Smart Energy Systems
Ziele und Inhalte
Learning Outcomes
By the end of this course, students should be able to:
- Identify suitable machine learning techniques for specific forecasting goals (e.g. household power consumption and generation behavior)
- Implement machine learning software modules (preferably in Python or Matlab);
- Identify elements of a smart energy system and carry out basic energy calculations;
- Formulate and solve optimization problems for micro energy systems;
- Develop smart solutions for integrating distributed generation (DG) and electric vehicles (EVs) into the power grid; and
- Apply the knowledge gained to real-life energy systems
Content
This course covers a multidisciplinary space between information technology and energy engineering. It consists mainly of two parts. The first part is formulated as a series of lectures in which theoretical materials are provided. These lectures cover fundamentals such as the energy supply chain, an introduction to distributed energy generation, different optimization methods, and machine learning (ML) techniques. The optimization methods are used to optimally control an energy system, and the ML techniques are employed to forecast the load and generation behaviour of a household. The second part of the course will be devoted to group work. In this part, students will be divided into teams, and each team will pick a topic. This topic should be an example of applying the methods and techniques taught in the first part. While the students work in teams, regular support sessions will be held biweekly. At the end of the semester, each team will present its results and key findings to the other teams.
Modulbestandteile
LV-Titel | LV-Art | SWS | LP | Semester |
Smart Energy Systems | PJ | 4 | 9 | WiSe & SoSe |
Prüfungselemente
Name | Punkte | Kategorie | Dauer/Umfang |
Exam | 18 | oral | 20 minutes |
Implementation | 40 | practical | 12 weeks |
Presentation | 10 | oral | 30 minutes |
Project paper | 22 | written | 10 pages |
Reflection paper | 10 | written | 2 pages |
Verwendbarkeit
- Informatik (Bachelor of Science)
- Naturwissenschaften in der Informationsgesellschaft (Bachelor of Science)
- Technische Informatik (Bachelor of Science)
- Wirtschaftsinformatik (Bachelor of Science)
- Wirtschaftsingenieurwesen (Master of Science)
Legende
- IV: Integrierte Lehrveranstaltung (VL + UE)
- LV: Lehrveranstaltung
- P: Pflichtbestandteil eines Moduls (muss belegt werden)
- PJ: Projekt. Methodenvermittlung und Systemeinführung zur Projektarbeit, Entwicklungs-, Dokumentations- und Kommunikationswerkzeugen. Wöchentliche Projektbesprechungen. Projektarbeit in Kleingruppen. Milestones. Abschlusspräsentation.
- SE: Seminar. Literaturarbeit und schriftliche Ausarbeitung unter Anleitung. Vorstellung der Ergebnisse in einem 20 minütigen Vortrag im Plenum.
- SoSe: Sommersemester
- UE: Übung. Vertiefung des Vorlesungsstoffs, Lehrgespräche zur Besprechung der Übungsaufgaben, Gruppenarbeit zur Bearbeitung der Übungsaufgaben.
- VL: Vorlesung
- WiSe: Wintersemester
- WP: Wahlpflichtbestandteil eines Moduls. Eine der Wahlpflichtveranstaltungen des Moduls muss belegt werden.
Copyright TU Berlin 2007