A method, system, device and storage medium for capacitive energy storage frequency modulation control

Abstract

The application discloses a kind of capacitive energy storage frequency modulation control method, system, equipment and storage medium, first to the history sequence of frequency modulation instruction " compression ", similar point is combined as 1 point to result, then again to the position of vacancy inserts compensatory point, obtains new prediction sequence, and then obtains final prediction result, through the flow of disturbance→error calculation→compression determination, similar error corresponding frequency modulation instruction is identified and merged, reduces data redundancy, improves data utilization, while the length of compressed frequency modulation instruction sequence is shortened, when input to prediction model, reduce the amount of calculation, speed up response speed, more suitable for real-time requirement high frequency modulation scene, before calculating disturbance error, first calculate the reference error of undisturbed, provide reference for subsequent disturbance error, facilitate quantitative analysis the specific influence of disturbance on error.

Description

Technical Field

[0001] This invention belongs to the field of frequency modulation command prediction technology, specifically relating to a capacitor energy storage frequency modulation control method, system, device and storage medium. Background Technology

[0002] Frequency stability is a key indicator for ensuring the safe and reliable power supply of the power grid during power system operation. With the continuous increase in the installed capacity of new energy sources and the increasing volatility of power load, the frequency regulation capability of traditional thermal power units faces severe challenges. In order to improve the frequency regulation performance of the power grid, the technical solution of using hybrid energy storage systems (a combination of supercapacitors and lithium batteries) to assist the frequency regulation of thermal power units has been widely studied and applied.

[0003] The traditional method of using hybrid energy storage (supercapacitor + lithium battery) to assist the frequency regulation of thermal power units involves transmitting the difference between the frequency regulation command and the thermal power unit to the hybrid energy storage, with the battery handling the low-frequency portion and the supercapacitor handling the high-frequency portion.

[0004] However, signal transmission (frequency modulation command transmission to the supercapacitor / lithium battery) takes time, and the supercapacitor or lithium battery itself also needs time to respond. This will cause a certain response time difference, which will further affect the K value and thus the power plant's revenue. Summary of the Invention

[0005] The purpose of this invention is to provide a capacitor energy storage frequency modulation control method, system, device and storage medium to solve the technical problems of large error and low accuracy of existing frequency modulation prediction methods.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] A capacitor energy storage frequency modulation control method includes the following steps:

[0008] The frequency modulation commands in the frequency modulation command sequence are perturbed sequentially, and the prediction error is calculated for each command to obtain the prediction error sequence.

[0009] The prediction error sequence is traversed sequentially, and the compressibility between the two frequency modulation commands with the closest prediction error values ​​is determined.

[0010] If two frequency modulation commands can be compressed, assign a value to the frequency modulation command that comes first in the sequence and replace the frequency modulation command that comes last in the sequence to obtain a new frequency modulation command sequence.

[0011] The new frequency modulation command sequence is input into the frequency modulation command prediction model for prediction.

[0012] Furthermore, the step of sequentially perturbing the frequency modulation commands in the frequency modulation command sequence, calculating the prediction error respectively, and obtaining the prediction error sequence is as follows:

[0013] Starting from the first frequency modulation command in the frequency modulation command sequence and ending at the last frequency modulation command in the frequency modulation command sequence, a perturbation is given to each frequency modulation command in the frequency modulation command sequence, and the perturbations of the remaining frequency modulation commands in the frequency modulation command sequence are removed. After each frequency modulation command is perturbed, the prediction error is calculated once.

[0014] The prediction error sequence is obtained by collecting all the prediction errors.

[0015] Furthermore, the range of the disturbance is [sin(z),exp(z)].

[0016] Furthermore, before calculating the prediction error, the prediction error is first calculated on the original frequency modulation command sequence by perturbing the frequency modulation commands in the frequency modulation command sequence.

[0017] Furthermore, the prediction error is expressed as mean absolute percentage error, and the formula for calculating mean absolute percentage error is as follows:

[0018]

[0019] in, This is the actual value. is the predicted value, n is the number of data points, and MAPE is the mean absolute percentage error.

