The macroscopic measure of traffic stream density is crucial in advanced traffic management systems. However, measuring the traffic stream density in the field is difficult since it is a spatial measurement. In this dissertation, several estimation approaches are developed to estimate the traffic stream density on signalized approaches using connected vehicle (CV) data. First, the dissertation introduces a novel variable estimation interval that allows for higher estimation precision, as the updating time interval always contains a fixed number of CVs. After that, the dissertation develops model-driven approaches, such as a linear Kalman filter (KF), a linear adaptive KF (AKF), and a nonlinear Particle filter (PF), to estimate the traffic stream density using CV data only. The proposed model-driven approaches are evaluated using empirical and simulated data, the former of which were collected along a signalized approach in downtown Blacksburg, VA. Results indicate that density estimates produced by the linear KF approach are the most accurate. A sensitivity of the estimation approaches to various factors including the level of market penetration (LMP) of CVs, the initial conditions, the number of particles in the PF approach, traffic demand levels, traffic signal control methods, and vehicle length is presented. Results show that the accuracy of the density estimate increases as the LMP increases. The KF is the least sensitive to the initial traffic density estimate, while the PF is the most sensitive to the initial traffic density estimate. The results also demonstrate that the proposed estimation approaches work better at higher demand levels given that more CVs exist for the same LMP scenario. For traffic signal control methods, the results demonstrate a higher estimation accuracy for fixed traffic signal timings at low traffic demand levels, while the estimation accuracy is better when the adaptive phase split optimizer is activated for high traffic demand levels. The dissertation also investigates the sensitivity of the KF estimation approach to vehicle length, demonstrating that the presence of longer vehicles (e.g. trucks) in the traffic link reduces the estimation accuracy. Data-driven approaches are also developed to estimate the traffic stream density, such as an artificial neural network (ANN), a k-nearest neighbor (k-NN), and a random forest (RF). The data-driven approaches also utilize solely CV data. Results demonstrate that the ANN approach outperforms the k-NN and RF approaches. Lastly, the dissertation compares the performance of the model-driven and the data-driven approaches, showing that the ANN approach produces the most accurate estimates. However, taking into consideration the computational time needed to train the ANN approach, the large amount of data needed, and the uncertainty in the performance when new traffic behaviors are observed (e.g., incidents), the use of the linear KF approach is highly recommended in the application of traffic density estimation due to its simplicity and applicability in the field. / Doctor of Philosophy / Estimating the number of vehicles (vehicle counts) on a road segment is crucial in advanced traffic management systems. However, measuring the number of vehicles on a road segment in the field is difficult because of the need for installing multiple detection sensors in that road segment. In this dissertation, several estimation approaches are developed to estimate the number of vehicles on signalized roadways using connected vehicle (CV) data. The CV is defined as the vehicle that can share its instantaneous location every time t. The dissertation develops model-driven approaches, such as a linear Kalman filter (KF), a linear adaptive KF (AKF), and a nonlinear Particle filter (PF), to estimate the number of vehicles using CV data only. The proposed model-driven approaches are evaluated using real and simulated data, the former of which were collected along a signalized roadway in downtown Blacksburg, VA. Results indicate that the number of vehicles produced by the linear KF approach is the most accurate. The results also show that the KF approach is the least sensitive approach to the initial conditions. Machine learning approaches are also developed to estimate the number of vehicles, such as an artificial neural network (ANN), a k-nearest neighbor (k-NN), and a random forest (RF). The machine learning approaches also use CV data only. Results demonstrate that the ANN approach outperforms the k-NN and RF approaches. Finally, the dissertation compares the performance of the model-driven and the machine learning approaches, showing that the ANN approach produces the most accurate estimates. However, taking into consideration the computational time needed to train the ANN approach, the huge amount of data needed, and the uncertainty in the performance when new traffic behaviors are observed (e.g., incidents), the use of the KF approach is highly recommended in the application of vehicle count estimation due to its simplicity and applicability in the field.

La qualité d'alimentation électrique d'un réseau ferroviaire peut être fortement affectée par l'indisponibilité d'un équipement électrique, que ce soit suite à un incident technique ou une opération de maintenance. Il est alors nécessaire de réduire le trafic prévu en ajustant les grilles horaires et les profils de vitesse, tout en conservant des performances d'exploitation optimales. Le but du travail présenté dans ce mémoire est de développer un outil d'aide à la décision pour assister les agents en charge de la réorganisation du trafic lors d'un incident sur infrastructure électrique. Le système étudié est complexe et son analyse repose sur des simulations coûteuses. Nous avons donc proposé une démarche en deux phases. Dans un premier temps, une analyse de sensibilité permet de détecter de manière efficace les variables d’ajustement du trafic les plus influentes. Après une analyse comparative entre différentes techniques, nous avons retenu l’analyse de sensibilité régionale par filtrage de Monte Carlo et test de KS, car cela permet de prendre en compte les contraintes opérationnelles, comme les niveaux de tension en ligne. La deuxième phase consiste à optimiser la solution en travaillant dans un espace de recherche de dimension réduite. Un ensemble de solutions Pareto optimales sont générées afin d’évaluer le meilleur compromis entre le critère principal qui est la densité de trafic et d’autres critères tels que les pertes ou les échauffements. Les techniques mises en œuvre ont abouti à la réalisation d’un prototype. Cet outil permet à l’ingénieur de définir les variables d’ajustement et les critères de performance du trafic. Il analyse ensuite l’influence des différentes variables d’ajustement et optimise le trafic par rapport aux critères définis. L’outil a été testé sur quatre cas d’étude correspondant à des portions de réseaux et à des trafics ferroviaires réels. / The power supply quality of a railway network can be strongly affected by the unavailability of electrical equipment, whether due to a technical incident or a maintenance operation. It is then necessary to reduce the expected traffic by adjusting the time schedules and speed profiles, while maintaining optimal operating performance. The purpose of the work presented in this thesis is to develop a decision support tool to assist the agents in charge of the reorganization of traffic during an incident on electrical infrastructure. The studied system is complex and its analysis is based on costly simulations. We therefore proposed a two-phase approach. As a first step, a sensitivity analysis can effectively detect the most influential traffic adjustment variables. After a comparative analysis between different techniques, we selected the regional sensitivity analysis by Monte Carlo filtering and KS test, because it allows us to take into account the operational constraints, like the tension levels in line. The second phase consists in optimizing the solution by working in a small research area. A set of Pareto-Optimal solutions are generated to evaluate the best trade-off between the main criterion "traffic density" and other criteria such as losses or overheating. The techniques implemented led to the production of a prototype. The tool allows the engineer to define traffic adjustment variables and traffic performance criteria. Then it analyzes the influence of the various adjustment variables and optimizes the traffic according to the defined criteria. The tool was tested on four case studies proposed by SNCF Réseau and corresponding to network segments and actual rail traffic.