{"id":{"repo_id":"alabama","oai_identifier":"oai:ir.ua.edu:123456789/14385"},"canonical_url":"https://search.dev.ndltd.org/etd/alabama/oai:ir.ua.edu:123456789/14385","repository":{"repo_id":"alabama","name":"University of Alabama","base_url":"https://ir-api.ua.edu/oai/request"},"display":{"title":"Electric Vehicle Fleet Charging Management","abstract":"Efforts to prioritize sustainability, especially in energy utilization, are crucial for a sustainable future. Electrifying transportation is pivotal in reducing CO_2 emissions, yet faces hurdles, particularly in charging operations. Despite infrastructure advancements, managing electric vehicle (EV) charging remains complex, especially compared to traditional vehicles. The disparity between demand and availability, alongside limited charging windows, poses challenges, notably for vehicle fleets. Charging-as-a-Service (CaaS) emerges as a novel solution, addressing diverse challenges in managing EV fleet charging. This dissertation significantly advances EV adoption towards a greener future by thoroughly examining EV fleet charging management from the CaaS providers' perspective, tackling three critical challenges. The first challenge pertains to the scheduling of diverse EV fleets at depots equipped with heterogeneous chargers. To tackle this issue, we introduce an online optimization method supported by predictive modeling. This approach integrates future arrival information to accommodate uncertainties concerning arrival times, charge requirements, and due times. Subsequently, a mathematical model is formulated to optimize charge schedules, encompassing decisions related to timing and charging rates. To alleviate computational complexity, we propose a construction warmstart heuristic to expedite the generation of feasible solutions. The second problem focuses on charge scheduling for EV fleets at stations with multi-connector chargers, which poses complexities further compounded by advanced chargers, leading to the curse of dimensionality. A Markov decision process (MDP) model is introduced to address this challenge. To mitigate high-dimensional nature, a novel approximate dynamic programming (ADP) policy is proposed. It incorporates a regression model to replace the charging decisions' expected value. It employs a value function approximation, enabling rapid charging solutions, even for large fleets, with competitive costs and service levels. Lastly, the dissertation examines a decision support system (DSS) integrating optimal stopping theory to manage charging demand within EV networks, like those in New York taxi services. This system aims to reduce vehicles' waiting and dwell times at charging stations while minimizing costs. The proposed optimal control policy establishes state-of-charge thresholds prompting charging initiation. This DSS could potentially integrate into EV charging management systems, representing significant progress in charging management techniques.","abstract_html":"Efforts to prioritize sustainability, especially in energy utilization, are crucial for a sustainable future. Electrifying transportation is pivotal in reducing CO_2 emissions, yet faces hurdles, particularly in charging operations. Despite infrastructure advancements, managing electric vehicle (EV) charging remains complex, especially compared to traditional vehicles. The disparity between demand and availability, alongside limited charging windows, poses challenges, notably for vehicle fleets. Charging-as-a-Service (CaaS) emerges as a novel solution, addressing diverse challenges in managing EV fleet charging. This dissertation significantly advances EV adoption towards a greener future by thoroughly examining EV fleet charging management from the CaaS providers' perspective, tackling three critical challenges. The first challenge pertains to the scheduling of diverse EV fleets at depots equipped with heterogeneous chargers. To tackle this issue, we introduce an online optimization method supported by predictive modeling. This approach integrates future arrival information to accommodate uncertainties concerning arrival times, charge requirements, and due times. Subsequently, a mathematical model is formulated to optimize charge schedules, encompassing decisions related to timing and charging rates. To alleviate computational complexity, we propose a construction warmstart heuristic to expedite the generation of feasible solutions. The second problem focuses on charge scheduling for EV fleets at stations with multi-connector chargers, which poses complexities further compounded by advanced chargers, leading to the curse of dimensionality. A Markov decision process (MDP) model is introduced to