[0020] Furthermore, the compressibility between the two frequency modulation commands with the closest prediction error values ​​is determined using a compressibility judgment formula. The compressibility judgment formula is as follows:

[0021]

[0022] In the formula, Indicates the compressed value. At that time, the two frequency modulation commands are compressed. , This indicates the frequency modulation command value after the disturbance is applied. Frequency modulation command value The corresponding prediction error, Indicates frequency modulation command value The corresponding prediction error, For the prediction error sequence and The closest prediction error.

[0023] Furthermore, the frequency modulation instruction preceding the sequence is assigned the following value:

[0024]

[0025] The replacement value for the later-ordered frequency modulation commands is:

[0026] .

[0027] Secondly, the present invention provides a capacitor energy storage frequency modulation control system, comprising a calculation module, a judgment module, an assignment and replacement module, and a prediction output module, wherein:

[0028] Calculation module: used to sequentially apply perturbations to the frequency modulation commands in the frequency modulation command sequence, calculate the prediction error for each command, and obtain the prediction error sequence;

[0029] Judgment module: used to sequentially traverse the prediction error sequence and judge the compressibility between the two frequency modulation commands with the closest prediction error values;

[0030] Assignment and replacement module: If two frequency modulation instructions can be compressed, assign a value to the frequency modulation instruction that comes first in the sequence and replace the frequency modulation instruction that comes last in the sequence to obtain a new frequency modulation instruction sequence;

[0031] Prediction output module: Used to input new frequency modulation command sequences into the frequency modulation command prediction model for prediction.

[0032] Thirdly, a terminal device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described method.

[0033] Fourthly, a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method.

[0034] Compared with the prior art, the present invention has the following beneficial technical effects:

[0035] This invention discloses a capacitor energy storage frequency modulation control method. First, the historical sequence of frequency modulation commands is "compressed" by merging points with similar results into one point. Then, filler points are inserted at the missing positions to obtain a new prediction sequence, which in turn yields the final prediction result. Through the process of disturbance → error calculation → compression judgment, frequency modulation commands corresponding to similar errors are identified and merged, reducing data redundancy and improving data utilization. At the same time, the length of the compressed frequency modulation command sequence is shortened, reducing the amount of calculation when input to the prediction model and speeding up the response, making it more suitable for frequency modulation scenarios with high real-time requirements.

[0036] Preferably, only a single instruction is perturbed at a time, and other perturbations are removed, to ensure that the error calculation only reflects the independent effect of the current instruction and avoids error confusion caused by the superposition of multiple perturbations.

[0037] Preferably, the unperturbed baseline error is calculated first to provide a reference for subsequent perturbation errors, which facilitates quantitative analysis of the specific impact of perturbation on the error. Attached Figure Description

[0038] Figure 1 This is a flowchart of a capacitor energy storage frequency modulation control method in an embodiment of the present invention. Detailed Implementation

[0039] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0040] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0041] In the description of this invention, it should be understood that the terms "comprising" and "including" indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0042] It should also be understood that the terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to limit the invention. As used in this specification and the appended claims, unless the context clearly indicates otherwise, the singular forms “a,” “an,” and “the” are intended to include the plural forms.

[0043] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0044] The core control logic of traditional hybrid energy storage (supercapacitor + lithium battery) assisted frequency regulation methods for thermal power units is to transmit the difference between the frequency regulation command and the actual output of the thermal power unit to the hybrid energy storage system. Efficient frequency regulation is achieved by rationally allocating the workload of the supercapacitor and the lithium battery. Specifically, the lithium battery handles the low-frequency frequency regulation, while the supercapacitor is responsible for the high-frequency frequency regulation. This division of labor theoretically leverages the advantages of both energy storage components: lithium batteries have high energy density, suitable for handling low-frequency, high-capacity energy exchange; supercapacitors have high power density and fast response speed, suitable for dealing with high-frequency, instantaneous power fluctuations.

