Plain-language summary
- What it solves
- How much energy Italian solar and wind will produce tomorrow, and with how much uncertainty.
- Who it can serve
- Anyone following the power system, and anyone studying forecasting with confidence intervals.
- What it produces
- A next-day forecast in three scenarios, an abundance index, and a comparison against a simple reference.
Produce a point-in-time capacity-normalised D+1 solar and wind forecast that can be compared with baselines.
3 · What it produces
P10/P50/P90, D+1 GWh, abundance index and OOS metrics versus baselines.
The cards expose multiple views of the same workflow so result, method, evidence and history remain distinct.
4 · How it works
Capacity-normalised point-in-time forecasting
1Terna Public API primary and ENTSO-E fallback for observed generation/capacity; without credentials, a non-publishable Open-Meteo proxy using declared 100 m wind nodes, local power curves before weighted aggregation, ECMWF D+1; 1/24/168h lags, seasonality and clear-sky
2Gradient Boosting on capacity factor; empirical intervals
3time split and persistence; proxy separated from actuals and never matured as a real forecast; prospective ENTSO-E A69 baseline when available; nMAE/RMSE/bias/coverage/skill
4Persistence, rendering and governed publishing.
5 · Data and signals
| Element | Detail |
|---|---|
| Data and signals | Terna Public API primary and ENTSO-E fallback for observed generation/capacity; without credentials, a non-publishable Open-Meteo proxy using declared 100 m wind nodes, local power curves before weighted aggregation, ECMWF D+1; 1/24/168h lags, seasonality and clear-sky |
| Industrial transferability | load shifting, energy planning, storage and flexibility |
| Research | vintage bias and skill versus physical/operator baselines |
| Interpretation condition | V1 covers solar+wind only and does not certify RFNBO |
Gradient Boosting on capacity factor; empirical intervals
time split and persistence; proxy separated from actuals and never matured as a real forecast; prospective ENTSO-E A69 baseline when available; nMAE/RMSE/bias/coverage/skill
Python, pandas, scikit-learn, requests, SQLite, Matplotlib
mistaking the weather/capacity proxy for observed generation, missing forecast vintages or installed-capacity growth mistaken for skill
Workflow technical dossier
Methods, checks, stack and transferability conditions.
Data and signals
Terna Public API primary and ENTSO-E fallback for observed generation/capacity; without credentials, a non-publishable Open-Meteo proxy using declared 100 m wind nodes, local power curves before weighted aggregation, ECMWF D+1; 1/24/168h lags, seasonality and clear-sky
Inference / calculation
Gradient Boosting on capacity factor; empirical intervals
Validation
time split and persistence; proxy separated from actuals and never matured as a real forecast; prospective ENTSO-E A69 baseline when available; nMAE/RMSE/bias/coverage/skill
Stack
Python, pandas, scikit-learn, requests, SQLite, Matplotlib
Limitations
mistaking the weather/capacity proxy for observed generation, missing forecast vintages or installed-capacity growth mistaken for skill
See recent outputs
The Publications page collects local previews and, on request, the public feed.
Potential transferability
Have a problem similar to Italy Variable Renewable Forecast?
A first discussion can start from the objective, available data and success criterion without sending confidential information. A result observed here is not assumed to transfer automatically to another context.