In a significant step towards understanding and managing the energy transition at the local level, a team of researchers from Karlsruhe Institute of Technology (KIT) in Germany has compiled and analyzed a comprehensive dataset of real-world energy data from low-voltage grids. The researchers, Manuel Treutlein, Pascal Bothe, Marc Schmidt, Roman Hahn, Oliver Neumann, Ralf Mikut, and Veit Hagenmeyer, have collaborated with the German distribution system operator Netze BW to gather and study data from 200 low-voltage feeders over a two-year period (2023-2025).
The dataset, named FeederBW, is a rich source of information that includes energy consumption and production data, weather information, and detailed metadata about each feeder. This metadata encompasses the number of housing units, the installed power of low-carbon technologies such as photovoltaic systems, heat pumps, and electric vehicle chargers, as well as aggregated industrial energy data. One of the unique aspects of the FeederBW dataset is its high temporal resolution of one minute, which allows for detailed analysis of energy flows and the impact of weather conditions on energy consumption and production.
The FeederBW dataset offers valuable insights into the growing influence of low-carbon technologies on low-voltage grids. As more of these technologies are installed, they are increasingly shaping the energy landscape at the local level. The dataset reveals patterns that can help distribution system operators better understand and manage these changes. For instance, the data can be used to improve load forecasting, which is crucial for ensuring grid stability and efficiency. Additionally, the dataset supports non-intrusive load monitoring, which can help identify and address issues in the grid without the need for physical inspections.
The FeederBW dataset also provides a basis for generating synthetic data, which can be used to simulate different scenarios and test the impact of various policies and technologies on the grid. This can be particularly useful for planning and decision-making purposes. Furthermore, the dataset allows for the analysis of the interplay between weather, feeder measurements, and metadata, which can provide valuable insights into the factors that influence energy consumption and production.
The FeederBW dataset was published in the journal Applied Energy, a leading publication in the field of energy research. The dataset is expected to be a valuable resource for researchers, policymakers, and industry professionals working on the energy transition and the integration of low-carbon technologies into the grid. By providing a detailed and comprehensive picture of the energy landscape at the local level, the FeederBW dataset can help pave the way for a more sustainable and resilient energy system.
In summary, the FeederBW dataset is a significant contribution to the field of energy research, offering a wealth of data and insights that can help guide the energy transition at the local level. By providing a detailed and comprehensive picture of the energy landscape, the dataset can support a range of applications, from load forecasting and non-intrusive load monitoring to the generation of synthetic data and the analysis of the interplay between weather, feeder measurements, and metadata. The dataset is a valuable resource for anyone working on the energy transition and the integration of low-carbon technologies into the grid.
This article is based on research available at arXiv.