address this challenge. To mitigate high-dimensional nature, a novel approximate dynamic programming (ADP) policy is proposed. It incorporates a regression model to replace the charging decisions' expected value. It employs a value function approximation, enabling rapid charging solutions, even for large fleets, with competitive costs and service levels. Lastly, the dissertation examines a decision support system (DSS) integrating optimal stopping theory to manage charging demand within EV networks, like those in New York taxi services. This system aims to reduce vehicles' waiting and dwell times at charging stations while minimizing costs. The proposed optimal control policy establishes state-of-charge thresholds prompting charging initiation. This DSS could potentially integrate into EV charging management systems, representing significant progress in charging management techniques.","abstract_has_math":false,"creators":["Mahyari, Ehsan"],"institution":"University of Alabama Libraries","degree_name":null,"degree_level":null,"degree_discipline":null,"degree_department":null,"school":null,"contributors":["Bott, Gregory","Kim, Youngsoo","Serra, Thiago","Yavuz, Mesut"],"advisors":["Freeman, Nickolas"],"committee_chairs":[],"committee_members":[],"year":2024,"date_issued":"2024","date_published":"2024","updated_at":"2026-07-27T18:44:14Z","subjects":["Electric Vehicle","Mathematical Modeling","Statistical Learning","Stochastic Optimization"],"languages":["en_US","English"],"rights":["All rights reserved by the author unless otherwise indicated."],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["1075966"],"render_values":[{"text":"1075966","href":null,"code":true}]}]},"links":{"outbound_url":"https://ir.ua.edu/handle/123456789/14385","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Bott, Gregory","Kim, Youngsoo","Serra, Thiago","Yavuz, Mesut"]},{"key":"dc:contributor.advisor","label":"Advisor","values":["Freeman, Nickolas"]},{"key":"dc:creator","label":"Author","values":["Mahyari, Ehsan"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2024-09-17T16:18:42Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2029-09-09"]},{"key":"dc:date.issued","label":"Date","values":["2024"]},{"key":"dc:publisher","label":"Institution","values":["University of Alabama Libraries"]},{"key":"dc:type","label":"Dc Type","values":["thesis","text"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Electric Vehicle","Mathematical Modeling","Statistical Learning","Stochastic Optimization"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["English"]},{"key":"dc:language.iso","label":"Language (ISO)","values":["en_US"]},{"key":"dc:rights","label":"Dc Rights","values":["All rights reserved by the author unless otherwise indicated."]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["1075966"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://ir.ua.edu/handle/123456789/14385"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Electronic Thesis or Dissertation"]},{"key":"dc:description.abstract","label":"Abstract","values":["Efforts to prioritize sustainability, especially in energy utilization, are crucial for a sustainable future. Electrifying transportation is pivotal in reducing CO_2 emissions, yet faces hurdles, particularly in charging operations. Despite infrastructure advancements, managing electric vehicle (EV) charging remains complex, especially compared to traditional vehicles. The disparity between demand and availability, alongside limited charging windows, poses challenges, notably for vehicle fleets. Charging-as-a-Service (CaaS) emerges as a novel solution, addressing diverse challenges in managing EV fleet charging. This dissertation significantly advances EV adoption towards a greener future by thoroughly examining EV fleet charging management from the CaaS providers' perspective, tackling three critical challenges. The first challenge pertains to the scheduling of diverse EV fleets at depots equipped with heterogeneous chargers. To tackle this issue, we introduce an online optimization method supported by predictive modeling. This approach integrates future arrival information to accommodate uncertainties concerning arrival times, charge requirements, and due times. Subsequently, a mathematical model is formulated to optimize charge schedules, encompassing decisions related to timing and charging rates. To alleviate computational complexity, we propose a construction warmstart heuristic to expedite the generation of feasible solutions. The second problem focuses on charge scheduling for EV fleets at stations with multi-connector chargers, which poses complexities further compounded by advanced chargers, leading to the curse of