Artificial Intelligence and Optimization of Energy Systems

Postgraduate course

Course description

Objectives and Content

Objectives

The main objective of the course is to provide an introduction to energy informatics and to equip participants with the basic knowledge and practical skills needed to understand and apply data-driven and computational methods in energy-related contexts. The course focuses on artificial intelligence, machine learning, and optimization as key approaches for analysing energy systems, supporting decision-making, and improving their operation.

Participants will gain an understanding of the fundamental principles behind these methods and develop the ability to use them to address practical problems. The course is designed for people working in or interested in the energy sector and does not require prior knowledge of a specific energy domain. No prior experience in AI, machine learning, or optimization is required, but basic familiarity with computer programming is expected.

Content

The course introduces key concepts and methods in energy informatics, with an emphasis on using data and computational techniques to understand, analyse, predict, and optimize energy systems. It covers the foundations of energy informatics and the role of data-driven methods in energy-related decision-making. Participants will be introduced to fundamental concepts in data analysis and machine learning, including data understanding and preparation, supervised and unsupervised learning, regression, feature extraction, dimensionality reduction, model evaluation, cross-validation, and model selection. The course also covers forecasting methods and their use in energy-related applications.

Optimization is introduced as a tool for making better decisions and achieving efficient operation of energy systems. Participants will learn the basics of optimization modelling and explore heuristic and other computational approaches for solving practical optimization problems.

Throughout the course, methods and concepts will be illustrated through practical energy-related applications, helping participants connect the underlying methodology to real-world challenges in the energy sector.

Learning Outcomes

Knowledge

· should be able to explain the basic principles of each step in the data science pipeline

· Demonstrate understanding of machine learning concept. Student can explain concepts of machine learning algorithms.

· Should be able to explain key concepts and principles of mathematical modelling, optimization, and metaheuristics.

Skills

· should be able to understand and evaluate preprocessing pipelines, visualization strategies, and analyses of real world data sets

· Apply techniques from machine learning to real world problems.

· should be able to understand and evaluate different modelling and optimization approaches, including their strengths, limitations, and suitability for different problems.

General Competence

· should be able to discuss successful examples of how data science can be used in different contexts in the energy domain

· should be able to discuss applications of machine learning in energy domain.

· Distinguish between various machine learning techniques for different problem contexts.

· should be able to discuss how the choice of model and optimization method affects solutions and decisions in different problem contexts.

ECTS Credits

10

Level of Study

Master

Semester of Instruction

Irregular autumn or/and spring

Place of Instruction

The course is delivered online via the University of Bergen’s learning platform, Mitt UiB.

Required Previous Knowledge

This is a master's level course, and you must therefore document that you meet both of the following admission requirements:

· A technical engineering degree or other natural science-based education at a minimum bachelor's level (3 years / at least 180 ECTS credits).

· A minimum of two years of full-time relevant work experience.

Extensive and highly relevant work experience beyond the minimum requirement of two years may, upon further assessment, replace up to one year of the educational requirement (equivalent to 60 ECTS credits).

Recommended Previous Knowledge

A general knowledge of computer science.

Credit Reduction due to Course Overlap

None

Access to the Course

Access to course will be given by application through UiBVidere

Teaching and learning methods

The course is delivered online via the University of Bergen’s learning platform, Mitt UiB, which you will gain access to once you are admitted as a student. There you will find the syllabus, video lectures, exercises, discussion forums, and other learning resources. The academic content is divided into modules, each corresponding to one week of work. Some modules conclude with a test that must be passed.

In addition to the modules, students will work on a semester project.

There will be one mandatory, in-person meeting during the semester.

The course is worth 10 ECTS credits, with a total workload of approximately 250 hours.

Compulsory Assignments and Attendance

All module tests and the semester project must be passed in order to be eligible for the final exam.

Forms of Assessment

Oral exam

Grading Scale

Pass / Fail

Assessment Semester

Examination only in the teaching semester.

Reading List

The reading list will be available within June 1st for the autumn semester and December 1st for the spring semester

Course Evaluation

The course will be evaluated by the students in accordance with the quality assurance system at UiB and the department.

Examination Support Material

None

Programme Committee

The Program Committee is responsible for the content, structure and quality of the study program and courses.

Course Coordinator

You find course responsible and administrative contact person on Mitt UiB

Course Administrator

The Faculty of Mathematics and Natural Sciences represented by the Department of Informatics is the course administrator for the course.