A method and system for controlling energy storage frequency modulation commands

Abstract

The present invention relates to the technical field of energy storage frequency modulation control, and discloses an energy storage frequency modulation command control method and system. The method includes: obtaining an energy storage frequency modulation command and performing variational mode decomposition; calculating the equilibrium value of the sequence after variational mode decomposition, and generating a supplementary sequence according to the equilibrium value; obtaining a de-padding sequence by processing the supplementary sequence, and forming a new set of subsequences by adding the sequence after variational mode decomposition and the supplementary sequence corresponding to each other and then combining them with the de-padding sequence; respectively inputting the sequences in the new set of subsequences into a recurrent neural network to obtain the final control result of the energy storage frequency modulation command. The present invention solves the problems of large prediction difficulty and low accuracy caused by the too strong volatility of the frequency modulation command sequence in the prior art, not only significantly reduces the irregularity and volatility of the original sequence, making the result more accurate and reliable, but also can respond to the frequency modulation demand in advance and improve the instant response ability of the system.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage frequency modulation control, and particularly to a method and system for controlling energy storage frequency modulation commands. Background Art

[0002] In a power system, frequency regulation is a key link to ensure the stable operation of the power grid. Traditional thermal power units have a slow response speed and are difficult to quickly adapt to load changes and maintain the stability of the power grid frequency. To improve this situation, a hybrid energy storage system (such as a combination of supercapacitor and lithium battery) is usually used to assist the thermal power unit in frequency regulation. In this mode, the hybrid energy storage system is responsible for handling the difference between the frequency modulation command and the output of the thermal power unit. The high-frequency component is borne by the supercapacitor with a fast response speed, while the low-frequency component is handled by the lithium battery with a higher energy density. However, in the actual operation process, the transmission of signals (frequency modulation commands transmitted to the supercapacitor / lithium battery) takes time, and the supercapacitor or the lithium battery itself also takes time to respond, which will inevitably lead to time delay, not only affecting the immediate response ability of the system, but also having a negative impact on the economic benefits of the power plant.

[0003] To solve this problem, researchers have developed algorithms to predict the change trend of frequency modulation commands in advance, enabling the energy storage system to act in advance, thereby improving the effect and economic benefits of frequency regulation. One of the traditional control methods is to use variational mode decomposition (VMD) to decompose the original frequency modulation command sequence into multiple subsequences, and process these subsequences separately, and finally synthesize the processing results. Although this method can theoretically improve the processing accuracy, it is found in practice that the decomposed subsequences have very strong volatility, increasing the difficulty. Such highly volatile subsequences make it complex and inaccurate to control each subsequence individually, limiting the improvement of the overall performance, and at the same time failing to effectively solve the problem of response time delay of the energy storage system, thereby affecting the frequency regulation effect and economic benefits.

[0004] Therefore, there is an urgent need for a new control method to overcome the deficiencies in the prior art, that is, to be able to more effectively handle the high volatility problem of the frequency modulation command sequence, while reducing the response time delay and improving the frequency regulation ability and economic benefits of the entire energy storage system. Summary of the Invention

[0005] In view of the above existing problems, the present invention is proposed.

[0006] Therefore, the present invention provides a method and system for controlling energy storage frequency modulation commands to solve the problem that when the existing method processes the frequency modulation command sequence, the decomposed subsequences have very strong volatility, resulting in high complexity and inaccuracy in individually processing each subsequence, and failing to effectively solve the problem of response time delay of the energy storage system, thereby affecting the frequency regulation effect and economic benefits.

[0007] To solve the above technical problems, the present invention provides the following technical solutions:

[0008] In a first aspect, the present invention provides a method for controlling energy storage frequency modulation commands, including:

[0009] Obtain the energy storage frequency modulation command of the hybrid energy storage system and perform variational mode decomposition;

[0010] Calculate the balance value of the sequence after the variational mode decomposition, and generate an augmented sequence according to the balance value;

[0011] Obtain a de-padding sequence by processing the augmented sequence. After adding the sequence after the variational mode decomposition and the augmented sequence correspondingly, a new set of subsequences is formed with the de-padding sequence;

[0012] Input the sequences in the new set of subsequences into a recurrent neural network respectively to obtain the final control result of the energy storage frequency modulation command.

