Title: Distributed reinforcement learning and consensus control of energy systems

Abstract

Disclosed herein are methods, systems, and devices for utilizing distributed reinforcement learning and consensus control to most effectively generate and utilize energy. In some embodiments, individual turbines within a wind farm may communicate to reach a consensus as to the desired yaw angle based on the wind conditions.

Inventors:

King, Jennifer Rose Rose; Fleming, Paul Aaron; Dall'Anese, Emiliano; Bay, Christopher Joseph; Graf, Peter Andrew

Issue Date:

2023-08-15

Research Org.:

National Renewable Energy Laboratory (NREL), Golden, CO (United States)

Sponsoring Org.:

USDOE

OSTI Identifier:

2222113

Patent Number(s):

11725625

Application Number:

17/264,967

Assignee:

Alliance for Sustainable Energy, LLC (Golden, CO)

Patent Classifications (CPCs):

F - MECHANICAL ENGINEERING F03 - MACHINES OR ENGINES FOR LIQUIDS F03D - WIND MOTORS

F - MECHANICAL ENGINEERING F05 - INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04 F05B - INDEXING SCHEME RELATING TO MACHINES OR ENGINES OTHER THAN NON-POSITIVE-DISPLACEMENT MACHINES OR ENGINES, TO WIND MOTORS, TO NON-POSITIVE DISPLACEMENT PUMPS, AND TO GENERATING COMBUSTION PRODUCTS OF HIGH PRESSURE OR HIGH VELOCITY

Show more

F - MECHANICAL ENGINEERING F03 - MACHINES OR ENGINES FOR LIQUIDS F03D - WIND MOTORS

F03D17/00 - Monitoring or testing of wind motors, e.g. diagnostics
F03D7/0204 - {for orientation in relation to wind direction}
F03D7/045 - {with model-based controls}
F03D7/046 - {with learning or adaptive control, e.g. self-tuning, fuzzy logic or neural network}
F03D7/048 - {Controlling wind farms}

F - MECHANICAL ENGINEERING F05 - INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04 F05B - INDEXING SCHEME RELATING TO MACHINES OR ENGINES OTHER THAN NON-POSITIVE-DISPLACEMENT MACHINES OR ENGINES, TO WIND MOTORS, TO NON-POSITIVE DISPLACEMENT PUMPS, AND TO GENERATING COMBUSTION PRODUCTS OF HIGH PRESSURE OR HIGH VELOCITY

F05B2260/821 - Parameter estimation or prediction
F05B2270/321 - Wind directions
F05B2270/326 - Rotor angle
F05B2270/709 - with neural networks

G - PHYSICS G05 - CONTROLLING G05B - CONTROL OR REGULATING SYSTEMS IN GENERAL

G05B13/027 - {using neural networks only}

Y - NEW / CROSS SECTIONAL TECHNOLOGIES Y02 - TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE Y02E - REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION

Y02E10/72 - Wind turbines with rotation axis in wind direction

Show less

DOE Contract Number:  

AC36-08GO28308

Resource Type:

Patent

Resource Relation:

Patent File Date: 07/31/2019

Country of Publication:

United States

Language:

English