FREEWAY – Automating Asynchronous Federated Learning and Edge Computing for Efficient Vehicle Operation Analytics
| Reference number | |
| Coordinator | Volvo Technology AB |
| Funding from Vinnova | SEK 7 349 996 |
| Project duration | August 2025 - August 2027 |
| Status | Ongoing |
| Venture | Transport and mobility solutions - FFI |
| Call | Transport and mobility services - FFI - spring 2025 |
Purpose and goal
The FREEWAY project aims to deliver next-generation digital services for electromobility by enabling asynchronous federated learning (AFL) to address scalability challenges, integrating advanced edge processing and MLOps workflows to enhance vehicle operational efficiency, safety, and uptime.
Expected effects and result
FREEWAY is expected to deliver an efficient, scalable AFL system incorporated with MLOps in the workflow, validated on real electromobility use cases, such as energy consumption forecasting, vehicle operation profiling, and anomaly detection. The impact extends from better-performing vehicle fleets to broader mobility innovations, positioning federated edge intelligence as a key enabler of sustainable digital services.
Planned approach and implementation
The FREEWAY project will be carried out over two years through four work packages. Halmstad University will lead the WPs for Knowledge dissemination and project management (WP0) and advanced analytics (WP2); Stream Analyze will lead WP1 edge computing infrastructure for AFL; Volvo Group Trucks Technology will lead MLOps for Centralized Solution and AFL (WP3). All partners will collaborate closely to ensure effective integration of results and achieve the overall goals.