[0013] As a preferred solution of a method for controlling energy storage frequency modulation commands according to the present invention, wherein: the calculation of the balance value of the sequence after the variational mode decomposition includes:

[0014] Obtain the energy storage frequency modulation command, and the energy storage frequency modulation command is decomposed into IMF1, IMF2, IMF3,......, IMF i ,......, IMF K ;

[0015] Set a subsequence after variational mode decomposition as IMF i = [X i1 , X i2 , X i3 ,......, X ii ,......, X iN , where X ii and X iN respectively represent the i-th element and the N-th element in the subsequence after variational mode decomposition;

[0016] The average value of the subsequence after the variational mode decomposition is X iavg , the median value is X iz , the maximum value and the minimum value are X max and X min respectively, then the balance value of the subsequence IMF i after the variational mode decomposition is expressed as:

[0017] ,

[0018] Wherein, Denote the subsequence IMF after variational mode decomposition i 's balance value.

[0019] As a preferred solution of an energy storage frequency modulation command control method according to the present invention, wherein: the generating of the supplementary sequence includes:

[0020] Traverse a certain subsequence IMF that has undergone the variational mode decomposition i = [X i1 , X i2 , X i3 ,......, X ii ,......, X iN ;

[0021] If the value X ii > 5X ip , then generate the corresponding , and the formula is expressed as:

[0022] ,

[0023] If the value X ip < X ii < 5X ip or 0.2X ip <X ii <X ip , then generate the corresponding = 0;

[0024] If the value X ii <0.2X ip , then generate the corresponding , and the formula is expressed as:

[0025] ,

[0026] Generate the supplementary sequence IMF i of the subsequence IMF after the variational mode decomposition according to the above three cases i 、 = .

[0027] As a preferred solution of an energy storage frequency modulation command control method according to the present invention, wherein: the generating of the supplementary sequence further includes:

[0028] Obtain the supplementary sequences of all subsequences IMF1 i in turn according to the method for obtaining the supplementary sequence of the subsequence IMF after the variational mode decomposition 、 , IMF2 、 , IMF3 、 ,......, IMF i、 ,......,IMF K 、 。

[0029] As a preferred solution of a method for controlling energy storage frequency modulation commands according to the present invention, wherein: obtaining the de-padding sequence by processing the supplementary sequence includes:

[0030] Adding up the supplementary sequences of all subsequences, IMF1 、 +IMF2 、 +IMF3 、 +.......+IMF K 、 To obtain the de-padding sequence S q =[X q1 , X q2 , X q3 ,......, X qi ,......, X qN , where X qi and X qN respectively represent the i-th element and the N-th element in the de-padding sequence;

[0031] Taking (X q1 +X q2 +X q3 +......+X qi +......+X qN ) / N = 0 and a single value close to 0 as the target, continuously randomizing each value of all the supplementary sequences IMF1 、 , IMF2 、 , IMF3 、 ,......, IMF i 、 ,......, IMF K 、 and looping according to the set number of times to find the supplementary sequences IMF1 、 , IMF2 、 , IMF3 、 ,......, IMF i 、 ,......, IMF K 、 whose randomly processed values are closest to the target, where N represents the number of elements in the de-padding sequence;

[0032] The de-padding sequence after random processing is S qfit =[X qfit1 , X qfit2 , X qfit3,......,X qfiti ,......,X qfitN ,(X qfit1 +X qfit2 +X qfit3 +......+X qfiti +......,+X qfitN ) / N = A, where X qfiti and X qfitN respectively represent the i-th element and the N-th element in the de-padded sequence after random processing, and A represents the average value of the de-padded sequence.

[0033] As a preferred solution of a method for controlling energy storage frequency modulation commands according to the present invention, wherein: the obtaining of the de-padded sequence by processing the augmented sequence further includes:

[0034] If A > 6, then each value of the de-padded sequence needs to be fine-tuned, and the formula is expressed as:

[0035] ,

[0036] where represents the value of the element in the de-padded sequence after fine-tuning.

