Carleton University
Optimization of Energy Management and Battery Cell Balancing in Battery Electric Vehicles Using Reinforcement Learning Techniques
Abstract
dc:description.abstractThe growing concerns regarding environmental pollution and the depletion of fossil fuel reserves have accelerated the global transition toward electric mobility. As a result, Electric Vehicles (EVs) have gained substantial traction. However, to achieve parity with conventional Internal Combustion Engine (ICE) vehicles, EVs must overcome critical challenges in driving range, charging time, and cost-effectiveness. To address these limitations, various EV configurations have been introduced, including Battery Electric Vehicles (BEVs), Hybrid Electric Vehicles (HEVs), and Plug-in Hybrid Electric Vehicles (PHEVs). Concurrently, advancements in computational technologies have significantly reduced the time required for large-scale numerical computations, thereby enabling the implementation of sophisticated control algorithms in real-time applications. This dissertation presents three key contributions toward advancing Energy Management Strategies (EMS), Battery Management Systems (BMSs) and battery cell balancing in BEVs through the deployment of Reinforcement Learning (RL) frameworks. First, a Multi-Agent Reinforcement Learning (MARL) framework based on the Twin-Delayed Deep Deterministic Policy Gradient (TD3) algorithm is proposed to optimize EMS while ensuring effective State of Charge (SOC) balancing across battery modules. Second, a MARL-based EMS employing Proximal Policy Optimization (PPO) agents is developed to simultaneously regulate SOC and State of Health (SOH), while minimizing the response time in meeting dynamic power demands. A hybrid BMS is proposed, integrating predictive capabilities via a Convolutional Neural Network–Long Short-Term Memory (CNN–LSTM) architecture and incorporating LSTM layers within a PPO-based control framework to monitor and alleviate battery capacity degradation.
Degree
thesis:*- Name thesis:degree_name
- Doctor of Philosophy (Ph.D.)
- Level thesis:degree_level
- Doctoral
- Discipline thesis:degree_discipline
- Engineering, Electrical and Computer
- Grantor dc:publisher
- Carleton University
- Year dc:date.issued
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Lotfy, Armin
Subjects
dc:subject × 1Rights
dc:rights- Statement dc:rights
-
- Copyright © 2025 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
- Language dc:language.iso
- en