Super capacitor energy storage frequency modulation grid connection method and system based on operation improved VMD

Abstract

The invention discloses a super capacitor energy storage frequency modulation grid connection method and system based on operation improved VMD, and belongs to the technical field of wind speed prediction, and the method comprises the following steps: decomposing an original wind speed time sequence through a variational mode decomposition method, and obtaining a plurality of subsequences; performing argumentation processing on each sub-sequence to obtain an amplitude representation form of each sub-sequence; carrying out independent calculation on the amplitude representation forms of all the subsequences to obtain independent values; progressively increasing the number of decomposition layers of variational mode decomposition, repeating the steps, and recording an independent value obtained in each cycle; the maximum independent value in all the independent values is obtained through comparison, and the sub-sequence corresponding to the maximum independent value serves as the optimal sub-sequence; and inputting the optimal sub-sequence into a prediction neural network for prediction to obtain prediction results, and adding the prediction results to obtain a wind speed prediction result of super-capacity energy storage grid connection. According to the invention, the prediction precision can be improved, the model robustness is enhanced, the reasonable utilization of super-capacity energy storage is promoted, and the grid-connected stability is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of wind speed prediction, and in particular relates to a supercapacitor energy storage frequency modulation grid-connected method and system based on an improved VMD calculation. Background Art

[0002] Due to the randomness of wind speed changes, large-scale wind farms are difficult to connect to the grid, which in turn affects the stability of the system. In order to improve the dispatchability of wind farms, the general method uses a neural network method to predict the wind speed for the next day, calculates the power sent by the wind farm to the grid through the predicted wind speed value, and submits the predicted value to the grid dispatching agency. At the same time, an ultra-capacity energy storage system is connected at the outlet of the wind farm to quickly respond to make up for the error between the actual power emitted by the wind farm and the predicted power, thereby improving the credibility of the grid in dispatching wind farm power generation based on wind power forecasts and improving the coordinated operation capabilities between wind farms and power systems.

[0003] However, the traditional prediction method generally uses VMD (Variational Mode Decomposition) to decompose the original data, and then puts it into the neural network for prediction. However, the existing variational mode decomposition has the problem that the decomposed subsequences are still correlated with each other, that is, the subsequences after VMD decomposition are highly correlated with each other, and the subsequences are not independent of each other. Putting the subsequences that are not independent of each other into the neural network prediction will lead to inaccurate prediction results. Summary of the invention

[0004] The purpose of the present invention is to overcome the problem that the decomposed subsequences of the existing variational mode decomposition are still correlated with each other, and a supercapacitor energy storage frequency modulation grid-connected method and system based on the operation of improved VMD are proposed.

[0005] In order to achieve the above object, the present invention adopts the following technical scheme: In a first aspect, the present invention provides a supercapacitor energy storage frequency modulation and grid-connected method based on an improved VMD operation, comprising the following steps: S1. Decompose the original wind speed time series using variational mode decomposition method to obtain several subsequences; S2, performing amplitude-angle processing on each subsequence to obtain an amplitude representation of each subsequence; S3, calculating the amplitude representation of all subsequences through independent operations to obtain independent values; S4, return to S1, increase the number of decomposition levels of variational mode decomposition, repeat steps S1-S3, and record the independent values ​​obtained in each cycle until the number of decomposition levels of variational mode decomposition reaches the maximum; S5. Compare and obtain the maximum independent value among all independent values, and take the subsequence corresponding to the maximum independent value as the optimal subsequence; S6. Input the optimal subsequence into the prediction neural network to obtain the prediction result, and add the prediction results to obtain the wind speed prediction result of the super-capacity energy storage grid-connected.

[0006] Furthermore, the number of the plurality of subsequences is an even number greater than or equal to 4.

[0007] Furthermore, the method of the amplitude processing is:

[0008]

[0009]

[0010] in, They are 1st, 2nd, 3rd, ..., k The amplitude representation of the subsequences, For the i The amplitude representation of the subsequences is is an element in the subsequence, For the i The amplitude of the subsequences is expressed in terms of angle, k is the number of subsequences, N is the number of elements in the subsequence, i is the intermediate variable, arccos() is the inverse cosine function, and ∠ represents the measure of the angle.

[0011] Furthermore, the independent operation is:

[0012]

[0013] in, is an independent value, is the ith independent sequence, For independent rules, is the amplitude representation of the 2i-1th subsequence, is the amplitude representation of the 2i-th subsequence, K is the number of subsequences, i is an intermediate variable.