[0037] As a preferred solution of a method for controlling energy storage frequency modulation commands according to the present invention, wherein: the obtaining of the final control result of the energy storage frequency modulation command includes:

[0038] By calculating the balance values of the sequences IMF1, IMF2, IMF3,......, IMF i ,......, IMF K after variational mode decomposition to generate the augmented sequence IMF1 、 , IMF2 、 , IMF3 、 ,......, IMF i 、 ,......, IMF K 、 , adding the corresponding terms of the sequence after variational mode decomposition and the augmented sequence to obtain IMF1 + IMF1 、 , IMF2 + IMF2 、 ,......, IMF K + IMF K 、 ;

[0039] Adding the sequence after variational mode decomposition and the augmented sequence corresponding to each other and the de-padded sequence S after random processing qfitConstruct a new set of subsequences, input each sequence in the new set of subsequences into a recurrent neural network respectively, output the values of the corresponding unknown groups, and then add up the values of the unknown groups output corresponding to each subsequence to obtain the final control result of the energy storage frequency modulation command.

[0040] In a second aspect, the present invention provides an energy storage frequency modulation command control system, including:

[0041] An instruction decomposition module, configured to obtain the energy storage frequency modulation command of the hybrid energy storage system and perform variational mode decomposition;

[0042] A sequence processing module, configured to calculate the balance value of the sequence after the variational mode decomposition, generate a supplementary sequence according to the balance value; obtain a de-padding sequence by processing the supplementary sequence, and after adding the sequence after the variational mode decomposition and the supplementary sequence correspondingly, form a new set of subsequences with the de-padding sequence;

[0043] An instruction control module, configured to input the sequences in the new set of subsequences into a recurrent neural network respectively to obtain the final control result of the energy storage frequency modulation command.

[0044] In a third aspect, the present invention provides an electronic device, including:

[0045] A memory and a processor;

[0046] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of an energy storage frequency modulation command control method are implemented.

[0047] In a fourth aspect, the present invention provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, the steps of an energy storage frequency modulation command control method are implemented.

[0048] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention provides a control method and system for energy storage frequency modulation commands, aiming to solve the problems of high prediction difficulty and low accuracy caused by the excessive volatility of the frequency modulation command sequence in the prior art, and at the same time reduce the response delay to improve the frequency regulation effect and the economic benefits of power plants. The present invention processes the frequency modulation command sequence of the hybrid energy storage system through variational mode decomposition technology, effectively reducing the irregularity and volatility of the original sequence. By combining the supplementary sequence and de-padding processing to generate a new set of subsequences, and using a recurrent neural network to obtain the final control result, it not only significantly improves the prediction accuracy and response speed, reduces the prediction difficulty caused by the excessive volatility of the command sequence, but also realizes the early response to the frequency modulation demand, enhancing the stability and reliability of the power grid. In addition, the present invention greatly improves the economic benefits of power plants in frequency modulation, providing strong technical support for the development of smart grids. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0050] Figure 1 It is a schematic diagram of the overall process logic of the method described in an embodiment of the present invention.

[0051] Figure 2 It is a schematic diagram of the control process of the method described in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0052] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will give a detailed description of the specific embodiments of the present invention with reference to the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0053] Example 1, referring to Figure 1 - Figure 2This is an embodiment of the present invention. The traditional prediction method is to use, for example, VMD decomposition to divide the original sequence into a series of subsequences, then predict them separately, and finally superimpose the predicted results. The problem is that the decomposed subsequences have very strong volatility, and the prediction difficulty is still very high. Therefore, this embodiment proposes a control method for energy storage frequency modulation commands, which fills each sequence with strong volatility into a smooth and easy-to-predict sequence, and then forms a de-filled sequence, and then puts it into a neural network for prediction, aiming to solve the problems of large prediction difficulty and low accuracy caused by the too strong volatility of the frequency modulation command sequence in the prior art. As Figure 1 Specifically, it includes the following steps:

[0054] S100: Obtain the energy storage frequency modulation command of the hybrid energy storage system and perform variational mode decomposition;

[0055] S200: Calculate the balance value of the sequence after variational mode decomposition, and generate an augmented sequence according to the balance value;

[0056] S300: Obtain a de-filled sequence by processing the augmented sequence, and form a new set of subsequences by adding the sequence after variational mode decomposition and the augmented sequence corresponding to each other and then combining them with the de-filled sequence;

[0057] S400: Input the sequences in the new set of subsequences into a recurrent neural network respectively to obtain the final control result of the energy storage frequency modulation command.

