逢甲大學 資 訊 工 程 學 系 博 士 班 博士論文 車聯網環境中的交通壅塞分析與監控 系統之研究 A Study of Traffic Congestion Analysis and Monitoring System on Internet of Vehicles 指導教授：竇其仁 研 究 生：阮杜賓 中 華 民 國 一 百 零 七 年 六 月 A Study of Traffic Congestion Analysis and Monitoring System on Internet of Vehicles Acknowledgement First and foremost, I would like to express my greatest and sincere gratitude to my advisor, Prof. Chyi-Ren Dow for his motivation, immense knowledge, and patience, especially for the continual supports of my Ph. It is an honor for me to be accepted as one of his Ph. I am truly indebted to all his ideas, time and document is used for viewing purpose only.
Any other purposes of using require the acceptance of National Central Library of Taiwan, author, and author's advisor of this thesis. funding contributions that make my Ph. experience energizing and productive. The passion and enthusiasm he has for the research were inspired and motivational to me, especially during tough periods in the Ph.
I am also grateful for the excellent advices he has offered as an outstanding professor. These advices encourage me in all the time of research and dissertation writing. From the bottom of my heart, I am sincerely indebted to him throughout my life time. In addition, I would like to thank my dissertation committee: Prof.
Shiow-Fen Hwang, Prof. Tsan-Pin Wang, Prof. Lien-Wu Chen, Prof. Chun-Hua Chen, Prof.
Meng- Yen Hsieh, and Prof. Yi-Chung Chen, for their insightful encouragement, but also for the meaningful suggestions which help me to widen my research from various perspectives. I am indebted to Dr. Jen-Cheng Chiu, Mr.
Po-Yu Lai, and Mr. Kuan-Chieh Wan, who provided me access to research materials and a great opportunity to work in their team as an intern. Without their precious support, it would not be possible for this research to be successfully conducted. I appreciate my mates at Mobile Computing lab for the inspiring discussions, unconditional supports, and for all the fun we have had in the last four years.
In particular, my grateful directly goes to Dr. Yu-Hong Lee, who enlightens me the first glance of research skills and Ms. Yu-Yun Chang (Amber) for providing essential local supports during the years. My time at Feng Chia University and abroad was made as an i FCU e-Theses & Dissertations (2018) A Study of Traffic Congestion Analysis and Monitoring System on Internet of Vehicles enjoyable period due to many friends became a part of my life.
I am appreciative for my backpacking buddies and memorable trips to various famous places in Taiwan, for time spent with roommates, for Hyde Lu’s hospitality as introducing me many interesting things about Taiwan’s culture, and for many other great friends I have ever met. document is used for viewing purpose only. Any other purposes of using require the acceptance of National Central Library of Taiwan, author, and author's advisor of this thesis. Last but not least, I owe thanks to my family members for all their encouragements and faith on me.
For my parents, who raised me up with a selfless love and give me unlimited support for any decision I made. For my brothers, who share the understanding and provide timely supports. And most of all for my loving, supportive and patient wife and son whose faithful contribution during the final stages of this Ph. is so appreciated.
ii FCU e-Theses & Dissertations (2018) A Study of Traffic Congestion Analysis and Monitoring System on Internet of Vehicles 摘要 近年來，車聯網已成為了一個興新的研究話題。該技術可以用來幫助現在的 交通運輸系統更加智能化，並解決一些問題，如：交通壅塞。然而，現今在車聯 網環境下的運輸系統在解決交通壅塞問題時，無法滿足準確性、立即性以及相容 性的需求與挑戰。為了解決這個問題，本研究針對車聯網提出一個基於 MQTT 技 document is used for viewing purpose only. Any other purposes of using require the acceptance of National Central Library of Taiwan, author, and author's advisor of this thesis. 術的交通壅塞分析與監控系統，該系統包含了資料收集、建立分段結構、建立車 流模型、本地路段壅塞預測以及起迄路線壅塞預測等部分。這個系統從台中市政 府所提供的公開資料取得即時資訊，每個路段的交通流模型將會被正規化，並使 用基於模糊理論與路段標頭來預測本地路段的交通壅塞狀態。為了加強預測效率， 這個研究也同時呈現了最小化錯誤率的驗證，該驗證基於 Rankine Hugoniot 條 件下。我們開發了一個使用本方法提供給汽車的起迄交通估計服務，並實作了一 個雛形系統去驗證本方法的彈性，實驗結果也在精確度與系統回應時間上驗證了 此方法可以有效率地預測交通壅塞。 關鍵詞: 車輛偵測器, 消息隊列遙測傳輸(MQTT), 交通壅塞, 資料分析, 車流量 預測, 模糊理論, 起迄估計. iii FCU e-Theses & Dissertations (2018) A Study of Traffic Congestion Analysis and Monitoring System on Internet of Vehicles Abstract In recent years, the Internet of Vehicles (IoV) has been an emerging research topic.
