 |
| Detailinformationen |
| Quellcurriculum |
Masterstudium Digital Energy Solutions 2026W |
| Lernergebnisse |
Kompetenzen |
| (*)Students can analyze and apply artificial intelligence (AI) methods in the context of energy systems. They understand fundamental AI concepts, supervised and unsupervised approaches, classification and regression, as well as timeseries forecasting and reinforcement learning. Students can evaluate the use of AI for applications such as trading, smart grids, energy management, and predictive maintenance. They are able to critically assess ethical, technical, and operational challenges of AI in energy, including data privacy, explainability, and security.
|
|
| Fertigkeiten |
Kenntnisse |
(*)- Understand the definition and basics of AI, including supervised and unsupervised methods (K4)
- Apply classification and regression models to energy-related problems (K5)
- Understand the difference between black-box and white-box models and evaluate their applicability (K5)
- Analyze methods for timeseries handling and forecasting in energy systems (K6)
- Understand and apply concepts of reinforcement learning in control and optimization tasks (K5)
- Evaluate the role of generative and agentic AI in energy-related applications (K4–K5)
- Apply AI techniques to energy trading, market analysis, smart grids, forecasting, energy management systems, and predictive maintenance (K6)
- Assess data privacy and security challenges in AI-based energy solutions (K5)
- Evaluate requirements for explainability of AI models in critical energy infrastructures (K6)
- Analyze technical and operational challenges of deploying AI in real-world energy environments (K5)
|
(*)- AI Fundamentals:
- Definition and basics
- Supervised/unsupervised learning
- Classification/regression
- Black-box/white-box models
- Timeseries handling & forecasting
- Reinforcement learning
- Generative & agentic AI
- Applications of AI in energy systems:
- Energy trading & market analysis
- Smart grids
- Forecasting
- Energy management systems
- Predictive maintenance
- Challenges & ethical considerations:
- Data privacy and security
- Explainability
- Technical and operational challenges
|
|
| Beurteilungskriterien |
(*)Final exam
|
| Lehrmethoden |
(*)Lecture, discussion, course material, exercise examples
|
| Abhaltungssprache |
Englisch |
| Literatur |
(*)Course materials (presentation slides) are made available via Moodle
|
| Lehrinhalte wechselnd? |
Nein |
|
