Super-capacity energy storage charging rate adjusting method and system based on acquisition error adjustment

Abstract

The invention provides a super-capacity energy storage charging rate adjusting method and system based on acquisition error adjustment, and belongs to the technical field of wind power generation. Specifically, the error type of each data point in an original wind speed sequence is judged; correcting data points with errors in the original wind speed sequence; the corrected wind speed sequence is input into a GRU model for prediction, and a wind speed prediction result is obtained; and dynamically adjusting the charging rate of the wind driven generator to the super-capacity energy storage system based on the wind speed prediction result. The original wind speed sequence of the wind driven generator in the super-capacity energy storage system is processed, data points with acquisition delay and acquisition data deviation are corrected, error points are corrected, the problem that in the prior art, due to inherent imperfection of wind speed acquisition equipment, acquisition data have acquisition deviation and acquisition delay is effectively solved, and the accuracy of the wind speed acquisition equipment is improved. Therefore, the accuracy of wind speed prediction based on the data is improved, the charging rate is adjusted in real time based on the prediction result, and the power generation efficiency and the energy storage efficiency are balanced.

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 adjusting the charging rate of a super-capacity energy storage system based on acquisition error adjustment. Background Art

[0002] Due to the randomness and unpredictability of wind speed changes, the grid connection of large-scale wind farms has brought unprecedented challenges to grid dispatching. This uncertainty not only increases the complexity of dispatching work, but may also have an adverse impact on the stability of the power system. In order to cope with this problem, improving the dispatchability of wind farms has become the focus of current research. A common and effective method is to use a neural network method to predict the wind speed for the next day. This method constructs a complex neural network model, uses a large amount of historical wind speed data as training samples, learns the laws and trends of wind speed changes, and thus predicts future wind speeds.

[0003] Based on the predicted wind speed value, the power sent by the wind farm to the grid can be further calculated, and these predicted values ​​can be submitted to the grid dispatching agency in a timely manner. In this way, the grid dispatching agency can formulate power generation plans and dispatching strategies based on these predicted data to ensure the stable operation of the power system. In order to further improve the credibility of the grid's wind farm power generation dispatching based on wind power forecasts, it is also necessary to connect a supercapacitor energy storage system at the outlet of the wind farm. This system can quickly respond to the error between the actual power generated by the wind farm and the predicted power, and balance this difference through energy storage and discharge, thereby ensuring that the power provided by the wind farm to the grid is stable and reliable.

[0004] However, there are still some problems in traditional wind speed prediction methods that cannot be ignored. These methods are generally based on historical wind speed series for prediction, ignoring the volatility and randomness of wind, and it is difficult to accurately capture the changing laws of wind speed series. The collection of historical wind speed series is completed by various instruments and equipment. These instruments / equipment for collecting historical wind speed series have some problems such as large collection errors and data collection delays. These problems will cause the collected historical data to be inaccurate, biased or delayed, which will further affect the accuracy of the prediction when it is put into the prediction model. If the historical data received by the prediction model is inaccurate, then no matter how advanced and accurate the model itself is, its prediction results will inevitably have large errors.

[0005] In response to the above problems, a Chinese patent application with publication number CN112183814A discloses a short-term wind speed prediction method, which uses a variational mode decomposition method to decompose the fluctuating original wind speed sequence into multiple stable wind speed subsequences with specific characteristics, predicts each wind speed subsequence separately, and finally combines the prediction results of each wind speed subsequence to obtain the predicted wind speed. However, the efficiency and accuracy of the variational mode decomposition method of this patent still need to be improved, and the accuracy and real-time performance of the wind speed subsequence prediction method also need to be further improved.