[0045] However, in practical applications, this method reveals a significant drawback: both signal transmission and the response of the energy storage element itself require a certain amount of time. On the one hand, there is a time delay between the generation of the frequency modulation command and its transmission to the control systems of the supercapacitor and lithium battery; on the other hand, after receiving the command, the electrochemical reactions or physical processes within the supercapacitor and lithium battery also require time to complete the release or storage of energy, thereby adjusting the output power.

[0046] This time delay causes a significant time lag in the response of hybrid energy storage systems to frequency regulation commands. In the frequency regulation performance evaluation indicators of power systems, the K-value is a crucial parameter, comprehensively reflecting key performance indicators such as the response speed and regulation accuracy of the frequency regulation system. The existence of a response time lag directly leads to a decrease in the K-value, thereby affecting the power plant's revenue in the frequency regulation service market. Specifically, a power plant's frequency regulation revenue is typically linked to the K-value; a lower K-value indicates poorer frequency regulation performance, and consequently, reduced revenue.

[0047] The present invention will now be described in further detail with reference to the accompanying drawings:

[0048] like Figure 1 As shown, a capacitor energy storage frequency modulation control method includes the following steps:

[0049] Step 1: Perturb the frequency modulation commands in the frequency modulation command sequence one by one, calculate the prediction error for each command, and obtain the prediction error sequence.

[0050] Before perturbing the frequency modulation commands in the frequency modulation command sequence, the prediction error of the original frequency modulation command sequence is calculated first. Using this error as a benchmark, the prediction error calculated after perturbing the frequency modulation commands in the frequency modulation command sequence should be less than the original prediction error. By first calculating the unperturbed benchmark error, a reference is provided for the subsequent perturbation error, which facilitates the quantitative analysis of the specific impact of the perturbation on the error.

[0051] The steps to obtain the prediction error sequence are as follows:

[0052] The frequency modulation command sequence is divided into a training set and a validation set;

[0053] The first frequency modulation command in the training set is perturbed, while the remaining frequency modulation commands remain unchanged. The corresponding prediction error is then calculated.

[0054] Starting with the first frequency modulation command in the training set, perturbations are sequentially applied to the frequency modulation commands in the training set, while the remaining frequency modulation commands remain unchanged. The corresponding prediction errors are then calculated.

[0055] The prediction error sequence is obtained by collecting all the prediction errors.

[0056] When a perturbation is given to a frequency modulation command, the perturbations of the remaining frequency modulation commands in the frequency modulation command sequence are cleared.

[0057] Step 2: Iterate through the prediction error sequence in sequence and determine the compressibility between the two frequency modulation commands with the closest prediction error values.

[0058] Specifically, the prediction error is obtained by first adding a disturbance to the first frequency modulation command in the frequency modulation command sequence. As a benchmark, find the comparison with The frequency modulation command corresponding to the closest prediction error is used to determine the compressibility between the first frequency modulation command in the frequency modulation command sequence and this command:

[0059] The formula for judging compressibility is:

[0060]

[0061] In the formula, Indicates the compressed value. At that time, the two frequency modulation commands are compressed. , This indicates the frequency modulation command value after the disturbance is applied. Frequency modulation command value The corresponding prediction error, Indicates frequency modulation command value The corresponding prediction error, For the prediction error sequence and The closest prediction error.

[0062] Step 3: If the two frequency modulation commands can be compressed, assign a value to the frequency modulation command that comes first in the sequence and replace the frequency modulation command that comes last in the sequence to obtain a new frequency modulation command sequence.

[0063] Step four: Input the new frequency modulation command sequence into the frequency modulation command prediction model for prediction.

[0064] This invention discloses a capacitor energy storage frequency modulation control method. First, the historical sequence of frequency modulation commands is "compressed" by merging points with similar results into one point. Then, filler points are inserted at the missing positions to obtain a new prediction sequence, which in turn yields the final prediction result. Through the process of disturbance → error calculation → compression judgment, frequency modulation commands corresponding to similar errors are identified and merged, reducing data redundancy and improving data utilization. At the same time, the length of the compressed frequency modulation command sequence is shortened, reducing the amount of calculation when input to the prediction model and speeding up the response, making it more suitable for frequency modulation scenarios with high real-time requirements.