[0014] Furthermore, the independent operation rules are specifically as follows:

[0015]

[0016] | |=

[0017] in, For the i independent sequences, | |For the i The size of the independent sequence, For the 2nd i -1 subsequence, For the 2nd i -1 subsequence amplitude representation, For the 2nd i -1 element in the subsequence, For the 2nd i -1 subsequence of amplitudes representing angles, For the 2nd i subsequences, 2nd i The amplitude of the subsequence is represented by For the 2nd i elements in a subsequence, For the 2nd i The amplitude of each subsequence represents the angle.

[0018] Furthermore, the direction of the independent sequence is specifically represented as: Perpendicular to and The plane formed; When A 2i-1 >A 2i hour, Perpendicular to and The flat surface formed faces upward; When A 2i-1 <A 2i hour, Perpendicular to and The flat surface formed faces downward.

[0019] Furthermore, the number of decomposition levels of the incremental variational modal decomposition is the number of decomposition levels plus 2.

[0020] In a second aspect, the present invention provides a supercapacitor energy storage frequency modulation grid-connected system based on an improved operation VMD, and a supercapacitor energy storage frequency modulation grid-connected method based on an improved operation VMD, comprising: The variational mode decomposition sequence module is used to decompose the original wind speed time series into several subsequences using the variational mode decomposition method; An amplitude processing module is used to perform amplitude processing on each subsequence to obtain an amplitude representation of each subsequence; An independent operation module, used for calculating the amplitude representation forms of all subsequences through independent operation rules to obtain independent values; An increasing loop module is used to increase the number of decomposition layers of the variational mode decomposition and record the independent values ​​obtained in each loop until the number of decomposition layers of the variational mode decomposition reaches the maximum; The optimal subsequence obtaining module is used to compare and obtain the maximum independent value among all independent values, and take the subsequence corresponding to the maximum independent value as the optimal subsequence; The wind speed prediction result obtaining module is used to input the optimal subsequence into the prediction neural network for prediction to obtain the prediction result, and add the prediction results to obtain the wind speed prediction result of the super-capacity energy storage grid connection.

[0021] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the supercapacitor energy storage frequency modulation and grid-connected method based on the operationally improved VMD is implemented.

[0022] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the supercapacitor energy storage frequency modulation and grid-connected method based on the operationally improved VMD.

[0023] Compared with the prior art, the present invention has the following beneficial technical effects: The supercapacitor energy storage frequency modulation and grid-connected method based on the improved VMD operation proposed in the present invention decomposes the original wind speed time series into multiple modal components of different frequencies and amplitudes, namely subsequences, which reflects the characteristics of wind speed data on different time scales, captures the volatility and trend of wind speed more finely, and has good adaptability to different types of wind speed data. Even in the face of complex and changeable wind speed environments, it can maintain a high prediction accuracy. By decomposing the wind speed sequence into multiple subsequences for prediction, even if a subsequence is affected by external interference or outliers, it will not have much impact on the entire prediction result, thereby enhancing the anti-interference ability of the model. By selecting the highest number of layers for decomposition, it can ensure that the subsequence used for prediction contains as much useful information as possible, thereby reducing the prediction error. Subsequences with high independence are less sensitive to noise and outliers, so the predictions based on these subsequences are more robust. Compared with directly predicting the original signal, selecting subsequences with high independence by signal decomposition can significantly reduce the computational complexity. The method can handle nonlinear and non-stationary wind speed time series and has good adaptability to different types of wind speed data.

[0024] Furthermore, the method proposed in the present invention decomposes the original wind speed time series through the improved VMD, decomposes the complex wind speed changes into multiple simple subsequences, and extracts key information through amplitude processing and specific operation rules. Through loop iteration and neural network prediction, an accurate prediction of the original wind speed time series is finally obtained. This method combines signal processing, mathematical operations and machine learning techniques, providing a new and effective way for wind speed prediction.

[0025] Furthermore, the grid-connected wind speed prediction method for overcapacity energy storage based on the improved VMD operation has significant benefits in improving prediction accuracy, enhancing model robustness, promoting the rational use of overcapacity energy storage, and improving grid stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are for explanation purposes only and are not intended to limit the scope of the present invention in any way. In addition, the shapes and proportional dimensions of the components in the drawings are only for illustration purposes to help understand the present invention, and are not intended to specifically limit the shapes and proportional dimensions of the components of the present invention. In the drawings: Figure 1 The present invention is a flow chart of the supercapacitor energy storage frequency modulation and grid-connected method based on the operation-improved VMD.

