Steel Industry – Energy Consumption Dataset

This dataset contains 15-minute interval energy usage records from a steel manufacturing facility. It includes continuous electrical measurements, CO₂ emissions, time-based features, and categorical indicators related to operational load and weekday/weekend status. The dataset is suitable for energy forecasting, industrial analytics, and smart factory research.

Features Included

• Usage_kWh – energy consumption

• Reactive Power (Lagging/Leading)

• CO₂ emissions

• Power Factor (Lagging/Leading)

• NSM (Number of Seconds from Midnight)

• WeekStatus – Weekday or Weekend

• Day_of_week

• Load_Type – Light, Medium, or Maximum load

• Timestamp (date)

Total instances: ~35040 records covering the full year 2018.

Intended Use

Ideal for machine learning tasks such as:

• Energy consumption prediction

• Load forecasting

• Peak demand analysis

• Industrial process optimization

• Machine learning modeling

Source / Reference

• Sathishkumar V. E., Shin C., Cho Y.,
  Efficient energy consumption prediction model for a data analytic-enabled industry building in a smart city,
  Building Research & Information, 2021.

• Sathishkumar V. E. et al.,
  An Energy Consumption Prediction Model for Smart Factory using Data Mining Algorithms,
  KIPS Transactions on Software and Data Engineering, Vol. 9, No. 5, 2020.

• Sathishkumar V. E. et al.,
  Industry Energy Consumption Prediction Using Data Mining Techniques,
  International Journal of Energy Information and Communications, Vol. 11, 2020.