Public defence in Power Electronics and Electric Drives, M.Sc. Amir Sepehr

M.Sc. Amir Sepehr will defend the thesis "Machine Learning Approaches to Improving the Transient Stability of Voltage-Source Converters in Weak Grids" on 28 April 2023 at 12 (EET) in Aalto University School of Electrical Engineering, Department of Electrical Engineering and Automation, in lecture hall AS1, Maarintie 8, Espoo.

Opponent: Prof. Sergio Vazquez, Universidad de Sevilla, Spain
Custos: Prof. Edris Pouresmaeil, Aalto University School of Electrical Engineering, Department of Electrical Engineering and Automation

Power systems are undergoing changes in generating resources, transmission networks, and consumption devices due to economic development, environmental sustainability, and deep electrification. The resource mix has shifted towards inverter-based resources such as wind, solar generation, and battery storage. The electricity infrastructure is being updated with dc power lines, FACTS, and solid-state transformers. Electric loads are being transformed by the adoption of new grid interfaces like variable frequency drives and digital power supplies, and the electrification of end uses like EVs. All of these changes rely on power electronics to connect to the rest of the power system, which will result in a high proportion of electricity being generated, transmitted, and consumed by power electronics in the future. 

Power electronics has great potential to help transform the power system to be more responsive, adaptive, and scalable. To fully harness the potential of ubiquitous power electronics in power systems technology, advances are required in the following areas: data and communications, modeling and simulation, and control and optimization methods. 

Therefore, this doctoral thesis aims to contribute to these areas. Specifically, it seeks to develop data and communications protocols to capture the new dynamic behaviors introduced by power electronics. Additionally, it aims to create accurate models and simulations that can help understand the behaviors of power electronics and their interactions with other components in the context of power systems. Finally, it seeks to develop control and optimization methods that can fully exploit the capabilities of power electronics for a new paradigm of performance beyond the conventional inertia-heavy system. 

In a nutshell, this thesis intends to make a valuable contribution towards enhancing the transient stability of power electronics. It proposes to employ cutting-edge deep learning and data analysis techniques that are expected to play a crucial role in the power system's future.

Contact information of doctoral candidate:

Thesis available for public display 10 days prior to the defence at: https://aaltodoc.aalto.fi/doc_public/eonly/riiputus/
Doctoral theses in the School of Electrical Engineering: https://aaltodoc.aalto.fi/handle/123456789/53