Alliander, the Netherlands’ electricity and gas distribution system operator (DSO), initiated a Short-Term-Forecasting (STEF) project to anticipate the load on the grid within the next few hours to days. Forecasting future load in the short term is essential to avoid local congestion, analyze grid safety, and optimize the use of existing assets. The stack has since been open sourced as LF Energy’s OpenSTEF Project.
In this episode of State of Energy recorded at the 2023 LF Energy Summit in Paris, Frederik Stoel, OpenSTEF Technical Steering Committee Member as well as Data Science Engineer at Alliander, talks about the status of the project and what lies ahead.
Highlights of this video interview:
- OpenSTEF is all about forecasting energy in the short term, particularly the power load for the next 48 hours.
- Energy forecasting has become more difficult because of the current dynamics, where even the small customers are becoming producers. As the demand for electricity grows, assets are getting more loaded.
- From the perspective of a grid operator, it might not really matter how the microgrid looks like. What would be beneficial to a grid operator is if a microgrid is able to balance itself. It would ease the load on the national grid and more of those microgrids (or more customers) can be connected.
- Forecasting is important for microgrids so that they can tell the grid operator what they need and the operator can provide the exact capacity by using dynamic contracts or other constructs.
- Some points in the grid indicate over-generation while others have over-consumption of electricity. When forecasting, both problems have to be taken into account.
- There is a lot of interest in OpenSTEF from 1) grid operators because they are dealing with the same problems as Alliander, 2) larger companies that have compounds or campuses with multiple buildings, and 3) other parties who want to collaborate on solutions.
- The project is currently in production at Alliander.
- Forecasting helps companies deal with climate change. They can determine what type of energy source is available tomorrow and plan accordingly to reduce carbon emissions.
- What’s ahead: OpenSTEF will research 1) the feasibility of disaggregating the load into wind, solar, etc. at the node level, and 2) how to combine forecasts to provide more insight into the grid (is it to simply compile the forecasts together OR add the data points and then make a forecast).
This summary was written by Camille Gregory.