Carleton University
Data-Driven Control Strategies for Bidirectional Voltage Source Inverters in Distributed Energy Resources
Abstract
dc:description.abstractThe increasing integration of distributed energy resources (DERs) into modern power systems has introduced new challenges in the control of grid-connected inverter-based systems. Many DERs are interfaced with the grid through voltage source inverters (VSIs), which are commonly controlled using a cascaded structure consisting of an outer power control loop and an inner current control loop. Conventional control approaches, typically based on proportional–integral (PI) regulators, rely on fixed parameters and accurate system modeling, which can limit their performance under nonlinear and dynamic operating conditions. These limitations motivate the development of advanced control strategies. This thesis proposes data-driven control strategies to improve conventional VSI control performance under transient conditions. First, an Adaptive Neuro-Fuzzy Inference System (ANFIS)-based controller is developed to replace the PI regulator in the inner current control loop. The proposed approach improves current-tracking accuracy and reduces oscillatory behavior under dynamic conditions while reducing the dependence on repeated manual gain tuning. Next, a feedforward neural network (FFNN)-based controller is introduced to replace the entire inner current control loop by directly generating inverter voltage commands from system measurements. This structure simplifies the control design and demonstrates improved robustness under measurement noise and varying operating conditions, including single- and multi-EV scenarios. Finally, a fully connected neural network (FCNN)-based controller is proposed for outer-loop power regulation, replacing the conventional outer-loop control strategy. The FCNN learns the nonlinear relationship between power-domain signals and reference current commands, resulting in faster transient response, reduced oscillations, and improved post-disturbance recovery. While accurate inner-loop current tracking ensures proper execution, improving the quality of reference current generation in the outer loop further enhances overall system performance. The effectiveness of the proposed methods is evaluated through extensive MATLAB/Simulink simulations under various operating scenarios, including step changes in reference power, measurement noise disturbances, and multi-EV operation. The results demonstrate improved current-tracking performance and enhanced dynamic response compared to conventional control approaches. Overall, the proposed data-driven control strategies provide an effective framework for enhancing control performance and robustness in inverter-interfaced DERs, including battery energy storage systems (BESS) and EV systems, under dynamic and disturbed operating conditions.
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
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Hasheminasab, Mohamad
Subjects
dc:subject × 1Rights
dc:rights- Statement dc:rights
-
- Copyright © 2026 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