dimensionality. A Markov decision process (MDP) model is introduced to address this challenge. To mitigate high-dimensional nature, a novel approximate dynamic programming (ADP) policy is proposed. It incorporates a regression model to replace the charging decisions' expected value. It employs a value function approximation, enabling rapid charging solutions, even for large fleets, with competitive costs and service levels. Lastly, the dissertation examines a decision support system (DSS) integrating optimal stopping theory to manage charging demand within EV networks, like those in New York taxi services. This system aims to reduce vehicles' waiting and dwell times at charging stations while minimizing costs. The proposed optimal control policy establishes state-of-charge thresholds prompting charging initiation. This DSS could potentially integrate into EV charging management systems, representing significant progress in charging management techniques."]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["electronic"]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Electric Vehicle Fleet Charging Management"]}]}],"canonical_facts":{"dc:contributor":["Bott, Gregory","Kim, Youngsoo","Serra, Thiago","Yavuz, Mesut"],"dc:contributor.advisor":["Freeman, Nickolas"],"dc:creator":["Mahyari, Ehsan"],"dc:date.accessioned":["2024-09-17T16:18:42Z"],"dc:date.available":["2029-09-09"],"dc:date.issued":["2024"],"dc:description":["Electronic Thesis or Dissertation"],"dc:description.abstract":["Efforts to prioritize sustainability, especially in energy utilization, are crucial for a sustainable future. Electrifying transportation is pivotal in reducing CO_2 emissions, yet faces hurdles, particularly in charging operations. Despite infrastructure advancements, managing electric vehicle (EV) charging remains complex, especially compared to traditional vehicles. The disparity between demand and availability, alongside limited charging windows, poses challenges, notably for vehicle fleets. Charging-as-a-Service (CaaS) emerges as a novel solution, addressing diverse challenges in managing EV fleet charging. This dissertation significantly advances EV adoption towards a greener future by thoroughly examining EV fleet charging management from the CaaS providers' perspective, tackling three critical challenges. The first challenge pertains to the scheduling of diverse EV fleets at depots equipped with heterogeneous chargers. To tackle this issue, we introduce an online optimization method supported by predictive modeling. This approach integrates future arrival information to accommodate uncertainties concerning arrival times, charge requirements, and due times. Subsequently, a mathematical model is formulated to optimize charge schedules, encompassing decisions related to timing and charging rates. To alleviate computational complexity, we propose a construction warmstart heuristic to expedite the generation of feasible solutions. The second problem focuses on charge scheduling for EV fleets at stations with multi-connector chargers, which poses complexities further compounded by advanced chargers, leading to the curse of dimensionality. A Markov decision process (MDP) model is introduced to address this challenge. To mitigate high-dimensional nature, a novel approximate dynamic programming (ADP) policy is proposed. It incorporates a regression model to replace the charging decisions' expected value. It employs a value function approximation, enabling rapid charging solutions, even for large fleets, with competitive costs and service levels. Lastly, the dissertation examines a decision support system (DSS) integrating optimal stopping theory to manage charging demand within EV networks, like those in New York taxi services. This system aims to reduce vehicles' waiting and dwell times at charging stations while minimizing costs. The proposed optimal control policy establishes state-of-charge thresholds prompting charging initiation. This DSS could potentially integrate into EV charging management systems, representing significant progress in charging management techniques."],"dc:format.medium":["electronic"],"dc:format.mimetype":["application/pdf"],"dc:identifier.other":["1075966"],"dc:identifier.uri":["https://ir.ua.edu/handle/123456789/14385"],"dc:language":["English"],"dc:language.iso":["en_US"],"dc:publisher":["University of Alabama Libraries"],"dc:rights":["All rights reserved by the author unless otherwise indicated."],"dc:subject":["Electric Vehicle","Mathematical Modeling","Statistical Learning","Stochastic Optimization"],"dc:title":["Electric Vehicle Fleet Charging Management"],"dc:type":["thesis","text"]},"updated_at":"2026-07-27T18:44:14Z"}