A method of controlling at least one wind turbine is provided. The method comprises predicting at least one future state related to the at least one wind turbine. The method further comprises evaluating a fitness of solutions associated with a plurality of individuals of a population for a current o
A method of controlling at least one wind turbine is provided. The method comprises predicting at least one future state related to the at least one wind turbine. The method further comprises evaluating a fitness of solutions associated with a plurality of individuals of a population for a current operating environment of the at least one wind turbine. Each individual comprising a dominant genotype and a recessive genotype. Each genotype represents a solution for controlling the at least one wind turbine. A fitness function is applied to the dominant genotype of each individual. The fitness function is based on the at least one predicted future state. The method further comprises storing previously encountered genotypes in the recessive genotypes of the individuals. The method further comprises selecting a solution for controlling operation of the at least one wind turbine based on the fitness evaluation.
대표청구항▼
1. A method of controlling at least one wind turbine, comprising: predicting at least one future state related to the at least one wind turbine;evaluating a fitness of solutions associated with a plurality of individuals of a population for a current operating environment of the at least one wind tu
1. A method of controlling at least one wind turbine, comprising: predicting at least one future state related to the at least one wind turbine;evaluating a fitness of solutions associated with a plurality of individuals of a population for a current operating environment of the at least one wind turbine, each individual comprising a dominant genotype and a recessive genotype, wherein each genotype represents a solution of the solutions associated with the plurality of individuals for controlling at least one wind turbine, wherein a fitness function is applied to the dominant genotype of each individual, wherein the fitness function is based on the at least one future state;storing previously encountered genotypes in the recessive genotypes of the individuals; andselecting a solution of the solutions associated with the plurality of individuals for controlling the at least one wind turbine based on the evaluating of the fitness solutions, wherein predicting the at least one future state comprises: collecting data related to operation of the at least one wind turbine;embedding the data in a reconstructed phase space to provide embedded data; andpredicting the at least one future state based on a rate of separation of trajectories of the embedded data within the reconstructed phase space. 2. The method of claim 1, wherein the data comprises data relating to at least one of a wind state, a wind turbine system load state, and a power demand state. 3. The method of claim 2, wherein the data is collected from a supervisory control and data acquisition system associated with the at least one wind turbine. 4. The method of claim 1, wherein the at least one future state is predicted based on a maximum Lyapunov exponent. 5. The method of claim 1, wherein the at least one wind turbine comprises a wind farm including a plurality of wind turbines. 6. The method of claim 1, further comprising detecting a change in the current operating environment of the at least one wind turbine by comparing a best fitness of a current generation of the population with a best fitness of a previous generation of the population. 7. A control system, comprising: an electronic processor configured to: embed time series data relating to at least one wind turbine within a reconstructed phase space to provide embedded data;predict at least one future state related to the at least one wind turbine based on a rate of separation of trajectories of the embedded data within the reconstructed phase space;control operation of the at least one wind turbine based on the atleast one future state, Wherein the processor is configured to generate a population comprising a plurality of individuals, each individual comprising a dominant genotype and a recessive genotype, wherein each genotype represents a solution for controlling the at least one wind turbine;evaluate a fitness of the solutions for controlling the at least one wind turbine associated with the plurality of individuals for a current operating environment of the at least one wind turbine by applying a fitness function to the dominant genotype of each individual, wherein the fitness function is based on the at least one future state;store previously encountered genotypes in a recessive genotype of the individuals; andselect a solution of the solutions for controlling operation of the at least one wind turbine based on the fitness evaluation. 8. The control system of claim 7, wherein the processor is configured to detect a change in the current operating environment of the at least one wind turbine by comparing a best fitness of a current generation of the population with a best fitness of a previous generation of the population. 9. The control system of claim 7, wherein the at least one future state comprises at least one of a wind state, a wind turbine system load state, and a power demand state. 10. The control system of claim 7, wherein the time series data is collected from a supervisory control and data acquisition system associated with the at least one wind turbine. 11. The control system of claim 7, wherein the processor is configured to embed the time series data within the reconstructed phase space by calculating a minimum embedding dimension using a False Nearest Neighbors process. 12. The control system of claim 7, wherein the at least one future state of the system is predicted based on a maximum Lyapunov exponent. 13. The control system of claim 7, wherein the at least one wind turbine comprises a wind farm including a plurality of wind turbines. 14. A non-transitory computer-readable medium having instructions stored thereon, the instructions being executable by a processor to execute a method, the method comprising: embedding data related to operation of at least one wind turbine in a reconstructed phase space to provide embedded data;predicting at least one future state of the at least one wind turbine based on a rate of separation of trajectories of the embedded data within the reconstructed phase space;generating a population comprising a plurality of individuals, each individual comprising a dominant genotype and a recessive genotype, wherein each genotype represents a solution for controlling the at least one wind turbine;evaluating a fitness of the solutions for controlling the at least one wind turbine associated with the plurality of individuals for a current operating environment of the at least one wind turbine by applying a fitness function to the dominant genotype of each individual, wherein the fitness function is based on the at least one future state;storing previously encountered genotypes in the recessive genotypes of the individuals; andselecting a solution of the solutions for controlling the at least one wind turbine based evaluating the fitness of the solutions. 15. The non-transitory computer-readable medium of claim 14, wherein the method further comprises detecting a change in the current operating environment of the at least one wind turbine by comparing a best fitness of a current generation of the population with a best fitness of a previous generation of the population. 16. The non-transitory computer-readable medium of claim 14, wherein the data comprises data relating to at least one of a wind state, a wind turbine system load state, and a power demand state. 17. The non-transitory computer-readable medium of claim 14, wherein the at least one future state of the system is predicted based on a maximum Lyapunov exponent. 18. The non-transitory computer-readable medium of claim 14, wherein the at least one wind turbine comprises a wind farm including a plurality of wind turbines.
연구과제 타임라인
LOADING...
LOADING...
LOADING...
LOADING...
LOADING...
이 특허에 인용된 특허 (15)
Kondo, Shinichi; Ono, Yasunori; Uchiyama, Noriyuki; Ichinose, Masaya; Matsutake, Mitsugu; Aihara, Takashi, Controller and control method for a wind farm including a plurality of wind turbine generators.
Mertins, Karl-Heinz Otto; Fulkerson, William Francis; Halterman, Jerry Ray; Muehlbach, George Bailey; Joshi, Deepak Jugatram, Method and system of determining a location for a wind-powered electrical energy facility.
Ubben, Enno; Middendorf, Joerg; Loh, Friedrich, System and method of selecting wind turbine generators in a wind park for curtailment of output power to provide a wind reserve.
Dalsgaard, Søren; Thomsen, Jesper Sandberg; Brath, Per; Kjær, Martin Ansbjerg, Warning a wind turbine generator in a wind park of an extreme wind event.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.