Catch underperforming turbines before the monthly report does.

The challenge

A 1–3% power-curve deviation across a 50 MW farm is millions of euros of lost revenue a year — and it rarely shows up in a standard availability report, because the turbine is technically "available". By the time it surfaces in a monthly performance review, the deviation has been bleeding for weeks.

The data needed to catch it lives in the same 10-minute SCADA file your CMS imports. The reason most operators don’t catch it earlier is that nobody is conditioning the comparison on wind speed, air density, and curtailment state continuously.

What success looks like

How WindTwin delivers it

• Real-time monitoring — power, wind speed, pitch, and air density per turbine. The deviation you care about is computed on every reading, not on monthly aggregates.
• Wind-conditioned binning — power vs. wind, bucketed and compared to the warranted curve, with corrections for air density and turbulence intensity.
• Curtailment-aware — turbines that are dispatch-curtailed are excluded from the comparison instead of dragging the score down.
• Multi-condition alarms — "deviation > 3% conditioned on wind speed 8–12 m/s for > 6 hours" instead of single-threshold rules.
• Digital twin context — when an alarm fires, the recent pitch, yaw, and converter state are one click away for the performance engineer.
• Tickets & mobile capture — the deviation turns into a dispatched job; the crew records what they found; the closing report attaches to the asset.

A typical workflow

1. A turbine drifts below its warranted curve in the 8–12 m/s wind bin by more than 3% over the rolling 6 hours.
2. WindTwin checks for curtailment, yaw misalignment, and pitch anomalies; the alarm carries that context.
3. The performance engineer opens the twin, reviews the recent state, and decides whether it’s a pitch issue, a sensor drift, or something deeper.
4. A work order goes out. The crew’s closing report attaches to the asset and the campaign.

Where this lands first

• Mid-life turbines — most likely to have started drifting; lowest-effort win.
• Post-curtailment recoveries — turbines that don’t fully return to spec after a dispatch event.
• End-of-warranty fleet — proof of underperformance against the warranted curve has direct commercial value.