Green light optimal speed advisory (GLOSA) systems require reliable estimates of signal switching times to improve vehicle energy/fuel efficiency. Deployment of successful infrastructure to vehicle communication requires Signal Phase and Timing (SPaT) messages to be populated with most likely estimates of switching times and confidence levels in these estimates. Obtaining these estimates is difficult for actuated signals where the length of each green indication changes to accommodate varying traffic conditions and pedestrian requests. This dissertation explores the different ways in which predictions can be made for the most likely switching times. Data are gathered from six intersections along the Gallows Road corridor in Northern Virginia. The application of long-short term memory neural networks for obtaining predictions is explored for one of the intersections. Different loss functions are tried for the purpose of prediction and a new loss function is devised. Mean absolute percentage error is found to be the best loss function in the short-term predictions. Mean squared error is the best for long-term predictions and the proposed loss function balances both well. The amount of historical data needed to make a single accurate prediction is assessed. The assessment concludes that the short-term prediction is accurate with only a 3 to 10 second time window in the past as long as the training dataset is large enough. Long term prediction, however, is better with a larger past time window. The robustness of LSTM models to different demand levels is then assessed utilizing the unique scenario created by the COVID-19 pandemic stay-at-home order. The study shows that the models are robust to the changing demands and while regularization does not really affect their robustness, L1 and L2 regularization can improve the overall prediction performance. An ensemble approach is used considering the use of transformers for SPaT prediction for the first time across the six intersections. Transformers are shown to outperform other models including LSTM. The ensemble provides a valuable metric to show the certainty level in each of the predictions through the level of consensus of the models. Finally, a hybrid approach integrating deep learning and controller logic is proposed by predicting actuations separately and using a digital twin to replicate SPaT information. The approach is proven to be the best approach with 58% less mean absolute error than other approaches. Overall, this dissertation provides a holistic methodology for predicting SPaT and the certainty level associated with it tailored to the existing technology and communication needs. / Doctor of Philosophy / Automated and connected vehicles waste a lot of fuel and energy to stop and go at traffic signals. The ideal case is for them to be able to know when the traffic signal turns green ahead of time and plan to reach the intersection by the time it is green, so they do not have to stop. Not having to stop can save up to 40 percent of the gas used at the intersection. This is a difficult task because the green time is not fixed. It has a minimum and maximum setting, and it keeps extending the green every time a new vehicle arrives. While this is good for adapting to traffic, it makes it difficult to know exactly when the traffic signal turns green to reach the intersection at that time. In this dissertation, different models to know ahead of time when the traffic signal will change are used. A model is chosen known as long-short term memory neural network (LSTM), which is a way to recognize how the traffic signal is expected to behave in the future from its past behavior. The point is to reduce the errors in the predictions. The first thing is to look at the loss function, which is how the model deals with error. It is found that the best thing is to take the average of the absolute value of the error as a percentage of the prediction if the prediction is that traffic signal will change soon. If it is a longer time until the traffic signal changes, the best way is to take the average of the square of the error. Finally, another function is introduced to balance between both. The second thing explored is how far back in time data was needed to be given to the model to predict accurately. For predictions of less than 20 seconds in the future, only 3 to 10 seconds in the past are needed. For predictions further in the future, looking further back can be useful. The third thing explored was how these models would do after rare events like COVID-19 pandemic. It was found that even though much fewer cars were passing through the intersections, the models still had low errors. Techniques were used to reduce the model reliance on specific data known as regularization techniques. This did not help the models to do better after COVID, but two techniques known as L1 and L2 regularization improved overall performance. The study was then expanded to include 6 intersections and used three additional models in addition to LSTM. One of these models, known as transformers, has never been used before for this problem and was shown to make better predictions than other models. The consensus between the models, which is how many of the models agree on the prediction, was used as a measure for certainty in the prediction. It was proven to be a good indicator. An approach is then introduced that combines the knowledge of the traffic signal controller logic with the powerful predictions of machine learning models. This is done by making a computer program that replicates the logic of the traffic signal controller known as a digital twin. Machine learning models are then used to predict vehicle arrivals. The program is then run using the predicted arrivals to provide a replication of the signal timing. This approach is found to be the best approach with 58 percent less error than the other approaches. Overall, this dissertation provides an end-to-end solution that uses real data generated from intersections to predict the time to green and estimate the certainty in prediction that can help automated and connected vehicles be more fuel efficient.

