Smart Transportation: History
View Latest Version
Please note this is an old version of this entry, which may differ significantly from the current revision.
Contributor:
Damilola Oladimeji
,
Khushi Gupta
,
Nuri Alperen Kose
,
Kubra Gundogan
,
Linqiang Ge
,
Fan Liang

As technology continues to evolve, our society is becoming enriched with more intelligent devices that help us perform our daily activities more efficiently and effectively. One of the most significant technological advancements of our time is the Internet of Things (IoT), which interconnects various smart devices (such as smart mobiles, intelligent refrigerators, smartwatches, smart fire alarms, smart door locks, and many more) allowing them to communicate with each other and exchange data seamlessly. 

  • smart transportation
  • internet of things
  • machine learning
  • intelligent systems

1. Introduction

The recent increasing urbanization is a severe multiple global problem that requires a multifaceted answer. The population living in urban areas has increased due to the increased inflow of people to the cities. The United Nations projects that the world’s urban population will reach about 4.9 billion by 2030. This raises many issues, such as pollution, traffic, resources, etc. Due to the development of Internet of Things (IoT), there are a massive number of IoT devices that are connected to the network. Those devices continuously collect data and transmit the data to computing nodes for further analysis. Due to the significant progress of deep learning techniques, many applications leverage deep learning to analyze the collected data and achieve “intelligence” and “automation”. Hence, based on the data analysis and IoT infrastructures, “Smart Cities” as a general application that includes smart grids, smart transportation, smart manufacturing, smart buildings, and much more, have become more popular [1][2][3][4].
Transportation systems are an indispensable part of people’s daily life. Since the population living in urban areas has increased, the world will thus witness explosive growth in motor vehicles, which will have a detrimental impact and contribute to traffic congestion, noise pollution, road accidents, and other issues [5]. Statistics reveal that there were around 290 million registered vehicles in the United States by the end of 2022 [6]. Furthermore, an average of 40% of the population is thought to have spent at least an hour daily on the road [7]. The increasing dependency on transportation systems has significantly increased in recent years, and thus it is common that a person in modern society has to deal with a sizable number of issues with current transportation systems on a typical day, such as traffic congestion, parking problems with limited parking spaces, longer commuting times, high levels of CO2 emissions, increased number of accidents, and many others.
According to estimates, traffic congestion costs the U.S. economy more than 101 billion dollars annually [8], and the economy of the European Union over 2% of GDP [9]. Moreover, as per reports published by the U.S. Federal Highway Administration, it was shown that about 50–60% of all traffic delays are the result of traffic incidents that occurred in the cities [10].
To improve the operational effectiveness of transportation systems, it is imperative to increase the use of information technology [10]. Intelligent Transportation Systems or Smart Transportation is defined as “The application of advanced sensor, computer, electronics, and communication technologies, and management strategies in an integrated manner to improve the safety and efficiency of the surface transportation system” [11]. Smart transportation systems improve traffic flow and safety, reducing travel times and fuel consumption. It is imperative to use IoT infrastructures more and seamlessly integrate information and communication technologies (ICT) to create a sustainable, intelligent transportation system. The implementation and application of cutting-edge communications, electronic, and computing capabilities enable information transfer, traffic flow control, and the administration of transportation networks. Four key concepts, sustainability, integration, safety, and responsiveness, are prioritized when adopting and implementing emerging technologies in transportation systems. These principles will be crucial in attaining the main goals of smart transportation, which are access and mobility, environmental sustainability, and economic development [12].
Smart transportation applications have a great deal of potential to address the problems faced by the constant influx of population to urban areas and deliver a safer traveling experience by extensively coordinating among various traffic control systems from different domains, operating at scale, and processing a sizable amount of data gathered from different sources. Emerging technologies will enable the sustainability of transportation infrastructures. By implementing novel techniques for gathering, processing, and disseminating information based on traffic conditions, they will encourage the efficient use of existing transportation infrastructures to regulate, control, and manage vehicular traffic. This will improve congestion management and lessen its effects [12].