[0065] In another embodiment of the present invention, a capacitor energy storage frequency modulation control method is provided, comprising the following steps:

[0066] Step 1: Perturb the frequency modulation commands in the frequency modulation command sequence one by one, calculate the prediction error for each command, and obtain the prediction error sequence.

[0067] Before perturbing the frequency modulation commands in the frequency modulation command sequence, the prediction error of the original frequency modulation command sequence is calculated first. Using this error as a benchmark, the prediction error calculated after perturbing the frequency modulation commands in the frequency modulation command sequence should be less than the original prediction error.

[0068] All prediction errors involved in this invention use the mean absolute percentage error (MASE), and the formula for calculating the mean absolute percentage error is as follows:

[0069]

[0070] in, This is the actual value. is the predicted value, n is the number of data points, and MAPE is the mean absolute percentage error.

[0071] The steps to obtain the prediction error sequence are as follows:

[0072] The frequency modulation command sequence is divided into a training set and a validation set;

[0073] The first frequency modulation command in the training set is perturbed, while the remaining frequency modulation commands remain unchanged. The corresponding prediction error is then calculated.

[0074] Starting with the first frequency modulation command in the training set, perturbations are sequentially applied to the frequency modulation commands in the training set, while the remaining frequency modulation commands remain unchanged. The corresponding prediction errors are then calculated.

[0075] The prediction error sequence is obtained by collecting all the prediction errors.

[0076] When a perturbation is given to a frequency modulation command, the perturbations of the remaining frequency modulation commands in the frequency modulation command sequence are cleared.

[0077] Add perturbations to a single instruction at a time and remove other perturbations to ensure that error calculations only reflect the independent impact of the current instruction and avoid error confusion caused by the superposition of multiple perturbations.

[0078] Step 2: Iterate through the prediction error sequence in sequence and determine the compressibility between the two frequency modulation commands with the closest prediction error values.

[0079] The prediction error obtained by adding a disturbance to the first frequency modulation command in the frequency modulation command sequence As a benchmark, find the comparison with The frequency modulation command corresponding to the closest prediction error is used to determine the compressibility between the first frequency modulation command in the frequency modulation command sequence and this command:

[0080] The formula for judging compressibility is:

[0081]

[0082] In the formula, This represents the compressed value (j > i). Indicates prediction error The corresponding frequency modulation command value after the disturbance is applied. Indicates and closest error The corresponding frequency modulation command value after the disturbance is applied;

[0083] The condition for compression between two frequency modulation commands is that the compression value is greater than 0.07.

[0084] Step 3: If the two frequency modulation commands can be compressed, assign a value to the frequency modulation command that comes first in the sequence and replace the frequency modulation command that comes last in the sequence to obtain a new frequency modulation command sequence.

[0085] The frequency modulation instruction at the beginning of the sequence is assigned the following value:

[0086]

[0087] The replacement value for the later-ordered frequency modulation commands is:

[0088] .

[0089] Step four: Input the new frequency modulation command sequence into the frequency modulation command prediction model for prediction.

[0090] In another embodiment of the present invention, a capacitor energy storage frequency modulation control method is provided, wherein the frequency modulation command is P. t =[X1,X2,X3,X4,...,X N The length of the preceding part is 0.9N[X1,X2,X3,X4,...,X] 0.9NThe sequence of ] is used as input to predict the experimental group [X]. 0.9N+1 ,X 0.9N+2 ,X 0.9N+3 ,...,X N ] and the unknown group [X N+1 ,X N+2 ,X N+3 ,...,X N+0.1N The value of ] is used to generate all subsequent errors, where the actual and predicted values ​​of the experimental group are used. This invention actually predicts the value of the unknown group.

