Maximum wind energy tracking method based on CAOA-Elman model and related equipment

Abstract

The invention discloses a maximum wind energy tracking method based on a CAOA-Elman model and related equipment. The method comprises the following steps: acquiring operation data of a to-be-tested wind turbine generator; the operation data comprises a wind wheel rotating speed, a pitch angle and generator output power; inputting the operation data into a CAOA-Elman model for wind speed prediction to obtain a wind speed prediction value of the to-be-tested wind turbine generator; calculating a reference rotating speed corresponding to the maximum power point of the to-be-measured wind turbine generator according to the wind speed predicted value of the to-be-measured wind turbine generator and a preset tip speed ratio; and transmitting the reference rotating speed to a rotating speed control system of the wind turbine generator to be tested so as to realize maximum wind energy tracking. According to the invention, efficient operation control under the condition of randomly changing wind speed can be realized.

Description

Technical Field

[0001] This invention relates to the field of wind power control technology, and in particular to a maximum wind energy tracking method and related equipment based on the CAOA-Elman model. Background Technology

[0002] As a clean and renewable energy source, wind energy has the advantage of being unaffected by geopolitics and the price fluctuations of traditional energy sources. It is of great strategic significance for reducing dependence on fossil fuels and enhancing national energy security.

[0003] In wind power systems, maximum power point tracking (MPPT) is one of the core technologies for improving wind energy capture efficiency. The MPPT method, also known as the maximum power point tracking method, works by adjusting the wind turbine's speed, pitch angle, and other operating parameters in real time to ensure the turbine always operates at its optimal power output point under different wind speed conditions, thereby maximizing the utilization of wind energy resources. Currently, the rapid development of the wind power industry has placed higher demands on wind energy utilization, making the research and optimization of MPPT technology a key focus of the industry.

[0004] Despite extensive research in MPPT by scholars both domestically and internationally, existing methods still face a series of challenges and limitations. First, most control strategies are designed for conditions with gradual wind speed changes or below the rated wind speed, lacking sufficient adaptability to the randomness and abrupt changes in wind speed commonly found in nature, making it difficult to maintain high-precision tracking performance under conditions of rapid or large wind speed fluctuations. Second, many advanced MPPT methods rely on real-time accurate measurements from wind speed sensors, which not only increases system cost and complexity, but the measurement delay, errors, and failure risks of sensors can also directly affect the reliability of control. Furthermore, traditional control strategies typically employ segmented logic between different operating ranges—"cut-in wind speed—rated wind speed—cut-out wind speed"—requiring a forced switch in the control algorithm when the wind speed crosses a critical point, which can easily lead to sudden changes in generator torque and output power, exacerbating mechanical component fatigue and affecting the stable operation of the power grid. Overall, existing technologies still have significant room for improvement in terms of adaptive capability under high dynamic wind speeds, response speed, and tracking accuracy under sensorless conditions.

[0005] Therefore, there is an urgent need to study a new intelligent control method that can be independent of wind speed sensors, highly adaptive, fast in response, and achieve smooth and accurate wind energy tracking across the entire wind speed range, so as to fundamentally improve the operating efficiency, reliability, and economy of wind power generation systems. Summary of the Invention

[0006] The purpose of this invention is to provide a maximum wind energy tracking method and related equipment based on the CAOA-Elman model, which can operate and control efficiently under randomly varying wind speed conditions.

[0007] To achieve the above objectives, the present invention employs the following technical solution:

[0008] In a first aspect, the present invention provides a maximum wind energy tracking method based on the CAOA-Elman model, comprising:

[0009] Acquire the operating data of the wind turbine under test; the operating data includes the rotor speed, blade pitch angle, and generator output power.

[0010] The operational data is input into the CAOA-Elman model to predict wind speed, and the predicted wind speed value of the wind turbine under test is obtained.

[0011] Based on the predicted wind speed of the wind turbine under test and the preset tip speed ratio, calculate the reference speed corresponding to the maximum power point of the wind turbine under test.

