In this dataset, we provide FeederBW, a real-world energy dataset of 200 feeders from low-voltage grids with metadata in Germany over two years. The data was collected by the distribution system operator Netze BW in the southwest of Germany. The dataset is published by Netze BW together with the Institute for Automation and Applied Informatics (IAI) at the Karlsruhe Institute of Technology (KIT). When using the dataset in any context, e.g. a publication, please cite the corresponding paper: [2602.03521] arXiv: Real-world energy data of 200 feeders from low-voltage grids with metadata in Germany over two years. A code companion is available under GitHub: https://github.com/KIT-IAI/FeederBW. It comprises functions for downloading the data from Zenodo, loading and joining of the data as well as minimal examples for load forecasting and pseudo-measurement generation. Dataset structure: Feeder measurement data: the measurements for each low-voltage feeder (minute-level resolution) are provided in a seperate file. We zipped 40 files together resulting in five zip files with feeder measurement data. The format parquet can be easily read, for example with pandas or polars in python. (uncompressed roughly 11.1 GB) Feeder metadata: one short CSV file containing the metadata Weather data: one parquet file (hourly resolution) containing the weather data for all 200 low-voltage feeders. The data originates from the ICON-D2 model of the German Meteorological Service (DWD). The dataset is currently under review. It will be published soon. We will provide extensive informations about the dataset in a paper format. Dataset changelog: v1.1: added substation ids in feeder_metadata.csv v1.0: intial dataset

The last mile of the distribution grid is crucial for a successful energy transition, as more low-carbon technology like photovoltaic systems, heat pumps, and electric vehicle chargers connect to the low-voltage grid. Despite considerable challenges in operation and planning, researchers often lack access to suitable low-voltage grid data. To address this, we present the FeederBW dataset with data recorded by the German distribution system operator Netze BW. It offers real-world energy data from 200 low-voltage feeders over two years (2023-2025) with weather information and detailed metadata, including changes in low-carbon technology installations. The dataset includes feeder-specific details such as the number of housing units, installed power of low-carbon technology, and aggregated industrial energy data. Furthermore, high photovoltaic feed-in and one-minute temporal resolution makes the dataset unique. FeederBW supports various applications, including machine learning for load forecasting, conducting non-intrusive load monitoring, generating synthetic data, and analyzing the interplay between weather, feeder measurements, and metadata. The dataset reveals insightful patterns and clearly reflects the growing impact of low-carbon technology on low-voltage grids.

Usage notes We encourage scientists conducting ML experiments with the dataset to follow a consistent split of the data into training and test to enhance comparability. We recognize that deviations may be appropriate depending on the research question or methodology. For locational splits, we recommend to use feeders F1 - F160 for training and F161 - F200 for testing. When conducting a cross validation, we recommend using a five-fold-cross validation with the folds F1 - F40 (test feeders in the first iteration), F41 - F80 (test feeders in the second iteration), F81 - F120 (test feeders in the third iteration), F121 - F160 (test feeders in the fourth iteration) and F161 - F200 (test feeders in the fifth iteration). The locational splits correspond to a random distribution. For temporal splits, we recommend to use the first year (April 1, 2023 to March 31, 2024) for training and the second year (April 1, 2024 to March 31, 2025) for testing. In addition, we encourage users to apply cross validation for time-series forecasting. We do not recommend folds for the time-series cross validation because they can differ based on your research question.