Wind Power Forecast Simulator

Forecast Model

Forecast horizon 2.0 h

Turbulence intensity 18%

Mean wind speed 10.0 m/s

Time speed 1.0×

Live Readouts

Wind speed

0.0 m/s

Actual power

0.0 MW

Forecast power

0.0 MW

Forecast MAE

0.0 MW

Farm capacity factor

Sim time

00:00

How it works

Wind speed v(t) at the farm follows an Ornstein–Uhlenbeck (mean-reverting) stochastic process — the standard textbook model for short-term wind fluctuation around a slowly-varying mean:

dv = θ(μ − v)·dt + σ·dW

θ = reversion rate (how fast gusts decay)
μ = mean wind speed (slider)
σ = turbulence intensity × μ (slider)
dW = Gaussian white noise

Each turbine converts wind speed into electrical power through the standard three-region power curve used in real turbine datasheets:

P(v) = 0        for v < v_cut-in  (≈3.5 m/s)
P(v) = ½ρA·Cp·v³ for v_cut-in ≤ v < v_rated (≈12.5 m/s)
P(v) = P_rated   for v_rated ≤ v < v_cut-out (≈25 m/s)
P(v) = 0        for v ≥ v_cut-out (safety shutdown)

The cubic v³ term in the middle region is why a small change in wind speed swings power output so much — the physical reason wind forecasting is economically important for grid operators.

The forecast is a persistence-decay model: it starts from the current true wind speed and relaxes toward the known long-run mean μ over the chosen horizon H, mimicking how a real short-term forecast loses skill the further out it looks:

v_forecast(t+H) = μ + (v(t) − μ)·e^(−H/τ)

Because the true wind keeps evolving stochastically while the forecast only decays deterministically, the two diverge — the running Mean Absolute Error (MAE) on the chart is exactly the metric grid operators use to score forecast providers. Longer horizons and higher turbulence both widen this gap, which is why real-world grid balancing leans on ML models that continuously re-forecast rather than a single long-range guess.

Actual power Forecast power

⚠ Couldn't load the 3D engineThree.js failed to load from the CDN. Check your connection and reload.