Stekker.app manages the charging for a fleet of electric vehicles, to save on electricity costs and CO₂ emissions. The company uses TIM’s InstantML capabilities to predict the most economical times to recharge e-vehicles using solar and wind energy.
“We were quite new to machine learning in Python, but within weeks we’ve been able to set up a dockerized production environment which gathers all the relevant weather and market information that builds a model through TIM. We used the Python client from the start, so moving from experimentation to a production setup was a matter of going through a couple of iterations. The forecasts were available in our production version of our smart charging app just days later. This went really smoothly, while the predictive accuracy for our application is high.
Screenshot of the app, containing real data and a forecast with the planned moment of charging.
It’s valuable to be able to contact the Tangent Works team if we run into something. The calls are always pleasant and practical. Our challenges are usually resolved very quickly and we’re quickly back on track to improve our forecasts.
We look forward to applying the strength of TIM and machine learning in general to more and more data challenges and we appreciate the fruitful partnership between Stekker.app BV and Tangent Works.”
Testimonial by Erik de Bruijn – Co-founder and developer @ Stekker.app.
Learn more about Stekker.app on www.stekker.app.