[0006] The Chinese patent application with publication number CN114897260A discloses a modeling method for a short-term wind speed prediction model based on an LSTM (Long Short-Term Memory) neural network. The model removes the fluctuation characteristics with significant regularity in the original wind speed sequence data through preprocessing, and optimizes the hyperparameters of the LSTM neural network model with a Bayesian optimization algorithm to obtain a short-term wind speed prediction model. However, the patent still has room for improvement in the preprocessing method, Bayesian optimization algorithm, and hyperparameter selection to further improve the convergence speed and prediction effect of the model.

[0007] Therefore, in order to improve the accuracy of wind speed prediction, in addition to continuously improving the prediction model and method, it is also necessary to strengthen the research and development and improvement of instruments / equipment for collecting historical wind speed series, reduce the collection error and delay problems, and ensure that the collected historical data is accurate and reliable. Only in this way can a more accurate data basis be provided for wind speed prediction, and the dispatchability of wind farms and the stability of power systems can be further improved. Summary of the invention

[0008] The purpose of the present invention is to overcome the inherent imperfections of wind speed collection equipment in the prior art, which lead to collection deviation and delay in the collected wind speed data, affecting the accuracy of short-term wind speed prediction based on these data, and to provide a super-capacity energy storage charging rate adjustment method and system based on collection error adjustment.

[0009] In order to achieve the above object, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for adjusting the charging rate of a supercapacitor energy storage system based on acquisition error adjustment, comprising the following steps: Obtain the original wind speed sequence of the wind turbine generator in the super-capacity energy storage system; Determine whether each data point in the original wind speed sequence belongs to the error type of acquisition data deviation, acquisition delay or both, and obtain a judgment result; Based on the judgment result, correcting the corresponding data points in the original wind speed sequence; The corrected wind speed sequence is input into the GRU model for prediction to obtain the wind speed prediction result; The charging rate of wind turbines to the super-capacity energy storage system is dynamically adjusted based on wind speed prediction results.

[0010] In the step of obtaining the original wind speed sequence of the wind turbine generator in the ultra-capacity energy storage system, the original wind speed sequence obtained is: ; in, Indicates data points, , Represents the number of data points in the original wind speed sequence; In the step of determining whether each data point in the original wind speed sequence belongs to the error type of acquisition data deviation, acquisition delay, or both, and obtaining the determination result, the method for determining whether each data point in the original wind speed sequence belongs to the error type of acquisition data deviation is as follows: a. Divide the data points in the original wind speed sequence, taking the first 0.9N data points as training data and the last 0.1N data points as test data; b. Train the GRU model based on the training data, predict the test data based on the trained GRU model, get the predicted value, and calculate the root mean square error between the predicted value and the actual value, denoted as ; c. For each data point in the first 0.9N-1 data points Perform random scaling changes. The expression for random scaling changes is: =rand(0.9,1.1) , the changed data points Add training data, add The training data is used as the new training data; the GRU model is trained based on the new training data to obtain a new GRU model; the test data is predicted based on the new GRU model, and the new root mean square error is calculated, which is recorded as ; d. Calculation and Find the ratio between hour i The corresponding data points , is the data point for collecting data deviation.

[0011] In the step of determining whether each data point in the original wind speed sequence belongs to an error type of acquisition data deviation, acquisition delay, or both, and obtaining a determination result, the method for determining whether each data point in the original wind speed sequence belongs to an error type of acquisition delay is as follows: I. Constructing approximate functions ;

[0012] in, To sum the subscripts, indicate different terms; represents the first fitting coefficient, represents the second fitting coefficient, Represents the time parameter, represents the base of natural logarithms; Keep adjusting , And the positive and negative signs between them make t=1, ; When t=2, ; When t=3, ; ..., when t=N, ; II. Original wind speed series The collection delay data points in meet the following conditions: Condition 1: and The signs are opposite; Condition 2: And ; in, and Represents continuous time points, t+0.5 represents and The midpoint of Express The second-order derivative, Express The second-order derivative, Express First-order derivative, Express First-order derivative, Express First-order derivative; The data points that meet the above two conditions are recorded as ,but To collect delayed data points.