2. Architectures and Frameworks of Smart Transportation Systems

Researchers discuss the various architectures and frameworks adopted for developing smart transportation systems. The architectures researchers discuss are distributed computing, centralized computing, and edge cloud computing. Additionally, researchers also discuss the various communication protocols that are used in smart transportation systems.

2.1. Distributed Computing

Applications for smart transportation, in general, have been supported and delivered in large part by centralized computing, such as cloud computing. The cloud and networking infrastructure, however, face significant challenges in transporting and processing transportation-related data, such as CCTV streams or road sensory data, due to the constantly growing number of linked vehicles. Thus, many applications in this field call for a distributed data processing strategy instead of a centralized one due to the latency sensitivity and large volume of transportation data [13].
For instance, driving in urban settings frequently necessitates making snap judgments about whether or not to change lanes or routes to avoid traffic bottlenecks. An application must collect pertinent information, such as location, driving speeds, traffic flow, or collision events, to assist the driver in making decisions. Additionally, it must analyze those data and respond instantly. In order to meet the objectives in this scenario, the cloud infrastructure has a problem because it must quickly gather and process a large amount of data in a short amount of time. Having a distributed data processing infrastructure greatly reduces this burden of the Cloud while still achieving the latency-sensitivity requirement [14].
A wireless sensor network for Intelligent Transportation System (WITS) is a prototype for an intelligent transportation system suggested by Chen et al. [15]. The information is gathered, and the data is transferred using the WITS system. The vehicle unit, the roadside unit along both sides of the road, and the intersection unit at the intersection are the three different types of WITS nodes utilized in this system. The roadside units get the vehicle parameters from the vehicle unit, which measures them. The intersection unit then receives the information gathered by the roadside unit about the nearby vehicles. Next, the strategy sub-system determines an appropriate scheme in accordance with the predetermined optimization aim after receiving and analyzing the information from other units and passing it to the intersection unit.
CarTel is a mobile distributed sensor computing system created by Hull et al. [16]. An embedded mobile computer connected to a group of sensors is called a CarTel node. Each node collects and processes sensor data locally before sending it to a central gateway, where it is stored in a database and made available for additional analysis and visualization. CarTel generally facilitates the collection, processing, delivery, and visualization of heterogeneous data from intermittently connected mobile nodes. By gathering data on the traffic, this method may help smoothen commute times.

2.1.1. Service Oriented Architectures

According to [17], (SOA) Service Oriented Architecture is a new approach to developing dependable distributed systems, one in which all the interacting components are loosely connected, and the functions are constructed as services. With all the interacting components being loosely connected and the functions being constructed as services, SOA offers an effective method for developing dependable distributed systems.
An intelligent traffic control data center for Beijing is presented by [18] and is based on SOA. The primary justification for choosing SOA for this implementation is that it includes common qualities such as distributed architecture, service-based applications, platform independence, and fine graininess. The Beijing Traffic Data Centre’s architecture aims for thorough data integration, effective data sharing, appropriate data exchange, support for on-demand services, and a cost-effective standard model for future development.
The issue of maintaining the quality of traffic information is mentioned by [19] due to the abundance of Travel Information Service (TIS) providers. This research presents the concept of a traffic information service built on SOA, which combines services or data from several sources to produce trustworthy, accurate, and comprehensive information for the traveling public. In order to collect and incorporate various types of transport information into public-oriented services, two mechanisms are therefore necessary: the first is to build a distributed architecture to integrate services from various providers, and the second is to introduce a set of uniform standards to categorize and present the description of TIS. The TIS system’s foundation in SOA enables interchange with other systems, allowing for simple integration of services from various suppliers.
The design of a GIS (Geographic Information System) transportation system built on web service technology is presented by [20]. Without the need to integrate GIS instruments, the primary goal of the GIS-T web services is to assist ITS applications with spatial data and the processing of various geoprocessing tasks, such as - detecting duplicate addresses, displaying maps, planning routes, etc. The GIS-T web service enables several transportation system departments to create a collaborative workspace, making coordination more straightforward and effective. Traditional GIS software finds accommodating all ITS requirements on a single platform difficult. However, GIS-T web services technology has provided a workable answer to this issue.

