Skip to main content

Federated machine learning for creating power load profiles

The project explores how federated machine learning can create dynamic load type profiles for a digital forecasting tool for future grid capacity.

Power lines, poles, twilight

Photo: Tomas Ärlemo, Svenska kraftnät

AI Sweden has been investigating and developing knowledge around federated machine learning on sensitive datasets in health, vehicle data, and financial transaction data for several years. This technology enables training on datasets across multiple parties without data sharing.  

Svenska Kraftnät has a government mandate to plan for increased electricity use and needs to develop long-term planning. Accurate forecasts are required to visualize where electricity production, flexibility resources, and electricity usage should be connected.  

This project investigates whether federated machine learning on electricity grid data can create dynamic load type profiles for a digital forecasting tool for future grid capacity. The project will also investigate the value of machine learning compared to classical methods and identify potential institutional barriers.

Challenges

The main challenge is how electricity grid companies can collaborate to create a common ML model for load type profiles without violating legislation. The project will also create a mockup of a user-friendly tool for visualizing available grid capacity.

Project purpose

The purpose is to investigate if and how federated machine learning on electricity grid data can contribute to the creation of dynamic load type profiles for a digital forecasting tool for future available grid capacity.

Expected outcomes

  • A functioning federated “learning infrastructure” of ML models
  • Selection of format and structure for necessary electricity grid data and metadata
  • A prototype of an ML model that generates synthetic load type profiles
  • A “mockup” of a capacity map and user interface
What is Federated machine learning?

Federated machine learning is a technique where multiple stakeholders collaboratively train a machine learning model without sharing their raw data. Instead, each device or silo trains the model locally and only shares updates (like gradients), keeping the data private and secure.

Facts

Funding: Svenska Kraftnät

Participants: 

Project period: April 2025 - March 2026

For more information, contact
Anna Svensson
Anna Svensson
Co-lead - Energy
+46 (0)70-972 57 79

Related projects

Map of Sweden with blue data points.

Simulation and visualization of Sweden's future electricity system

This project focuses on developing a digital tool for users to conduct "what-if" scenarios related to Sweden's future electricity needs. It aims to facilitate discussions among industry...
The image showcases a diverse Swedish neighborhood with various housing types, set against a backdrop of pine trees and rocky terrain, bathed in warm, golden light.

Future electricity grids created with federated machine learning

This project addresses the critical need for improved tools for energy companies in analyzing their customers behaviour. By developing a federated machine learning model for analyzing electricity grid...
Highway extending through a lake with surrounding forests and mountains.

E-Charge 2: Pioneering AI solutions for heavy transport electrification

AI-optimized charging for electric heavy transport. AI Sweden enables accurate power forecasting & smart grid use for zero-emission trucking.
Preview of the website for the VGR and AI Sweden project 'Generation Toolkit'

Generation Toolkit

Digital scenario tool for future electricity production The Västra Götaland region currently imports 70% of the electricity that is used in the region. The project will develop a digital scenario tool...