Semester of Graduation

Summer 2025

Degree

Master of Computer and Information Science (MCIS)

Department

Division of Computer Science and Engineering

Document Type

Thesis

Abstract

Electric vehicle (EV) charging optimization is a critical challenge in sustainable transportation. This study focuses on three fundamental questions: (1) when is the best time to charge an EV, (2) where is the optimal charging location, and (3) how should charging be planned considering navigation and routing decisions. Our primary objective is to determine the optimal time and location for EV charging while accounting for key factors such as real-time traffic conditions, spatial distribution of charging stations, and EV-specific attributes such as state of charge (SOC), driving range, and efficiency. To develop a robust and adaptive EV charging recommendation system, we employ Multi-Agent Reinforcement Learning (MARL) to derive an intelligent, self-improving charging strategy that dynamically adapts to evolving conditions. Unlike traditional approaches, which often rely on static road network data, our model integrates real-time traffic information like accidents from Google Maps to support dynamic decision-making. By incorporating live traffic data, we can better predict congestion patterns and optimize charging locations to minimize delays and improve overall travel efficiency. The proposed approach enhances system performance by optimizing charging schedules, reducing wait times, and improving route planning. By integrating real-world traffic data, our model provides a practical and scalable solution for EV users and urban planners, contributing to more efficient and intelligent EV charging infrastructure.

Date

7-27-2025

Committee Chair

Wang, Hao

Download

Available for download on Tuesday, July 14, 2026

Share

COinS