2.1.2. Grid Computing

Grid computing uses numerous computer resources to work together and is loosely coupled to solve a specific problem. In grid computing, a big task is split up among numerous workstations to make the most efficient use of the resources that are available [10].
By combining the Grid, Service Oriented Architecture (SOA), and Web Service technologies, [21] introduce the Shanghai Transportation Information Service Application Grid (STISAG), a module for ITS. STISAG primarily focuses on the issue of traffic congestion in Shanghai and provides end users with a variety of real-time traffic and travel information services. The model incorporates information or services from various traffic sources, including the Shanghai Transportation Information Center, the Shanghai Taxi Company, and the Shanghai Bus Company. The model also incorporates Shanghai Grid nodes to handle and store a significant amount of traffic data as well as real-time transportation information.

2.1.3. Fog Computing

Fog is defined as a network of numerous heterogeneous and decentralized devices that interact and may work together to accomplish processing and storage functions without the involvement of outside parties [22]. Fog computing can be used as a solution to the shortcomings of the cloud for smart transportation systems. The Fog computing paradigm uses the processing, storage, and network resources within the edge of the network to augment the capabilities of the cloud [23]. The Fog computing approach may be a preferable option for creating distributed applications [24] since it distributes computer resources closer to people and things, especially for latency-sensitive applications like Smart Transportation apps [25].
One of the primary application domains where the Fog Computing model exhibits the best fit, according to the authors of the original study on fog computing [23], is VANETs applications. This is especially true in light of recent developments in communication technology that enable complete Internet connectivity for infrastructure, automobiles, and other devices.
A vehicular search application using CCTVs networked in transportation infrastructure to look for a suspect driving a car is an example of a fog-based smart transportation application that can be found in [13]. An application is disseminated across various devices, including CCTV cameras, roadside units, and the like, according to a suggested programming model. To identify the vehicle in the frame, images from CCTVs are relayed to neighboring or local computing resources, like a roadside unit. If the recognition attempt fails, the computer system will send a Pan-Tilt-Zoom signal to the camera to direct its attention to a specified area to capture a clearer picture of the suspected car.

2.1.4. Edge Computing

A broad definition of edge is “Enabling technologies that enable computation to occur at the network edge so that computation occurs close to data sources” [26]. The authors in the research [27] present an Edge Computing based Public Vehicle (ECPV) system to schedule ridesharing among travelers and reduce the latency of decision-making by utilizing edge computing. This system would increase traffic efficiency and vehicle occupancy ratios. In order to cut down on travel times and boost traffic efficiency, the research formalizes the public vehicle scheduling problem as an optimization problem with maximum traveler satisfaction as the goal.

