federAted oRchestration In EV fLeets
ARIEL
Federated AI orchestration for edge systems, a winning proposal of the O-CEI Open Call (Horizon Europe), powered by Indigma’s FedMaestro.
- Programme
- Horizon Europe · O-CEI Open Call
- Orchestrator
- FedMaestro (Indigma)
- Validation
- O-CEI Pilot 3, ML at the edge
- Focus
- Privacy-preserving distributed AI
ARIEL is a privacy-preserving AI orchestration platform for electric vehicles and fleets. Training happens across edge devices while Indigma’s FedMaestro coordinates workflows, client participation and model aggregation across edge and cloud environments.
Raw data stays local. Secure aggregation and differential privacy protect what is shared.
Key features.
01
Federated learning
Collaborative training without sharing raw data.
02
Edge deployment
Execution on distributed, resource-constrained devices.
03
Privacy-preserving design
Secure aggregation and privacy-enhancing techniques.
04
Flexible orchestration
Workflows across heterogeneous edge and cloud infrastructure.
Use cases.
01
Solar forecasting
Clients train models to predict solar generation from local historical signals.
02
Charging demand forecasting
Clients tied to EVs, chargers or charger groups predict near-term charging demand.
Impact
Scalable, privacy-preserving AI aligned with European trustworthy-AI priorities.
ARIEL lays groundwork for wider adoption of federated learning in energy, mobility and distributed infrastructure.
More R&D projects.
FLAME
Privacy-preserving forecasting of demand and renewable production for Energy Communities, trained at the edge.
02FLORA
An ovulation-tracking app that keeps personal data on the device while training prediction models collaboratively.
03FLAMENCO
A federated learning application that helps identify communication disorders in children.