IPE 17-2022 Bachelor / Master Thesis
Smart energy: Analysis of data-driven optimization algorithms for a sustainable energy management

Organisationseinheit

Institut für Prozessdatenverarbeitung und Elektronik (IPE)

Ihre Aufgaben

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 coordinate energy flows and optimize them toward different objectives. In order to perform the optimization, an energy management system must select and implement a suitable optimization algorithm. However, this is increasingly challenging as various algorithms exist in the fields of nature-inspired optimization, mathematical optimization, and reinforcement learning. In your thesis, you analyze and compare the performance of selected algorithms for load scheduling and forecasting to facilitate the selection of a suitable optimization algorithm.

Your Thesis:

• Review: You will review different optimization algorithms in the domain of artificial neural networks, nature-inspired optimization techniques, and reinforcement learning. Here you focus on their functionality, application areas, performance, advantages, and disadvantages.
• Implement: Based on previous work, you will apply selected algorithms on a real dataset to compare their performance regarding optimality, robustness, and other criteria.
• Benchmark: You will thoroughly evaluate the experiments and provide a benchmarking of the different algorithms.

Eintrittstermin

Immediately

Ihre Qualifikation

• You study Computer Science, engineering, industrial engineering, or a related course of study
• You are deeply interested in topics such as energy systems, optimization, or forecasting
• You are able to read and write scientific texts in English or German
• You already have experience in Python
• You show an above-average degree of initiative and commitment, as well as a thorough way of working