The OpenSTEF project provides a valuable portfolio of automated, Open Source machine learning pipelines that provide accurate short-term load forecasting for energy grids.
Developed by energy experts and constantly refined as part of an open industry development process, the OpenSTEF forecasting pipelines combine inputs of measured historical grid data, together with relevant external predictors such as weather and market pricing. Users can forecast the future load on any grid, with the ability to look at energy consumption, (renewable) generation, or a combination of both.
OpenSTEF outputs forecasts via either an API or (expert) graphical user interface. The entire technology stack is built on Open Source technology and open standards, and its microservice architecture is optimized for cloud-native deployment.
RTE contributes to the development of OpenSTEF.