{"id":{"repo_id":"buffalo","oai_identifier":"oai:ubir.buffalo.edu:10477/86614"},"canonical_url":"https://search.dev.ndltd.org/etd/buffalo/oai:ubir.buffalo.edu:10477/86614","repository":{"repo_id":"buffalo","name":"Buffalo","base_url":"https://ubir.buffalo.edu/oai/request"},"display":{"title":"Optimal Traffic Flow Control Strategies, on a Lane Group- and Vehicle-Based Level, at Freeway Lane-Drops under the Environment of Connected and Automated Vehicles","abstract":"Ph.D.","abstract_html":"Ph.D.","abstract_has_math":false,"creators":["Seliman, Salaheldeen; 0000-0002-1650-1040"],"institution":"State University of New York at Buffalo","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Sadek, Adel","Civil, Structural and Environmental Engineering"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-02-21T20:58:50Z","date_published":"2025-02-21T20:58:50Z","updated_at":"2026-07-27T19:05:32Z","subjects":["civil engineering"],"languages":["eng"],"rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/10477/86614","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Sadek, Adel","Civil, Structural and Environmental Engineering"]},{"key":"dc:creator","label":"Author","values":["Seliman, Salaheldeen; 0000-0002-1650-1040"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2025-02-21T20:58:50Z","2020"]},{"key":"dc:publisher","label":"Institution","values":["State University of New York at Buffalo"]},{"key":"dc:type","label":"Dc Type","values":["Text","Dissertation"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["civil engineering"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["eng"]},{"key":"dc:rights","label":"Dc Rights","values":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/10477/86614"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Ph.D.","The research of the current dissertation consists of two main parts. The first part of this dissertation's research develops optimal variable, lane group-based, speed limits for traffic control at freeway lane-drop areas (e.g. work zones). The proposed approach uses the microscopic traffic simulation model VISSIM, along with a calibrated and validated macroscopic traffic flow model METANET, to develop the optimal speed limits. A multi-objective optimization framework is adopted whereby the model primarily seeks to improve traffic safety, by reducing the average number of stops, while taking other objectives, such as the average travel time and throughput, into consideration. For optimization, the heuristic, biologically inspired, optimization technique, known as Particle Swarm Optimization (PSO), is utilized, and the ε-constraint method is adopted to allow for considering multiple objectives in the optimization process. The proposed traffic control strategy is then evaluated for a hypothetical freeway lane drop area under a real-world congested traffic scenario. The research findings show that the proposed lane group-based control strategy outperforms other variable, link-based, speed limits, reported in the literature. The reduction in the average number of stops reached up to nearly 50 percent with respect to the base case during the congested traffic situations. This was achievable, while avoiding significant deteriorations in the values of the average travel time and the vehicle throughput (the reductions were constrained in our study to at most 10 percent difference with respect to the base case). The second part of this dissertation’s research develops an optimal, real-time and adaptive control algorithm for helping a Connected and Automated Vehicle (CAV), navigate a freeway lane-drop site (e.g. work zones). The proposed traffic control strategy is based on the Deep Q-Network (DQN) Reinforcement Learning (RL) algorithm, and is designed to determine the driving speed and lane-change maneuvers that would enable the CAV to go through the bottleneck, with the least amount of delay. The DQN RL agent was trained using the microscopic traffic simulator VISSIM, where the learning focused on how the CAV may be able to optimally maneuver the lane drop site while driving as close as possible to the freeway speed limit. VISSIM was also used to compare the performance of the DQN-controlled AV, as opposed to a human-driven vehicle with no intelligent control, in terms of the driving speed or travel time needed to traverse the lane drop site, under a congested, real life-like traffic scenario. The research findings demonstrate the promise of DQN RL in allowing the CAV to intelligently and optimally navigate through the lane drop site. On the scenario for which the agent was trained, the reduction in the CAV travel time was around 96 percent with respect to the base case. For validation and stability purposes, several experiments with different random seeds were carried out. The reductions in the mean and standard deviation of the DQN-controlled CAV travel times were 30.91 and 61.43 percent respectively compared to the base case. Further experiments with higher input demands and different configuration were implemented and again on average the DQN RL agent showed a better and more stable performance in terms of the travel time compared to the base case.