[0058] It should be noted that the present invention provides a control method and system for energy storage frequency modulation commands, aiming to solve the problems of large prediction difficulty and low accuracy caused by the too strong volatility of the frequency modulation command sequence in the prior art, and at the same time reduce the response delay to improve the frequency regulation effect and the economic benefits of the power plant. The present invention processes the frequency modulation command sequence of the hybrid energy storage system through variational mode decomposition technology, effectively reducing the non-regularity and volatility of the original sequence, combining the augmented sequence and the de-filled processing to generate a new set of subsequences, and using a recurrent neural network to obtain the final control result, which not only significantly improves the prediction accuracy and response speed, reduces the prediction difficulty caused by the too strong volatility of the command sequence, but also realizes the early response to the frequency modulation demand, enhancing the stability and reliability of the power grid. In addition, the present invention greatly improves the economic benefits of the power plant in frequency modulation, providing strong technical support for the development of smart grids.

[0059] In the embodiment of the present invention, the above step S100 of obtaining the energy storage frequency modulation command of the hybrid energy storage system and performing variational mode decomposition includes:

[0060] Set the energy storage frequency modulation command to be expressed as Pt = [X1, X2, X3,......, X i ,......, X N ;

[0061] The energy storage frequency modulation instruction Pt is subjected to variational mode decomposition, and the sequence after variational mode decomposition is expressed as IMF1, IMF2, IMF3, ..., IMF K ;

[0062] It should be noted that the above step S100 uses variational mode decomposition to process the energy storage frequency modulation instructions, which can effectively extract the multi-scale features in the original instruction sequence, reduce its volatility and complexity, and provide more stable and easy-to-analyze sequence data for subsequent steps, thereby improving the accuracy and efficiency of the entire control process.

[0063] In the embodiment of the present invention, the above step S200 calculates the equilibrium value of the sequence after variational mode decomposition, and generates the supplementary sequence according to the equilibrium value, including:

[0064] Specifically, calculating the equilibrium value of the sequence after variational mode decomposition includes:

[0065] Set a subsequence after variational mode decomposition as IMF i =[X i1 ,X i2 ,X i3 ,......,X ii ,......,X iN ], where X ii and X iN Respectively represent the i-th element and the N-th element in the subsequence after variational mode decomposition;

[0066] The average value of the subsequence after variational mode decomposition is X iavg , the median value is X iz The maximum and minimum values ​​are X max and X min , then the subsequence IMF of variational mode decomposition is i The equilibrium value is expressed as:

[0067] ,

[0068] in, Represents the subsequence IMF after variational mode decomposition i The balance value.

[0069] Specifically, the steps of generating a supplementary sequence according to the balance value include:

[0070] Traverse a subsequence IMF after variational mode decomposition i =[X i1 ,X i2 ,X i3 ,......,X ii ,......,XiN ;

[0071] If the value of X ii > 5X ip , then generate the corresponding , and the formula is expressed as:

[0072] ,

[0073] If the value of X ip < X ii < 5X ip or 0.2X ip <X ii <X ip , then generate the corresponding = 0;

[0074] If the value of X ii <0.2X ip , then generate the corresponding , and the formula is expressed as:

[0075] ,

[0076] Generate the subsequence IMF of variational mode decomposition according to the above three cases i The supplementary sequence IMF of i 、 = , and obtain all the supplementary sequences IMF1 of the subsequences according to the method of obtaining the supplementary sequence of the subsequence IMF of variational mode decomposition i by analogy 、 , IMF2 、 , IMF3 、 ,......, IMF i 、 ,......, IMF K 、 .

[0077] It should be noted that the above step S200 generates the supplementary sequence by calculating the balance value of the sequence after variational mode decomposition, effectively reducing the volatility and non - regularity of the original frequency - modulation command sequence, making the subsequent processed de - padding sequence more stable, thereby improving the accuracy and reliability of the final result.

