IPE 15-2022 Bachelor / Master Thesis
Smart energy: Federated Learning for secure load forecasting using reinforcement learning
Institut für Prozessdatenverarbeitung und Elektronik (IPE)
The energy transition and the resulting expansion of renewable energy resources increasingly pose a challenge to the energy system due to their volatile and intermittent nature. In this context, energy management systems are central as they monitor and forecast energy flows. One way to automatically predict energy flows is reinforcement learning. Here, learning agents are trained on smart meter data and get rewarded for desired behaviors and punished for undesired ones. However, using smart meter data for load forecasting is challenging due to data privacy requirements. One solution to improve data privacy is federated learning, as data is kept private, and only the trained machine learning models are merged and updated on a global server. Your thesis analyzes how federated learning can improve data privacy and accuracy for load forecasting.
- Review: You will review the state-of-the-art research on reinforcement learning, load forecasting, and federated learning. Here, you focus on algorithms and architecture.
- Architecture concept: Based on your research, you propose a federated learning architecture for secure load forecasting.
- Implement: You will implement your concept with a selected algorithm on real datasets.
- Evaluate: You will thoroughly evaluate the experiments.
- You study Computer Science, engineering, industrial engineering, or a related course of study
- You are deeply interested in topics such as artificial intelligence, deep learning, energy systems, or load forecasting
- You are able to read and write scientific texts in English or German
- You already have some experience in Python
- You show an above-average degree of initiative and commitment, as well as a thorough way of working
according to study regulations
Contact person in line-management
For further information, please contact Jonas Sievers, phone +01573 2470 449, email: email@example.com.
Bitte bewerben Sie sich online über den unten stehenden Button für die Ausschreibungsnummer IPE 15-2022.
Ausschreibungsnummer: IPE 15-2022
Bei gleicher Eignung werden anerkannt schwerbehinderte Menschen bevorzugt berücksichtigt.
Bei allgemeinen Fragen zur Bewerbung:
Personalservice (PSE) - Personalbetreuung
Frau Carrasco Sanchez
Telefon: +49 721 608-42016,
Kaiserstr. 12, 76131 Karlsruhe