[0027] Figure 2 This is a structural diagram of the supercapacitor energy storage frequency modulation grid-connected system based on the computationally improved VMD of the present invention.

[0028] Figure 3 This is an electronic device diagram of the supercapacitor energy storage frequency modulation grid-connected method based on the improved VMD calculation of the present invention.

[0029] Figure 4 The supercapacitor energy storage frequency modulation and grid connection method based on the improved VMD in the embodiment of the present invention is Direction diagram.

[0030] Figure 5 The supercapacitor energy storage frequency modulation and grid connection method based on the improved VMD in the embodiment of the present invention is Schematic diagram of another direction. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0032] Embodiment 1 See also Figure 1 The method for supercapacitor energy storage frequency modulation and grid connection based on the improved VMD operation includes the following steps: S1. Decompose the original wind speed time series using variational mode decomposition method to obtain several subsequences; The number of the plurality of subsequences in S1 is an even number greater than or equal to 4.

[0033] This step is the basic operation of the VMD method. By iteratively optimizing the bandwidth and center frequency of each mode, the original signal is decomposed into multiple modal components, which helps to capture the wind speed changes of different frequency components.

[0034] S2, performing amplitude-angle processing on each subsequence to obtain an amplitude representation of each subsequence; That is, the subsequence is converted from the time domain to the frequency domain or complex plane to obtain its amplitude and phase information.

[0035] The amplitude angularization process in S2 is:

[0036]

[0037]

[0038] in, They are 1st, 2nd, 3rd, ..., k The amplitude representation of the subsequences, For the i The amplitude representation of the subsequences is is an element in the subsequence, For the i The amplitude of the subsequences is expressed in terms of angle, k is the number of subsequences, N is the number of elements in the subsequence, i is the intermediate variable, arccos() is the inverse cosine function, and ∠ represents the measure of the angle.

[0039] S3. The amplitude representation of all subsequences is calculated through independent operations to obtain independent values; the independent values ​​can evaluate the potential contribution of each subsequence to the prediction results and can further extract the most critical information for wind speed prediction.

[0040] The independent operations described in S3 are:

[0041]

[0042] in, is an independent value, is the ith independent sequence, For independent rules, is the amplitude representation of the 2i-1th subsequence, is the amplitude representation of the 2i-th subsequence, K is the number of subsequences, i is an intermediate variable.

[0043] The independent operation rules are specifically:

[0044]

[0045] | |=

[0046] in, For the i independent sequences, | |For the i The size of the independent sequence, For the 2nd i -1 subsequence, For the 2nd i -1 subsequence amplitude representation, For the 2nd i -1 element in the subsequence, For the 2nd i -1 subsequence of amplitudes representing angles, For the 2nd i subsequences, 2nd i The amplitude of the subsequence is represented by For the 2nd i elements in a subsequence, For the 2nd i The amplitude of each subsequence represents the angle.

[0047] The direction of the independent sequence is specifically represented as: Perpendicular to and The plane formed; When A 2i-1 >A 2i hour, Perpendicular to and The flat surface formed faces upward; When A 2i-1 <A 2i hour, Perpendicular to and The flat surface formed faces downward.

[0048] S4, increasing the number of decomposition layers of the variational mode decomposition, repeating steps S1-S3, and recording the independent values ​​obtained in each cycle until the number of decomposition layers of the variational mode decomposition reaches the maximum; As a preferred solution, the increment in S4 is the number of decomposition layers plus 2.

[0049] S5. Compare and obtain the maximum independent value among all independent values, and take the subsequence corresponding to the maximum independent value as the optimal subsequence; The optimal subsequence can be obtained through S4 incremental loop and S5 comparison, and the subsequence that contributes most to the prediction result can be automatically selected, thereby improving the overall prediction accuracy.

[0050] The improved variational mode decomposition method improves the prediction accuracy by judging the total independence of the subsequences under the current decomposition layer and selecting the layer with the highest degree of independence for decomposition. By adjusting the decomposition parameters of VMD, generating different numbers of subsequences, and increasing the decomposition layer of variational mode decomposition, the optimal subsequence under different decomposition schemes is explored. This optimal subsequence will be used for subsequent neural network prediction.

[0051] S6. Input the optimal subsequence into the prediction neural network to obtain the prediction result, and add the prediction results to obtain the wind speed prediction result of the super-capacity energy storage grid-connected.

