BACHELOR THESIS – MACHINE LEARNING FOR RENEWABLE ENERGY FORCASTING (M/F/D)

fortiss is the research institute of the Free State of Bavaria for software-intensive systems and services with headquarters in Munich. The institute currently employs around 180 employees, who collaborate on research, development and transfer projects with universities and technology companies in Bavaria, Germany, and Europe. Research is focused on state-of-the-art methods, techniques and tools of software development, systems & service engineering, and their application to reliable, secure cyber-physical systems, such as the Internet of Things (IoT). fortiss has the legal structure of a non-profit limited liability company (GmbH). Its shareholders are the Free State of Bavaria (as majority shareholder) and the Fraunhofer Society for the Promotion of Applied Research.  www.fortiss.org

Machine Learning for Renewable Energy Forecasting (m/f/d)

To meet climate goals, a high ratio of renewable energy production is crucial. In Germany, wind and photovoltaics contribute most to the renewable share of the electricity mix, both facing the problem of high temporal power fluctuations due to their dependence on the weather. Therefore, reliable forecasts are essential to include more and more renewable energy into today's electricity system.

For PV power forecasting at small time scales (Intra-hour), a rather unconventional source of data can be utilized: Images from All sky cameras. Those cameras monitor the sky and provide detailed information about clouds and the position of the sun. They offer the benefit of a high spatial resolution on a small temporal horizon.

This thesis aims at building a prototypical sky imager. The Sky Imager should regularly take pictures from the sky and upload them to a server. These Images are used to make precise short-time forecasts of the power output from a nearby PV system using Machine Learning.


_________
Goals of thesis:
  • Building a sky imager and install it on the fortiss rooftop (in Munich)
  • Building a training data set from sky images and corresponding PV power output timeseries
  • Using Machine Learning to forecast the PV power based on the sky images
  • Comparing the forecasts to other methods and to the literature
 __________
Your profile:
  • Studies of informatics, electrical engineering or similar
  • Interest in energy-related topics
  • Knowledge of python
  • Basic knowledge of machine learning and neural networks is a plus
  • Knowledge of Raspberry Pi (Hardware/Software) is a plus
  • Good communication skills in English, basic skills in German are a plus
__________
Our offer:
  • Varied and future-oriented field of activity
  • Young, dynamic and team-oriented working atmosphere
  • Space for new ideas, for assuming responsibility, as well as for personal and professional development
  • Cooperation with industry and the research facilities of the Technical University of Munich
  • Please note that this Master thesis is not remunerated
__________
Did we catch your interest?

 
Please submit your application with a motivational statement, a detailed CV and a current transcript of records to recruitment(at)fortiss.org.

Job-ID: ASCI-BT-01-2022
Contact: Dr. Markus Duchon