[0013] In the step of determining whether each data point in the original wind speed sequence belongs to the error type of acquisition data deviation, acquisition delay, or both, and obtaining the determination result, the method for determining whether the data point belongs to the error type of both is as follows: When there is an intersection between the data points of the acquisition data deviation and the data points of the acquisition delay, the intersection is an error type in which both the acquisition data deviation and the acquisition delay exist.

[0014] In the step of correcting the corresponding data points in the original wind speed sequence based on the judgment result, the correction method for the data points of the collected data deviation is as follows:

[0015] in, sigmoid is the first activation function, tanh is the second activation function.

[0016] In the step of correcting the corresponding data points in the original wind speed sequence based on the judgment result, the correction method for the delayed data points is as follows: ; in, Representation function of Iterations; ∈{+1,-1}, indicating that the positive and negative signs are randomly selected with equal probability.

[0017] In the step of correcting the corresponding data points in the original wind speed sequence based on the judgment result, the correction method for the intersection of the data points with poor acquisition accuracy and the data points with acquisition delay is as follows: set up is the intersection of the data point of the data deviation and the data point of the data delay, then Use the following method to make corrections:

[0018] in, , represents the first weight coefficient; , represents the second weight coefficient.

[0019] In a second aspect, the present invention provides a supercapacitor energy storage charging rate adjustment system based on acquisition error adjustment, comprising: An acquisition module, used to acquire the original wind speed sequence of the wind turbine generator in the ultra-capacity energy storage system; A judgment module is used to judge whether each data point in the original wind speed sequence belongs to the error type of acquisition data deviation, acquisition delay or both, and obtain a judgment result; Correction module: used for correcting corresponding data points in the original wind speed sequence based on the judgment result; The prediction module is used to input the corrected wind speed sequence into the GRU model for prediction to obtain the wind speed prediction result; The adjustment module is used to dynamically adjust the charging rate of the wind turbine to the super-capacity energy storage system based on the wind speed prediction result.

[0020] In a third aspect, the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a method for adjusting a supercapacity energy storage charging rate based on acquisition error adjustment are implemented.

[0021] In a fourth aspect, the present invention provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of a method for adjusting a supercapacity energy storage charging rate based on acquisition error adjustment.

[0022] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a super-capacity energy storage charging rate adjustment method based on acquisition error adjustment, comprising the following steps: obtaining an original wind speed sequence of a wind generator in a super-capacity energy storage system; judging whether each data point in the original wind speed sequence belongs to an error type of acquisition data deviation, acquisition delay or both, and obtaining a judgment result; based on the judgment result, correcting the corresponding data points in the original wind speed sequence; inputting the corrected wind speed sequence into a recurrent neural network GRU (Gated Recurrent Unit) model for prediction, and obtaining a wind speed prediction result; and dynamically adjusting the charging rate of the wind generator to the super-capacity energy storage system based on the wind speed prediction result. By processing the original wind speed sequence of the wind turbine in the ultra-capacity energy storage system, judging and correcting the data points with acquisition delays and data deviations, and correcting the error points, the problem of acquisition deviations and delays in the acquired data caused by the inherent imperfections of the wind speed acquisition equipment in the prior art is effectively solved, thereby improving the accuracy of wind speed prediction based on these data, adjusting the charging rate in real time based on the prediction results, and balancing the power generation and energy storage efficiency; the correction method is simple and efficient, does not require complex optimization algorithms, avoids the defects of the existing methods in preprocessing and optimization algorithms, and improves the convergence speed of the prediction model.

[0023] Furthermore, the GRU model is used for wind speed prediction, which fully considers the volatility and randomness of the wind speed series, can accurately capture the changing law of the wind speed series, and the prediction effect is better than traditional physical models, statistical models and other methods.

[0024] Furthermore, the GRU model structure is relatively simple and the hyperparameter selection is relatively easy, which avoids the shortcomings of complex model structure and difficult hyperparameter selection in existing wind speed prediction methods based on deep learning models, and improves the real-time performance of the prediction.

