Wind turbine generator active support control method and system based on frequency adjustment

Abstract

The invention discloses a wind turbine generator active support control method and system based on frequency adjustment, belongs to the technical field of wind power generation, and solves the problems that a fan linearization model is poor in effectiveness, real-time performance and response speed due to the fact that an existing method cannot effectively extract key features related to frequency vacancy. The method comprises the following steps: acquiring day-ahead wind turbine generator output data and power grid power parameters of a power system, identifying and analyzing the day-ahead wind turbine generator output data and the power grid power parameters based on a frequency situation prediction model, and calculating overspeed control-based reserve capacity at a power fluctuation point by taking energy conversion efficiency and primary frequency modulation as constraints; according to the method, the frequency situation prediction in the prediction period is realized by constructing the frequency situation prediction model, the power fluctuation point in the prediction period and the power fluctuation value at the power fluctuation point are determined based on the frequency prediction set, and key features related to frequency vacancy are effectively extracted. And the primary frequency modulation capability and the response speed of active support control of the wind turbine generator are ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of wind power generation, and in particular relates to a method and system for actively supporting and controlling a wind turbine generator set based on frequency regulation. Background Art

[0002] At present, wind energy is generally considered to be the most promising renewable energy source. The penetration rate of renewable energy represented by wind power is constantly increasing. As a renewable energy source, wind farms have certain value in energy conservation, emission reduction and optimization of power supply structure. However, considering the instability, pulsation and uncontrollability of wind farms, they cannot produce inertial response to the frequency change of the power system in a timely manner like traditional synchronous generators.

[0003] Chinese patent CN114899892B discloses a method for active frequency support control of a wind turbine, the method comprising: performing overspeed control on the rotor of the wind turbine to reserve mechanical power reserve; constructing an active frequency support controller for the wind turbine consisting of a short-term frequency support controller and a long-term frequency support controller; establishing a wind turbine linearization model containing the active frequency support controller of the wind turbine, and determining the stable operating range of the parameters of the active frequency support controller through Nyquist diagram and modal analysis; however, the feature extraction capability of the wind turbine linearization model in the existing method is relatively limited, and the key features related to the frequency deficiency cannot be effectively extracted, resulting in poor effectiveness, real-time performance, and response speed of the wind turbine linearization model. In view of the above problems, we propose a method and system for active support control of wind turbines based on frequency regulation. Summary of the invention

[0004] The purpose of the present invention is to address the shortcomings of the prior art and provide a method and system for active support control of wind turbines based on frequency regulation, thereby solving the problem that the linearization model of wind turbines in the existing method has relatively limited feature extraction capability and cannot effectively extract key features related to frequency deficiency, resulting in poor effectiveness, real-time performance and response speed of the linearization model of wind turbines.

[0005] The present invention is implemented in this way: a wind turbine active support control method based on frequency regulation, the wind turbine active support control method based on frequency regulation comprises: Obtain the day-ahead wind turbine output data and grid power parameters of the power system, and standardize the day-ahead wind turbine output data and grid power parameters; Load the wind turbine output data and power grid power parameters of the day before, migrate the wind turbine output data and power grid power parameters of the day before to the modeling sample set, traverse the modeling sample set to generate training set and test set, pre-build a frequency situation prediction model based on multi-layer perceptron, use the training set and test set to iteratively train the frequency situation prediction model, and output a converged frequency situation prediction model; Real-time collection of daily wind turbine output data and grid power parameters. Taking the daily wind turbine output data and grid power parameters as input, the frequency situation prediction model is used to identify and analyze the daily wind turbine output data and grid power parameters, and outputs the frequency prediction set within the prediction period. The frequency prediction set is loaded, and the power fluctuation points and the power fluctuation values ​​at the power fluctuation points within the prediction period are determined based on the frequency prediction set. The power fluctuation points and the power fluctuation values ​​at the power fluctuation points are used as prior information, and the energy conversion efficiency and primary frequency regulation are taken into account as constraints to calculate the spare capacity based on overspeed control at the power fluctuation points.

[0006] Obtain the spare capacity at the power fluctuation point, determine the wind turbine load reduction point based on the cyclic congestion sorting strategy, and generate the active support strategy for the wind turbine set with the steady-state frequency deviation at the wind turbine load reduction point as a constraint; In response to the active support strategy of the wind turbine generator set, the PID speed regulator triggers an active support instruction based on the active support strategy of the wind turbine generator set.

[0007] Preferably, the method of iteratively training the frequency situation prediction model using a training set and a test set comprises: Obtain training sets and test sets, and load the initial model of the frequency situation prediction model; Set the training batch size, training complete times, learning rate, activation function, and loss function for the initial model; Based on the feedforward neural network, the weights and frequency thresholds between the input layer and the hidden layer are generated, the training set is loaded, and the training set is normalized by dimensionality reduction. The normalized training sample sequence is used as the column of the training matrix, and the sample features are used as the row of the training matrix to complete the construction of the training matrix, and the weights are added to the training matrix. Get the training matrix after adding the weight matrix, input the training matrix into the variable convolution attention module, get the feature convolution result, perform Fourier frequency analysis on the feature convolution result, and output the frequency value of the feature; Determine whether the frequency value of the feature exceeds the preset frequency threshold. If it exceeds the preset frequency threshold, retain the current feature. If it does not exceed the preset frequency threshold, prune and compress the current feature weight. Load the initial model after feature weight pruning and compression, use the training set to retrain the initial model until convergence, and output the converged initial model; Load the test set, use the test set as input, execute the initial model, and the initial model outputs the test results to determine whether the test results meet the preset accuracy threshold. If they meet the accuracy threshold, output the converged frequency situation prediction model.

[0008] Preferably, the frequency situation prediction model uses a multi-layer perceptron model as an initial model, the initial model consists of an input layer, a hidden layer, and an output layer, the hidden layer is located between the input layer and the output layer, and when pre-constructing a frequency situation prediction model based on a multi-layer perceptron, a sparse autoencoder is introduced between the output layer and the hidden layer, the sparse autoencoder is used to ensure the sparsity of the hidden layer, and the sparse autoencoder activation function is a sigmiod activation function; The hidden layers of the initial model include the first hidden layer and the second hidden layer. The number of neurons in the first hidden layer is 40. The hidden layers of the initial model are improved by freezing the second hidden layer and replacing it with a variable convolutional attention module. The variable convolutional attention module includes a multi-head attention mechanism, three-layer convolution and a global average pooling layer. The three-layer convolution includes the first convolution layer, the second convolution layer and the third convolution layer. The convolution kernel size of the first and second convolution layers is 3×3, and the convolution kernel size of the third convolution layer is 5×5. A flexible trigger mechanism is introduced into the input layer of the initial model, and the input layer extracts the frequency deficiency features based on the flexible trigger mechanism.