[0012] The reference speed is transmitted to the speed control system of the wind turbine under test to achieve maximum wind energy tracking.

[0013] Optionally, before inputting the operational data into the optimized wind speed prediction model, preprocessing is further included, the preprocessing including:

[0014] The operating data of the wind turbine under test is cleaned to remove missing and outlier values, resulting in cleaned operating data.

[0015] The cleaned operational data is normalized to eliminate the influence of characteristic dimensions, resulting in preprocessed operational data.

[0016] Optionally, obtaining the CAOA-Elman model includes:

[0017] Obtain the historical operation dataset of the wind turbine under test, and preprocess the historical operation dataset to obtain the preprocessed historical operation dataset;

[0018] The preprocessed historical dataset is divided into training and testing sets according to a preset ratio;

[0019] The structure of the Elman model is determined, including the number of nodes in the input layer, hidden layer, connecting layer, and output layer, as well as the parameters to be optimized. The parameters to be optimized include: the connection weights between the connecting layer and the hidden layer, the connection weights between the input layer and the hidden layer, the connection weights between the output layer and the hidden layer, the hidden layer threshold, and the output layer threshold.

[0020] Initialize a crocodile population, which includes several individuals; each individual represents a set of parameters to be optimized.

[0021] For each individual in the initial crocodile population, its initial fitness value is calculated using the training set, and the initial global optimal individual is calculated based on the initial fitness.

[0022] Based on the training set, the initial crocodile population, and the initial global best individual, the crocodile population is iteratively updated until the termination iteration number is reached, and the last updated global best individual in the crocodile population is obtained.

[0023] And based on the last updated global optimal individual, a preliminary CAOA-Elman model is obtained;

[0024] The preliminary CAOA-Elman model was validated using a test set, resulting in the CAOA-Elman model.

[0025] Optionally, each iteration includes:

[0026] Determine whether the stage is exploratory or development based on the ratio of the current iteration count to the terminated iteration count;

[0027] During the exploration phase, a land patrol mechanism is used to generate new individuals;

[0028] If it is in the development phase, a new individual will be generated using an underwater ambush mechanism;

[0029] The fitness value of the new individual is calculated using the training set, and the fitness values ​​of the new individual and the original individual are compared. If the fitness value of the new individual is greater than that of the original individual, the new individual replaces the original individual; otherwise, the original individual is retained.

[0030] If the fitness value of an individual in the current crocodile population is higher than that of the historical global best individual, then that individual is updated to be the global best individual; otherwise, the global best individual is not updated.

[0031] Optionally, determining whether the stage is the exploration phase or the development phase based on the ratio of the current iteration number to the final iteration number includes:

[0032] If the ratio of the current iteration count to the final iteration count is less than a preset ratio coefficient, then the system is in the exploration phase.

[0033] If the ratio of the current iteration number to the terminated iteration number is not less than the preset ratio coefficient, then it is in the development stage.

[0034] Optionally, the formula for calculating the reference rotational speed is as follows:

[0035] ;

[0036] Where, ω ref For reference rotational speed; λ opt The preset tip speed ratio; v pred R is the predicted wind speed of the wind turbine under test; R is the rotor radius of the wind turbine under test.

[0037] Secondly, the present invention provides a maximum wind energy tracking system based on the CAOA-Elman model, comprising:

[0038] The data acquisition module is used to acquire the operating data of the wind turbine under test; the operating data includes the rotor speed, blade pitch angle and generator output power.

[0039] The wind speed prediction module is used to input the operating data into the CAOA-Elman model to predict the wind speed and obtain the predicted wind speed value of the wind turbine under test.

[0040] The reference speed calculation module is used to calculate the reference speed corresponding to the maximum power point of the wind turbine under test based on the predicted wind speed and the preset tip speed ratio of the wind turbine under test.

[0041] The transmission module is used to transmit the reference rotational speed to the speed control system of the wind turbine under test in order to achieve maximum wind energy tracking.

[0042] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor;

[0043] The memory is used to store programs;

[0044] The processor is used to execute the program to implement the maximum wind energy tracking method based on the CAOA-Elman model as described in the first aspect.