Its techniques can be used to transform current transport systems into intelligent transport systems and resolve problems in transport, including traffic congestion. However, existing transport systems do not fully consider and resolve accuracy, document is used for viewing purpose only. Any other purposes of using require the acceptance of National Central Library of Taiwan, author, and author's advisor of this thesis. instantaneity, and compatibility challenges while resolving traffic congestion in an IoV environment.
To deal with this problem, this study proposes an MQTT-based traffic congestion analysis and monitoring system for the IoV, which includes data collection, segmented structure establishment, traffic-flow modelling, local segment traffic congestion prediction, and origin-destination traffic congestion estimation. The proposed system collects real data from open data provided by Taichung City Government. Macroscopic model-based traffic-flow factors were formalized for each segment of the segmented structure on the basis of the analysis results obtained using the collected data. Fuzzy rules-based local segment traffic congestion prediction was performed using segment headers to determine the traffic congestion state.
To enhance prediction efficiency, this study also presents a verification process for minimizing false predictions which is based on the Rankine-Hugoniot condition. An origin-destination traffic congestion estimation service for vehicles was developed on the basis of the proposed scheme. To verify the feasibility of the proposed system, a prototype was implemented. The experimental results demonstrate that the proposed scheme can effectively predict traffic congestion in terms of accuracy and system response time.
Keywords: Vehicle Detector Sensor, MQTT, Traffic Congestion, Data Analysis, Traffic Forecasting, Fuzzy-based Rules, Origin-destination Estimation. iv FCU e-Theses & Dissertations (2018) A Study of Traffic Congestion Analysis and Monitoring System on Internet of Vehicles Table of Contents Acknowledgement. iv document is used for viewing purpose only. Any other purposes of using require the acceptance of National Central Library of Taiwan, author, and author's advisor of this thesis.
Table of Contents. v List of Figures. viii List of Tables. ix Chapter 1 Introduction .2 Overview of Research.
8 Chapter 2 Related Work.1 Historical Traffic Data Analysis Strategies .2 Mobility Structures for Data Sharing and Management in Vehicular Environment .3 IoV and Light-weight Protocols .4 Traffic Congestion Forecasting Methodologies. 17 Chapter 3 Segmented Structure Scheme .1 Segmented Structure Establishment .1 VD Sensors Based Segment Demarcation.2 E-Tag Sensors Based Segment Demarcation. 23 v FCU e-Theses & Dissertations (2018) A Study of Traffic Congestion Analysis and Monitoring System on Internet of Vehicles 3.2 Traffic Data Collection Mechanism .1 MQTT Publish/Subscribe Framework.2 Vehicle Detector and E-tag Based Segment Data Collection.3 Vehicular Data Collection. 29 document is used for viewing purpose only.
Any other purposes of using require the acceptance of National Central Library of Taiwan, author, and author's advisor of this thesis. Chapter 4 Traffic Modelling and Analysis .1 Traffic Flow Modelling .2 VD Based Segment Traffic Modeling .3 E-tag Based Segment Traffic Modeling .2 Traffic Congestion Observation Map. 43 Chapter 5 Traffic Congestion Monitoring Scheme .1 Local Segment Traffic Congestion Prediction .1 Fuzzy-based Traffic Congestion Evaluation .2 Traffic Congestion Condition Verification.2 Origin-destination Traffic Congestion Estimation. 57 Chapter 6 System Prototype and Implementation.
66 Chapter 7 Experimental Results.1 Analysis Results of Traffic Congestion Coefficient .2 Average System Response Time. 72 vi FCU e-Theses & Dissertations (2018) A Study of Traffic Congestion Analysis and Monitoring System on Internet of Vehicles 7.3 Local Segment Traffic Congestion Prediction Results .4 Origin-Destination Traffic Congestion Estimation Results. 81 document is used for viewing purpose only. Any other purposes of using require the acceptance of National Central Library of Taiwan, author, and author's advisor of this thesis.