[0009] Preferably, the method for extracting frequency deficiency features at the input layer based on a flexible trigger mechanism comprises: Load the daily wind turbine output data and grid power parameters, and define the shortage fusion threshold of the frequency shortage feature based on the daily wind turbine output data, the maximum frequency change rate of the grid in the grid power parameters, the active shortage, and the wind turbine inertia time constant. and mechanism trigger threshold ; Construct the square wave function of the maximum frequency change rate of the power grid, the active power shortage, and the inertia time constant of the wind turbine within the daily sampling interval, and construct the Hessia matrix of the sampling interval based on the square wave function within the sampling interval; The square wave function within the sampling interval is expressed as: (1) The Hessia matrix of the sampling interval is expressed as: (2) in, represents the square wave function within the sampling interval, represents the sampling interval, is the active power shortage within the sampling interval, represents the fan inertia time constant, is the maximum frequency change rate of the power grid, is the Hessia matrix output representation of the sampling interval, The square wave function element and variables, Represents the square wave function and The second-order partial derivatives of variables; Get the Hessia matrix of the sampling interval, use the quasi-Newton method to calculate the Hessia matrix result, and determine whether the Hessia matrix result exceeds the missing fusion threshold ; If the deficit fusion threshold is exceeded , integrate the Hessia matrix results into an integral space set, perform integral calculation on the integral space set, and output the integral calculation results. When the integral calculation results accumulate to the mechanism trigger threshold When , the flexible trigger mechanism is triggered to extract the characteristics of the maximum frequency change rate, active power shortage and wind turbine inertia time constant of the power grid within the daily sampling interval, and output the Hessia matrix result; The integral calculation of the integral space set is expressed as: (3) in, represents the result of the integral space set integral calculation, are the start and end time of the sampling interval respectively.

[0010] Preferably, the method for identifying and analyzing daily wind turbine output data and power grid power parameters based on the frequency situation prediction model includes: Obtain daily wind turbine output data and grid power parameters. The input layer extracts frequency shortage features based on a flexible trigger mechanism and outputs the Hessia matrix results. Normalize the daily wind turbine output data and grid power parameters after removing the frequency deficiency characteristics, filter the normalized results, and output the filtered normalized characteristics; The sparse autoencoder performs sparse encoding and sparse decoding on the normalized features to obtain the normalized features after adding the gain matrix. Based on the relative entropy, a sparse penalty term is introduced to the normalized features after adding the gain matrix, and the autoencoding result is output; Obtain the autoencoding result, perform weighted summation on the autoencoding result in the first hidden layer, and then normalize the weighted summation result using the sigmiod activation function to obtain a weighted autoencoding set; The variable convolutional attention module obtains the weighted autoencoder set and Hessia matrix results. The variable convolutional attention module couples the weighted autoencoder set and Hessia matrix results to the objective function, calculates the frequency prediction results within the prediction period based on the objective function, and outputs the frequency prediction set within the prediction period.

[0011] Preferably, when normalizing the daily wind turbine output data and grid power parameters after removing the frequency shortage feature, the normalization result is expressed as: (4) in, To normalize the results, Represents the data matrix composed of wind turbine output data and grid power parameters within a day. is the data mean, represents the data variance; The autoencoding result is expressed as: (5) (6) (7) in, represents the autoencoding result, Relative entropy of normalized features, used to represent the relative entropy value of two groups of random variables. represents the sparse penalty term, Normalized features The gain matrix, is the number of data, is the characteristic number, represents the sparse ratio, is the activation value of the normalized feature, Represents the maximum value of normalized features; When calculating the frequency prediction results within the prediction period based on the objective function, the objective function is defined as: (8) in, represents the frequency prediction result, They are the grid frequency of the previous sampling interval and the intraday frequency average.

[0012] Preferably, the calculation of the spare capacity based on overspeed control at the power fluctuation point taking into account the energy conversion efficiency and the primary frequency regulation as constraints includes: Loading power fluctuation points and power fluctuation values ​​at the power fluctuation points, and determining the steady-state deviation of the fan frequency based on the power fluctuation values ​​at the power fluctuation points; The steady-state deviation of fan frequency is expressed as: (9) in, is the steady-state deviation of the fan frequency, is the air density, is the wind speed, represents the leaf coverage area, is the power fluctuation value at the fluctuation point, represents the wind energy utilization coefficient, is the unit adjustment coefficient; (10) in, is the fan tip speed ratio, Represent the fan speed and blade radius respectively; Obtain the steady-state deviation of the fan frequency, and calculate the primary frequency regulation capability of the fan by combining the wind energy utilization coefficient and the steady-state deviation of the fan frequency; The calculation expression of the fan primary frequency regulation capacity is as follows: (11) Calculate the spare capacity based on overspeed control at the power fluctuation point based on the primary frequency regulation capability and energy conversion efficiency of the wind turbine; (12) in, Indicates the primary frequency regulation capability of the fan. are the mechanical torque and electromagnetic torque of the fan respectively, represents the rotor damping coefficient, is the energy conversion efficiency.

[0013] On the other hand, the present invention further provides a wind turbine active support control system based on frequency regulation, the wind turbine active support control system based on frequency regulation comprises: The data acquisition module is used to obtain the wind turbine output data and grid power parameters of the power system on the previous day, and to standardize the wind turbine output data and grid power parameters on the previous day; The prediction model building module is used to load the wind turbine output data and power grid power parameters of the day before, migrate the wind turbine output data and power grid power parameters of the day before to the modeling sample set, traverse the modeling sample set to generate a training set and a test set, pre-build a frequency situation prediction model based on a multi-layer perceptron, use the training set and the test set to iteratively train the frequency situation prediction model, and output a converged frequency situation prediction model; The frequency prediction module is used to collect the daily wind turbine output data and grid power parameters in real time. It takes the daily wind turbine output data and grid power parameters as input, identifies and analyzes the daily wind turbine output data and grid power parameters based on the frequency situation prediction model, and outputs the frequency prediction set within the prediction period; A capacity calculation module is used to load a frequency prediction set, determine the power fluctuation point and the power fluctuation value at the power fluctuation point within the prediction period based on the frequency prediction set, use the power fluctuation point and the power fluctuation value at the power fluctuation point as prior information, and calculate the spare capacity based on overspeed control at the power fluctuation point taking into account energy conversion efficiency and primary frequency modulation as constraints; The active support module is used to obtain the spare capacity at the power fluctuation point, determine the wind turbine load reduction operation point based on the cyclic congestion sorting strategy, and generate the wind turbine active support strategy based on the steady-state frequency deviation at the wind turbine load reduction operation point as a constraint. In response to the active support strategy of the wind turbine, the PID speed regulator triggers the active support instruction based on the active support strategy of the wind turbine.