[0091] First, let [X1,X2,X3,...,X] 0.9N The data is fed into a GRU network for prediction, and the error value (MAPE) W of the experimental group is obtained. Next, let X1 = X1 + δ1, δ1 ∈ [sin(1), exp(1)], and let [X1 + δ1, X2, X3....., X 0.9N The data is fed into a GRU network for prediction, and the error value (MAPE) W1 of the experimental group is obtained. Next, X1 is restored, and X2 = X2 + δ2, δ2 ∈ [sin(2), exp(2)]. The [X1, X2 + δ2, X3....., X 0.9N The data is fed into a GRU network for prediction, and the error value (MAPE) W2 of the experimental group is obtained. This process is repeated until an error W is generated. 0.9N .

[0092] First, in the error sequence [W2, W3, ..., W...] 0.9N Find the error W that is closest to W1 in the [reference]. i The corresponding value X i Now for X1 and X i The compressibility between them is determined, and the determination process is as follows:

[0093]

[0094] If this value is greater than 0.07, then X1 and X i The space between them can be compressed, at which point let , and then =0.

[0095] Next, in the error sequence [W3, W4, ..., W...] 0.9N Find the error W that is closest to W2 in the [reference]. j The corresponding value X j (If j=i, then skip this search). Now, for X2 and X... j The compressibility between them is determined, and the determination process is as follows:

[0096]

[0097] If this value is greater than 0.07, then X2 and X j The space between them can be compressed, at which point let Then, let =0.

[0098] Repeatedly, reading through all [X1,X2,X3,X4,...,X] 0.9N Find all values ​​that can be compressed.

[0099] For values ​​already assigned 0, a substitution conversion is performed using the following formula:

[0100]

[0101] Finally, the replaced sequence is fed into the GRU prediction.

[0102] In another embodiment of the present invention, a capacitor energy storage frequency modulation control system is provided, comprising a calculation module, a judgment module, an assignment and replacement module, and a prediction output module, wherein:

[0103] Calculation module: used to sequentially apply perturbations to the frequency modulation commands in the frequency modulation command sequence, calculate the prediction error for each command, and obtain the prediction error sequence;

[0104] Judgment module: used to sequentially traverse the prediction error sequence and judge the compressibility between the two frequency modulation commands with the closest prediction error values;

[0105] Assignment and replacement module: If two frequency modulation instructions can be compressed, assign a value to the frequency modulation instruction that comes first in the sequence and replace the frequency modulation instruction that comes last in the sequence to obtain a new frequency modulation instruction sequence;

[0106] Prediction output module: Used to input new frequency modulation command sequences into the frequency modulation command prediction model for prediction.

[0107] Specifically, the frequency modulation commands in the frequency modulation command sequence are perturbed sequentially, and the prediction error is calculated. Before obtaining the prediction error sequence, the data is preprocessed, and the training set and test set are divided. The working process of the calculation module is as follows:

[0108] Starting with the first frequency modulation command in the frequency modulation command sequence, perturbations are applied to the frequency modulation commands sequentially, and the corresponding prediction errors are calculated.

[0109] When a frequency modulation command is given a disturbance, the disturbances of the remaining frequency modulation commands in the frequency modulation command sequence are cleared.

[0110] The prediction error sequence is obtained by collecting all the prediction errors.

[0111] The prediction error obtained by adding a disturbance to the first frequency modulation command in the frequency modulation command sequence in the judgment module As a benchmark, find the comparison with The frequency modulation command corresponding to the closest prediction error is used to determine the compressibility between the first frequency modulation command in the frequency modulation command sequence and this command:

[0112] The formula for judging compressibility is:

[0113]

[0114] In the formula, This represents the compressed value (j > i). Indicates prediction error The corresponding frequency modulation command value after the disturbance is applied. Indicates and closest error The corresponding frequency modulation command value after perturbation is given. If the compression condition between two frequency modulation commands is that the compression value is greater than 0.07, then the two frequency modulation commands are compressed.

[0115] The principle of the assignment and replacement module is to assign a value to the frequency modulation instruction that comes first in the sequence of two frequency modulation instructions, and replace the frequency modulation instruction that comes later in the sequence to obtain a new frequency modulation instruction sequence.

