KIT | KIT-Bibliothek | Impressum | Datenschutz

SPARK: High-Resolution Energy Data from a Sustainable Industrial Production Area in Karlsruhe

Sievers, Jonas ORCID iD icon 1; Bischof, Simon; Simon, Frank ORCID iD icon 1; Blank, Thomas ORCID iD icon 1
1 Institut für Prozessdatenverarbeitung und Elektronik (IPE), Karlsruher Institut für Technologie (KIT)

Abstract:

This dataset comprises high-resolution electricity measurements from 22 industrial machines - including mills, lathes, chip presses, and pumps - as well as a photovoltaic system, recorded at a 5-second sampling rate over periods ranging from one to seven years. The measurements were collected at the Campus North of the Karlsruhe Institute of Technology and include detailed electrical quantities such as voltages, currents, active and reactive power, harmonics, total harmonic distortion, and frequency. This dataset provides a comprehensive basis for research on industrial energy analytics, power quality, and flexibility assessment.


Zugehörige Institution(en) am KIT Institut für Programmstrukturen und Datenorganisation (IPD)
Institut für Prozessdatenverarbeitung und Elektronik (IPE)
Publikationstyp Forschungsdaten
Publikationsdatum 12.01.2026
Erstellungsdatum 01.01.2018 - 31.12.2024
Identifikator DOI: 10.35097/bjdg3m3rg5jv3skk
KITopen-ID: 1000185704
HGF-Programm 37.12.02 (POF IV, LK 01) Design,Operation & Digitalization of the Future Energy Grids
Lizenz Creative Commons Namensnennung 4.0 International
Schlagwörter Energy, Electricity Data, Dataset, High resolution, Power, Current, Voltage, Frequency, Harmonics, Industrial Machines, Milling Machines, Lathes, Chip Saw
Liesmich

The dataset follows the directory structure MACHINE/MEASUREMENT/VALUES_PER_YEAR, with all files compressed in .csv.xz format for space-efficient storage. Each data file contains the columns WsDateTime and the corresponding MEASUREMENT values. The accompanying validation folder mirrors this structure and includes, for each dataset, a _stats.csv file summarizing statistical metrics (mean, standard deviation, and quantiles) and a _missing.csv file detailing missing data, gap lengths, and data availability.

Art der Forschungsdaten Dataset
Relationen in KITopen
KIT – Die Universität in der Helmholtz-Gemeinschaft
KITopen Landing Page