[0014] Preferably, the active support module comprises: An operating point determination unit, used to obtain the spare capacity at the power fluctuation point and determine the wind turbine load reduction operating point based on a cyclic congestion sorting strategy; A strategy generation unit generates an active support strategy for the wind turbine using the steady-state frequency deviation at the wind turbine load reduction operation point as a constraint; The strategy response unit responds to the active support strategy of the wind turbine generator set, and the PID speed regulator triggers the active support instruction based on the active support strategy of the wind turbine generator set.

[0015] Compared with the prior art, the embodiments of the present application have the following beneficial effects: In an embodiment of the present invention, a frequency situation prediction model is constructed to realize frequency situation prediction within a prediction period, and power fluctuation points within the prediction period and power fluctuation values ​​at the power fluctuation points are determined based on the frequency prediction set, thereby providing prior information for the spare capacity based on overspeed control, effectively extracting key features related to frequency shortage, and ensuring the primary frequency regulation capability and response speed of the active support control of the wind turbine set, thereby overcoming the problem that the wind turbine linearization model of the existing method has relatively limited feature extraction capability and cannot effectively extract key features related to frequency shortage, resulting in poor effectiveness, real-time performance and response speed of the wind turbine linearization model.

[0016] In the embodiment of the present invention, the frequency situation prediction model uses a multi-layer perceptron model as the initial model, and introduces a sparse autoencoder, a variable convolutional attention module, and a flexible trigger mechanism, which helps the model capture more representative features and improve generalization capabilities. The flexible trigger mechanism can respond quickly and trigger active support instructions in time to help wind turbines quickly adjust output power and maintain the stability of the grid frequency. At the same time, when the frequency situation prediction model is trained, the feature weights are pruned and compressed by judging whether the frequency value of the feature exceeds a preset frequency threshold, thereby reducing the storage space and transmission bandwidth of the model and improving the processing efficiency and speed of the model.

[0017] In an embodiment of the present invention, frequency deficiency characteristics are extracted based on a flexible trigger mechanism, and frequency deficiency characteristics are defined based on the maximum frequency change rate of the power grid, active power deficiency, and wind turbine inertia time constant, which helps to more accurately identify and extract key features related to frequency deficiency, thereby improving the accuracy and efficiency of frequency situation prediction.

[0018] In the embodiment of the present invention, the frequency situation prediction model is used to identify and analyze the daily wind turbine output data and power grid power parameters, so as to accurately output the frequency prediction set within the prediction period, so as to more accurately determine the required backup capacity size, avoid resource waste caused by excessive backup capacity or the risk of insufficient power supply caused by too small backup capacity, and also help to smooth wind power fluctuations, improve the dispatchability of wind power, and thus increase the penetration rate of wind power in the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 It is a schematic diagram of the implementation flow of the active support control method for wind turbines based on frequency regulation provided by the present invention.

[0020] Figure 2 The figure shows a schematic diagram of the implementation process of the iterative training method of the frequency situation prediction model using a training set and a test set.

[0021] Figure 3 The figure shows a schematic diagram of the implementation process of the method for extracting frequency deficiency features based on a flexible trigger mechanism at the input layer.

[0022] Figure 4 The figure shows a schematic diagram of the implementation process of the method for identifying and analyzing the daily wind turbine output data and power grid power parameters based on the frequency situation prediction model.

[0023] Figure 5 The present invention shows a schematic diagram of the implementation process of a method for calculating the reserve capacity based on overspeed control at power fluctuation points taking energy conversion efficiency and primary frequency modulation as constraints.

[0024] Figure 6 It is a structural schematic diagram of a wind turbine active support control system based on frequency regulation provided by the present invention. DETAILED DESCRIPTION

[0025] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0026] The feature extraction capability of the wind turbine linearization model in the existing method is relatively limited, and it is unable to effectively extract the key features related to the frequency shortage, resulting in poor effectiveness, real-time performance, and response speed of the wind turbine linearization model. To address the above problems, we propose a wind turbine active support control method and system based on frequency regulation. In short, when the method is implemented, the output data of the wind turbines and the power parameters of the power grid in the power system are first obtained, and then a frequency situation prediction model based on a multi-layer perceptron is pre-constructed. The output data of the wind turbines and the power parameters of the power grid are identified and analyzed based on the frequency situation prediction model, and the frequency prediction set within the prediction period is output. The power fluctuation points and the power fluctuation values ​​at the power fluctuation points within the prediction period are determined based on the frequency prediction set. The power fluctuation points and the power fluctuation values ​​at the power fluctuation points are used as prior information, and the energy conversion efficiency and primary frequency regulation are taken as constraints to calculate the spare capacity based on overspeed control at the power fluctuation points. The wind turbine load reduction operation point is determined based on the cyclic congestion sorting strategy, and the steady-state frequency deviation at the wind turbine load reduction operation point is used as a constraint to generate the wind turbine active support strategy. In an embodiment of the present invention, a frequency situation prediction model is constructed to realize frequency situation prediction within a prediction period, and power fluctuation points within the prediction period and power fluctuation values ​​at the power fluctuation points are determined based on the frequency prediction set, thereby providing prior information for the spare capacity based on overspeed control, effectively extracting key features related to frequency shortage, and ensuring the primary frequency regulation capability and response speed of the active support control of the wind turbine set, thereby overcoming the problem that the wind turbine linearization model of the existing method has relatively limited feature extraction capability and cannot effectively extract key features related to frequency shortage, resulting in poor effectiveness, real-time performance and response speed of the wind turbine linearization model.

[0027] The embodiment of the present invention provides a method for actively supporting and controlling a wind turbine generator system based on frequency regulation. Figure 1 The following is a schematic diagram of the implementation process of the active support control method for wind turbines based on frequency regulation. The active support control method for wind turbines based on frequency regulation specifically includes: S10, obtaining the wind turbine output data and power grid power parameters of the power system a day ago, and standardizing the wind turbine output data and power grid power parameters a day ago; It should be noted that the wind turbine output data on the day before includes but is not limited to the day before wind speed data, wind direction data, temperature data, humidity data, power data, wind rotor diameter, rated power, output voltage, wind turbine speed, and rotor parameters; the grid power parameters include but are not limited to the minimum grid frequency, the time of the minimum value, the steady-state frequency of the grid, the maximum frequency change rate, the active power shortage, the inertia time constant, the speed regulator dead zone range, the initial response time, and the average frequency change rate.

