Reducing curtailment of wind power generation

1. A method comprising:

receiving, by a computer, historical electrical power output measurements of a wind turbine for a time period immediately preceding a specified past time;

receiving, by the computer, historical wind speed micro-forecasts for the geographic location of the wind turbine, for a time period immediately preceding the specified past time and for a time period immediately following the specified past time;

generating, by the computer, based on the historical electrical power output measurements and the historical wind speed micro-forecasts, a trained machine learning model for predicting wind power output of the wind turbine;

receiving real-time electrical power output measurements of the wind turbine and real-time wind speed micro-forecasts for the geographic location of the wind turbine; and

outputting, by the computer, using the trained machine learning model with the real-time electrical power output measurements of the wind turbine and the real-time wind speed micro-forecasts, a wind power output forecast for the wind turbine at a future time;

determining, by the computer, that an oversupply of wind power would be generated, based in part on the predicted wind power output of the wind turbine; and

curtailing, by the computer, wind power output of the wind turbine.

2. The method of claim 1 ,

wherein the historical electrical power output measurements of the wind turbine for a time period immediately preceding a specified past time comprise a predefined number of measurements at equal time intervals, ending at the specified past time, and

wherein the historical wind speed micro-forecasts for the geographic location of the wind turbine for a time period immediately preceding the specified past time and for a time period immediately following the specified past time comprise a predefined number of wind speed micro-forecasts at equal time intervals, ending at the specified past time, and a predefined number of wind speed micro-forecasts at equal time intervals beginning with the specified past time, respectively.

3. The method of claim 1 ,

wherein the real-time electrical power output measurements of the wind turbine comprise a predefined number of measurements at equal time intervals, ending at the current time, and

wherein the real-time wind speed micro-forecasts for the geographic location of the wind turbine comprise a predefined number of wind speed micro-forecasts at equal time intervals, ending at the current time, and a predefined number of wind speed micro-forecasts at equal time intervals, beginning with the current time.

4. The method of claim 1 , wherein the trained machine learning model is one of: a regression neural network, a support vector regression (SVR) model, or a linear regression model.

5. The method of claim 1 , wherein the wind power output forecast of the wind turbine for a future time is a short-term forecast, corresponding to a time 0 to 6 hours in the future.

6. A method comprising:

receiving, by a computer, historical wind speed measurements at a wind turbine for a time period immediately preceding a specified past time;

receiving, by the computer, historical wind speed micro-forecasts for a geographic location of the wind turbine, for a time period immediately preceding the specified past time and for a time period immediately following the specified past time;

generating, by the computer, based on the historical wind speed measurements and the historical wind speed micro-forecasts, a trained machine learning model for predicting wind power output of the wind turbine;

receiving real-time wind speed measurements at the wind turbine and real-time wind speed micro-forecasts for the geographic location of the wind turbine;

outputting, by the computer, using the trained machine learning model with the real-time wind speed measurements at the wind turbine and the real-time wind speed micro-forecasts, a wind power output forecast of the wind turbine for a future time;

determining, by the computer, that an oversupply of wind power would be generated, based in part on the predicted wind power output of the wind turbine; and

curtailing, by the computer, wind power output of the wind turbine.

7. The method of claim 6 ,

wherein the historical wind speed measurements at a wind turbine for a time period immediately preceding a specified past time comprise a predefined number of measurements at equal time intervals, ending at the specified past time, at hub height of the wind turbine, and

wherein the historical wind speed micro-forecasts for the geographic location of the wind turbine for a time period immediately preceding the specified past time and for a time period immediately following the specified past time comprise a predefined number of wind speed micro-forecasts at equal time intervals, ending at the specified past time, and a predefined number of wind speed micro-forecasts at equal time intervals, beginning with the specified past time, respectively.

8. The method of claim 6 ,

wherein the real-time wind speed measurements at the wind turbine comprise a predefined number of measurements at equal time intervals, ending at the current time, at hub height of the wind turbine, and

wherein the real-time wind speed micro-forecasts for the geographic location of the wind turbine comprise a predefined number of wind speed micro-forecasts at equal time intervals, ending at the current time, and a predefined number of wind speed micro-forecasts at equal time intervals, beginning with the current time.

9. The method of claim 6 , wherein the machine learning model is one of: a regression neural network, a support vector regression (SVR) model, or a linear regression model.

10. The method of claim 6 , wherein the wind power output forecast of the wind turbine for a future time is a short-term forecast, corresponding to a time 0 to 6 hours in the future.

11. A system comprising:

a wind turbine;

a meter for measuring power output of the wind turbine;

a computer, a computer-readable storage medium, and program instructions stored on the computer-readable storage medium, which when executed cause the computer to perform a method comprising:

receiving, by the computer, historical electrical power output measurements of the wind turbine, measured by the meter, for a time period immediately preceding the specified past time;

receiving, by the computer, historical wind speed micro-forecasts for the geographic location of the wind turbine for a time period immediately preceding a specified past time and for a time period immediately following the specified past time;

generating, by the computer, based on the historical wind speed micro-forecasts and the historical electrical power output measurements, a trained machine learning model for predicting wind power output of the wind turbine;

receiving, by the computer, real-time electrical power output measurements of the wind turbine, measured by the meter, and real-time wind speed micro-forecasts for the geographic location of the wind turbine;

using the machine learning model with the real-time electrical power output measurements and the real-time wind speed micro-forecasts to predict wind power output of the wind turbine at a future time;

determining, by the computer, that an oversupply of wind power would be generated, based in part on the predicted wind power output of the wind turbine; and

curtailing, by the computer, wind power output of the wind turbine.

12. The system of claim 11 ,

wherein the historical electrical power output measurements of the wind turbine for a time period immediately preceding a specified past time comprise a predefined number of measurements at equal time intervals, ending at the specified past time, and

wherein the historical wind speed micro-forecasts for the geographic location of the wind turbine for a time period immediately preceding the specified past time and for a time period immediately following the specified past time comprise a predefined number of wind speed micro-forecasts at equal time intervals, ending at the specified past time, and a predefined number of wind speed micro-forecasts at equal time intervals, beginning with the specified past time, respectively.

13. The system of claim 11 ,

wherein the real-time electrical power output measurements of the wind turbine comprise a predefined number of measurements at equal time intervals, ending at the current time, and

wherein the real-time wind speed micro-forecasts for the geographic location of the wind turbine comprise a predefined number of wind speed micro-forecasts at equal time intervals, ending at the current time, and a predefined number of wind speed micro-forecasts at equal time intervals, beginning with the current time.