References
Research Project: H2KMU-Ki
This image was created using DALL·E, an advanced AI system for image generation. It illustrates the vision of seamlessly integrating advanced artificial intelligence with renewable energy sources.
Project Sponsor: Energy Solution Nord GmbH (ESN)
Project Contributors: David Erzmann (University of Bremen)
Project Leaders: Prof. Dr. Dr. h.c. Peter Maaß (University of Bremen) Patrick Hansel (ESN)
Project Funding: Bremer Aufbau Bank (BAB), funded by the State; FEI-Funding for Research, Development, and Innovation
Project Duration: January 1, 2024 – June 30, 2025
More and more companies, especially those that are energy-intensive, are seeking new ways to save energy and increase energy efficiency. One consequence of this trend is the increased expansion of renewable energy sources. However, this comes with the challenge of volatile energy production. Since both energy generation and consumption are volatile and not precisely predictable, energy storage systems are needed to ensure energy is available as needed.
This leads to the creation of complex energy systems that require appropriate regulation and control. Whenever large amounts of data are used to manage or optimize processes, the use of AI for automation becomes worthwhile. This can result in more efficient energy storage and utilization. Additionally, complex data analysis and predictive algorithms can be used to create energy capacities for peak loads.
The goal of this ambitious project is to develop and implement an artificial intelligence (AI) system for energy management and the control of complex renewable energy installations in small and medium-sized enterprises (SMEs). This AI system aims to enable the efficient use and storage of renewable energy and green hydrogen in solar and wind energy plants.
The AI will be driven by innovative algorithms and advanced data analysis methods, utilizing diverse data sources such as weather information, electricity market conditions, machine operation and generation data, and load profiles. It will determine the most economically optimal times to operate electrolyzers, batteries, and fuel cells, thereby maximizing the overall efficiency of the system and ensuring the sustainable use of green hydrogen. In close collaboration with the University of Bremen, which, together with the Steinbeis Zentrum, is responsible for developing this AI, we aim to employ pioneering technologies in the field of AI to revolutionize energy management in SMEs.