Sequential Computational Data-Enabled Assimilation and Machine-Learning for Energy Systems
Syllabus, Master's level, 1EL306
- Code
- 1EL306
- Education cycle
- Second cycle
- Main field(s) of study and in-depth level
- Renewable Electricity Production A1F, Technology A1F
- Grading system
- Fail (U), Pass (3), Pass with credit (4), Pass with distinction (5)
- Finalised by
- The Faculty Board of Science and Technology, 2 March 2022
- Responsible department
- Department of Electrical Engineering
Entry requirements
120 credits in Science and Technology. 30 credits mathematics including linear algebra and statistics. A course in power systems or power system analysis or electromagnetism or equivalent. A course in energy conversion systems. A course in statistics. Control theory or Linear algebra II. English 6. (A Swedish Bachelor's degree that fulfils the requirement in English.)
Learning outcomes
On completion of the course the student shall be able to:
- describe and apply basic sequential methods of data assimilation and machine learning that combine output from a computational / numerical / digital twin model of energy systems with observational data to estimate, predict and assess system parameters and states,
- describe, use and construct different sequential linear algorithms of data assimilation and linear regression regarding the Kalman filter and its variants,
- describe and use basic algorithms of machine learning: feedforward and its variant of neural network of deep learning and artificial intelligence,
- use data structures, data-enabled algorithms and data management to prepare data analysis as well visualization of the results
Content
Data-enabled algorithms with their data structures, data management and visualization. Data-activated sequential linear algorithms for data assimilation and linear regression (Kalman filters and defined variants) with their inherent stochastic processes, optimization and controls and with a brief review of its non-linear, non-normal variants. Data-enabled algorithms for machine learning with feedforward and its variant of neural networks in-depth learning as well as an initial review of other variant algorithms. Data-enabled algorithms of machine learning namely feedforward and its variant neural networks of deep learning with an introductory review of its other counterparts. Project work examples from physical and artificial processes related to hydropower, solar, wind, wave, electricity, resources, e-mobility, power systems, electricity markets, etc.
Instruction
Lectures, seminars, project work and assignments with practical applications in Matlab.
Assessment
Project report (2.5 credits) and assignments (2.5 credits).
If there are special reasons for doing so, an examiner may make an exception from the method of assessment indicated and allow a student to be assessed by another method. An example of special reasons might be a certificate regarding special pedagogical support from the disability coordinator of the university.