Important results from the project
The project did well in developing and evaluating how well federated machine learning as a method and framework is applicable to electricity grid data. This is the first time this has been done on real data from electricity meters at each electricity grid company, not only in Sweden but also internationally. By using Fed ML methods, data from several electricity grid companies can form the basis for ML, which enriches the amount of different user behaviors that the model is exposed to.
Expected long term effects
The long-term effects are mainly about two things:
1. That electricity grid companies start using machine learning to create different insights.
2. That electricity grid companies develop common models and solutions which will accelerate the use of AI/ML.
This will improve the electricity grid companies´ ability to support the industry´s need for more electrical power.
Approach and implementation
The project followed the schedule well, but was slightly delayed due to difficulties in obtaining data. The delay was managed, and most objectives were reached. The only unmet goal was creating typical load profiles, mainly due to a lack of personnel resources at participating grid companies. Cooperation was very successful and will continue.
External links
The project description has been provided by the project members themselves and the text has not been looked at by our editors.