[0025] Furthermore, there is no need to perform complex decomposition of the wind speed series, thus avoiding the shortcomings of existing methods such as variational mode decomposition in terms of decomposition efficiency and accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1is a flow chart of the method of the present invention; Figure 2 It is a system structure diagram of the present invention; Figure 3 This is a system diagram of Example 7 of the present invention. DETAILED DESCRIPTION

[0027] In order to further understand the content of the present invention, the present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the embodiments are only for explaining the present invention and are not intended to limit it.

[0028] Example 1 like Figure 1 As shown, a method for adjusting the charging rate of a supercapacitor energy storage system based on acquisition error adjustment includes the following steps: S1: Obtain the original wind speed sequence of the wind turbine in the super-capacity energy storage system; S2: Determine whether each data point in the original wind speed sequence belongs to the error type of acquisition data deviation, acquisition delay or both, and obtain the judgment result; S3: Based on the judgment result, correct the corresponding data points in the original wind speed sequence; S4: Input the corrected wind speed sequence into the GRU model for prediction to obtain the wind speed prediction result; S5: Dynamically adjust the charging rate of the wind turbine to the super-capacity energy storage system based on the wind speed prediction results.

[0029] Example 2 Assume the original wind speed sequence (wind speed data collected by equipment / instruments), ,in, Indicates data points, , Represents the number of data points in the original wind speed sequence; Use these N data to predict the next 0.1N wind speed sequences, with a sampling interval of 15 minutes, that is, the time between the i-th point and the i+1-th point is 15 minutes.

[0030] Determine whether the wind speed sequence collected by the equipment / instrument has data collection deviation: Deviation of collected data: Assuming the actual wind speed is 5m / s, the inherent imperfections of wind speed collection equipment may cause the collected data to be too high or too low, for example, the collected data may be 4.9m / s or 5.1m / s.

[0031] The specific judgment method is as follows: a. Data preparation: Divide the data points in the original wind speed sequence, use the first 0.9N data points as the training set for training the GRU model, and use the last 0.1N data points as the test set for evaluating the prediction performance; b. Initial prediction and error calculation: Train the GRU model based on the training data; Predict the prediction data based on the trained GRU model to obtain the predicted value; Calculate the root mean square error between the predicted value and the actual value, denoted as ; c. Data perturbation and error analysis: For each data point in the first 0.9N-1 data Perform random scaling changes ranging from 0.9 to 1.1 times the original value. The expression for random scaling changes is: =rand(0.9,1.1) , Indicates the data point after the change; Each time a data point is scaled, the changed data point Add training data, add The training data is used as new training data; the GRU model is retrained based on the new training set to obtain a new GRU model, and the test data is predicted based on the new GRU model; For each predicted value after scaling change, calculate the new root mean square error, denoted as ; d. Identify points with unsatisfactory accuracy For the new RMS error , calculate its difference with the initial error The ratio of ; Find satisfaction hour i The corresponding data points , is the data point for collecting data deviation.

[0032] The correction method for data points with collection data deviation is as follows:

[0033] in, sigmoid is the first activation function, tanh is the second activation function.

[0034] Example 3 Based on Example 2, determine whether the wind speed sequence collected by the device / instrument has a problem of data collection delay: Data collection delays can cause The wind speed data collected at all times becomes (The next time step, represents the time step, The wind speed value at the time of random variation (indicates the wind speed value at the random variation), for example, the wind speed data at the 30th minute is 6m / s, and the wind speed data at the 30.5th minute is 7m / s. Then the wind speed sequence should have collected data of 6m / s at the 30th minute, but it has changed to 7m / s.