The Hybrid Electric Vehicle Team (HEVT) at Virginia Tech participates in the 4-Year EcoCAR Mobility Challenge organized by Argonne National Laboratory. The objective of this competition is to modify a stock 2019 internal combustion engine Chevrolet Blazer and incorporate a hybrid powertrain and advanced driver assist systems. The Blazer has a P4 hybrid architecture which contains an electric traction motor on the rear axle and an internal combustion engine on the front axle. HEVT seeks to develop a vehicle with advanced driving capabilities to demonstrate energy savings by utilizing existing technologies. The hybrid market has generally been tailored to small compact vehicles however, a Chevrolet Blazer is a midsize utility vehicle that offers additional space with the benefit of increased fuel economy. The research discussed in this paper focuses on the design of a Signalized Intersection Control Strategy. First, research is performed on different methods of intersection control and implementation with an existing Model Predictive Adaptive Cruise Controller. Based on ease of integration into an existing tuned Eco Adaptive Cruise Control System (ACC), a control strategy operating in the background of the main vehicle controllers is chosen. The main topic of this research is the development and simulation of a Signalized Intersection Control Strategy that works through an Eco ACC system to achieve further energy savings during an approach to a connected intersection while ensuring rider safety. This paper expands on the current knowledge of vehicle utilization of Signal Phase and Timing (SPaT) signals through simulated test cases of a vehicle system model using MATLAB. In each case, the tractive energy consumption and travel times are analyzed for both the Eco ACC system with Signalized Intersection Control Strategy (informed) vehicle and an assumed uninformed driver for comparison. In the case of a vehicle approaching a green intersection which turns red several seconds after SPaT information is received, the informed system shows a 92% decrease or 75 Wh/mi reduction in propel energy consumption at when compared to an uninformed driver. However, in a similar case where the vehicle accelerates back to cruising speed after the light turns green, displays only an 11% decrease or 47 Wh/mi reduction in propel energy consumption at the wheel when compared to the uninformed driver. These simulations confirm that the Signalized Intersection Control Strategy reduces the propel energy consumption at the wheel during approaches to signalized intersections without extending the travel time greatly and in some cases at all. The results of this research show that the control strategy reduces tractive energy consumption while maintaining travel time. / Master of Science / The Hybrid Electric Vehicle Team (HEVT) at Virginia Tech participates in the 4-Year EcoCAR Mobility Challenge organized by Argonne National Laboratory. The objective of this competition is to change a stock 2019 internal combustion engine Chevrolet Blazer into a functioning hybrid. This conversion is accomplished with the addition of an electric motor to allow the vehicle to burn less gasoline and increase customer appeal. The hybrid market has generally been tailored to small compact vehicles however, a Chevrolet Blazer is a midsize utility vehicle that offers additional space with the benefit of increased fuel economy. The research discussed in this paper focuses on the design of a Signalized Intersection Control Strategy. First, research is performed on various methods of existing intersection speed control. Based on ease of integration, a background process is chosen to update the set speed of the vehicle. The main topic of this research is the development and simulation of a Signalized Intersection Control Strategy that achieves greater energy savings during approaches to intersections. This paper expands on the current knowledge of vehicle utilization of Signal Phase and Timing (SPaT) signals through simulated test cases of a vehicle system model using MATLAB. In the case of a vehicle approaching a green intersection which turns red several seconds later, the implemented strategy shows a 92% decrease in energy consumption when compared to an uninformed driver. However, a similar case where the vehicle accelerates back to cruising speed after the light turns green displays only an 11% decrease in energy consumption when compared to an uninformed driver. These simulations confirm that the Signalized Intersection Control Strategy successfully reduces energy consumption without significant travel time extensions. The results of this research show that the control strategy reduces tractive energy consumption while maintaining travel time.