Energy generation controller for wind turbine with shadow-effect energy generator(s)

Patent metadata

Field	Value
Publication number	US-12492677-B1
Application number	US-202519007663-A
Country	US
Kind code	B1
Filing date	Jan 2, 2025
Priority date	Jan 2, 2025
Publication date	Dec 9, 2025
Grant date	Dec 9, 2025

Abstract

An energy generation control process is provided for a wind turbine with shadow-effect energy generator(s). The control process includes determining, by an energy generation controller, an adjustment to a blade angle of a wind turbine to increase cumulative energy generation over a forecast time interval from the wind turbine. The wind turbine generates wind-based energy, and the wind turbine includes one or more shadow-effect energy generators to generate shadow-effect energy. The cumulative energy generation includes any wind-based energy generation and shadow-effect energy generation over the forecast time interval. The control process further includes initiating, by the energy generation controller, dynamically adjusting of the blade angle of the wind turbine using the determined adjustment to the blade angle to increase the cumulative energy generation over the forecast time interval from the wind turbine and the one or more shadow-effect energy generators.

First claim

What is claimed is:

1 . A method comprising:
determining, by an energy generation controller, an adjustment to a blade angle of a wind turbine to increase cumulative energy generation over a forecast time interval from the wind turbine, where the wind turbine generates wind-based energy, and the wind turbine includes one or more shadow-effect energy generators to generate shadow-effect energy, the cumulative energy generation including at least shadow-effect energy generation within the forecast time interval; and initiating, by the energy generation controller, dynamically adjusting of the blade angle of the wind turbine using the determined adjustment to the blade angle to increase the cumulative energy generation over the forecast time interval from the wind turbine and the one or more shadow-effect energy generators.

2 . The method of claim 1 , further comprising data-analysis-based predicting, by the energy generation controller, a maximum cumulative energy generation over the forecast time interval from the wind turbine and the one or more shadow-effect energy generators based on multiple forecasted conditions for the forecast time interval, wherein the adjustment to the blade angle of the wind turbine is determined based, at least in part, on the predicted maximum cumulative energy generation over the forecast time interval from the wind turbine and the one or more shadow-effect energy generators.

3 . The method of claim 2 , wherein the data-analysis-based predicting, by the energy generation controller, of the maximum cumulative energy generation comprises estimating, via one or more machine learning models, potential wind energy generation for one or more forecasted time instances of the forecast time interval, and potential shadow-effect energy generation for the one or more forecasted time instances of the forecast time interval.

4 . The method of claim 3 , wherein the estimating, via the one or more machine learning models, the potential wind energy generation includes determining the potential wind energy generation as a function of the blade angle and a blade tip speed, and the estimating, via the one or more machine learning models, the potential shadow-effect energy generation includes determining the potential shadow-effect energy generation as a function of the blade angle relative to a direction of solar irradiance and a shadow-to-illumination contrast ratio across an area of the one or more shadow-effect energy generators.

5 . The method of claim 3 , wherein the data-analysis-based predicting of the maximum cumulative energy generation over the forecast time interval further comprises subtracting from an estimated cumulative energy generation over the forecast time interval from the wind turbine and the one or more shadow-effect energy generators an energy cost based on a size of adjustment of the blade angle for the forecast time interval.

6 . The method of claim 3 , wherein the initiating, by the energy generation controller, the dynamic adjustment of the blade angle of the wind turbine is based on determining that, with the adjustment, a predicted cumulative energy gain over the forecast time interval from the wind turbine and the one or more shadow-effect energy generators exceeds a specified threshold.

7 . The method of claim 2 , wherein the multiple forecasted conditions for the forecast time interval comprises a forecasted wind speed and wind direction for the wind turbine and a forecasted solar irradiance for the one or more shadow-effect energy generators of the wind turbine.

8 . The method of claim 1 , wherein the one or more shadow-effect energy generators comprise one or more shadow-effect energy generators associated with one or more blades of the wind turbine.

9 . The method of claim 8 , wherein the wind turbine is a spiral blade wind turbine, and the one or more shadow-effect energy generators are incorporated as part of one or more blades of the spiral blade wind turbine.

10 . A computer program product comprising:
one or more computer-readable storage media; and program instructions stored on the one or more computer-readable storage media to perform operations comprising:
determining, by an energy generation controller, an adjustment to a blade angle of a wind turbine to increase cumulative energy generation over a forecast time interval from the wind turbine, where the wind turbine generates wind-based energy, and the wind turbine includes one or more shadow-effect energy generators to generate shadow-effect energy, the cumulative energy generation including at least shadow-effect energy generation within the forecast time interval; and
initiating, by the energy generation controller, dynamically adjusting of the blade angle of the wind turbine using the determined adjustment to the blade angle to increase the cumulative energy generation over the forecast time interval from the wind turbine and the one or more shadow-effect energy generators.

11 . The computer program product of claim 10 , wherein the operations further comprise data-analysis-based predicting, by the energy generation controller, a maximum cumulative energy generation over the forecast time interval from the wind turbine and the one or more shadow-effect energy generators based on multiple forecasted conditions for the forecast time interval, wherein the adjustment to the blade angle of the wind turbine is determined based, at least in part, on the predicted maximum cumulative energy generation over the forecast time interval from the wind turbine and the one or more shadow-effect energy generators.

12 . The computer program product of claim 11 , wherein the data-analysis-based predicting, by the energy generation controller, of the maximum cumulative energy generation comprises estimating, via one or more machine learning models, potential wind energy generation for one or more forecasted time instances of the forecast time interval, and potential shadow-effect energy generation for the one or more forecasted time instances of the forecast time interval.

13 . The computer program product of claim 12 , wherein the estimating, via the one or more machine learning models, the potential wind energy generation includes determining the potential wind energy generation as a function of the blade angle and a blade tip speed, and the estimating, via the one or more machine learning models, the potential shadow-effect energy generation includes determining the potential shadow-effect energy generation as a function of the blade angle relative to a direction of solar irradiance and a shadow-to-illumination contrast ratio across an area of the one or more shadow-effect energy generators.

14 . The computer program product of claim 12 , wherein the data-analysis-based predicting of the maximum cumulative energy generation over the forecast time interval further comprises subtracting from an estimated cumulative energy generation over the forecast time interval from the wind turbine and the one or more shadow-effect energy generators an energy cost based on a size of adjustment of the blade angle for the forecast time interval.

15 . The computer program product of claim 12 , wherein the initiating, by the energy generation controller, the dynamic adjustment of the blade angle of the wind turbine is based on determining that, with the adjustment, a predicted cumulative energy gain over the forecast time interval from the wind turbine and the one or more shadow-effect energy generators exceeds a specified threshold.

16 . The computer program product of claim 11 , wherein the multiple foreca

Assignees

• IBM

Inventors

• Rakshit Sarbajit Kumar
• Hazra Jagabondhu
• Padmanaban Manikandan

Classifications

• F05B2250/25

  helical · CPC title

• F03D9/007

  the wind motor being combined with means for converting solar radiation into useful energy · CPC title

• F03D7/02

  the wind motors having rotation axis substantially parallel to the air flow entering the rotor · CPC title

• F03D1/0608

  characterised by their aerodynamic shape · CPC title

• H02P2101/15

  for wind-driven turbines · CPC title