Wind Speed Forecasts for Wind Generation
This dataset provides detailed day-ahead hub-height wind speed and direction forecasts for wind farm locations, including model type, confidence scores, and optional power generation estimates. It is designed for power grid operators, energy analysts, and wind farm managers to optimize wind power scheduling, grid balancing, and operational planning using advanced mesoscale and machine learning models.
Sample rows
preview · 8 of 140 rows · all 15 columns| forecast_idstring | model_typestring | forecasted_wind_speed_mpsfloat | wind_farm_idstring | wind_farm_namestring | latitudefloat | longitudefloat | elevation_mfloat | forecast_datetimedatetime | forecasted_wind_direction_degfloat | forecasted_power_mwfloat | forecast_lead_time_hoursinteger | confidence_scorefloat | created_atdatetime | updated_atdatetime |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| FCST00001 | mesoscale | 15.6 | WF001 | Eagle Ridge | 41.5123 | -108.2121 | 1320 | 2024-07-01T10:00:00Z | 187.4 | 28.1 | 24 | 0.89 | 2024-06-30T10:01:13Z | 2024-06-30T11:01:13Z |
| FCST00002 | machine_learning | 9.8 | WF002 | Pacific Shores | 36.7824 | -121.6123 | 12.2 | 2024-07-01T11:00:00Z | 254.7 | 18.5 | 9 | 0.93 | 2024-06-30T15:01:13Z | 2024-06-30T15:11:13Z |
| FCST00003 | mesoscale | 21.3 | WF003 | Mountain Edge | 44.6721 | -106.1667 | 1654.8 | 2024-07-01T13:00:00Z | 104.4 | 35.2 | 48 | 0.81 | 2024-06-29T13:01:13Z | blank |
| FCST00004 | hybrid | 7.5 | WF004 | Plains Horizon | 39.1122 | -98.5567 | 321.6 | 2024-07-01T14:00:00Z | 133.2 | 12.8 | 18 | 0.76 | 2024-06-30T20:01:13Z | blank |
| FCST00005 | machine_learning | 13.4 | WF005 | Coastal Breeze | 34.0553 | -118.2448 | 7.3 | 2024-07-01T15:00:00Z | 202.5 | 22.1 | 6 | 0.91 | 2024-06-30T22:01:13Z | 2024-06-30T22:31:13Z |
| FCST00006 | mesoscale | 19.9 | WF006 | Lakeview Fields | 42.3421 | -88.1312 | 234 | 2024-07-02T09:00:00Z | 145.2 | 32.6 | 36 | 0.85 | 2024-07-01T09:01:13Z | 2024-07-01T09:16:13Z |
| FCST00007 | hybrid | 3.8 | WF007 | Sunset Prairie | 47.2134 | -101.5243 | 410.5 | 2024-07-02T10:00:00Z | 318.6 | 5.2 | 14 | 0.67 | 2024-07-01T20:01:13Z | blank |
| FCST00008 | machine_learning | 17.7 | WF008 | Northern Gale | 58.4029 | -135.4455 | 5 | 2024-07-02T11:00:00Z | 243.8 | 25 | 10 | 0.94 | 2024-07-01T23:01:13Z | 2024-07-01T23:03:13Z |
| FCST00009 | mesoscale | 24 | WF009 | Highland Crest | 51.2345 | -2.4456 | 1780 | 2024-07-02T12:00:00Z | 76.5 | 34.9 | 72 | 0.77 | 2024-06-29T12:01:13Z | blank |
| FCST00010 | hybrid | 5.6 | WF010 | Urban Windworks | 40.7128 | -74.006 | 43.6 | 2024-07-02T13:00:00Z | 229.1 | 8.4 | 12 | 0.61 | 2024-07-01T01:01:13Z | 2024-07-01T01:21:13Z |
| FCST00011 | machine_learning | 11.2 | WF011 | Seaside Flow | 51.5074 | 0.1278 | 9.2 | 2024-07-02T14:00:00Z | 112 | 16.7 | 5 | 0.84 | 2024-07-02T09:01:13Z | 2024-07-02T09:31:13Z |
| FCST00012 | mesoscale | 16.7 | WF012 | Eastern Plateau | 35.2223 | -80.8431 | 635 | 2024-07-02T15:00:00Z | 158.9 | 27.6 | 36 | 0.69 | 2024-07-01T15:01:13Z | blank |
| FCST00013 | hybrid | 7.9 | WF013 | Midwest Winds | 41.8781 | -87.6298 | 184 | 2024-07-03T08:00:00Z | 194.8 | 13.3 | 18 | 0.71 | 2024-07-02T08:01:13Z | 2024-07-02T08:56:13Z |
| FCST00014 | mesoscale | 18.3 | WF014 | Windy Heights | 55.9533 | -3.1883 | 1021 | 2024-07-03T09:00:00Z | 36.7 | 30.7 | 48 | 0.83 | 2024-07-01T09:01:13Z | 2024-07-01T09:04:13Z |
| FCST00015 | machine_learning | 16.1 | WF015 | Bayfront Energy | 37.7749 | -122.4194 | 18 | 2024-07-03T10:00:00Z | 270.1 | 24.3 | 8 | 0.93 | 2024-07-02T10:01:13Z | 2024-07-02T10:11:13Z |
| FCST00016 | hybrid | 2 | WF016 | Desert Valley | 33.4484 | -112.074 | 315 | 2024-07-03T11:00:00Z | 88.2 | 2.5 | 6 | 0.53 | 2024-07-02T11:01:13Z | blank |
| FCST00017 | other | 64.2 | WF017 | Global Winds | 48.8566 | 2.3522 | 45 | 2024-07-03T12:00:00Z | 210.3 | 98.7 | 120 | 0.11 | 2024-06-28T12:01:13Z | 2024-06-28T12:21:13Z |
| FCST00018 | hybrid | 12.4 | WF001 | Eagle Ridge | 41.5123 | -108.2121 | 1320 | 2024-07-04T10:00:00Z | 180.2 | 17.1 | 22 | 0.77 | 2024-07-03T10:01:13Z | 2024-07-03T10:34:13Z |
