SET3125: Machine Learning Workflows for Digital Energy Systems
Graduate course, TU Delft, Faculty of Electrical Engineering, Mathematics and Computer Science, 2024
SET3125 is a graduate-level course offered to MSc students at TU Delft, focusing on the fundamentals of machine learning and its applications in sustainable energy systems, with an emphasis on digital technologies. The course provides a foundation for further studies in digital energy technologies and machine learning, and prepares students for thesis work involving artificial intelligence.
Course Details
- Degree Program: MSc Sustainable Energy Technology
- ECTS: 4
- Language: English
- Education Period: Quarter 2 (early November to late December)
- Exam Periods: Quarter 2 and Quarter 3
- Contact Hours / Week: 0/2/0/0
- Prerequisites:
- Basic programming skills in any programming language.
- Elementary knowledge of probability theory and statistics.
- Instructors:
- Dr. J.L. Cremer (J.L.Cremer@tudelft.nl)
- Dr. S.H. Tindemans (S.H.Tindemans@tudelft.nl)
- Dr. P.P. Vergara Barrios (P.P.VergaraBarrios@tudelft.nl)
- Dr. J. Stiasny (J.B.Stiasny@tudelft.nl)
Course Content
The course covers the following topics:
- Statistical Learning (Supervised and Unsupervised)
- Supervised Regression
- Neural Networks
- Designing Machine Learning Workflows
- Physics-Informed Learning for Energy Applications
- Learning with Inductive Bias in Grids
Study Goals
By the end of the course, students will be able to:
- Describe machine learning concepts.
- Compare concepts of effective learning in the energy system domain.
- Apply machine learning training strategies through calculations and analysis of energy system problems.
- Design elements of a machine learning workflow for energy systems.
Education Method
The course includes lectures, homework assignments, a project, and office hours to support student learning.