EV charging demand forecast

The brief

A charging network sees queues at some stations and idle chargers at others. Forecast hourly charging sessions and energy per site, with daily and weekly patterns, to plan where and when to add chargers. Good looks like: forecasts that beat a seasonal baseline, back-tested over several weeks, and a recommendation per site.

What you will build

1. Build hourly demand series per site
2. Explore daily and weekly patterns
3. Compare seasonal-naive and gradient-boosted forecasts
4. Back-test over several weeks
5. Recommend where to add chargers

Free, open data to build it with

• ACN-Data: EV charging sessions ↗ Caltech

Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.