The Cost of Coverage: Conformalising Native Forecast Uncertainty for GB Wind Power
Organizations: University College London
Abstract
Uncertainty bands on wind forecasts help inform reserve sizing and commitments, but often fail to deliver their stated coverage. We apply conformal prediction to native bands to see what it adds and what it costs, comparing six forecasters, from ARIMA to a tabular foundation model, at two wind farms in Great Britain (GB) under operational conditions. We show that calibration repairs empirical marginal coverage with little or no Winkler Score penalty, but this apparent success conceals under-coverage in high winds. Calibrating by forecast wind regime turns marginal coverage into regime-level coverage, cutting day-ahead out-of-band volume in high winds by over 40% relative to pooled calibration while narrowing bands overall.
Figures & tables
| Forecaster | Reference(s) | Class | Native Uncertainty Band |
|---|---|---|---|
| Persistence | - | Empirical residual | Expanding-window residual quantiles |
| ARIMA | Box et al. (2015) | Parametric | State-space Gaussian forecast interval |
| LightGBM-QR | Ke et al. (2017) | Direct quantile | Pinball-optimised quantile interval |
| Bootstrap ensemble | Breiman (1996) | Ensemble spread | Out-of-bag residual quantiles |
| TabPFN v3 | Grinsztajn et al. (2026) | Amortised Bayesian | Posterior predictive distribution |
| GEFS power curve | Gneiting et al. (2005) | NWP ensemble | Censored EMOS over member scatter |
Appendix figures & tables5 assets
Supplementary material from the paper’s appendix.
Appendix
| Coverage | Width | Winkler Score | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 30 min | 3 h | 24 h | 30 min | 3 h | 24 h | 30 min | 3 h | 24 h | ||
| Subject | Method | |||||||||
| Persistence | Native | 0.90 | 0.90 | 0.89 | 0.25 | 0.56 | 1.09 | 0.39 | 0.81 | 1.47 |
| OSSCP | 0.90 | 0.90 | 0.90 | 0.25 | 0.56 | 1.11 | 0.39 | 0.79 | 1.44 | |
| NexCP | 0.91 | 0.90 | 0.89 | 0.26 | 0.56 | 1.09 | 0.37 | 0.78 | 1.45 | |
| ACI ( ) | 0.90 | 0.90 | 0.90 | 0.25 | 0.55 | 1.17 | 0.38 | 0.78 | 1.48 | |
| Coverage | Width | Winkler Score | ||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 30 min | 3 h | 24 h | 30 min | 3 h | 24 h | 30 min | 3 h | 24 h | ||
| Subject | Method | |||||||||
| Persistence | Native | 0.92 | 0.92 | 0.92 | 0.28 | 0.67 | 1.34 | 0.39 | 0.88 | 1.59 |
| OSSCP | 0.89 | 0.89 | 0.89 | 0.23 | 0.58 | 1.20 | 0.38 | 0.86 | 1.54 | |
| NexCP | 0.90 | 0.90 | 0.89 | 0.24 | 0.59 | 1.16 | 0.36 | 0.83 | 1.52 | |
| ACI ( ) | 0.90 | 0.90 | 0.90 | 0.23 | 0.59 | 1.27 | 0.36 | 0.83 | 1.59 | |
| Low (0–5 m/s) | Average (5–11 m/s) | High (11+ m/s) | |||||
|---|---|---|---|---|---|---|---|
| Kelmarsh | Penmanshiel | Kelmarsh | Penmanshiel | Kelmarsh | Penmanshiel | ||
| Subject | Method | ||||||
| Persistence | Native | 0.93 | 0.97 | 0.91 | 0.92 | 0.67 | 0.80 |
| OSSCP | 0.94 | 0.95 | 0.91 | 0.89 | 0.75 | 0.81 | |
| Mondrian-OSSCP | 0.96 | 0.90 | 0.90 | 0.89 | 0.87 | 0.91 | |
| ARIMA | Native | 0.99 | 1.00 | 0.96 | 0.97 | 0.45 | 0.65 |
| Farm | Method | Missed energy (MWh) | Share of total missed energy (%) | Above upper bound (%) |
|---|---|---|---|---|
| Kelmarsh | Native | 0.26 | 34 | 94 |
| OSSCP | 0.23 | 35 | 94 | |
| Mondrian-OSSCP | 0.13 | 23 | 90 | |
| Penmanshiel | Native | 0.50 | 38 | 91 |
| OSSCP | 0.50 | 38 | 93 | |
| Mondrian-OSSCP | 0.29 | 25 | 92 |
Wind Power Forecasting
Wind power forecasting predicts turbine and farm output from operational data, weather forecasts, and remote observations to support reliable energy planning.
See all 27 papers