers) G0104753016 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/125638 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 資訊科學系 zh_TW dc.description (描述) 104753016 zh_TW dc.description.abstract (摘要) 隨著物聯網技術高度發展，相關應用也愈來愈廣泛及多元，Gartner 預測到 2020 年，透過物聯網(IoT)相連的裝置將高達 260 億台，其中又以汽車物聯 網的成長速率最快。物聯網的概念是將每個可以聯網的裝置進行連接，彼此之 間共享資訊，以達到資訊共享的目的，並為資料分析與機器學習應用開創新的 應用領域。本篇論文以現行建置在各大路口的紅綠燈為基礎，在紅綠燈上安裝 必要的物聯網裝置，針對上下班時段或因交通事故所造成的交通壅塞狀況，以 及假日節慶可能湧現的大量車潮，提出一個「以軟體定義網路為基礎的智慧交 通控制平台」。在網路管理部份，我們擬藉助軟體定義網路(Software Defined Networking，SDN)監控、設定與管理的優勢，應用於紅綠燈號誌管理，以期 達到動態調節紅燈與綠燈時脈，紓解車流量，降低平均行車時間的目的。系統 整體架構分為交通資訊的中控端，即 SDN 的控制平面(control plane)，與靠 近駕駛人的紅綠燈端，亦即SDN的資料平面(data plane)。控制平面直接和雲 端模組連接，負責計算及監測大範圍區域中紅綠燈與車流量的狀態，當車流量 大時啟動協同管理模式，將許多小區域的紅綠燈群組起來並做協調。資料平面 和霧計算模組連接，主要針對小區域中的紅綠燈做時脈調控。紅綠燈上的物聯 網裝置負責蒐集道路上車輛的行車資訊，透過軟體定義網路為基礎的智慧交通 控制平台，結合無線通訊、軟體定義網路及雲與霧計算等技術，並透過提出的 演算法達到紅綠燈自適應調配的目標，進而紓解壅塞的車流，減少平均行車時間。在智慧交通控制平台中，實驗結果顯示所提出的紅綠燈號誌演算法，可有 效降低行車時間最高達79.7%，且在100公尺x 100公尺的模擬地圖中，隨著車 輛數由 100 輛車增加到 600 輛車，能有效減少等待紅燈的時間，相對縮短了整 段路程所需要的行車時間。當單位面積車輛數增加時，愈能顯示該演算法所發 揮的效益。 zh_TW dc.description.abstract (摘要) With the trend of the rapid development of the Internet of Things (IoT), therelated applications are becoming more and more diverse. Gartner predicted that by 2020, there are up to 26 billion devices connected via the IoT devices. Among these, one major part is the automotive IoT devices. The concept of the IoT is to connect every device that can be connected, share information, to achieve the purpose of information sharing, and open up new application areas for data analysis and machine learning. This research is based on the assumption that there are IoT devices embedded in the traffic lights at road intersections. An "SDN Based Smart Traffic Control Platform" is proposed for the traffic congestion which is caused by traffic accidents or a large number of traffic flows that may arise during holiday festivals. In the part of network management, we apply Software Defined Networking (SDN) to traffic light management based on its underlying advantages like monitoring, setting, and management, to dynamically adjust the timing of stop light and thus reduce the average travel time. The system structure consists of the central control of the traffic, which is the control plane of the SDN, and the traffic lights close to the vehicles, which is the data plane of the SDN. The IoT devices on the traffic lights are responsible for collecting information from the vehicles. This kind of information is exchanged through IoT devices and SDN.In summary, this research proposed an "SDN Based Smart Traffic Control Platform" that combines wireless communication, software-defined networking, and other relevant technologies together with the proposed algorithm to effectively relieve traffic congestion and reduce average travel time. Experiment results show that the proposed algorithm is able to reduce the moving time up to 79.7%. With the number of vehicles increased from 100 to 600 on an 100m x 100m simulating environment, the waiting time for red lights can be largely reduced. en_US dc.description.tableofcontents 第一章 緒論 11.1 研究背景 11.2 研究動機 11.3 研究目標 21.4 論文架構 4第二章 相關研究 52.1 物聯網(Internet of Things，IoT) 52.2 