[0028] In this embodiment, the methods for standardizing the wind turbine output data and power grid power parameters of the day before include but are not limited to logarithmic function normalization, centering, quartile method and grey wolf optimized box plot algorithm.

[0029] S20, loading the output data of the wind turbines and the power parameters of the power grid on the previous day, migrating the output data of the wind turbines and the power parameters of the power grid on the previous day to the modeling sample set, traversing the modeling sample set to generate a training set and a test set, pre-building a frequency situation prediction model based on a multi-layer perceptron, using the training set and the test set to iteratively train the frequency situation prediction model, and outputting a converged frequency situation prediction model; In this embodiment, the allocation ratio of the training set to the test set may be 3:1 or 4:1.

[0030] S30, collecting daily wind turbine output data and grid power parameters in real time, taking the daily wind turbine output data and grid power parameters as input, identifying and analyzing the daily wind turbine output data and grid power parameters based on a frequency situation prediction model, and outputting a frequency prediction set within a prediction period; S40, loading the frequency prediction set, determining the power fluctuation points and the power fluctuation values ​​at the power fluctuation points within the prediction period based on the frequency prediction set, taking the power fluctuation points and the power fluctuation values ​​at the power fluctuation points as prior information, taking into account the energy conversion efficiency and the primary frequency modulation as constraints, and calculating the spare capacity based on overspeed control at the power fluctuation points.

[0031] S50, obtaining the spare capacity at the power fluctuation point, determining the wind turbine load reduction operation point based on the cyclic congestion sorting strategy, and generating the wind turbine active support strategy with the steady-state frequency deviation at the wind turbine load reduction operation point as a constraint; S60, in response to the active support strategy of the wind turbine generator set, the PID speed regulator triggers an active support instruction based on the active support strategy of the wind turbine generator set.

[0032] It should be noted that the PID (proportional-integral-differential) speed regulator is a classic control algorithm, which is widely used in various industrial control systems, including the control systems of wind turbines. When the grid frequency deviates, the PID speed regulator calculates the amount of power that needs to be adjusted according to the preset control logic and algorithm, and generates corresponding active support instructions. These instructions are used to guide wind turbines to adjust their output power to participate in the frequency regulation of the grid.

[0033] In an embodiment of the present invention, a frequency situation prediction model is constructed to realize frequency situation prediction within a prediction period, and power fluctuation points within the prediction period and power fluctuation values ​​at the power fluctuation points are determined based on the frequency prediction set, thereby providing prior information for the spare capacity based on overspeed control, effectively extracting key features related to frequency shortage, and ensuring the primary frequency regulation capability and response speed of the active support control of the wind turbine set, thereby overcoming the problem that the wind turbine linearization model of the existing method has relatively limited feature extraction capability and cannot effectively extract key features related to frequency shortage, resulting in poor effectiveness, real-time performance and response speed of the wind turbine linearization model.

[0034] The embodiment of the present invention provides a method for iteratively training a frequency situation prediction model using a training set and a test set. Figure 2 The following is a schematic diagram of the implementation process of the iterative training method for the frequency situation prediction model using the training set and the test set. The method of iterative training the frequency situation prediction model using the training set and the test set specifically includes: Step S101, obtaining a training set and a test set, and loading an initial model of a frequency situation prediction model; Step S102, setting the training batch size, number of complete training times, learning rate, activation function and loss function of the initial model; In this embodiment, the training batch size of the initial model can be 15-20, the number of complete training times can be 150-200 times, the learning rate is set to 0.002, the activation function of the initial model is the softmax function, and the loss function can be the hinge-loss loss function.

[0035] Step S103, generating weights and frequency thresholds between the input layer and the hidden layer based on the feedforward neural network, loading the training set, performing dimensionality reduction and normalization processing on the training set, using the normalized training sample sequence as the column of the training matrix, and the sample features as the row of the training matrix, completing the construction of the training matrix, and adding the weights to the training matrix; In this embodiment, the weight represents the relative importance of the input feature to the prediction result. In the frequency situation prediction, different input features (such as historical frequency data, weather conditions, wind turbine status, etc.) have different degrees of influence on the grid frequency. Through the training process, the feedforward neural network will automatically learn and adjust these weights so that the features that are more important to the prediction result have greater weights. During the training process, the frequency threshold can be adjusted as a hyperparameter. Through methods such as cross-validation, the optimal frequency threshold can be found, so that the model can reasonably control the frequency and amplitude of active support actions while maintaining a high prediction accuracy.

[0036] Step S104, obtaining the training matrix after adding the weight matrix, inputting the training matrix into the variable convolution attention module, obtaining the feature convolution result, performing Fourier frequency analysis on the feature convolution result, and outputting the frequency value of the feature; Step S105, determining whether the frequency value of the feature exceeds a preset frequency threshold; In this embodiment, the preset frequency threshold may be 0.3-0.55.

[0037] Step S106, if the frequency exceeds the preset threshold, retain the current feature; Step S107, if the frequency does not exceed the preset threshold, prune and compress the current feature weight; Step S108, loading the initial model after feature weight pruning and compression processing, retraining the initial model with the training set until convergence, and outputting the converged initial model; Step S109, loading the test set, taking the test set as input, executing the initial model, and the initial model outputs the test result; Step S1010, determining whether the test result meets a preset accuracy threshold. In this embodiment, the preset accuracy threshold may be 0.89-0.91; Step S1011: if the accuracy threshold is met, output a converged frequency situation prediction model.

[0038] In the embodiment of the present invention, the frequency situation prediction model uses a multi-layer perceptron model as the initial model, and introduces a sparse autoencoder, a variable convolutional attention module, and a flexible trigger mechanism, which helps the model capture more representative features and improve generalization capabilities. The flexible trigger mechanism can respond quickly and trigger active support instructions in time to help wind turbines quickly adjust output power and maintain the stability of the grid frequency. At the same time, when the frequency situation prediction model is trained, the feature weights are pruned and compressed by judging whether the frequency value of the feature exceeds a preset frequency threshold, thereby reducing the storage space and transmission bandwidth of the model and improving the processing efficiency and speed of the model.

[0039] In this embodiment, the frequency situation prediction model uses a multi-layer perceptron model as an initial model. The initial model consists of an input layer, a hidden layer, and an output layer. The hidden layer is located between the input layer and the output layer. When pre-constructing a frequency situation prediction model based on a multi-layer perceptron, a sparse autoencoder is introduced between the output layer and the hidden layer. The sparse autoencoder is used to ensure the sparsity of the hidden layer, and the sparse autoencoder activation function is a sigmiod activation function. It should be noted that the input layer is connected to the hidden layer, and the hidden layer is connected to the output layer.

