Net demand forecast with wind and solar
Inspired by publicly reported work at NESO
Forecast demand and embedded wind and solar together, with uncertainty, so operators know how much backup to hold.
The brief
NESO has described working with The Alan Turing Institute on machine learning to balance the grid, and publishes demand and embedded wind and solar forecasts openly. Build a probabilistic net-demand forecaster: forecast demand and renewable output, combine them, give ranges rather than single numbers, and turn the ranges into a reserve recommendation. Good looks like: pinball loss and interval coverage against NESO's published forecasts, weather features that help, and a reserve dashboard.
Read the case first
What NESO has said in public about this kind of work, on its own pages:
- ESO and The Alan Turing Institute use machine learning to help balance the GB electricity grid (NESO) ↗
- NESO Data Portal ↗
Make it your own
Size it for a smaller grid: a rooftop-solar housing society, a college campus or a solar-heavy Indian state. Decide what a shortfall costs there and set the reserve rule to match.
AITeky has no link with NESO, which has not reviewed or endorsed this brief. The brief only draws on what the company has published, uses open data rather than its data, and is a learning exercise: don't present your project as NESO's work or system.
What you will build
- Join demand, embedded wind and solar, and weather data
- Forecast demand and renewables separately
- Combine into net demand with quantile models
- Evaluate pinball loss and coverage against published forecasts
- Turn intervals into a reserve recommendation
- Build an operator dashboard
Free, open data to build it with
Sign up free to get the data and links
It takes a minute with your email. AiTeky Pass (₹999/month or ₹9,999/year) is free for your first 30 days.