Jump to content

MAS535 Energy Informatics

Course description for academic year 2023/2024

Contents and structure

The course provides introductory coverage on the applications of machine learning and data analytics in power systems. The emerging multi-scale data from various components and sections in an electricity network offers tremendous opportunities and challenges for the industry in managing the electric grid. The course lectures and projects will help students better understand integrating data-driven and physics-based reasoning in modern power systems.

The outcomes of the Energy Informatics course are at the heart of several UN Sustainable Development Goals - from expanding access to electricity to improving clean energy, from transportation electrification to curbing deadly air pollution that each year prematurely kills millions around the world. Specifically, the Energy Informatics Course serves the objectives of:

  • GOAL 7: Affordable and Clean Energy,
  • GOAL 9: Industry, Innovation, and Infrastructure,
  • GOAL 11: Sustainable Cities and Communities,
  • GOAL 13: Climate Action.

Course Main Topics:

  • Power systems basics and structure
  • Data types in power systems
  • Application of data analytics and machine learning in power systems

Learning Outcome

Knowledge

The student…

  • understand and can explain power systems fundamental,
  • have a basic understanding of data sources in the electric grid
  • understand where and how data analytics and machine learning methods applied to real-life power systems problems.

Skills

The student…

  • can implement machine learning techniques on power systems data
  • can validate machine learning algorithms performance in power system problems
  • can recognize new problems in power systems that are amenable to the techniques learned in this course.

General competency

The student…

  • can reflect on one's own professional practice and work in teams.
  • can present one’s own work though presentation and written report.

Entry requirements

None.

Recommended previous knowledge

Basic knowledge of statistics and machine learning.

Familiarity with Python programming, for example ING201 Programming for Engineers.

Teaching methods

Lectures, self-study, group projects.

The final project covering a topic related to data analytics for power systems and it will be specified at the beginning of the semester. Final projects will be done in small groups.

Compulsory learning activities

The course will have four assignments, that must be approved in order to qualify for the submission of the final project report.

  • Three written assignments
  • One short presentation about students’ semester project.

Assessment

Semester project report (group).

The grading scale used is pass and fail.

Examination support material

All written and printed materials.

More about examination support material