2.2. Centralized Computing

Cloud Computing

Several researchers have applied various cutting-edge technologies to create smart transportation systems, but due to its sophisticated electronic data storage and communication medium, cloud computing serves as a prominent player [28]. Cloud computing gives us the ability to create and deploy computing services with minimal effort, equipment, and up-front costs [29].
Incorporating information technology, control technology, sensor technology, communication technology, and system inclusive technology, Cai and Sun [30] describe a contemporary intelligent transportation system based on cloud computing. In order to address the issues and difficulties with the current intelligent transportation system, this article presents a new generation of intelligent transportation systems based on cloud computing. From a technological standpoint, it covers the design of a cloud transportation system. From a managerial one, it shows how to develop the cloud transportation system.
Additionally, Jaworski et al. [31] proposed an urban traffic control system that uses cloud computing. Its objectives are to improve traffic flow and traffic regulation for better participant safety, less fuel consumption, and lower carbon emissions. The urban vehicle control scenario assumes that an off-board control unit that monitors each traffic intersection determines the speed of every vehicle in the controlled region. An Intersection control service (ICS) is the piece of software in charge of that. The system views the cars as cloud services, and they are found and called upon using a cloud computing technique. Targeting all vehicles in the designated zones is accomplished via geographic multicast addressing. Geographical multicast addressing uses a simple addressing mechanism by pointing to all the vehicles in a particular region. ICSs are a component of a city-wide cloud network that manages traffic flow between intersections.
On-demand bus services are demand-responsive transportation services where users can reserve their bus seats before their commute. Although on-demand bus services have been introduced in many cities, their high operating costs make them less popular. Tsubouchi et al. [32] describe their innovative solution considering the issue of high costs. Their solution is based on cloud computing technology, wherein their proposed system includes four major modules: a schedule calculation system, communication devices, a reservation interface, and a database. The primary benefit of this method is the implementation of the software blocks on remote servers. As a result, the service can be operated by the local transport authorities without them having to invest in purchasing their own servers. Thus, the system’s operational expenses are consequently decreased.

2.3. Edge Cloud Computing

The current Intelligent Transportation System (ITS) uses various remote sensors to assess the status of a road network in real-time. It then transmits control signals to roadside systems and road users. To transmit situation awareness and control messages, future ITS may need to communicate with users of the road network and roadside furniture. To transmit driving intention information, such as emergency braking or road conditions, vehicles may need to interact with one another. Additionally, in order to receive advanced notice of impending road conditions or to transmit control signals to controlled intersections to clear lanes for emergency vehicles and public transportation, vehicles may also need to connect with roadside equipment.
Currently, available cloud providers operate from data centers in well-connected nations. However, network latency for end users can be high due to long distances between the user and the cloud data center, and using mobile networks adds additional latency overheads. End users’ expectations are expanding to include those with wireless network connections, many of whom are actively mobile, as opposed to those who are headquartered at fixed physical locations with hard network connections [29].
By developing products based on their core cloud offerings that can run on smaller computing systems while maintaining compatibility with their core cloud platforms, established cloud vendors are beginning to experiment with edge-cloud computing.

2.4. Smart Transportation Communication Protocols

Modern vehicles have increasingly been equipped with a variety of sensors, actuators, and communication devices such as GPS devices, mobile devices, and embedded computers. Vehicles and nearby roadside units (RSUs) nowadays are equipped with powerful communication, sensing, networking, and processing capabilities making a vehicular ad-hoc network (VANET). They can exchange and communicate data and information with other vehicles (Vehicle—to—Vehicle network (V2V)), smart transportation devices (Vehicles—to—Infrastructure (V2I)), and applications and with the outside world using a variety of technologies (Internet of Things (IoT), Cloud computing, and distributed computing) and communication protocols (WiFi, 4G/5G, TCP/IP) which when enforced together can help researchers obtain advanced and improved transportation systems.