86 vii FCU e-Theses & Dissertations (2018) A Study of Traffic Congestion Analysis and Monitoring System on Internet of Vehicles List of Figures Figure 3.1 VD Sensors Based Demarcation .2 E-tag Sensors Based Demarcation.3 Publish/ Subscribe Framework .1 E-tag Segment Traffic Data Modelling. 42 document is used for viewing purpose only. Any other purposes of using require the acceptance of National Central Library of Taiwan, author, and author's advisor of this thesis.2 Traffic Congestion Observation Map .1 Velocity and Density Performance Index Membership Function .2 Traffic Flows MQTT Topic .3 Origin-destination MQTT Topic .4 Origin-destination Estimation .2 Congestion Map on Control Center Interface .3 Section Information on Control Center Interface .4 Client Interface of Traffic Congestion Monitoring System .1 Traffic Congestion Coefficient Analysis Results of School Area .2 Traffic Congestion Coefficient Analysis Results of Business Area .3 Area-based Traffic Congestion Coefficient Comparison.4 Delay Time Comparison between MQTT and AMQP Protocols .5 System Response Time .6 Traffic Congestion Evaluation Results Using KNN Method .7 Traffic Congestion Evaluation Results Using the Proposed Method .8 Origin-destination Estimation Results. 80 viii FCU e-Theses & Dissertations (2018) A Study of Traffic Congestion Analysis and Monitoring System on Internet of Vehicles List of Tables Table 3.2 VD Data Fields .3 E-tag Data Fields .4 Real-Time Vehicle’s Data Fields.
30 document is used for viewing purpose only. Any other purposes of using require the acceptance of National Central Library of Taiwan, author, and author's advisor of this thesis.2 Traffic Congestion Coefficient Table .1 Fuzzy Rules for Traffic Congestion Evaluation .2 Inflow Neighbor Table .1 QoS Levels Assignment.1 Parameters of SUMO Simulation. 69 ix FCU e-Theses & Dissertations (2018) A Study of Traffic Congestion Analysis and Monitoring System on Internet of Vehicles Chapter 1 Introduction Transportation is one of none separable parts of human society and has close relationship to other areas of society development. Over the last few decades, numerous studies were proposed as the effort to make transportation become more convenient.
document is used for viewing purpose only. Any other purposes of using require the acceptance of National Central Library of Taiwan, author, and author's advisor of this thesis. Various heterogeneous sensors and techniques [31, 65] were used to transform traditional transport systems into intelligent transport systems (ITS) and resolve problems in transport. In recent years, traffic congestion has become a serious problem in cities, which not only negatively affects the daily lives of humans but also impedes stable economic and societal development.
Traffic congestion increases air pollution, travel time, and economic losses [13]. These effects of traffic congestion require analysis and forecasting scheme to monitor and reduce in advance. Governments increasingly strive to manage and resolve traffic congestion; however, the task is difficult because of the complexity of the problem; specifically, traffic congestion is difficult to predict. Traffic congestion may occur when slower cars share roads with faster cars, or when following cars make a lane changing to overtake a bus exhibiting stop-and-go behavior, or an accident suddenly on a road.
Generally, traffic congestion occurs when the number of vehicles reaches the capacity of a road segment. In this circumstance, the average vehicle speed and number of vehicles that pass the road segment markedly decrease. The complexity of traffic congestion is also reflected in its dynamic and interrelated characteristics. Traffic congestion can propagate from a congested road segment to neighboring road segments.
Because of these complexities, fully automatic analysis of traffic congestion is difficult to achieve. Several methods [1, 4, 10, 48, 68, 72, 75] were applied to determine traffic congestion condition. These technologies are beneficiary in traffic congestion management; however, they possess several drawbacks, such as, inaccurate traffic estimation, flexibility problem, 1 FCU e-Theses & Dissertations (2018) A Study of Traffic Congestion Analysis and Monitoring System on Internet of Vehicles bandwidth problems and redundant data, especially in an urban environment.1 Motivation ITS not only make traveling of individual vehicle become more convenient and enjoyable by providing different entertainment, information services and utilities, but also provide a capability of traffic transition management [26], which is an essential document is used for viewing purpose only. Any other purposes of using require the acceptance of National Central Library of Taiwan, author, and author's advisor of this thesis.
factor for traffic planning, further road structure development, and resolve traffic problems.