Adaptive control of wave energy converters
A wave energy capture system deployed in water converts mechanical motion induced by waves in the water to electrical energy. A controller of the wave energy capture system receives input regarding real-time wave conditions in a vicinity of the wave energy capture system. The controller applies a control model to the received input to select a value of a control parameter for the wave energy capture system, where the control model includes a model that has been trained using machine learning to take wave condition data as input and to output control parameter values selected based on the wave condition data in order to increase an amount of energy captured by the wave energy capture system. The controller implements the selected value of the control parameter on the wave energy capture system.
1. A method comprising:
receiving, at a controller of a wave energy capture system deployed in a body of water, input regarding real-time wave conditions in a vicinity of the wave energy capture system;
wherein the wave energy capture system comprises an adjustable-length arm coupled to a main body;
applying, by the controller, a control model to the received input to select a control parameter value for the wave energy capture system,
wherein the control model comprises a model that has been trained using machine learning to take wave condition data as input and to output control parameter values selected based on the wave condition data in order to increase an amount of energy captured by the wave energy capture system; and
wherein applying the control model to select the value of the control parameter for the wave energy capture system comprises:
selecting an arm length for the adjustable-length arm; or
selecting a resting angle between the adjustable-length arm, waterline of the body of water at rest, and the main body; and
implementing, by the controller, the selected value of the control parameter on a physical, electrical, or software configuration of the wave energy capture system.
2. The method of claim 1 , wherein the input regarding real-time wave conditions comprises direct or indirect measurements of wave height, wave speed, wave direction, wave frequency, wave wavelength, or wave amplitude.
3. The method of claim 1 , wherein the control model is trained offline by a computing system based on a wave simulator model that is configured to predict an amount of electrical energy that will be produced by the wave energy capture system given simulated wave conditions.
4. The method of claim 3 , wherein the computing system is configured to train the control model by:
obtaining a training dataset including historical wave condition measurements, parameters of the wave energy capture system, and amounts of electrical energy produced by the wave energy capture system corresponding to the historical wave condition measurements and the parameters of the wave energy capture system;
determining a calculation of energy utilization that estimates total energy used by the control model;
causing the wave simulator model to output, for each of a plurality of samples of the training dataset, a predicted amount of electrical energy to be produced by the wave energy capture system under wave conditions and wave energy capture system parameters corresponding to each sample; and
training the control model based on the predicted amount of electrical energy being penalized by the calculation of energy utilization.
5. The method of claim 1 , further comprising:
storing, by the controller, historical data including measurements of wave conditions, parameters of the wave energy capture system, and amounts of electrical energy produced by the wave energy capture system corresponding to the wave condition measurements and the parameters of the wave energy capture system; and
retraining the control model, by the controller, based on the stored historical data.
6. The method of claim 1 , wherein the wave energy capture system comprises:
a floatation device pivotably coupled to a main body via an arm; and
a mechanical energy capture system coupled to the floatation device via a gear assembly;
wherein applying the control model to select the value of the control parameter for the wave energy capture system comprises selecting a gear ratio for the gear assembly through a clutch device at a joint of the arm and the main body.
7. The method of claim 1 , wherein the wave energy capture system comprises a floatation device coupled to a main body via an arm, wherein the floatation device has an adjustable buoyancy, and wherein applying the control model to select the value of the control parameter for the wave energy capture system comprises:
increasing or decreasing the buoyancy of the floatation device.
8. The method of claim 1 , wherein the wave energy capture system comprises an adjustable center of gravity, and wherein applying the control model to select the value of the control parameter for the wave energy capture system comprises:
modifying the center of gravity of the wave energy capture system.