This entry is adapted from the peer-reviewed paper 10.3390/s23083880

References

  1. Tekler, Z.D.; Low, R.; Yuen, C.; Blessing, L. Plug-Mate: An IoT-based occupancy-driven plug load management system in smart buildings. Build. Environ. 2022, 223, 109472.
  2. Zhuang, D.; Gan, V.J.; Tekler, Z.D.; Chong, A.; Tian, S.; Shi, X. Data-driven predictive control for smart HVAC system in IoT-integrated buildings with time-series forecasting and reinforcement learning. Appl. Energy 2023, 338, 120936.
  3. Low, R.; Tekler, Z.D.; Cheah, L. Predicting commercial vehicle parking duration using generative adversarial multiple imputation networks. Transp. Res. Rec. 2020, 2674, 820–831.
  4. Kang, H.S.; Lee, J.Y.; Choi, S.; Kim, H.; Park, J.H.; Son, J.Y.; Kim, B.H.; Noh, S.D. Smart manufacturing: Past research, present findings, and future directions. Int. J. Precis. Eng. Manuf.-Green Technol. 2016, 3, 111–128.
  5. Kandogan, Y.; Johnson, S.D. Role of economic and political freedom in the emergence of global middle class. Int. Bus. Rev. 2016, 25, 711–725.
  6. How Many Cars Are in the U.S.? 2022. Available online: https://www.fool.com/the-ascent/research/car-ownership-statistics/ (accessed on 20 July 2022).
  7. Zhang, J.; Wang, F.Y.; Wang, K.; Lin, W.H.; Xu, X.; Chen, C. Data-driven intelligent transportation systems: A survey. IEEE Trans. Intell. Transp. Syst. 2011, 12, 1624–1639.
  8. Eisele, W.L.; Fossett, T.; Schrank, D.L.; Farzaneh, M.; Meier, P.J.; Williams, S.P. Greenhouse Gas Emissions and Urban Congestion: Incorporation of Carbon Dioxide Emissions and Associated Fuel Consumption into Texas A&M Transportation Institute Urban Mobility Report. Transp. Res. Rec. 2014, 2427, 73–82.
  9. Allen, H.; Millard, K.; Stonehill, M. A summary of the proceedings from the united nations climate change conference in doha qatar and their significance for the land transport sector. In Proceedings of the Copenhagen: Bridging the Gap (btg) Initiative, Doha, Qatar, 1 September 2013.
  10. Nasim, R.; Kassler, A. Distributed architectures for intelligent transport systems: A survey. In Proceedings of the 2012 Second Symposium on Network Cloud Computing and Applications, London, UK, 3–4 December 2012; pp. 130–136.
  11. McGregor, R.V.; Eng, P.; MacIver, A. Regional its architectures—From policy to project implementation. In Proceedings of the The Transportation Factor 2003. Annual Conference and Exhibition of the Transportation Association of Canada.(Congres et Exposition Annuels de l’Association des transport du Canada) Transportation Association of Canada (TAC), St. John’s, NL, Canada, 21–24 September 2003.
  12. Guerrero-Ibanez, J.A.; Zeadally, S.; Contreras-Castillo, J. Integration challenges of intelligent transportation systems with connected vehicle, cloud computing, and internet of things technologies. IEEE Wirel. Commun. 2015, 22, 122–128.
  13. Hong, K.; Lillethun, D.; Ramachandran, U.; Ottenwälder, B.; Koldehofe, B. Mobile fog: A programming model for large-scale applications on the internet of things. In Proceedings of the Second ACM SIGCOMM Workshop on Mobile Cloud Computing, Hong Kong, China, 16 August 2013; pp. 15–20.
  14. Giang, N.K.; Leung, V.C.; Lea, R. On developing smart transportation applications in fog computing paradigm. In Proceedings of the 6th ACM Symposium on Development and Analysis of Intelligent Vehicular Networks and Applications, Valletta, Malta, 13–17 November 2016; pp. 91–98.
  15. Chen, W.; Chen, L.; Chen, Z.; Tu, S. Wits: A wireless sensor network for intelligent transportation system. In Proceedings of the First International Multi-Symposiums on Computer and Computational Sciences (IMSCCS’06), Hangzhou, China, 20–24 June 2006; Volume 2, pp. 635–641.