[0045] Fourthly, the present invention provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the maximum wind energy tracking method based on the CAOA-Elman model as described in the first aspect.

[0046] Fifthly, the present invention provides a computer program product, including a computer program that, when executed by a processor, implements the maximum wind energy tracking method based on the CAOA-Elman model as described in the first aspect.

[0047] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0048] This invention provides a maximum wind energy tracking (MAX) method and related equipment based on the CAOA-Elman model. This method uses an Elman neural network globally optimized by the CAOA (Crocodile Ambush Optimization Algorithm), i.e., the CAOA-Elman model, as the core prediction model. By learning from historical operating data, it can accurately capture the complex nonlinear dynamic characteristics of wind turbine systems. This model exhibits excellent adaptability to random fluctuations and rapidly changing wind speeds, achieving stable MAX tracking under complex wind conditions without relying on precise wind speed measurements, thus improving the system's robustness in uncertain environments. Simultaneously, the CAOA algorithm effectively overcomes the problem of traditional gradient-based methods easily getting trapped in local optima during Elman network training, obtaining superior network parameters through global optimization. This enables the constructed CAOA-Elman model to make more accurate real-time predictions, significantly improving the instantaneous accuracy and overall efficiency of wind energy capture.

[0049] This invention provides a maximum wind energy tracking method based on the CAOA-Elman model, which makes predictions entirely based on historical wind turbine operating data, without the need for additional wind speed sensors or reliance on real-time data. This not only reduces system hardware costs and avoids control risks caused by sensor failure, measurement delays, or insufficient accuracy, but also simplifies the system structure and improves reliability.

[0050] This invention provides a maximum wind energy tracking method based on the CAOA-Elman model. The CAOA-Elman model provides a unified and continuous optimal speed reference curve for the entire operating range, from the cut-in wind speed to the cut-out wind speed. This method fundamentally avoids the sudden changes in torque and power that occur when switching near the rated wind speed point in traditional segmented control, achieving a smooth transition in operating states, effectively reducing stress impact and fatigue wear on mechanical transmission components, and contributing to extending the unit's lifespan. Attached Figure Description

[0051] Figure 1 The diagram shown is a flowchart of the maximum wind energy tracking method in one embodiment of the present invention.

[0052] Figure 2 The diagram shown is a schematic representation of the CAOA-Elman model acquisition process in one embodiment of the present invention. Detailed Implementation

[0053] The present invention will be further described below with reference to the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and should not be used to limit the scope of protection of the present invention.

[0054] Example 1

[0055] like Figure 1 As shown in the figure, this invention provides a maximum wind energy tracking method based on the CAOA-Elman model, which includes the following steps:

[0056] Step S1: Obtain the operating data of the wind turbine under test; the operating data includes the rotor speed, blade pitch angle, and generator output power;

[0057] Step S2: Input the operating data into the CAOA-Elman model to predict the wind speed and obtain the predicted wind speed value of the wind turbine to be tested;

[0058] Step S3: Calculate the reference rotational speed corresponding to the maximum power point of the wind turbine under test based on the predicted wind speed and the preset tip speed ratio of the wind turbine under test.

[0059] Step S4: Transmit the reference rotational speed to the wind turbine speed control system under test to achieve maximum wind energy tracking.

[0060] This embodiment introduces a maximum wind energy tracking (MPPT) method based on the CAOA-Elman model. It creatively combines an advanced metaheuristic optimization algorithm (CAOA algorithm) with a recurrent neural network (Elman model) and applies it to the field of wind power MPPT control. This not only improves the tracking performance and system robustness under random wind conditions, but also reduces costs and maintenance complexity through sensorless design. At the same time, it ensures smooth operation under all operating conditions, which has important practical value for improving the operational safety of wind farms.

[0061] In this embodiment, before inputting the running data into the optimized wind speed prediction model in step S2, preprocessing is further included, specifically including:

[0062] The operating data of the wind turbine under test is cleaned to remove missing and outlier values, resulting in cleaned operating data.

