Planning Winter EV Charging for a 6,000-Vehicle Fleet with Synthetic Data

How AVL used synthetic fleet operational data to plan winter charging for a 6,000-vehicle electric delivery fleet before the first cold season arrived.

Electric vehicles lose efficiency in the cold: they draw more power and charge more slowly, putting extra strain on the electricity grid. Austrian Post delivers mail nationwide on an electric fleet and faces this every winter, but every system it had tested was validated against summer data only. Multiverse Computing built SynthiaFleet to close that gap, generating the winter operational data needed to schedule charging, split demand between solar and grid supply, and keep the depot from overloading at peak hours.

The Challenge

The only measured data available from the fleet came from the summer. Records covered state-of-charge and odometer readings from the electric vans across several summer months, together with on-site weather and solar production data. No winter operational data existed yet, so there was no way to validate a charging strategy before the cold season arrived. Waiting for a full winter of real measurements would have delayed the pilot by an entire season, and the physics that matter most for depot planning, higher consumption and slower charging, only appear in the data the fleet had never recorded.

Our Solution

Read the full story

Add your email to unlock all the content

By continuing, you agree to Multiverse Computing's Terms and Privacy Policy