Parth Bhavsar

Decision Support System for Predicting Traffic Diversion Impact Across Transportation Networks Using Support Vector Regression

This paper describes follow-up research to a previous study by the authors that used case-based reasoning (CBR) and support vector regression (SVR) to evaluate the likely impacts of implementing diversion strategies in response to incidents on highway networks. In the previous study, the training and testing of the CBR and SVR tools were performed on a single transportation network from South Carolina, which limited the applicability of the developed tool to the specific network for which it was developed. To address this limitation, the current study investigates the feasibility of developing a generic decision support system (DSS) capable of predicting traffic diversion impacts for new transportation networks that the tool has not previously seen. In such cases, users need only to input the geometric and traffic variables, via a graphical user interface, and the tool, which uses a SVR model, will predict the benefits of diverting traffic for a specific incident on the new site. To illustrate the feasibility of developing such a tool, two different highway networks covering portions of I-85 and I-385 in South Carolina were used to train the SVR model, which was then tested on a third network covering portions of I-89 in Vermont. The study found only a 15% difference between the predictions of the SVR model and those of a detailed simulation counterpart, demonstrating the feasibility of developing a generic DSS. Adding more sites and parameters to train the software is also expected to improve the prediction accuracy of the DSS.

Applications of Artificial Intelligence Paradigms to Decision Support in Real-Time Traffic Management

Decision support for real-time traffic management is a critical component for the success of intelligent transportation systems. Theoretically, microscopic simulation models can be used to evaluate traffic management strategies in real time before a course of action is recommended. However, the problem is that the strategies would have to be evaluated in real time; this might not be computationally feasible for large-scale networks and complex simulation models. To address this problem, two artificial intelligence (AI) paradigms—support vector regression (SVR) and case-based reasoning (CBR)—are presented as alternatives to the simulation models as a decision support tool. Specifically, prototype SVR and CBR decision support tools are developed and used to evaluate the likely impacts of implementing diversion strategies in response to incidents on a highway network in Anderson, South Carolina. The performances of the two prototypes are then evaluated by a comparison of their predictions of traffic conditio...

Energy Consumption Reduction Strategies for Plug-In Hybrid Electric Vehicles with Connected Vehicle Technology in Urban Areas

Automobile manufacturers have introduced plug-in hybrid electric vehicles (PHEVs) to reduce fossil fuel consumption. This paper details three optimization strategies that can be used to minimize the energy consumption of PHEVs further through an information exchange between PHEVs and infrastructure agents supported by connected vehicle technology (CVT). An earlier study focused on a freeway scenario. The study reported here developed strategies for an urban scenario with frequent stop-and-go conditions. Three strategies were considered on the basis of different types of information availability with the use of CVT. Only signal timing information was available in Strategy 1; only headway information was available in Strategy 2; and both signal timing and headway information were available in Strategy 3. The performance of PHEVs that received no real-time information was used as the base case for Strategies 1, 2, and 3 to evaluate each strategy. The optimization strategies resulted in energy consumption savings that ranged from 60% to 76%. An analysis, with various levels of penetration of CVT-supported PHEVs in traffic, was conducted to demonstrate the impact of these optimization strategies with their increased market share. For a case study network, a linear trend was found between energy savings and the penetration rate of CVT-supported PHEVs. Strategy 3, in which signal timing and headway data were provided to CVT-supported PHEVs, resulted in about 31% to 35% energy savings, with a 30% penetration of CVT-supported PHEVs at the peak hour volume.

Infrastructure cost issues related to inductively coupled power transfer for electric vehicles

The electrification of vehicles has been accelerated over the last few years due to tighter emission regulations, volatile fuel prices, and progress in standardization as well as improvement of battery technologies. Key hurdles of electric vehicles (EV) to gain a larger share in the automotive market are the cost of the energy storage system (ESS) and the density of the EV charging infrastructure. The achievable range of an EV or full electric driving of a plugin hybrid electric vehicle (PHEV) is limited by its battery capacity. The time to recharge the battery is related to the power level of charging as well as allowable charging parameters to protect the battery life. In order to overcome the constraints of limited range of EVs (all electric driving) as well as the cost of ESS, inductively coupled power transfer (ICPT) is an interesting technology path to be considered, in particular if applied as opportunity (stop-and-go) or in-motion charging (also called dynamic wireless charging or move and charge). In-motion wireless charging could lead to significant reductions of the vehicle-related cost of electrification but this comes with the price of an infrastructure that needs to be built and maintained. In order to design the ICPT infrastructure and calculate the cost of construction and operation, certain assumptions have to be made with respect to the vehicle specifications, the specification of the charging system itself and the cost of integration into the existing road infrastructure. The objective of this paper is to provide a thorough analysis of the cost associated with the implementation of a dynamic ICPT infrastructure to support the operation of electrified vehicles and to present transportation agencies a business model that can provide a starting point for the development of a new EV infrastructure.