軟體定義網路(Software Defined Networking，SDN) 52.2.1 OpenFlow 72.2.2 Ryu Controller 82.3 雲計算(Cloud Computing) 92.4 霧計算(Fog Computing) 92.5 車載網路(Vehicular Ad-hoc NETwork , VANET) 122.6 交通控制理論 13第三章 研究方法 143.1 問題分析 143.1.1 大數據與系統負載 143.1.2 系統即時性服務 143.1.3 多元化車載網路 153.1.4 網路頻寬分配 153.2 方法論 163.2.1 系統架構 163.2.1.1 智慧路由 173.2.1.2 智慧運算 193.2.2 系統功能模組 203.2.2.1 號誌變換模組 203.2.2.2 運算相關參數 213.2.3 交通號誌變換演算法 23第四章 模擬實驗與結果分析 334.1 實驗環境 334.1.1 SDN 環境架設與設定 344.1.2 伺服器群架設與設定 364.1.3 VanetSimulator 車載模擬器相關設定 364.1.4 實驗環境介接 394.2 實驗結果與分析 434.2.1 實驗參數 434.2.2 實驗一 :比較不同密度下，旅行時間與等待時間之關係 434.2.3 實驗二 :比較有/無演算法，旅行時間長短之關係 484.2.4 實驗三 :比較不同網路架構下，傳送封包所需的流量 49第五章 結論與未來研究 535.1 結論 535.2 未來研究 53參考文獻 55 zh_TW dc.format.extent 7120037 bytes - dc.format.mimetype application/pdf - dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0104753016 en_US dc.subject (關鍵詞) 軟體定義網路 zh_TW dc.subject (關鍵詞) 物聯網 zh_TW dc.subject (關鍵詞) 智慧交通 zh_TW dc.subject (關鍵詞) Software Defined Networking (SDN) en_US dc.subject (關鍵詞) Internet of Things (IoT) en_US dc.title (題名) 以軟體定義網路為基礎的智慧交通控制平台 zh_TW dc.title (題名) SDN based Smart Traffic Control Platform en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) [1] M. S. Ahmed and A. R. Cook, “Analysis of Freeway Traffic Time-Series Data by Using Box–Jenkins Techniques,” Transp. Res. Rec., no. 722, pp. 1– 9, 1979.[2] Flavio Bonomi, Rodolfo Milito, Jiang Zhu, Sateesh Addepalli, Cisco Systems Inc.,” Fog Computing and Its Role in the Internet of Things,” Aug. 2012.[3] Christos Bouras, Anastasia Kollia and Andreas Papazois, "SDN & NFV in 5G: Advancements and Challenges", 20th Conference on Innovations in Clouds, Internet and Networks (ICIN) , 2017.[4] Yi Cao, Jinhua Guo, Yue Wu, “SDN Enabled Content Distribution in Vehicular Networks,” Innovative Computing Technology (INTECH), 2014 Fourth International Conference on, IEEE 164-169, Electronic ISBN: 978- 1-4799-4233-6.[5] Yuan-Yuan Chen, Yisheng Lv, Zhenjiang Li, and Fei-Yue Wang, “Long Short-Term Memory Model for Traffic Congestion Prediction with Online Open Data,” IEEE 19th International Conference on Intelligent Transportation System, 2016.[6] Cisco White Paper, “Fog Computing and the Internet of Things: Extend the Cloud to Where the ThingsAre” ,https://www.cisco.com/c/dam/en_us/solutions/trends/iot/docs/comput ing-overview.pdf, Printed in USA, 2015.[7] Tej Tharang Dandala, Vallidevi Krishnamurthy, Rajan Alwan, "Internet of Vehicles (IoV) for Traffic Management" International Conference on Computer, Communication and Signal Processing (ICCCSP), 2017.[8] Beying Deng and Xufeng Zhang, "Car Networking Application in Vehicle Safety", IEEE Workshop on Advanced Research and Technology in Industry Applications (WARTIA), 2014.[9] Bilal Ghazal, Khaled ElKhatib, Khaled Chahine, "Smart Traffic Light Control System", Third International Conference on Electrical, Electronics, Computer Engineering and their Applications (EECEA), 2016.[10] Sushant Gautam, Aryasupurna Timalsina, Sumana Manandhar and Aditi Gajurel,”Real Time-Based Smart Traffic Light System with its Simulation using 8051 Microcontroller”, KEC Conference, At Kathmandu,Nepal,Volume 1st,September 2018[11] Jehn-Ruey Jiang, Hsin-Wen Huang, Ji-Hau Liao, and Szu-Yuan Chen, “Extending Dijkstra’s Shortest Path Algorithm for Software Defined Networking,” Department of Computer Science and Information Engineering, National Central University Jhongli City, Taiwan, September 2014, Conference: 2014 16th Asia-Pacific Network Operations and Management Symposium (APNOMS).