[0035] The method for determining whether each data point in the original wind speed sequence belongs to the collection data delay is as follows: I. Constructing approximate functions ;

[0036] in, To sum the subscripts, indicate different terms; represents the first fitting coefficient, represents the second fitting coefficient, Indicates time, represents the base of natural logarithms; Keep adjusting , And the positive and negative signs between them make t=1, ; When t=2, ; When t=3, ; ..., when t=N, This effect is an ideal effect. When 95% of the conditions are met, it can be considered that The build was successful.

[0037] II. Original wind speed series The collection delay data points in meet the following conditions: Condition 1: and The signs are opposite; Condition 2: And ; in, and Represents continuous time points, t+0.5 represents and The midpoint of Express The second-order derivative, Express The second-order derivative, Express First-order derivative, Express First-order derivative, Express First-order derivative; The data points that meet the above two conditions are recorded as ,but These are data points with collection delays.

[0038] The correction method for data points with acquisition delay is as follows:

[0039] in, Representation function of Iterations; ∈{+1,-1}, indicating that the positive and negative signs are randomly selected with equal probability.

[0040] Example 4 On the basis of Example 3, a method for determining whether a data point belongs to an error type that has both of the above is: the intersection of data points with acquisition data deviation and data points with acquisition delay.

[0041] The correction method for the intersection of data points with acquisition data deviation and data points with acquisition delay is as follows: set up is the intersection of the data points with data collection deviation and the data points with collection delay, then Use the following method to make corrections:

[0042] in, , represents the first weight coefficient; , represents the second weight coefficient.

[0043] Example 5 Based on the above embodiment, a corrected wind speed sequence is obtained, and the corrected wind speed sequence is input into the GRU model for prediction to obtain a wind speed prediction result. Based on the wind speed prediction result, the charging rate of the wind turbine to the super-capacity energy storage system is dynamically adjusted. The specific method is as follows: The corrected wind speed series is standardized to eliminate the dimension difference; The corrected wind speed sequence is divided into training set, validation set and test set. The training set is used to train the GRU model, the validation set is used to adjust the network parameters, and the test set is used to evaluate the network performance; Design the architecture of the GRU model, including the input layer, GRU layer, and fully connected layer; select appropriate parameters such as the number of network layers, the number of GRU units, and the activation function according to the task requirements and data characteristics; preferably, in this embodiment, design a network containing two GRU layers, each containing 256 GRU units; select the activation function sigmoid and tanh , the learning rate is set to 0.001, the batch size is 64, the regularization method selects L2 regularization, the weight decay coefficient is 0.0001, and the Dropout probability is set to 0.5.

[0044] Use the training set data to train the designed GRU model, and update the GRU model parameters through the back propagation algorithm to minimize the prediction error; use the validation set data to monitor the performance of the model to avoid overfitting and obtain a trained GRU model; Input the test set data into the trained GRU model to obtain the wind speed prediction result; According to the wind speed prediction results, calculate the power output corresponding to the predicted wind speed; The charging rate of the wind turbine to the super-capacity energy storage system is dynamically adjusted according to the predicted power output and the current state of the super-capacity energy storage system.

[0045] Example 6 A supercapacitor energy storage charging rate adjustment system based on acquisition error adjustment, comprising: An acquisition module, used to acquire the original wind speed sequence of the wind turbine generator in the ultra-capacity energy storage system; A judgment module is used to judge whether each data point in the original wind speed sequence belongs to the error type of acquisition data deviation, acquisition delay or both, and obtain a judgment result; Correction module: used for correcting corresponding data points in the original wind speed sequence based on the judgment result; The prediction module is used to input the corrected wind speed sequence into the GRU model for prediction to obtain the wind speed prediction result; The adjustment module is used to dynamically adjust the charging rate of the wind turbine to the super-capacity energy storage system based on the wind speed prediction result.