| FCST00019 | mesoscale | 22.6 | WF002 | Pacific Shores | 36.7824 | -121.6123 | 12.2 | 2024-07-04T11:00:00Z | 163.9 | 33.4 | 72 | 0.74 | 2024-07-01T11:01:13Z | blank |
| FCST00020 | other | 88.3 | WF003 | Mountain Edge | 44.6721 | -106.1667 | 1654.8 | 2024-07-04T13:00:00Z | 345.8 | 175 | 168 | 0.95 | 2024-06-29T13:01:13Z | 2024-06-29T13:31:13Z |
What the 140 rows show
from the 140-row sampleOther (model type) stands out: mean forecasted_
- 15.4median forecasted_
wind_ speed_ mps - 184.0median elevation_
m - 182.7median forecasted_
wind_ direction_ deg - 22.4median forecasted_
power_ mw - 17median forecast_
lead_ time_ hours - 0.80median confidence_
score
Median 15.4, from 0.0 to 100.0.
- string 4
- integer 1
- float 7
- datetime 3
Columns
15 columns in three groups| column | type | description | example |
|---|---|---|---|
| Text 4 columns | |||
forecast_id | string | Unique identifier for each wind speed forecast recordunique | FCST00001 |
wind_farm_id | string | Unique identifier for the wind farm location | WF001 |
wind_farm_name | string | Name of the wind farm | Eagle Ridge |
model_type | string | Type of forecasting model used (e.g., mesoscale, machine learning)mesoscale · machine_learning · hybrid · other | mesoscale |
| Numbers 8 columns | |||
latitude | float | Latitude coordinate of the wind farm location-90 to 90 | 41.5123 |
longitude | float | Longitude coordinate of the wind farm location-180 to 180 | -108.2121 |
elevation_m | float | Elevation of the wind farm hub in meters above sea level0 to 2,000 | 1320 |
forecasted_wind_speed_mps | float | Forecasted wind speed at hub height in meters per second0 to 100 | 15.6 |
forecasted_wind_direction_deg | float | Forecasted wind direction at hub height in degrees (meteorological convention)0 to 360 | 187.4 |
forecasted_power_mw | float | Forecasted wind power generation in megawatts for the given time and location0 or more · optional | 28.1 |
forecast_lead_time_hours | integer | Number of hours ahead the forecast is made (e.g., 24 for day-ahead)0 to 168 | 24 |
confidence_score | float | Confidence score of the forecast (0 to 1, higher is more confident)0 to 1 · optional | 0.89 |
| Dates and times 3 columns | |||
forecast_datetime | datetime | Date and time for which the wind speed and direction are forecasted | 2024-07-01T10:00:00Z |
created_at | datetime | Timestamp when the forecast record was created | 2024-06-30T10:01:13Z |
updated_at | datetime | Timestamp when the forecast record was last updatedoptional | 2024-06-30T11:01:13Z |
Use it for
An energy dashboard
Forecasted_
wind_ speed_ mps by model_ type. Excel, Power BI or Tableau. Why do the 14 other rows have a mean forecasted_
wind_ speed_ mps of 74.1? A root-cause class exercise
Hand out the rows and one question. The answer is in the data, not in the brief.
- Forecasts140FCST0000115.6mesoscaleFCST000029.8machine_…FCST0000321.3mesoscale
A software demo
Believable forecasts with wind_
farm_ id, wind_ farm_ name and latitude to fill a screen in front of a buyer.
This dataset140 rows15 columns
Yours1,000 rows15 columns
blueprint · wind-speed-forecasts-for-wind-generation
Behind this dataset
Same schema. As many rows as you need.
These 140 rows came out of a blueprint — 15 columns with generation rules behind each one. Open it in Data Factory to retune a column, add your own, wire in foreign keys, and run it at the size you actually need.
Rules it was built with
- Wind farm ID and turbine hub height (meters)
- Forecast timestamp and valid time (hourly intervals)
- Wind speed at hub height (m/s or mph) from mesoscale models
- Wind direction (degrees, 0-360) for directional turbines
- Wind shear exponent for vertical extrapolation
- Power curve mapping: wind speed to turbine MW output
- Aggregate wind farm output forecast (MW)
- Forecast uncertainty and persistence model comparison
Open the blueprint in Data Factory
1 credit per row. Preview 20 rows free. Buy rows for the full run.
- Exports
- CSV, JSON, JSONL, Parquet, SQL, Excel, TSV, XML
- Licence
- yours to use, including commercially
- API slug
- wind-speed-forecasts-for-wind-generation