Master Thesis: Probabilistic electricity price forecasting methods

 


Advertising division: IEK-10 - Energy Systems Engineering
Reference number: 2021M-045,

Master Thesis: Probabilistic electricity price forecasting methods

Background
IEK-10 focuses on the optimal design and operation of integrated, decentralized energy systems with a high share of renewable energy. Computer simulation and numerical optimization are our essential tools to arrive at efficient, reliable, and cost-effective solutions. We contribute both to the development of mathematical models and the development of improved optimization algorithms, tailored to specific problems related to energy systems. Our methods and software tools are validated against the operating data of real systems. Furthermore, we conduct comprehensive case studies to test and further improve the scalability and the performance of our models and algorithms.

Context and Assignment
Electricity for industrial consumers can be purchased at short notice on the so-called day-ahead and intraday electricity markets for hourly/quarter-hourly changing prices, respectively. Knowledge about future electricity prices is essential for the scheduling optimization of energy-intensive processes and, thus, electricity procurement decisions. Electricity prices exhibit high uncertainties due to their dependence on exogenous factors, e.g., renewable energy production and load demands. Incorporating these uncertainties into the scheduling optimization is economically beneficial and, hence, the price uncertainty must be considered in forecasting, e.g., by probabilistic forecasting.

In this thesis, a probabilistic electricity prices forecasting method will be developed. To this end, a suitable machine learning model will be developed and compared to state-of-the-art regression models. Finally, our probabilistic forecasts will be used for scheduling an energy-intensive process under uncertainty.

Your profile

  • Very good student from the field of Computational Engineering Sciences, Computer Science, Energy- or Process Systems Engineering, Mechanical Engineering, or similar
  • Prior programming experience in Python or MatLab
  • Experience with regression models desired
  • Ability to work independently
  • Interest in prediction methods, energy systems, and electricity markets

Our offer

  • Highly motivated scientists of different subject areas working together
  • A friendly and welcoming work environment
  • Supervision by experts in their respective fields

Due to the SARS-CoV-2 regulations, work is done in the home office. We are committed to equality and diversity and welcome applications from everyone! If you are interested, please send us your complete application.

Contact:
Eike Cramer
Forschungszentrum Jülich GmbH
Institute of Energy and Climate Research
Energy Systems Engineering (IEK-10)
52425 Jülich
Email: e.cramer@fz-juelich.de

No comments:

Post a Comment

Search This Blog

The University of Antwerp in Belgium invites application for vacant (32) PhD, Postdoctoral and Academic Positions

The University of Antwerp in Belgium invites application for vacant (32) PhD, Postdoctoral and Academic Positions