[0046] Example 7 like Figure 3 As shown, the present invention also provides an electronic device 100 for a supercapacity energy storage charging rate adjustment method based on acquisition error adjustment; the electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0047] The memory 101 can be used to store the computer program 103, and the processor 102 implements the steps of the super-capacity energy storage charging rate adjustment method based on acquisition error adjustment described in Example 1 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101. The memory 101 may mainly 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 (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data (such as audio data) created according to the use of the electronic device 100, etc. In addition, the memory 101 may include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0048] The at least one processor 102 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 may be a microprocessor or any conventional processor, etc. The processor 102 is the control center of the electronic device 100, and uses various interfaces and lines to connect various parts of the entire electronic device 100.

[0049] The memory 101 in the electronic device 100 stores a plurality of instructions to implement a method for adjusting the charging rate of a supercapacitor energy storage system based on acquisition error adjustment. The processor 102 may execute the plurality of instructions to implement: Obtain the original wind speed sequence of the wind turbine generator in the super-capacity energy storage system; Determine whether each data point in the original wind speed sequence belongs to the error type of acquisition data deviation, acquisition delay or both, and obtain a judgment result; Based on the judgment result, correcting the corresponding data points in the original wind speed sequence; The corrected wind speed sequence is input into the GRU model for prediction to obtain the wind speed prediction result; The charging rate of wind turbines to the super-capacity energy storage system is dynamically adjusted based on wind speed prediction results.

[0050] Example 8 If the module / unit integrated in the electronic device 100 is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory and read-only memory (ROM, Read-Only Memory).

[0051] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) containing computer-usable program code.

[0052] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0053] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0054] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0055] Finally, it should be noted that: although the present invention is described herein in conjunction with various embodiments, in the process of implementing the claimed invention, those skilled in the art can understand and implement other changes to the disclosed embodiments by viewing the drawings, the disclosure, and the appended claims. In the claims, the word "comprising" does not exclude other components or steps, and "one" or "an" does not exclude multiple situations. A single processor or other unit can implement several functions listed in the claims. Certain measures are recorded in different dependent claims, but this does not mean that these measures cannot be combined to produce good results.

[0056] Although the present invention has been described in conjunction with specific features and embodiments thereof, it is apparent that various modifications and combinations may be made thereto without departing from the spirit and scope of the present invention. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present invention as defined by the appended claims and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present invention. Obviously, those skilled in the art may make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, the present invention is intended to include such modifications and variations if they fall within the scope of the claims of the present invention and their equivalents.

Claims

1. A method for adjusting the charging rate of supercapacity energy storage based on acquisition error adjustment, characterized in that: The steps include: Obtain the original wind speed sequence of the wind turbine generator in the super-capacity energy storage system; Determine whether each data point in the original wind speed sequence belongs to the error type of acquisition data deviation, acquisition delay or both, and obtain a judgment result; Based on the judgment result, correcting the corresponding data points in the original wind speed sequence; The corrected wind speed sequence is input into the GRU model for prediction to obtain the wind speed prediction result; The charging rate of wind turbines to the super-capacity energy storage system is dynamically adjusted based on wind speed prediction results.

2. The method for adjusting the charging rate of supercapacity energy storage based on acquisition error adjustment according to claim 1, characterized in that: In the step of obtaining the original wind speed sequence of the wind turbine generator in the ultra-capacity energy storage system, the original wind speed sequence obtained is: ; in, Indicates data points, , Represents the number of data points in the original wind speed sequence; In the step of determining whether each data point in the original wind speed sequence belongs to the error type of acquisition data deviation, acquisition delay, or both, and obtaining the determination result, the method for determining whether each data point in the original wind speed sequence belongs to the error type of acquisition data deviation is as follows: a. Divide the data points in the original wind speed sequence, taking the first 0.9N data points as training data and the last 0.1N data points as test data; b. Train the GRU model based on the training data, predict the test data based on the trained GRU model, get the predicted value, and calculate the root mean square error between the predicted value and the actual value, denoted as ; c. For each data point in the first 0.9N-1 data points Perform random scaling changes. The expression for random scaling changes is: =rand(0.9,1.1) , the changed data points Add training data, add The training data is used as the new training data; the GRU model is trained based on the new training data to obtain a new GRU model; the test data is predicted based on the new GRU model, and the new root mean square error is calculated, which is recorded as ; d. Calculation and Find the ratio between hour i The corresponding data points , is the data point for collecting data deviation.