  16. Hull, B.; Bychkovsky, V.; Zhang, Y.; Chen, K.; Goraczko, M.; Miu, A.; Shih, E.; Balakrishnan, H.; Madden, S. Cartel: A distributed mobile sensor computing system. In Proceedings of the 4th International Conference on Embedded networked Sensor Systems, Boulder, CO, USA, 31 October–3 November 2006; pp. 125–138.
  17. Srinivasan, L.; Treadwell, J. An overview of service-oriented architecture, web services and grid computing. HP Softw. Glob. Bus. Unit 2005, 2, 1–13.
  18. Zhou, C.; Duan, J.; Xin, Z. Beijing traffic data center based on SOA technology. In Proceedings of the International Conference on Computer Application and System Modeling (ICCASM 2010), Taiyuan, China, 22–24 October 2010; Volume 15, pp. 232–235.
  19. Li, C. Travel Information Service system for public travel based on SOA. In Proceedings of the Proceedings of 2010 IEEE International Conference on Service Operations and Logistics, and Informatics, Qingdao, China, 15–17 July 2010; pp. 321–324.
  20. Lu, X.l. Research on architecture for web services based uniform GIS transportation information platform. In Proceedings of the 2006 International Conference on Machine Learning and Cybernetics, Dalian, China, 13–16 August 2006; pp. 2770–2775.
  21. Tao, X.; Jiang, C.; Han, Y. Applying SOA to intelligent transportation system. In Proceedings of the 2005 IEEE International Conference on Services Computing (SCC’05) Vol-1, Orlando, FL, USA, 11–15 July2005; Volume 2, pp. 101–104.
  22. Vaquero, L.M.; Rodero-Merino, L. Finding your way in the fog: Towards a comprehensive definition of fog computing. ACM SIGCOMM Comput. Commun. Rev. 2014, 44, 27–32.
  23. Bonomi, F.; Milito, R.; Zhu, J.; Addepalli, S. Fog computing and its role in the internet of things. In Proceedings of the First Edition of the MCC Workshop on Mobile Cloud Computing, Helsinki, Finland, 17 August 2012; pp. 13–16.
  24. Hajibaba, M.; Gorgin, S. A review on modern distributed computing paradigms: Cloud computing, jungle computing and fog computing. J. Comput. Inf. Technol. 2014, 22, 69–84.
  25. Sarkar, S.; Chatterjee, S.; Misra, S. Assessment of the Suitability of Fog Computing in the Context of Internet of Things. IEEE Trans. Cloud Comput. 2015, 6, 46–59.
  26. Shi, W.; Dustdar, S. The promise of edge computing. Computer 2016, 49, 78–81.
  27. Lin, J.; Yu, W.; Yang, X.; Zhao, P.; Zhang, H.; Zhao, W. An edge computing based public vehicle system for smart transportation. IEEE Trans. Veh. Technol. 2020, 69, 12635–12651.
  28. Mobin, G.; Roy, A. A literature review on cloud based smart transport system. In Proceedings of the 2021 5th International Conference on Trends in Electronics and Informatics (ICOEI), Tirunelveli, India, 3–5 June 2021; pp. 1245–1250.
  29. Arthurs, P.; Gillam, L.; Krause, P.; Wang, N.; Halder, K.; Mouzakitis, A. A taxonomy and survey of edge cloud computing for intelligent transportation systems and connected vehicles. IEEE Trans. Intell. Transp. Syst. 2021, 23, 6206–6221.
  30. Cai, W.H.; Sun, T.T. CTS: The new generation intelligent transportation system. In Proceedings of the 2011 Second International Conference on Innovations in Bio-inspired Computing and Applications, Shenzhen, China, 16–18 December 2011; pp. 137–140.
  31. Jaworski, P.; Edwards, T.; Moore, J.; Burnham, K. Cloud computing concept for intelligent transportation systems. In Proceedings of the 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC), Washington, DC, USA, 5–7 October 2011; pp. 391–936.
  32. Tsubouchi, K.; Yamato, H.; Hiekata, K. Innovative on-demand bus system in Japan. IET Intell. Transp. Syst. 2010, 4, 270–279.
More
© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license; additional terms may apply. By using this site, you agree to the Terms and Conditions and Privacy Policy.
This entry is offline, you can click here to edit this entry!
ScholarVision Creations
Feedback