Risk Analysis of Autonomous Vehicles in Mixed Traffic Streams

The introduction of autonomous vehicles in the surface transportation system could improve traffic safety and reduce traffic congestion and negative environmental effects. Although the continuous evolution in computing, sensing, and communication technologies can improve the performance of autonomous vehicles, the new combination of autonomous automotive and electronic communication technologies will present new challenges, such as interaction with other nonautonomous vehicles, which must be addressed before implementation. The objective of this study was to identify the risks associated with the failure of an autonomous vehicle in mixed traffic streams. To identify the risks, the autonomous vehicle system was first disassembled into vehicular components and transportation infrastructure components, and then a fault tree model was developed for each system. The failure probabilities of each component were estimated by reviewing the published literature and publicly available data sources. This analysis resulted in a failure probability of about 14% resulting from a sequential failure of the autonomous vehicular components alone in the vehicle’s lifetime, particularly the components responsible for automation. After the failure probability of autonomous vehicle components was combined with the failure probability of transportation infrastructure components, an overall failure probability related to vehicular or infrastructure components was found: 158 per 1 million mi of travel. The most critical combination of events that could lead to failure of autonomous vehicles, known as minimal cut-sets, was also identified. Finally, the results of fault tree analysis were compared with real-world data available from the California Department of Motor Vehicles autonomous vehicle testing records.

Development of a Professional Services Management Training Program

The lack of training programs in systems that allow insufficient references in departments of transportation (DOTs) can create a procurement and administration process that is inefficient, inconsistent, and ineffective. Public agency activities related to contracts must be efficient, fair, and consistent to maintain compliance with state and federal policies. The South Carolina DOT identified a need to develop a comprehensive training program for professional service contract managers to support consistent and efficient execution of department contracts. The objectives of this study were to develop a training program for South Carolina DOT professional services contract managers and to evaluate the training program for statewide adoption. The study resulted in the development of a comprehensive training program to ensure that current and future South Carolina DOT contract managers across the department procure and administer professional services contracts with consistency and effectiveness. Lessons learned and issues identified during development of the training program by an external research team, with oversight by a South Carolina DOT steering committee, are discussed. The training was implemented with South Carolina DOT contract managers in a pilot training session that included contract managers and their supervisors. This papers presentation of the training programs development process and unique experiences can be applied to other state DOTs to support the improvement of their procurement and administrative processes.

A Case Study on the Impacts of Connected Vehicle Technology on No-Notice Evacuation Clearance Time

No-notice evacuations of metropolitan areas can place significant demands on transportation infrastructure. Connected vehicle (CV) technology, with real-time vehicle to vehicle and vehicle to infrastructure communications, can help emergency managers to develop efficient and cost-effective traffic management plans for such events. The objectives of this research were to evaluate the impacts of CVs on no-notice evacuations using a case study of a downtown metropolitan area. The microsimulation software VISSIM was used to model the roadway network and the evacuation traffic. The model was built, calibrated, and validated for studying the performance of traffic during the evacuation. The researchers evaluated system performance with different CV penetration rates (from 0 to 30 percent CVs) and measured average speed, average delays, and total delays. The findings suggest significant reductions in total delays when CVs reached a penetration rate of 30 percent, albeit increases in delays during the beginning of the evacuation. Additionally, the benefits could be greater for evacuations that last longer and with higher proportions of CVs in the vehicle stream.

Machine Learning in Transportation Data Analytics

The primary goal of this chapter is to provide a basic understanding of the machine learning methods for transportation-related applications. This chapter discusses how the machine learning methods can be utilized to improve performance of transportation data analytics tools. The chapter focuses on selected machine learning methods and importance of quality and quantity of available data. An example is provided along with the MATLAB code to present how the machine learning method can improve performance of data-driven transportation system by predicting a speed of the roadway section.