[12] Ievgeniia Kuzminvkh, "Development of Traffic Light Control Algorithm in Smart Municipal Network", 13th International Conference on Modern Problems of Radio Engineering, Telecommunications and Computer Science (TCSET), 2016.[13] Héctor Jalil Desirena Lopez, Mario Siller, Iván Huerta, "Internet of vehicles: Cloud and Fog Computing Approaches", IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI),2017.[14]Frank Po-Chen Lin, Zsehong Tsai, “Hierarchial Edge-Cloud SDNController System with Optimal Adaptive Resource Allocation for Load-Balancing”, IEEE Systems Journal, 12 February 2019.[15] Ivan Stojmenovic and Sheng Wen, “The Fog Computing Paradigm:Scenarios and Security Issues,” 2014 Federated Conference on ComputerScience and Information Systems (FedCSIS), Oct. 2014.[16] M. Van Der Voort, M. Dougherty and S. Watson, ‘Combining Kohonen Maps with ARIMA Time Series Models to Forecast Traffic Flow,’Transport. Res. C: Emerging Technol., 1996, 4, (5), pp. 307–318.[17] B. M. Williams and L. A. Hoel, "Modeling and Forecasting Vehicular Traffic Flow as a Seasonal ARIMA Process: Theoretical Basis andEmpirical Results," J. Transp. Eng., vol. 129, no. 6, pp. 664–672, 2003.[18] Yu Xiao and Chao Zhu "Vehicular Fog computing: Vision and Challenges"IEEE International Conference on Pervasive Computing andCommunications Workshops (PerCom Workshops), 2017.[19] Wenchao Xu, Haibo Zhou, Nan Cheng, "Internet of Vehicles in Big Data Era" IEEE/CAA Journal of Automatica Sinica (Volume: 5, Issue: 1) , Jan.2018.[20] Kai Xiong, Supeng Leng, Jie Hu, Xiaosha Chen, Kun Yang, “SmartNetwork Slicing for Vehicular Fog-RANs,” IEEE Transcations on VehiclarTechnology, 19 February 2019.[21] Shun-Ren Yang, Yu-Ju Su, Yao-Yuan Chang, Hui-Nien Hung, “Short-TermTraffic Prediction for Edge Computing-Enhanced Autonomous and Connected Cars,” IEEE Transcations on Vehicular Technology, 13 February 2019.[22] Zheng Zhao, Weihai Chen, Xingming Wu, Peter C. Y. Chen, Jingmeng Liu, “LSTM Network: A Deep Learning Approach for Short-Term Traffic Forecast,” IET Intelligent Transport System Volume 11, Issue 2, March 2017.[23] Shaokun Zhang, Zejian Kang, Zhemin Zhang, Congren Lin, Cheng Wang, Jonathan Li, “A Hybrid Model for Foreasting Traffic Flow: Using Layerwise Structure and Markov Transition Matrix,” IEEE Access, 22 February 2019.[24] “SDN和OpenFlow介紹”, http://www.just4coding.com/blog/2016/12/31/introducing- openflow/,Retrieved Date July 25, 2018[25] “剖析交換器Pipeline關鍵流程看懂SDN網路封包轉發處理,深入 OpenFlow 協定 詳解 Flow Table 比對機制”,http://www.netadmin.com.tw/article_print.aspx?sn=1610070003, RetrievedDate July 25, 2018[26] “實戰錄 | 絕對乾貨!SDN controller Ryu 答疑解惑”,https://read01.com/z3KeQO.html#.W1hTyS33Wi4, Retrieved Date July 25,2018[27] 陳一昌、張開國、張仲杰、何志宏、邱素文、徐國鈞、石家豪、蔣封文、吳悅慈、莊捷媚, “都市交通號誌全動態控制邏輯模式之研究(IV) -網路路口實例研究,” 96-10-3311,MOTC-IOT-95-SDB001, 交通部運輸 研究所，中華民國 96 年 3 月。 zh_TW dc.identifier.doi (DOI) 10.6814/NCCU201900658 en_US