9. The method of claim 1 , wherein the wave energy capture system comprises:
a floatation device pivotably coupled to a main body;
a mechanical energy capture system, coupled to the floatation device via a gear assembly, the mechanical energy capture system configured to convert mechanical motion of the floatation device relative to the main body to electrical energy; and
a battery electrically coupled to the mechanical energy capture system and configured to store the electrical energy output by the mechanical energy capture system;
wherein the controller reduces greenhouse gas emissions for recharging the battery by causing the mechanical energy capture system to passively convert mechanical wave energy to electrical energy.
10. A system comprising:
a processor; and
a non-transitory computer-readable medium storing instructions that, when executed by the processor, cause the system to:
receive input regarding real-time wave conditions in a vicinity of a wave energy capture system deployed in a body of water;
wherein the wave energy capture system comprises:
a floatation device pivotably coupled to a main body via an arm; and
a mechanical energy capture system coupled to the floatation device via a gear assembly;
apply a control model to the received input to select a configuration for the wave energy capture system,
wherein the control model comprises a model that has been trained using machine learning to take wave condition data as input and to output configuration commands selected based on the wave condition data in order to increase an amount of energy captured by the wave energy capture system; and
wherein applying the control model to select the configuration for the wave energy capture system comprises selecting a gear ratio of the gear assembly through a clutch device at a joint of the arm and the main body;
control the wave energy capture system by issuing one or more of the configuration commands to change kinematic energy capture motion by the wave energy capture system.
11. The system of claim 10 , wherein the instructions when executed by the processor further cause the system to:
store historical data including measurements of wave conditions, parameters of the wave energy capture system, and amounts of electrical energy produced by the wave energy capture system corresponding to the wave condition measurements and the configuration of the wave energy capture system; and
retraining the control model based on the stored historical data.
12. The system of claim 10 , wherein the wave energy capture system comprises an adjustable-length arm coupled to a main body, and wherein applying the control model to select the configuration for the wave energy capture system comprises:
selecting an arm length for the adjustable-length arm; or
selecting a resting angle between the adjustable-length arm, ocean waterline at rest, and the main body.
13. The system of claim 10 , wherein the wave energy capture system comprises a floatation device coupled to a main body via an arm, wherein the floatation device has an adjustable buoyancy, and wherein applying the control model to select the configuration for the wave energy capture system comprises:
increasing or decreasing the buoyancy of the floatation device.
14. The system of claim 10 , wherein the wave energy capture system comprises an adjustable center of gravity, and wherein applying the control model to select the configuration for the wave energy capture system comprises:
modifying the center of gravity of the wave energy capture system.
15. A non-transitory, computer-readable storage medium storing instructions that, when executed by a processor of a system, cause the system to:
receive input regarding real-time wave conditions in a vicinity of a wave energy capture system deployed in a body of water;
wherein the wave energy capture system comprises an adjustable-length arm coupled to a main body;
apply a control model to the received input to select a value of a control parameter for the wave energy capture system,
wherein the control model comprises a model that has been trained using machine learning to take wave condition data or one or more current control parameters as input and to output control parameter values selected based on the wave condition data in order to increase an amount of energy captured by the wave energy capture system; and
wherein applying the control model to select the value of the control parameter for the wave energy capture system comprises:
selecting an arm length for the adjustable-length arm; or
selecting a resting angle between the adjustable-length arm, waterline of the body of water at rest, and the main body; and
control the wave energy capture system by implementing one or more of the control parameter values on the wave energy capture system.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the wave energy capture system comprises:
a floatation device pivotably coupled to a main body via an arm; and
a mechanical energy capture system coupled to the floatation device via a gear assembly;
wherein applying the control model to select the value of the control parameter for the wave energy capture system comprises selecting a gear ratio of the gear assembly through a clutch device at a joint between the arm and main body.
17. The non-transitory computer-readable storage medium of claim 15 , wherein the wave energy capture system comprises a floatation device coupled to a main body via an arm, wherein the floatation device has an adjustable buoyancy, and wherein applying the control model to select the value of the control parameter for the wave energy capture system comprises:
increasing or decreasing the buoyancy of the floatation device.