[0052] By optimizing the selection of subsequences and combining the prediction ability of neural networks, the accuracy and reliability of wind speed prediction can be improved, thereby optimizing the operating efficiency of the super-capacity energy storage grid-connected system.

[0053] In this embodiment, since the VMD method can decompose multiple frequency components, the model can learn the characteristics of wind speed data more comprehensively, thereby enhancing the generalization ability of the model. By selecting the optimal subsequence for prediction, the model's dependence on specific data sets can be further reduced, and the applicability of the model under different wind speed conditions can be improved. The design of the incremental loop allows the system to gradually optimize and find the optimal number of decomposition layers in the process of gradually increasing the number of decomposition layers, thereby optimizing the calculation efficiency while ensuring the prediction accuracy. The processing of amplitude angle processing and independent calculation is relatively simple and efficient, which helps to reduce the calculation complexity and improve the calculation speed.

[0054] This embodiment can improve the accuracy and reliability of wind speed prediction by optimizing the selection of subsequences and combining the prediction ability of neural networks, thereby optimizing the operating efficiency of the super-capacity energy storage grid-connected system. Through the improved variational mode decomposition method, the original wind speed time series is decomposed into multiple subsequences, and the optimal subsequence is selected for prediction. This method can more effectively capture the nonlinear and non-stationary characteristics of wind speed data, thereby improving the accuracy of the prediction. Combined with the powerful prediction ability of neural networks, the prediction results can be further refined, the errors can be reduced, and the prediction results can be closer to the actual wind speed changes.

[0055] Accurate wind speed prediction results help the super-capacity energy storage system to arrange charging and discharging plans more reasonably. When the wind speed forecast value is high, the system can use more wind energy to generate electricity and reduce the discharge of the energy storage system; when the wind speed forecast value is low, the energy storage system can supplement the power supply to ensure the stable operation of the power grid. By optimizing the use of the energy storage system, the operating cost of the system can be reduced, the energy utilization efficiency can be improved, and the dependence on traditional energy can be reduced, sustainable development can be promoted, carbon emissions can be reduced, and the goals of environmental protection and sustainable development can be achieved. Accurate wind speed prediction helps the power grid dispatching department to better plan power production and distribution and reduce the imbalance between power supply and demand caused by wind speed fluctuations. Under extreme weather conditions, such as a sudden increase or decrease in wind speed, accurate wind speed prediction can provide timely early warning information for the power grid, helping the dispatching department to take necessary measures to ensure the safe and stable operation of the power grid.

[0056] The improved VMD can effectively extract key information from the wind speed time series by optimizing the decomposition process, reduce the error in the decomposition process, and thus improve the accuracy of wind speed prediction. Based on the wind speed prediction results of the improved VMD, the super-capacity energy storage system can more accurately judge the changing trend of wind speed, and thus formulate a more reasonable charging and discharging strategy. The combination of accurate wind speed prediction and optimized charging and discharging strategy can enable the super-capacity energy storage grid-connected system to better adapt to wind speed fluctuations and reduce the imbalance of power supply and demand caused by wind speed changes.

[0057] Embodiment 2 See also Figure 2 , a supercapacitor energy storage frequency modulation grid-connected system based on an improved VMD operation, using the supercapacitor energy storage frequency modulation grid-connected method based on an improved VMD operation described in Example 1, comprising: The variational mode decomposition sequence module is used to decompose the original wind speed time series into several subsequences using the variational mode decomposition method; An amplitude processing module is used to perform amplitude processing on each subsequence to obtain an amplitude representation of each subsequence; An independent operation module, used for calculating the amplitude representation forms of all subsequences through independent operation rules to obtain independent values; An increasing loop module is used to increase the number of decomposition layers of the variational mode decomposition and record the independent values ​​obtained in each loop until the number of decomposition layers of the variational mode decomposition reaches the maximum; The optimal subsequence obtaining module is used to compare and obtain the maximum independent value among all independent values, and take the subsequence corresponding to the maximum independent value as the optimal subsequence; The wind speed prediction result obtaining module is used to input the optimal subsequence into the prediction neural network for prediction to obtain the prediction result, and add the prediction results to obtain the wind speed prediction result of the super-capacity energy storage grid connection.

[0058] This embodiment optimizes the selection of subsequences and combines the prediction ability of neural networks to adjust the charging and discharging strategy of the super-capacity energy storage system according to the predicted wind speed results, thereby optimizing the operating efficiency of the super-capacity energy storage grid-connected system. The traditional VMD method decomposes the signal into multiple modal component subsequences by iteratively searching the center frequency and bandwidth of each mode. The improved VMD algorithm optimizes the decomposition process, improves the decomposition effect, and obtains accurate wind speed prediction results.