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Optimal Traffic Flow Control Strategies, on a Lane Group- and Vehicle-Based Level, at Freeway Lane-Drops under the Environment of Connected and Automated Vehicles"]}]}],"canonical_facts":{"dc:contributor":["Sadek, Adel","Civil, Structural and Environmental Engineering"],"dc:creator":["Seliman, Salaheldeen; 0000-0002-1650-1040"],"dc:date":["2025-02-21T20:58:50Z","2020"],"dc:description":["Ph.D.","The research of the current dissertation consists of two main parts. The first part of this dissertation's research develops optimal variable, lane group-based, speed limits for traffic control at freeway lane-drop areas (e.g. work zones). The proposed approach uses the microscopic traffic simulation model VISSIM, along with a calibrated and validated macroscopic traffic flow model METANET, to develop the optimal speed limits. A multi-objective optimization framework is adopted whereby the model primarily seeks to improve traffic safety, by reducing the average number of stops, while taking other objectives, such as the average travel time and throughput, into consideration. For optimization, the heuristic, biologically inspired, optimization technique, known as Particle Swarm Optimization (PSO), is utilized, and the ε-constraint method is adopted to allow for considering multiple objectives in the optimization process. The proposed traffic control strategy is then evaluated for a hypothetical freeway lane drop area under a real-world congested traffic scenario. The research findings show that the proposed lane group-based control strategy outperforms other variable, link-based, speed limits, reported in the literature. The reduction in the average number of stops reached up to nearly 50 percent with respect to the base case during the congested traffic situations. This was achievable, while avoiding significant deteriorations in the values of the average travel time and the vehicle throughput (the reductions were constrained in our study to at most 10 percent difference with respect to the base case). The second part of this dissertation’s research develops an optimal, real-time and adaptive control algorithm for helping a Connected and Automated Vehicle (CAV), navigate a freeway lane-drop site (e.g. work zones). The proposed traffic control strategy is based on the Deep Q-Network (DQN) Reinforcement Learning (RL) algorithm, and is designed to determine the driving speed and lane-change maneuvers that would enable the CAV to go through the bottleneck, with the least amount of delay. The DQN RL agent was trained using the microscopic traffic simulator VISSIM, where the learning focused on how the CAV may be able to optimally maneuver the lane drop site while driving as close as possible to the freeway speed limit. VISSIM was also used to compare the performance of the DQN-controlled AV, as opposed to a human-driven vehicle with no intelligent control, in terms of the driving speed or travel time needed to traverse the lane drop site, under a congested, real life-like traffic scenario. The research findings demonstrate the promise of DQN RL in allowing the CAV to intelligently and optimally navigate through the lane drop site. On the scenario for which the agent was trained, the reduction in the CAV travel time was around 96 percent with respect to the base case. For validation and stability purposes, several experiments with different random seeds were carried out. The reductions in the mean and standard deviation of the DQN-controlled CAV travel times were 30.91 and 61.43 percent respectively compared to the base case. Further experiments with higher input demands and different configuration were implemented and again on average the DQN RL agent showed a better and more stable performance in terms of the travel time compared to the base case.","**To request an accessible version of the file(s) associated with this item, contact library@buffalo.edu. Please include the item's persistent URL [http://hdl.handle.net/. . .] in your request.**"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/10477/86614"],"dc:language":["eng"],"dc:publisher":["State University of New York at Buffalo"],"dc:rights":["Users of works found in University at Buffalo Institutional Repository (UBIR) are responsible for identifying and contacting the copyright owner for permission to reuse. University at Buffalo Libraries do not manage rights for copyright-protected works and cannot assist with permissions.","Copyright retained by author."],"dc:subject":["civil engineering"],"dc:title":["Optimal Traffic Flow Control Strategies, on a Lane Group- and Vehicle-Based Level, at Freeway Lane-Drops under the Environment of Connected and Automated Vehicles"],"dc:type":["Text","Dissertation"]},"updated_at":"2026-07-27T19:05:32Z"}