[0063] The cleaned operational data is normalized to eliminate the influence of characteristic dimensions, resulting in preprocessed operational data.

[0064] like Figure 2 As shown, in this embodiment, obtaining the CAOA-Elman model in step S2 includes:

[0065] S21: Obtain the historical operation dataset of the wind turbine under test, and preprocess the historical operation dataset to obtain the preprocessed historical operation dataset;

[0066] S22: Divide the preprocessed historical dataset into a training set and a test set according to a preset ratio;

[0067] S23: Determine the structure of the Elman model, including the number of nodes in the input layer, hidden layer, connecting layer, and output layer, as well as the parameters to be optimized; the parameters to be optimized include: the connection weights between the connecting layer and the hidden layer, the connection weights between the input layer and the hidden layer, the connection weights between the output layer and the hidden layer, the hidden layer threshold, and the output layer threshold;

[0068] Specifically, the Elman model comprises an input layer, hidden layers, and an output layer. In addition, there is a new type of hidden layer, the support layer, which receives feedback information from the hidden layers and connects it to the corresponding support layer nodes. The function of the support layer is to combine the previous hidden layer state with the current model input to provide feedback on the hidden layer's state. The signal enters from the input layer neurons, is processed by the hidden layers and support layers, and the processing result is output from the output layer neurons. Hidden layer neurons feed their output signals back to the support layers, which then store the signals and feed them back to the hidden layers.

[0069] In this embodiment, the Elman model is well known to those skilled in the art and will not be described in detail here;

[0070] S24: Initialize the crocodile population, which includes several individuals; each individual represents a set of parameters to be optimized;

[0071] Specifically, during the initialization phase, the algorithm randomly generates a population of N crocodiles within the problem's search space. Each individual represents a potential solution and is assigned an initial value.

[0072] S25: For each individual in the initial crocodile population, calculate its initial fitness value using the training set, and calculate the initial global optimal individual based on the initial fitness.

[0073] Specifically, the initial fitness value is calculated using the training set, including:

[0074] The data in the training set is input into the Elman model decoded by each individual and processed to obtain the output value of the Elman model decoded by each individual.

[0075] The fitness value is calculated based on the output value of the Elman model decoded by each individual and the corresponding real label in the training set data to obtain the initial fitness value. In this embodiment, the fitness value calculation formula is the calculation formula of mean squared error (MSE), mean absolute error (MAE), or correlation coefficient (R²), which will not be described in detail here.

[0076] S26: Based on the training set, the initial crocodile population, and the initial global best individual, iteratively update the crocodile population until the termination iteration number is reached, and obtain the last updated global best individual in the crocodile population.

[0077] Specifically, in the iterative updating of the crocodile population, each iteration process includes:

[0078] Determine whether the stage is exploratory or development based on the ratio of the current iteration count to the terminated iteration count;

[0079] During the exploration phase, a land patrol mechanism is used to generate new individuals;

[0080] If it is in the development phase, a new individual will be generated using an underwater ambush mechanism;

[0081] The fitness value of the new individual is calculated using the training set, and the fitness values ​​of the new individual and the original individual are compared. If the fitness value of the new individual is greater than that of the original individual, the new individual replaces the original individual; otherwise, the original individual is retained.

[0082] If the fitness value of an individual in the current crocodile population is higher than that of the historical global best individual, then that individual is updated to be the global best individual; otherwise, the global best individual is not updated.

[0083] Specifically, determining whether the stage is exploratory or development based on the ratio of the current iteration count to the final iteration count includes:

[0084] If the ratio of the current iteration count to the final iteration count is less than a preset ratio coefficient, then the system is in the exploration phase.

[0085] If the ratio of the current iteration number to the terminated iteration number is not less than the preset ratio coefficient, then it is in the development stage.

