Versions Compared


  • This line was added.
  • This line was removed.
  • Formatting was changed.

OpensSTF OpenSTEF provides automated machine learning pipelines to deliver accurate, self-correcting and explainable forecasts of the load on the grid for the next 48 hours.



The energy transition poses new challenges to all parties in the energy sector. For grid operators, the rise in renewable energy and electrification of energy consumption leads to the capacity of the grid to near its physical constraints. Forecasting the load on the grid in the next hours to days is essential for anticipating on local congestion and making the most of existing assets.  

OpenSTF OpenSTEF provides a complete software stack which forecasts the load on the electricity grid for the next hours to days. Given a timeseries of measured (net) load or generation, a fully automated machine learning pipeline is executed which delivers a probabilistic forecast of future load. This works for energy consumption, (renewable) generation or a combination of both. OpenSTF OpenSTEF performs validation on the input data, combines measurements with external predictors such as weather data and market prices, trains any scikit-learn compatible machine learning model, and delivers the forecast via both an API and an (expert) graphical user interface. The stack is based on open source technology and standards and is organized in a microservice architecture optimized for cloud-deployment.


Screenshot of the operational dashboard showing the key functionality of OpenSTFOpenSTEF


openstfOpenSTEFAutomated Machine Learning Pipelines. Builds the Open Short Term Forecasting package
openstfOpenSTEF-dbcProvides (company specific) database connector for the OpenSTF OpenSTEF package

Provides Jupyter Notebooks showing how to use OpenSTF OpenSTEF and apply it's functionality to your usecase

openstfOpenSTEF-referenceDeploy the entire OpenSTF OpenSTEF stack on your machine. Provides a reference implementation of the OpenSTF OpenSTEF stack