[0040] The hidden layers of the initial model include the first hidden layer and the second hidden layer. The number of neurons in the first hidden layer is 40. The hidden layers of the initial model are improved by freezing the second hidden layer and replacing it with a variable convolutional attention module. The variable convolutional attention module includes a multi-head attention mechanism, three-layer convolution and a global average pooling layer. The three-layer convolution includes the first convolution layer, the second convolution layer and the third convolution layer. The convolution kernel size of the first and second convolution layers is 3×3, and the convolution kernel size of the third convolution layer is 5×5. A flexible trigger mechanism is introduced into the input layer of the initial model, and the input layer extracts the frequency deficiency features based on the flexible trigger mechanism.

[0041] The embodiment of the present invention provides a method for extracting frequency deficiency features at an input layer based on a flexible trigger mechanism. Figure 3 The schematic diagram of the implementation flow of the method for extracting frequency deficiency features based on the flexible trigger mechanism of the input layer is shown. The method for extracting frequency deficiency features based on the flexible trigger mechanism of the input layer specifically includes: S201, loading the daily wind turbine output data and power grid power parameters, and defining the shortage fusion threshold of the frequency shortage feature based on the daily wind turbine output data, the maximum frequency change rate of the power grid in the power grid power parameters, the active shortage, and the wind turbine inertia time constant. and mechanism trigger threshold ; In the embodiment of the present invention, the frequency shortage feature is defined based on the maximum frequency change rate of the power grid, the active power shortage, and the inertia time constant of the fan, wherein the maximum frequency change rate of the power grid refers to the maximum rate of change of the power grid frequency in a unit time, which is one of the important indicators for measuring the stability of the power grid. When the power grid has an active power shortage or surplus, the frequency will change, and the speed of change reflects the response ability of the power grid to this unbalanced state, and the active power shortage is the main reason for the decrease in the power grid frequency. When the active power shortage is large, the power grid frequency will drop significantly, and may even cause serious accidents such as frequency collapse. The inertia time constant of the fan refers to the time constant of the fan rotor continuing to rotate due to mechanical inertia after losing electrical input. It reflects the response speed and regulation ability of the fan to the change of the power grid frequency. Taking the above three factors into consideration, a comprehensive frequency shortage feature index is defined. The larger the frequency shortage feature value, the more serious the frequency shortage of the power grid is, and more active measures need to be taken for frequency support and recovery.

[0042] S202, constructing a square wave function of the maximum frequency change rate of the power grid, the active power shortage, and the inertia time constant of the wind turbine within the daily sampling interval, and constructing a Hessia matrix of the sampling interval based on the square wave function within the sampling interval; The square wave function within the sampling interval is expressed as: (1) The Hessia matrix of the sampling interval is expressed as: (2) in, represents the square wave function within the sampling interval, represents the sampling interval, is the active power shortage within the sampling interval, represents the fan inertia time constant, is the maximum frequency change rate of the power grid, is the Hessia matrix output representation of the sampling interval, The square wave function element and variables, Represents the square wave function and The second-order partial derivatives of variables; S203, obtaining the Hessia matrix of the sampling interval, and calculating the Hessia matrix result using the quasi-Newton method; It should be noted that Quasi-Newton Methods are a class of iterative algorithms used to solve unconstrained optimization problems. They avoid directly calculating the second-order derivatives by constructing an approximation of the Hessian matrix, thereby improving computational efficiency.

[0043] S204, judging whether the Hessia matrix result exceeds the missing fusion threshold ; S205: If the threshold of the missing fusion is exceeded , integrate the Hessia matrix results into an integral space set, perform integral calculation on the integral space set, and output the integral calculation results. When the integral calculation results accumulate to the mechanism trigger threshold When , the flexible trigger mechanism is triggered to extract the characteristics of the maximum frequency change rate, active power shortage and wind turbine inertia time constant of the power grid within the daily sampling interval, and output the Hessia matrix result; The integral calculation of the integral space set is expressed as: (3) in, represents the result of the integral space set integral calculation, are the start and end time of the sampling interval respectively.

[0044] In an embodiment of the present invention, frequency deficiency characteristics are extracted based on a flexible trigger mechanism, and frequency deficiency characteristics are defined based on the maximum frequency change rate of the power grid, active power deficiency, and wind turbine inertia time constant, which helps to more accurately identify and extract key features related to frequency deficiency, thereby improving the accuracy and efficiency of frequency situation prediction.

[0045] The embodiment of the present invention provides a method for identifying and analyzing the output data of wind turbines and power parameters of power grids within a day based on a frequency situation prediction model. Figure 4 The schematic diagram of the implementation process of the method for identifying and analyzing the output data of wind turbines and power parameters of power grids within a day based on the frequency situation prediction model is shown. The method for identifying and analyzing the output data of wind turbines and power parameters of power grids within a day based on the frequency situation prediction model specifically includes: S301, obtain the daily wind turbine output data and grid power parameters, extract the frequency shortage characteristics based on the flexible trigger mechanism at the input layer, and output the Hessia matrix result; S302, normalizing the daily wind turbine output data and power grid power parameters after removing the frequency shortage feature, filtering the normalized result, and outputting the filtered normalized feature; In this embodiment, when the daily wind turbine output data and grid power parameters are normalized after the frequency shortage feature is removed, the normalization result is expressed as: (4) in, To normalize the results, Represents the data matrix composed of wind turbine output data and grid power parameters within a day. is the data mean, Represents the data variance.

[0046] S303, the sparse autoencoder performs sparse encoding and sparse decoding on the normalized features to obtain the normalized features after adding the gain matrix, introduces a sparse penalty term to the normalized features after adding the gain matrix based on relative entropy, and outputs the autoencoding result; Among them, the self-encoding result is expressed as: (5) (6) (7) in, represents the autoencoding result, Relative entropy of normalized features, used to represent the relative entropy value of two groups of random variables. represents the sparse penalty term, Normalized features The gain matrix, is the number of data, is the characteristic number. In this embodiment, the characteristic number is 3-15. represents the sparse ratio, is the activation value of the normalized feature, which can be 0.35-0.68, Represents the normalized feature maximum value.

[0047] S304, obtaining the autoencoding result, performing weighted summation processing on the autoencoding result in the first hidden layer, and then normalizing the weighted summation result using a sigmiod activation function to obtain a weighted autoencoding set; In this embodiment, when the first hidden layer performs weighted summation on the autoencoding results, each neuron in the first hidden layer performs weighted summation on the received input. This means that each input feature is multiplied by the corresponding weight, and then all the products are added to obtain the total input of the neuron, and the result of the weighted summation is the total input of the neuron. The input value is compressed between 0 and 1 through the sigmiod activation function, which makes the output more stable and helps with probability interpretation or binary classification tasks.