[0059] Embodiment 3 See also Figure 3 , an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the supercapacitor energy storage frequency modulation and grid-connected method based on the improved VMD operation described in Example 1 is implemented.

[0060] Embodiment 4 A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the supercapacitor energy storage frequency modulation and grid-connected method based on the improved VMD operation described in Example 1 is implemented.

[0061] Embodiment 5 This embodiment provides a supercapacitor energy storage frequency modulation and grid-connected method based on the improved VMD operation. Taking 4 subsequences as an example, the specific process is as follows: Step 1: Decompose the original wind speed time series x(t) using VMD to obtain a series of subsequences IMF 1 、IMF 2 、IMF 3 ,...IMF K , IMF (Intrinsic Mode Function), K is the number of decomposition levels of VMD, that is, the number of subsequences, which must be an even number greater than or equal to 4. In this example, K=4.

[0062] Step 2: Argument the subsequences one by one; Specifically, taking the first subsequence For example, the amplitude angularization process is as follows:

[0063]

[0064] Among them, arccos() is the inverse cosine function; According to this process, we can get: .

[0065] is the amplitude representation of the first subsequence, is the amplitude representation of the first subsequence, is the angle represented by the amplitude of the first subsequence; is the amplitude representation of the second subsequence, is the amplitude representation of the second subsequence, is the angle represented by the amplitude of the second subsequence; is the amplitude representation of the third subsequence, is the amplitude representation of the third subsequence, is the angle represented by the amplitude of the third subsequence; is the amplitude representation of the 4th subsequence, is the amplitude representation of the 4th subsequence, The angle represented by the amplitude of the 4th subsequence.

[0066] Here, ∠ represents the measure of the angle.

[0067] Step 3: Adoption Operation rules, calculation . Because of the sign problem when adding, The vertical plane is positive when it is upward and negative when it is downward. is an independent value, is the ith independent sequence, is an independent operation rule. is the amplitude representation of the 2i-1th subsequence, is the amplitude representation of the 2i-th subsequence, i is an intermediate variable.

[0068] Specifically, for the step 2 ,use The operation rules get the first independent sequence and the second independent sequence ; Below An example of the generation process:

[0069] The direction of Figure 4 As shown: Perpendicular to and The plane formed; when hour, Perpendicular to and The resulting flat surface faces upward.

[0070] when hour, Perpendicular to and The resulting flat surface faces downward. Figure 5 shown.

[0071] The size of is determined as follows: The size is:

[0072] The first subsequence IMF1 The elements in The second subsequence Elements in is the angle represented by the amplitude of the first subsequence, is the angle represented by the amplitude of the second subsequence; Step 4: K=K+2, repeat steps 1 to 3, continue the cycle, and get the corresponding , output maximum The corresponding K, and the corresponding subsequences under K, put these subsequences into the neural network for prediction, and then add the prediction results to get the final super-capacity energy storage grid-connected wind speed prediction result.

[0073] Specifically: Follow the logic in step 3 to iterate until K=32 and find The subsequence corresponding to the maximum corresponding K value is put into the neural network for prediction to get the final result.

[0074] In order to further verify the advantages of this embodiment, the method of this embodiment and the general prediction method are used to predict the wind speed of the super-capacity energy storage grid using the test data set, and the MAPE (Mean Absolute Percentage Error) is compared. The results are shown in Table 1 below: Table 1 Comparison of the average absolute error percentage of wind speed prediction results of this embodiment and general prediction methods

[0075] It can be seen that the MAPE value generated by the wind speed prediction method provided in this embodiment to obtain the optimal wind speed sequence for super-capacity energy storage grid-connected system is significantly lower than that of the traditional wind speed prediction method. The lower MAPE value means that the wind speed prediction result is more accurate, thereby better guiding the charging and discharging strategy of the super-capacity energy storage grid-connected system.

[0076] 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.

[0077] 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.

[0078] 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 comprising 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.

[0079] 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 Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention is described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation of the present invention can still be modified or replaced by equivalents, and any modification or equivalent replacement that does not deviate from the spirit and scope of the present invention should be included in the protection scope of the present invention.

