Calculating energy loss during an outage

Patent metadata

Field	Value
Publication number	US-12066472-B2
Application number	US-202117566383-A
Country	US
Kind code	B2
Filing date	Dec 30, 2021
Priority date	Dec 30, 2021
Publication date	Aug 20, 2024
Grant date	Aug 20, 2024

Abstract

Calculating energy loss during an outage, including: determining that windspeed data indicating device windspeeds measured at an energy generating device are unavailable within a particular time duration; receiving meteorological data associated with a site location of the energy generating device, the meteorological data including meteorological windspeed data collected within the particular time duration; and predicting one or more estimated device windspeeds at the energy generating device during the particular time duration based on the meteorological data using a trained model for the energy generating device, the trained model being trained using a machine learning algorithm that utilizes historical meteorological windspeed data associated with the site location collected during a previous time duration and corresponding historical device windspeed data measured at the energy generating device during the previous time duration.

First claim

What is claimed is:

1. A method, comprising:
receiving historical meteorological windspeed data associated with a site location of an energy generating device collected during a previous time duration;
receiving historical device windspeed data measured at the energy generating device during the previous time duration;
training, using a machine learning algorithm, a neural network using at least a portion of the historical meteorological windspeed data and the historical device windspeed data;
receiving an alert indicating that windspeed data indicating device windspeeds measured at the energy generating device are unavailable within a particular time duration;
receiving meteorological data associated with the site location of the energy generating device, the meteorological data including meteorological wind speed data collected within the particular time duration; and
predicting one or more estimated device windspeeds at the energy generating device during the particular time duration based on the meteorological data using the neural network for the energy generating device.

2. The method of claim 1 , further comprising:
determining a reference energy production value for the energy generating device during the particular time period based on the one or more estimated device windspeeds utilizing a reference energy production algorithm.

3. The method of claim 2 , wherein the reference energy production algorithm is based on one or more of an estimated windspeed of one or more near neighboring energy generating devices, a windspeed vs power curve associated with the energy generating device, or a machine learning algorithm.

4. The method of claim 2 , further comprising:
determining an estimated energy production loss for the energy generating device during the particular time period based on the reference energy production value.

5. The method of claim 4 , wherein the determining of the estimated energy production loss is responsive to receiving the alert indicating the unavailability of the device windspeeds during the particular time duration.

6. The method of claim 1 , wherein the particular time duration corresponds to a downtime event of the energy generating device.

7. The method of claim 1 , wherein the energy generating device comprises a wind turbine.

8. The method of claim 7 , wherein the estimated device windspeeds correspond to an estimated windspeed at a height of a turbine hub of the wind turbine.

9. A non-transitory computer-readable medium storing instructions, that when executed by at least one processor, cause the at least one processor to:
receive historical meteorological windspeed data associated with a site location of an energy generating device collected during a previous time duration;
receive historical device windspeed data measured at the energy generating device during the previous time duration;
train, using a machine learning algorithm, a neural network using at least a portion of the historical meteorological windspeed data and the historical device windspeed data;
receive an alert indicating that windspeed data indicating device windspeeds measured at the energy generating device are unavailable within a particular time duration;
receive meteorological data associated with the site location of the energy generating device, the meteorological data including meteorological windspeed data collected within the particular time duration; and
predict one or more estimated device windspeeds at the energy generating device during the particular time duration based on the meteorological data using the neural network for the energy generating device.

10. The non-transitory computer-readable medium of claim 9 , wherein the instructions further cause the at least one processor to:
determine a reference energy production value for the energy generating device during the particular time period based on the one or more estimated device windspeeds utilizing a reference energy production algorithm.

11. The non-transitory computer-readable medium of claim 10 , wherein the reference energy production algorithm is based on one or more of an estimated windspeed of one or more near neighboring energy generating devices, a windspeed vs power curve associated with the energy generating device, or a machine learning algorithm.

12. The non-transitory computer-readable medium of claim 10 , wherein the instructions further cause the at least one processor to:
determine an estimated energy production loss for the energy generating device during the particular time period based on the reference energy production value.

13. An apparatus, comprising:
at least one processor; and
at least one memory, the at least one memory storing instructions, that when executed by the at least one processor, cause the at least one processor to:
receive historical meteorological windspeed data associated with a site location of an energy generating device collected during a previous time duration;
receive historical device windspeed data measured at the energy generating device during the previous time duration;
train, using a machine learning algorithm, a neural network using at least a portion of the historical meteorological windspeed data and the historical device windspeed data;
receive an alert indicating that windspeed data indicating device windspeeds measured at the energy generating device are unavailable within a particular time duration;
receive meteorological data associated with the site location of the energy generating device, the meteorological data including meteorological windspeed data collected within the particular time duration; and
predict one or more estimated device windspeeds at the energy generating device during the particular time duration based on the meteorological data using the neural network for the energy generating device.

14. The apparatus of claim 13 , wherein the instructions further cause the at least one processor to:
determine a reference energy production value for the energy generating device during the particular time period based on the one or more estimated device windspeeds utilizing a reference energy production algorithm.

15. The apparatus of claim 14 , wherein the reference energy production algorithm is based on one or more of an estimated windspeed of one or more near neighboring energy generating devices, a windspeed vs power curve associated with the energy generating device, or a machine learning algorithm.

16. The apparatus of claim 14 , wherein the instructions further cause the at least one processor to:
determine an estimated energy production loss for the energy generating device during the particular time period based on the reference energy production value.

17. The apparatus of claim 14 , wherein the particular time duration corresponds to a downtime event of the energy generating device.

Assignees

• Sparkcognition Inc

Inventors

• Maheswari Sahil
• Gupta Sandeep
• Shah Jayesh
• Wessels Kate

Classifications

• G01W1/18

  Testing or calibrating meteorological apparatus · CPC title

• G01R31/003

  Environmental or reliability tests (of individual semiconductors G01R31/2642; of PCB's G01R31/2817; of IC's G01R31/2855; of other circuits G01R31/2849) · CPC title

• G06N20/00

  Machine learning · CPC title

• G01R22/06

  by electronic methods · CPC title

• G01W1/10 Primary

  Devices for predicting weather conditions (computers per se G06; display devices G09) · CPC title