[0048] S305, the variable convolution attention module obtains the weighted autoencoder set and the Hessia matrix result, and the variable convolution attention module unifies the coupling constraints of the weighted autoencoder set and the Hessia matrix result into the objective function, calculates the frequency prediction result within the prediction period based on the objective function, and outputs the frequency prediction set within the prediction period.

[0049] When calculating the frequency prediction results within the prediction period based on the objective function, the objective function is defined as: (8) in, represents the frequency prediction result, They are the grid frequency of the previous sampling interval and the intraday frequency average.

[0050] In the embodiment of the present invention, the frequency situation prediction model is used to identify and analyze the daily wind turbine output data and power grid power parameters, so as to accurately output the frequency prediction set within the prediction period, so as to more accurately determine the required backup capacity size, avoid resource waste caused by excessive backup capacity or the risk of insufficient power supply caused by too small backup capacity, and also help to smooth wind power fluctuations, improve the dispatchability of wind power, and thus increase the penetration rate of wind power in the power grid.

[0051] The embodiment of the present invention provides a method for calculating the spare capacity based on overspeed control at the power fluctuation point by taking energy conversion efficiency and primary frequency modulation as constraints. Figure 5 The schematic diagram of the implementation flow of the method for calculating the spare capacity based on overspeed control at the power fluctuation point taking into account the energy conversion efficiency and the primary frequency modulation as constraints is shown. The method for calculating the spare capacity based on overspeed control at the power fluctuation point taking into account the energy conversion efficiency and the primary frequency modulation as constraints specifically includes: S401, loading a power fluctuation point and a power fluctuation value at the power fluctuation point, and determining a steady-state deviation of a wind turbine frequency based on the power fluctuation value at the power fluctuation point; The steady-state deviation of fan frequency is expressed as: (9) in, is the steady-state deviation of the fan frequency, is the air density, is the wind speed, represents the leaf coverage area, is the power fluctuation value at the fluctuation point, represents the wind energy utilization coefficient, is the unit adjustment coefficient; (10) in, is the fan tip speed ratio, Represent the fan speed and blade radius respectively; It should be noted that the steady-state frequency deviation of a wind turbine refers to the difference between the output frequency of a wind turbine and the rated frequency of the power grid when the wind turbine is operating in a steady state. The steady-state frequency deviation of a wind turbine can reflect the system's ability to resist active disturbances through primary frequency modulation.

[0052] S402, obtaining a steady-state deviation of the wind turbine frequency, and calculating the primary frequency regulation capability of the wind turbine by combining the wind energy utilization coefficient and the steady-state deviation of the wind turbine frequency; The calculation expression of the fan primary frequency regulation capacity is as follows: (11) S403, calculating the spare capacity based on overspeed control at the power fluctuation point based on the primary frequency regulation capability and energy conversion efficiency of the wind turbine; (12) in, Indicates the primary frequency regulation capability of the fan. are the mechanical torque and electromagnetic torque of the fan respectively, Represents the rotor damping coefficient. The rotor damping coefficient is an important parameter to describe the vibration stability of the generator rotor. It refers to the ratio of the rotor vibration attenuation rate to the vibration frequency. The larger this coefficient is, the faster the rotor vibration attenuation rate is, the smaller the speed fluctuation range is, and the more stable the rotor is. Conversely, the smaller the damping coefficient is, the larger the speed fluctuation range is, and the more unstable the rotor is. The energy conversion efficiency can be 35-45%.

[0053] The embodiment of the present invention provides a wind turbine active support control system based on frequency regulation. Figure 6 The structure diagram of the wind turbine active support control system based on frequency regulation is shown. The wind turbine active support control system based on frequency regulation specifically includes: The data acquisition module 100 is used to acquire the wind turbine output data and grid power parameters of the power system on the previous day, and to standardize the wind turbine output data and grid power parameters on the previous day; The prediction model building module 200 is used to load the wind turbine output data and power grid power parameters of the day before, migrate the wind turbine output data and power grid power parameters of the day before to the modeling sample set, traverse the modeling sample set to generate a training set and a test set, pre-build a frequency situation prediction model based on a multi-layer perceptron, use the training set and the test set to iteratively train the frequency situation prediction model, and output a converged frequency situation prediction model; The frequency prediction module 300 is used to collect the daily wind turbine output data and grid power parameters in real time, take the daily wind turbine output data and grid power parameters as input, identify and analyze the daily wind turbine output data and grid power parameters based on the frequency situation prediction model, and output the frequency prediction set within the prediction period; The capacity calculation module 400 is used to load the frequency prediction set, determine the power fluctuation point and the power fluctuation value at the power fluctuation point within the prediction period based on the frequency prediction set, use the power fluctuation point and the power fluctuation value at the power fluctuation point as prior information, and calculate the spare capacity based on overspeed control at the power fluctuation point taking into account the energy conversion efficiency and the primary frequency modulation as constraints; The active support module 500 is used to obtain the spare capacity at the power fluctuation point, determine the wind turbine load reduction operation point based on the cyclic congestion sorting strategy, and generate the wind turbine active support strategy based on the steady-state frequency deviation at the wind turbine load reduction operation point as a constraint. In response to the active support strategy of the wind turbine, the PID speed regulator triggers the active support instruction based on the active support strategy of the wind turbine.

[0054] It should be noted that the data acquisition module 100, the prediction model construction module 200, the frequency prediction module 300, the capacity calculation module 400, and the active support module 500 are connected by a local area network or a DTU communication, and the wind turbine active support control system based on frequency regulation provided in the embodiment of the present invention corresponds to the above-mentioned wind turbine active support control method based on frequency regulation. The explanations, examples, beneficial effects and other parts of the relevant contents can refer to the corresponding contents in the wind turbine active support control method based on frequency regulation, and will not be repeated here.

[0055] In this embodiment, the active support module 500 includes: An operating point determination unit 510 is used to obtain the spare capacity at the power fluctuation point and determine the wind turbine load reduction operating point based on the cyclic congestion sorting strategy; A strategy generating unit 520 generates an active support strategy for the wind turbine generator set based on the steady-state frequency deviation at the wind turbine load reduction operation point as a constraint; The strategy response unit 530 responds to the active support strategy of the wind turbine generator set, and the PID speed regulator triggers the active support instruction based on the active support strategy of the wind turbine generator set.

[0056] On the other hand, an embodiment of the present invention further provides a computer device, the computer device comprising a memory and a processor, the memory storing a computer program, and the computer program implementing any one of the above-mentioned methods when executed by the processor.