3. The method for adjusting the charging rate of supercapacity energy storage based on acquisition error adjustment according to claim 2 is characterized in that: In the step of determining whether each data point in the original wind speed sequence belongs to an error type of acquisition data deviation, acquisition delay, or both, and obtaining a determination result, the method for determining whether each data point in the original wind speed sequence belongs to an error type of acquisition delay is as follows: I. Constructing approximate functions ; in, To sum the subscripts, indicate different terms; represents the first fitting coefficient, represents the second fitting coefficient, Represents the time parameter, represents the base of natural logarithms; Keep adjusting , And the positive and negative signs between them make t=1, ; When t=2, ; When t=3, ; ..., when t=N, ; II. Original wind speed series The collection delay data points in meet the following conditions: Condition 1: and The signs are opposite; Condition 2: And ; in, and Represents continuous time points, t+0.5 represents and The midpoint of Express The second-order derivative, Express The second-order derivative, Express First-order derivative, Express First-order derivative, Express First-order derivative; The data points that meet the above two conditions are recorded as ,but To collect delayed data points.

4. The method for adjusting the charging rate of supercapacity energy storage based on acquisition error adjustment according to claim 3 is characterized in that: In the step of determining whether each data point in the original wind speed sequence belongs to the error type of acquisition data deviation, acquisition delay, or both, and obtaining the determination result, the method for determining whether the data point belongs to the error type of both is as follows: When there is an intersection between the data points of the acquisition data deviation and the data points of the acquisition delay, the intersection is an error type in which both the acquisition data deviation and the acquisition delay exist.

5. The method for adjusting the charging rate of supercapacity energy storage based on acquisition error adjustment according to claim 4 is characterized in that: In the step of correcting the corresponding data points in the original wind speed sequence based on the judgment result, the correction method for the data points of the collected data deviation is as follows: in, sigmoid is the first activation function, tanh is the second activation function.

6. The method for adjusting the charging rate of supercapacity energy storage based on acquisition error adjustment according to claim 5 is characterized in that: In the step of correcting the corresponding data points in the original wind speed sequence based on the judgment result, the correction method for the delayed data points is as follows: ； in, Representation function of Iterations; ∈{+1,-1}, indicating that the positive and negative signs are randomly selected with equal probability.

7. A method for adjusting the charging rate of supercapacity energy storage based on acquisition error adjustment according to claim 6, characterized in that: In the step of correcting the corresponding data points in the original wind speed sequence based on the judgment result, the correction method for the intersection of the data points with poor acquisition accuracy and the data points with acquisition delay is as follows: set up is the intersection of the data point of the data deviation and the data point of the data delay, then Use the following method to make corrections: in, , represents the first weight coefficient; , represents the second weight coefficient.

8. A supercapacitor energy storage charging rate adjustment system based on acquisition error adjustment, characterized in that: include: An acquisition module, used to acquire the original wind speed sequence of the wind turbine generator in the ultra-capacity energy storage system; A judgment module is used to judge whether each data point in the original wind speed sequence belongs to the error type of acquisition data deviation, acquisition delay or both, and obtain a judgment result; Correction module: used for correcting corresponding data points in the original wind speed sequence based on the judgment result; The prediction module is used to input the corrected wind speed sequence into the GRU model for prediction to obtain the wind speed prediction result; The adjustment module is used to dynamically adjust the charging rate of the wind turbine to the super-capacity energy storage system based on the wind speed prediction result.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for adjusting the charging rate of super-capacity energy storage based on acquisition error adjustment described in any one of claims 1 to 7 are implemented.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for adjusting the charging rate of super-capacity energy storage based on acquisition error adjustment according to any one of claims 1 to 7 are implemented.

Images