[0116] The new frequency modulation command sequence is input into the frequency modulation command prediction model for training, and the frequency modulation command is predicted through the prediction output module.

[0117] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0118] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0119] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0120] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0121] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit its scope of protection. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that after reading the present invention, they can still make various changes, modifications or equivalent substitutions to the specific implementation of the invention, but these changes, modifications or equivalent substitutions are all within the scope of protection of the pending claims of the invention.

Claims

1. A capacitor energy storage frequency modulation control method, characterized in that, Includes the following steps: The frequency modulation commands in the frequency modulation command sequence are perturbed sequentially, and the prediction error is calculated for each command to obtain the prediction error sequence. The prediction error sequence is traversed sequentially, and the compressibility between the two frequency modulation commands with the closest prediction error values ​​is determined. If two frequency modulation commands can be compressed, assign a value to the frequency modulation command that comes first in the sequence and replace the frequency modulation command that comes last in the sequence to obtain a new frequency modulation command sequence. The new frequency modulation command sequence is input into the frequency modulation command prediction model for prediction.

2. The capacitor energy storage frequency modulation control method according to claim 1, characterized in that, The steps of sequentially perturbing the frequency modulation commands in the frequency modulation command sequence, calculating the prediction error respectively, and obtaining the prediction error sequence are as follows: Starting from the first frequency modulation command in the frequency modulation command sequence and ending at the last frequency modulation command in the frequency modulation command sequence, a perturbation is given to each frequency modulation command in the frequency modulation command sequence, and the perturbations of the remaining frequency modulation commands in the frequency modulation command sequence are removed. After each frequency modulation command is perturbed, the prediction error is calculated once. The prediction error sequence is obtained by collecting all the prediction errors.

3. The capacitor energy storage frequency modulation control method according to claim 2, characterized in that, The range of values ​​for the disturbance is [sin(z),exp(z)].

4. The capacitor energy storage frequency modulation control method according to claim 1, characterized in that, Before calculating the prediction error, the prediction error is first calculated on the original frequency modulation command sequence, by perturbing the frequency modulation commands in the frequency modulation command sequence.

5. A capacitor energy storage frequency modulation control method according to claim 1 or 4, characterized in that, The prediction error is expressed as mean absolute percentage error, and the formula for calculating mean absolute percentage error is: in, This is the actual value. is the predicted value, n is the number of data points, and MAPE is the mean absolute percentage error.

6. The capacitor energy storage frequency modulation control method according to claim 1, characterized in that, The compressibility between the two frequency modulation commands with the closest prediction error values ​​is determined using a compressibility judgment formula, which is as follows: In the formula, Indicates the compressed value. At that time, the two frequency modulation commands are compressed. , This indicates the frequency modulation command value after the disturbance is applied. Frequency modulation command value The corresponding prediction error, Indicates frequency modulation command value The corresponding prediction error, For the prediction error sequence and The closest prediction error.

7. The capacitor energy storage frequency modulation control method according to claim 1, characterized in that, The frequency modulation command at the beginning of the sequence is assigned the following value: The replacement value for the later-ordered frequency modulation commands is: 。 8. A capacitor energy storage frequency modulation control system, characterized in that, The capacitor energy storage frequency modulation control method according to any one of claims 1-7 includes a calculation module, a judgment module, an assignment and replacement module, and a prediction output module, wherein: Calculation module: used to sequentially apply perturbations to the frequency modulation commands in the frequency modulation command sequence, calculate the prediction error for each command, and obtain the prediction error sequence; Judgment module: used to sequentially traverse the prediction error sequence and judge the compressibility between the two frequency modulation commands with the closest prediction error values; Assignment and replacement module: If two frequency modulation instructions can be compressed, assign a value to the frequency modulation instruction that comes first in the sequence and replace the frequency modulation instruction that comes last in the sequence to obtain a new frequency modulation instruction sequence; Prediction output module: Used to input new frequency modulation command sequences into the frequency modulation command prediction model for prediction.

9. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1-7.

Images