Claims

1. A supercapacitor energy storage frequency modulation and grid-connected method based on computationally improved VMD, characterized in that: The following steps are involved: S1. Decompose the original wind speed time series using variational mode decomposition method to obtain several subsequences; S2, performing amplitude-angle processing on each subsequence to obtain an amplitude representation of each subsequence; S3, calculating the amplitude representation of all subsequences through independent operations to obtain independent values; S4, return to S1, increase the number of decomposition levels of variational mode decomposition, repeat steps S1-S3, and record the independent values ​​obtained in each cycle until the number of decomposition levels of variational mode decomposition reaches the maximum; S5. Compare and obtain the maximum independent value among all independent values, and take the subsequence corresponding to the maximum independent value as the optimal subsequence; S6. Input the optimal subsequence into the prediction neural network to obtain the prediction result, and add the prediction results to obtain the wind speed prediction result of the super-capacity energy storage grid-connected.

2. The supercapacitor energy storage frequency modulation and grid-connected method based on the operation-modified VMD according to claim 1 is characterized in that: The number of the plurality of subsequences is an even number greater than or equal to 4.

3. The supercapacitor energy storage frequency modulation and grid-connected method based on the operation-modified VMD according to claim 1 is characterized in that: The method of the amplitude processing is: in, They are 1st, 2nd, 3rd, ..., k The amplitude representation of the subsequences, For the i The amplitude representation of the subsequences is is an element in the subsequence, For the i The amplitude of the subsequences is expressed in terms of angle, k is the number of subsequences, N is the number of elements in the subsequence, i is the intermediate variable, arccos() is the inverse cosine function, and ∠ represents the measure of the angle.

4. The supercapacitor energy storage frequency modulation and grid-connected method based on the operation-modified VMD according to claim 1 is characterized in that: The independent operations are: in, is an independent value, is the ith independent sequence, is an independent operation rule. is the amplitude representation of the 2i-1th subsequence, is the amplitude representation of the 2i-th subsequence, K is the number of subsequences, i is an intermediate variable.

5. The supercapacitor energy storage frequency modulation and grid-connected method based on the operation-modified VMD according to claim 4 is characterized in that: The independent operation rules are specifically: | |= in, For the i independent sequences, | |For the i The size of the independent sequence, For the 2nd i -1 subsequence, For the 2nd i -1 subsequence amplitude representation, For the 2nd i -1 element in the subsequence, For the 2nd i -1 subsequence of amplitudes representing angles, For the 2nd i subsequences, 2nd i The amplitude of the subsequence is represented by For the 2nd i elements in a subsequence, For the 2nd i The amplitude of each subsequence represents the angle.

6. The supercapacitor energy storage frequency modulation and grid connection method based on the operation-modified VMD according to claim 4 is characterized in that: The direction of the independent sequence is specifically represented as: Perpendicular to and The plane formed; When A 2i-1 >A 2i hour, Perpendicular to and The flat surface formed faces upward; When A 2i-1 <A 2i hour, Perpendicular to and The flat surface formed faces downward.

7. The supercapacitor energy storage frequency modulation and grid-connected method based on the operation-modified VMD according to claim 1 is characterized in that: The decomposition level of the incremental variational mode decomposition refers to the decomposition level plus 2.

8. A supercapacitor energy storage frequency modulation grid-connected system based on an operation-improved VMD, using the supercapacitor energy storage frequency modulation grid-connected method based on an operation-improved VMD as described in any one of claims 1 to 7, characterized in that: include: The variational mode decomposition sequence module is used to decompose the original wind speed time series into several subsequences using the variational mode decomposition method; An amplitude processing module is used to perform amplitude processing on each subsequence to obtain an amplitude representation of each subsequence; An independent operation module, used for calculating the amplitude representation forms of all subsequences through independent operation rules to obtain independent values; An increasing loop module is used to increase the number of decomposition layers of the variational mode decomposition and record the independent values ​​obtained in each loop until the number of decomposition layers of the variational mode decomposition reaches the maximum; The optimal subsequence obtaining module is used to compare and obtain the maximum independent value among all independent values, and take the subsequence corresponding to the maximum independent value as the optimal subsequence; The wind speed prediction result obtaining module is used to input the optimal subsequence into the prediction neural network for prediction to obtain the prediction result, and add the prediction results to obtain the wind speed prediction result of the super-capacity energy storage grid connection.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the supercapacitor energy storage frequency modulation and grid-connected method based on the operation-improved VMD described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the supercapacitor energy storage frequency modulation and grid-connected method based on the operation-improved VMD described in any one of claims 1 to 7 is implemented.

Images