LF Energy Summit Europe 2026

OpenSTEF 4 introduces a redesigned, modular architecture that makes it easier to build and adapt energy forecasting solutions to your specific context. Rather than prescribing a single way of to integrate OpenSTEF in your setup, version 4 gives users the flexibility to create forecasting pipelines that fit their data, workflows, and IT environment.

In this hands-on tutorial, participants will explore the new architecture and learn how to assemble forecasting workflows using OpenSTEF's modular building blocks. You'll discover how to customize data preparation and feature engineering, integrate your preferred tools, experiment with different modeling approaches, and adapt forecasting setups to your own use case.

The tutorial provides a practical introduction to the newly developed capabilities of OpenSTEF 4, including support for ensemble forecasting, benchmarking and backtesting through STEF BEAM, and integration of deep learning and foundation models. Participants will work through real examples and gain insight into how

OpenSTEF can support everything from experimentation to production-scale forecasting.

Who should attend?
Whether you are a researcher exploring new forecasting methods, a data scientist building operational models, an organization looking to scale forecasting capabilities, or whether you are already experienced with forecasting (potentially through using OpenSTEF 3), this session is for you.