[0057] As a non-volatile computer-readable storage medium, the memory can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as the program instructions / modules corresponding to the wind turbine active support control method based on frequency regulation in the embodiment of the present application. The memory may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created by the use of the wind turbine active support control method based on frequency regulation, etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the local module via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0058] In summary, the present invention provides a method and system for active support control of wind turbines based on frequency regulation. In an embodiment of the present invention, a frequency situation prediction model is constructed to realize frequency situation prediction within a prediction period, and the power fluctuation point within the prediction period and the power fluctuation value at the power fluctuation point are determined based on the frequency prediction set, thereby providing prior information for the spare capacity based on overspeed control, effectively extracting key features related to frequency shortage, ensuring the primary frequency regulation capability and response speed of active support control of wind turbines, and overcoming the problem that the linearization model of wind turbines in existing methods has relatively limited feature extraction capability and cannot effectively extract key features related to frequency shortage, resulting in poor effectiveness, real-time performance and response speed of the linearization model of wind turbines.

[0059] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on these embodiments, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field can still combine, add, delete or make other adjustments to the features in the various embodiments of the present invention according to the circumstances without conflict, without making creative work, so as to obtain different other technical solutions that do not deviate from the concept of the present invention in essence, and these technical solutions also belong to the scope of protection of the present invention.

Claims

1. A wind turbine active support control method based on frequency regulation, characterized in that: The wind turbine active support control method based on frequency regulation includes: Obtain the day-ahead wind turbine output data and grid power parameters of the power system, and standardize the day-ahead wind turbine output data and grid power parameters; Load the wind turbine output data and power grid power parameters of the day before, migrate the wind turbine output data and power grid power parameters of the day before to the modeling sample set, traverse the modeling sample set to generate training set and test set, pre-build a frequency situation prediction model based on multi-layer perceptron, use the training set and test set to iteratively train the frequency situation prediction model, and output a converged frequency situation prediction model; Real-time collection of daily wind turbine output data and grid power parameters. Taking the daily wind turbine output data and grid power parameters as input, the frequency situation prediction model is used to identify and analyze the daily wind turbine output data and grid power parameters, and outputs the frequency prediction set within the prediction period. The frequency prediction set is loaded, and the power fluctuation points and the power fluctuation values ​​at the power fluctuation points within the prediction period are determined based on the frequency prediction set. The power fluctuation points and the power fluctuation values ​​at the power fluctuation points are used as prior information, and the energy conversion efficiency and primary frequency regulation are taken into account as constraints to calculate the spare capacity based on overspeed control at the power fluctuation points.

2. The wind turbine active support control method based on frequency regulation according to claim 1, characterized in that: The wind turbine active support control method based on frequency regulation also includes: Obtain the spare capacity at the power fluctuation point, determine the wind turbine load reduction point based on the cyclic congestion sorting strategy, and generate the active support strategy for the wind turbine set with the steady-state frequency deviation at the wind turbine load reduction point as a constraint; In response to the active support strategy of the wind turbine generator set, the PID speed regulator triggers an active support instruction based on the active support strategy of the wind turbine generator set.

3. The wind turbine active support control method based on frequency regulation according to claim 1, characterized in that: The method of iteratively training the frequency situation prediction model using a training set and a test set includes: Obtain training sets and test sets, and load the initial model of the frequency situation prediction model; Set the training batch size, training complete times, learning rate, activation function, and loss function for the initial model; Based on the feedforward neural network, the weights and frequency thresholds between the input layer and the hidden layer are generated, the training set is loaded, and the training set is normalized by dimensionality reduction. The normalized training sample sequence is used as the column of the training matrix, and the sample features are used as the row of the training matrix to complete the construction of the training matrix, and the weights are added to the training matrix. Get the training matrix after adding the weight matrix, input the training matrix into the variable convolution attention module, get the feature convolution result, perform Fourier frequency analysis on the feature convolution result, and output the frequency value of the feature; Determine whether the frequency value of the feature exceeds the preset frequency threshold. If it exceeds the preset frequency threshold, retain the current feature. If it does not exceed the preset frequency threshold, prune and compress the current feature weight. Load the initial model after feature weight pruning and compression, use the training set to retrain the initial model until convergence, and output the converged initial model; Load the test set, use the test set as input, execute the initial model, and the initial model outputs the test results to determine whether the test results meet the preset accuracy threshold. If they meet the accuracy threshold, output the converged frequency situation prediction model.

4. The wind turbine active support control method based on frequency regulation according to claim 3, characterized in that: The frequency situation prediction model uses a multi-layer perceptron model as an initial model. The initial model consists of an input layer, a hidden layer, and an output layer. The hidden layer is located between the input layer and the output layer. When pre-building a frequency situation prediction model based on a multi-layer perceptron, a sparse autoencoder is introduced between the output layer and the hidden layer. The sparse autoencoder is used to ensure the sparsity of the hidden layer, and the activation function of the sparse autoencoder is a sigmiod activation function. The hidden layers of the initial model include the first hidden layer and the second hidden layer. The number of neurons in the first hidden layer is 40. The hidden layers of the initial model are improved by freezing the second hidden layer and replacing it with a variable convolutional attention module. The variable convolutional attention module includes a multi-head attention mechanism, three-layer convolution and a global average pooling layer. The three-layer convolution includes the first convolution layer, the second convolution layer and the third convolution layer. The convolution kernel size of the first and second convolution layers is 3×3, and the convolution kernel size of the third convolution layer is 5×5. A flexible trigger mechanism is introduced into the input layer of the initial model, and the input layer extracts the frequency deficiency features based on the flexible trigger mechanism.

5. The wind turbine active support control method based on frequency regulation according to claim 4, characterized in that: The method for extracting frequency deficiency features based on the flexible trigger mechanism at the input layer includes: Load the daily wind turbine output data and grid power parameters, and define the shortage fusion threshold of the frequency shortage feature based on the daily wind turbine output data, the maximum frequency change rate of the grid in the grid power parameters, the active shortage, and the wind turbine inertia time constant. and mechanism trigger threshold ; Construct the square wave function of the maximum frequency change rate of the power grid, the active power shortage, and the inertia time constant of the wind turbine within the daily sampling interval, and construct the Hessia matrix of the sampling interval based on the square wave function within the sampling interval; The square wave function within the sampling interval is expressed as: （1） The Hessia matrix of the sampling interval is expressed as: （2） in, represents the square wave function within the sampling interval, represents the sampling interval, is the active power shortage within the sampling interval, represents the fan inertia time constant, is the maximum frequency change rate of the power grid, is the Hessia matrix output representation of the sampling interval, The square wave function element and variables, Represents the square wave function and The second-order partial derivatives of variables; Get the Hessia matrix of the sampling interval, use the quasi-Newton method to calculate the Hessia matrix result, and determine whether the Hessia matrix result exceeds the missing fusion threshold ; If the deficit fusion threshold is exceeded , integrate the Hessia matrix results into an integral space set, perform integral calculation on the integral space set, and output the integral calculation results. When the integral calculation results accumulate to the mechanism trigger threshold When , the flexible trigger mechanism is triggered to extract the characteristics of the maximum frequency change rate, active power shortage and wind turbine inertia time constant of the power grid within the daily sampling interval, and output the Hessia matrix result; The integral calculation of the integral space set is expressed as: （3） in, represents the result of the integral space set integral calculation, are the start and end time of the sampling interval respectively.

