PhD Machine Learning for Energy System Dynamics

TU Delft is a top tier university and is exceedingly active in the field of Artificial intelligence and the TU Delft's campus has strong expertise in energy systems. Energy systems are the backbone of our modern society, but are becoming increasingly complex and challenging to operate as renewable energy, heating and transport sectors are integrated into the system. It’s crucially important that energy systems are sustainable, reliable and effective, now and in the future. The DAI Energy Lab investigates how the new area of data-driven and scientific computing can contribute to managing energy systems.

We combine ground-breaking machine learning with the reliable theory of the physical energy system. The area of data-driven scientific computing promises to combine statistics, time-frequency analysis, low-dimensional model reductions, and other techniques to extract information from data. With machine learning, we make such information useful for the management of complex energy systems. For example, it is possible to use neural networks to model differential equations that describe dynamics, and for predicting extreme, rare events. The DAI Energy Lab investigates data-driven scientific modelling for their applicability in monitoring the 'health' of energy system components, and for the early detection of threats. We are currently a team of seven PhD researchers and an Assistant Professor and an Associate Professor. You will extend the team and integrate your own ambitious research program within our research vision. We distinguish between IN-AI and WITH-AI research. IN-AI projects focus on fundamental methods from data-driven scientific computing for energy system applications. WITH-AI projects focus on assembling such methods to build full workflows for the application to energy system problems.

This PhD position is a four-year doctoral appointment for a WITH-AI project with the theme for predicting dynamics for time-varying systems and will be supervised by Dr. J. Cremer. Along with your colleagues, you will work on real-time estimation of the system’s operating condition, and extract physical information to enhance machine learning workflows. You will investigate such workflows with a focus on the impacts on time-varying parameters for dynamic studies. You will discover how the discrete behavior of parameter changes can be mitigated in novel neural network-based approaches with the final objective of making the workflows useful for dynamic security assessment studies, and, applicable for real-time purposes.

About the department

The research in the Department of Electrical Sustainable Energy is inspired by the technical, scientific, and societal challenges originating from the transition towards a more sustainable society and focuses on three areas:

• DC Systems, Energy Conversion and Storage (DCE&S)
• Photovoltaic Materials and Devices (PVMD)
• Intelligent Electrical Power Grids (IEPG)

The Electrical Sustainable Energy Department provides expertise in each of these areas throughout the entire energy system chain. The department owns a large ESP laboratory assembling High Voltage testing, DC Grids testing environment, and a large RTDS that is actively used for real-time simulation of future electrical power systems, AC and DC protection, and wide-area monitoring and protection.

The Intelligent Electrical Power Grid (IEPG) group, headed by Professor Peter Palensky, works on the future of our power system. The goal is to generate, transmit and use electrical energy in a highly reliable, efficient, stable, clean, affordable, and safe way. IEPG integrates new power technologies and smart controls, which interact with other systems and allow for more distributed and variable generation.