[0086] Specifically, new individuals are generated using a land patrol mechanism, including:

[0087] Choose either the first or second strategy to generate a new individual:

[0088] If the first strategy is chosen, a different individual from the current individual is randomly selected from the crocodile population as a random reference, and then the fusion formula is followed: Generate the parameter vector of the new individual; where α and β are step size factors, and xt+1i represents the parameter vector of the i-th individual after the (t+1)-th iteration, that is, the parameter vector of the new individual; Let represent the parameter vector of the i-th individual in the t-th iteration; r is a random number that follows a uniform distribution in [0,1]; besttj is the j-th component of the globally optimal individual in the t-th iteration; Let be the component of the j-th dimension of the i-th individual at the t-th iteration;

[0089] If the second strategy is chosen, a random perturbation vector following a Gaussian distribution is directly superimposed on the parameter vector of the current individual to generate a new individual.

[0090] S27: And based on the last updated global optimal individual, a preliminary CAOA-Elman model is obtained;

[0091] S28: Use the test set to validate the preliminary CAOA-Elman model and obtain the CAOA-Elman model.

[0092] In this embodiment, the formula for calculating the reference rotational speed in step S3 is as follows:

[0093] ;

[0094] Where, ω ref For reference rotational speed; λ opt The preset tip speed ratio; v pred R is the predicted wind speed of the wind turbine under test; R is the rotor radius of the wind turbine under test.

[0095] Example 2

[0096] This embodiment provides a maximum wind energy tracking system based on the CAOA-Elman model, including:

[0097] The data acquisition module is used to acquire the operating data of the wind turbine under test; the operating data includes the rotor speed, blade pitch angle and generator output power.

[0098] The wind speed prediction module is used to input the operating data into the CAOA-Elman model to predict the wind speed and obtain the predicted wind speed value of the wind turbine under test.

[0099] The reference speed calculation module is used to calculate the reference speed corresponding to the maximum power point of the wind turbine under test based on the predicted wind speed and the preset tip speed ratio of the wind turbine under test.

[0100] The transmission module is used to transmit the reference rotational speed to the speed control system of the wind turbine under test in order to achieve maximum wind energy tracking.

[0101] The specific functions of each module described above are explained in the relevant content of the method in Embodiment 1, and will not be repeated here.

[0102] This embodiment provides a maximum wind energy tracking system based on the CAOA-Elman model, which is embedded in the main control system of a wind turbine or the control unit of a converter to achieve real-time online control.

[0103] Example 3

[0104] This embodiment describes an electronic device, including: a memory and a processor;

[0105] The memory is used to store programs;

[0106] The processor is used to execute the program to implement the maximum wind energy tracking method based on the CAOA-Elman model in Embodiment 1.

[0107] This embodiment also introduces a readable storage medium on which a computer program is stored. When the computer program is executed by a processor, it implements the maximum wind energy tracking method based on the CAOA-Elman model in Embodiment 1.

[0108] This embodiment also describes a computer program product, including a computer program that, when executed by a processor, implements the maximum wind energy tracking method based on the CAOA-Elman model in Embodiment 1. Those skilled in the art will understand that the embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0110] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0111] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other forms under the guidance of the present invention without departing from the spirit and scope of the claims. All of these forms are within the protection scope of the present invention.

Claims

1. A maximum wind energy tracking method based on the CAOA-Elman model, characterized in that, include: Acquire the operating data of the wind turbine under test; the operating data includes the rotor speed, blade pitch angle, and generator output power. The operational data is input into the CAOA-Elman model to predict wind speed, and the predicted wind speed value of the wind turbine under test is obtained. Based on the predicted wind speed of the wind turbine under test and the preset tip speed ratio, calculate the reference speed corresponding to the maximum power point of the wind turbine under test. The reference speed is transmitted to the speed control system of the wind turbine under test to achieve maximum wind energy tracking.

2. The maximum wind energy tracking method based on the CAOA-Elman model according to claim 1, characterized in that, Before inputting the operational data into the optimized wind speed prediction model, preprocessing is also included, which includes: The operating data of the wind turbine under test is cleaned to remove missing and outlier values, resulting in cleaned operating data. The cleaned operational data is normalized to eliminate the influence of characteristic dimensions, resulting in preprocessed operational data.