6. The wind turbine active support control method based on frequency regulation according to claim 5, characterized in that: The method for identifying and analyzing daily wind turbine output data and power grid power parameters based on the frequency situation prediction model includes: Obtain daily wind turbine output data and grid power parameters. The input layer extracts frequency shortage features based on a flexible trigger mechanism and outputs the Hessia matrix results. Normalize the daily wind turbine output data and grid power parameters after removing the frequency shortage feature, filter the normalized result, and output the filtered normalized feature; The sparse autoencoder performs sparse encoding and sparse decoding on the normalized features to obtain the normalized features after adding the gain matrix. Based on the relative entropy, a sparse penalty term is introduced to the normalized features after adding the gain matrix, and the autoencoding result is output; Obtain the autoencoding result, perform weighted summation on the autoencoding result in the first hidden layer, and then normalize the weighted summation result using the sigmiod activation function to obtain a weighted autoencoding set; The variable convolutional attention module obtains the weighted autoencoder set and Hessia matrix results. The variable convolutional attention module couples the weighted autoencoder set and Hessia matrix results to the objective function, calculates the frequency prediction results within the prediction period based on the objective function, and outputs the frequency prediction set within the prediction period.

7. The wind turbine active support control method based on frequency regulation according to claim 6, characterized in that: When the daily wind turbine output data and grid power parameters are normalized after removing the frequency deficiency characteristics, the normalization result is expressed as: （4） in, is the normalized processing result, Represents the data matrix composed of wind turbine output data and grid power parameters within a day. is the data mean, represents the data variance; The autoencoding result is expressed as: （5） （6） （7） in, represents the autoencoding result, Relative entropy of normalized features, used to represent the relative entropy value of two groups of random variables. represents the sparse penalty term, Normalized features The gain matrix, is the number of data, is the characteristic number, represents the sparse ratio, is the activation value of the normalized feature, Represents the maximum value of normalized features; When calculating the frequency prediction results within the prediction period based on the objective function, the objective function is defined as: （8） in, represents the frequency prediction result, They are the grid frequency of the previous sampling interval and the intraday frequency average.

8. The wind turbine active support control method based on frequency regulation according to claim 1, characterized in that: The method of calculating the reserve capacity based on overspeed control at the power fluctuation point by taking energy conversion efficiency and primary frequency regulation into consideration as constraints includes: Loading power fluctuation points and power fluctuation values ​​at the power fluctuation points, and determining the steady-state deviation of the fan frequency based on the power fluctuation values ​​at the power fluctuation points; The steady-state deviation of fan frequency is expressed as: （9） in, is the steady-state deviation of the fan frequency, is the air density, is the wind speed, represents the leaf coverage area, is the power fluctuation value at the fluctuation point, represents the wind energy utilization coefficient, is the unit adjustment coefficient; （10） in, is the fan tip speed ratio, Represent the fan speed and blade radius respectively; Obtain the steady-state deviation of the fan frequency, and calculate the primary frequency regulation capability of the fan by combining the wind energy utilization coefficient and the steady-state deviation of the fan frequency; The calculation expression of the fan primary frequency regulation capacity is as follows: （11） Calculate the spare capacity based on overspeed control at the power fluctuation point based on the primary frequency regulation capability and energy conversion efficiency of the wind turbine; （12） in, Indicates the primary frequency regulation capability of the fan. are the mechanical torque and electromagnetic torque of the fan respectively, represents the rotor damping coefficient, is the energy conversion efficiency.

9. A wind turbine active support control system based on frequency regulation, used to implement the wind turbine active support control method based on frequency regulation as claimed in any one of claims 1 to 8, characterized in that: The wind turbine active support control system based on frequency regulation includes: The data acquisition module is used to obtain the wind turbine output data and grid power parameters of the power system on the previous day, and to standardize the wind turbine output data and grid power parameters on the previous day; The prediction model building module is used to load the wind turbine output data and power grid power parameters of the day before, migrate the wind turbine output data and power grid power parameters of the day before to the modeling sample set, traverse the modeling sample set to generate a training set and a test set, pre-build a frequency situation prediction model based on a multi-layer perceptron, use the training set and the test set to iteratively train the frequency situation prediction model, and output a converged frequency situation prediction model; The frequency prediction module is used to collect the daily wind turbine output data and grid power parameters in real time. It takes the daily wind turbine output data and grid power parameters as input, identifies and analyzes the daily wind turbine output data and grid power parameters based on the frequency situation prediction model, and outputs the frequency prediction set within the prediction period; A capacity calculation module is used to load a frequency prediction set, determine the power fluctuation point and the power fluctuation value at the power fluctuation point within the prediction period based on the frequency prediction set, use the power fluctuation point and the power fluctuation value at the power fluctuation point as prior information, and calculate the spare capacity based on overspeed control at the power fluctuation point taking into account energy conversion efficiency and primary frequency modulation as constraints; The active support module is used to obtain the spare capacity at the power fluctuation point, determine the wind turbine load reduction operation point based on the cyclic congestion sorting strategy, and generate the wind turbine active support strategy based on the steady-state frequency deviation at the wind turbine load reduction operation point as a constraint. In response to the active support strategy of the wind turbine, the PID speed regulator triggers the active support instruction based on the active support strategy of the wind turbine.

10. The wind turbine active support control system based on frequency regulation according to claim 9, characterized in that: The active support module comprises: An operating point determination unit, used to obtain the spare capacity at the power fluctuation point and determine the wind turbine load reduction operating point based on a cyclic congestion sorting strategy; A strategy generation unit generates an active support strategy for the wind turbine using the steady-state frequency deviation at the wind turbine load reduction operation point as a constraint; The strategy response unit responds to the active support strategy of the wind turbine generator set, and the PID speed regulator triggers the active support instruction based on the active support strategy of the wind turbine generator set.

Images