3. The maximum wind energy tracking method based on the CAOA-Elman model according to claim 2, characterized in that, The acquisition of the CAOA-Elman model includes: Obtain the historical operation dataset of the wind turbine under test, and preprocess the historical operation dataset to obtain the preprocessed historical operation dataset; The preprocessed historical dataset is divided into training and testing sets according to a preset ratio; The structure of the Elman model is determined, including the number of nodes in the input layer, hidden layer, connecting layer, and output layer, as well as the parameters to be optimized. The parameters to be optimized include: the connection weights between the connecting layer and the hidden layer, the connection weights between the input layer and the hidden layer, the connection weights between the output layer and the hidden layer, the hidden layer threshold, and the output layer threshold. Initialize a crocodile population, which includes several individuals; each individual represents a set of parameters to be optimized. For each individual in the initial crocodile population, its initial fitness value is calculated using the training set, and the initial global optimal individual is calculated based on the initial fitness. Based on the training set, the initial crocodile population, and the initial global best individual, the crocodile population is iteratively updated until the termination iteration number is reached, and the last updated global best individual in the crocodile population is obtained. And based on the last updated global optimal individual, a preliminary CAOA-Elman model is obtained; The preliminary CAOA-Elman model was validated using a test set, resulting in the CAOA-Elman model.

4. The maximum wind energy tracking method based on the CAOA-Elman model according to claim 3, characterized in that, Each iteration includes: Determine whether the stage is exploratory or development based on the ratio of the current iteration count to the terminated iteration count; During the exploration phase, a land patrol mechanism is used to generate new individuals; If it is in the development phase, a new individual will be generated using an underwater ambush mechanism; The fitness value of the new individual is calculated using the training set, and the fitness values ​​of the new individual and the original individual are compared. If the fitness value of the new individual is greater than that of the original individual, the new individual replaces the original individual; otherwise, the original individual is retained. If the fitness value of an individual in the current crocodile population is higher than that of the historical global best individual, then that individual is updated to be the global best individual; otherwise, the global best individual is not updated.

5. The maximum wind energy tracking method based on the CAOA-Elman model according to claim 4, characterized in that, The determination of whether the stage is exploratory or development based on the ratio of the current iteration count to the final iteration count includes: If the ratio of the current iteration count to the final iteration count is less than a preset ratio coefficient, then the system is in the exploration phase. If the ratio of the current iteration number to the terminated iteration number is not less than the preset ratio coefficient, then it is in the development stage.

6. The maximum wind energy tracking method based on the CAOA-Elman model according to claim 5, characterized in that, The formula for calculating the reference rotational speed is as follows: ； Where, ω ref For reference rotational speed; λ opt The preset tip speed ratio; v pred R is the predicted wind speed of the wind turbine under test; R is the rotor radius of the wind turbine under test.

7. A maximum wind energy tracking system based on the CAOA-Elman model, characterized in that, include: The data acquisition module is used to acquire the operating data of the wind turbine under test; the operating data includes the rotor speed, blade pitch angle and generator output power. The wind speed prediction module is used to input the operating data into the CAOA-Elman model to predict the wind speed and obtain the predicted wind speed value of the wind turbine under test. The reference speed calculation module is used to calculate the reference speed corresponding to the maximum power point of the wind turbine under test based on the predicted wind speed and the preset tip speed ratio of the wind turbine under test. The transmission module is used to transmit the reference rotational speed to the speed control system of the wind turbine under test in order to achieve maximum wind energy tracking.

8. An electronic device, characterized in that, include: Memory and processor; The memory is used to store programs; The processor is used to execute the program to implement the maximum wind energy tracking method based on the CAOA-Elman model as described in any one of claims 1-6.

9. A readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the maximum wind energy tracking method based on the CAOA-Elman model as described in any one of claims 1-6.

10. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program implements the maximum wind energy tracking method based on the CAOA-Elman model as described in any one of claims 1-6.

Images