[0078] In the embodiment of the present invention, the above step S300 obtains the de - padding sequence by processing the supplementary sequence. The specific method of forming a new subsequence set by adding the sequence after variational mode decomposition and the supplementary sequence corresponding to each other and the de - padding sequence includes:

[0079] Add the supplementary sequences of all subsequences IMF1 、 + IMF2、 + IMF3 、 +.......+ IMF K 、 Obtain the depopulated sequence S q = [X q1 , X q2 , X q3 ,......, X qi ,......, X qN , where X qi and X qN represent the i-th element and the N-th element in the depopulated sequence respectively;

[0080] With the goal of (X q1 + X q2 + X q3 +......+ X qi +......+ X qN ) / N = 0 and each single value being close to 0, continuously randomize each value of all subsequence supplementary sequences IMF1 、 , IMF2 、 , IMF3 、 ,......, IMF i 、 ,......, IMF K 、 and loop according to the set number of times to find the supplementary sequence IMF1 of the randomly generated values that is closest to the target 、 , IMF2 、 , IMF3 、 ,......, IMF i 、 ,......, IMF K 、 , where N represents the number of elements in the depopulated sequence;

[0081] The depopulated sequence after random processing is S qfit = [X qfit1 , X qfit2 , X qfit3 ,......, X qfiti ,......, X qfitN , (X qfit1 + X qfit2 + X qfit3 +......+ X qfiti +......,+ X qfitN ) / N = A, where X qfiti and X qfitNrespectively represent the i-th element and the N-th element in the padded-removed sequence after random processing, and A represents the average value of the padded-removed sequence.

[0082] If A > 6, then each value in the padded-removed sequence needs to be fine-tuned, and the formula is expressed as:

[0083] ,

[0084] where, represents the value of the element in the padded-removed sequence after fine-tuning.

[0085] It should be noted that the above step S300 obtains the padded-removed sequence by processing the augmented sequence, and combines it with the sequence after variational mode decomposition and the augmented sequence to generate a new set of subsequences, effectively reducing the non-regularity and volatility of the original sequence, laying a foundation for accurately obtaining the energy storage frequency modulation instruction subsequently, and improving the accuracy and reliability of the result.

[0086] In the embodiment of the present invention, the above step S400 inputting the sequences in the new set of subsequences into the recurrent neural network respectively to obtain the final control result of the energy storage frequency modulation instruction specifically includes:

[0087] By calculating the balance values of the sequences IMF1, IMF2, IMF3,......, IMF i ,......, IMF K to generate the augmented sequences IMF1 、 , IMF2 、 , IMF3 、 ,......, IMF i 、 ,......, IMF K 、 , adding the corresponding terms of the sequence after variational mode decomposition and the augmented sequence to obtain IMF1 + IMF1 、 , IMF2 + IMF2 、 ,......, IMF K + IMF K 、 ;

[0088] Adding the corresponding terms of the sequence after variational mode decomposition and the augmented sequence and combining them with the padded-removed sequence S qfit after random processing to form a new set of subsequences, and inputting each sequence in the new set of subsequences into the recurrent neural network respectively, outputting the values of the corresponding unknown groups, and then adding the values of the unknown groups output corresponding to each subsequence to obtain the final control result of the energy storage frequency modulation instruction. The detailed process is as Figure 2 .

[0089] It should be noted that by inputting the new subsequence set into the recurrent neural network in the above step S400, the energy storage frequency modulation command can be accurately predicted, effectively reducing the prediction difficulty caused by the irregularity and volatility of the original sequence, improving the prediction accuracy and the immediate response ability of the system, thereby enhancing the stability and reliability of the power grid and improving the economic benefits of the power plant.

[0090] Example 2. Based on the previous example, this example provides an application example of an energy storage frequency modulation command control method and system to verify and illustrate the technical effects adopted in this method.

[0091] To further verify the advantages of the present invention, in this example, the energy storage frequency modulation command control method provided by the present invention and the control method of VMD-GRU are respectively used to process the frequency modulation sequence. The results are shown in Table 1, and the definitions of the four evaluation indexes are shown in Table 2.

[0092] Table 1: Results of processing the frequency modulation sequence by the method of the present invention and the control method of VMD-GRU

[0093]

[0094] Table 2: Four evaluation indexes

[0095]

[0096] Among them, represents the sample size, and respectively represent the actual value and the predicted value at time n.

[0097] From the above comparison results, it can be seen that the energy storage frequency modulation command control method provided by the present invention performs well in all four evaluation indexes, and its performance is better than that of the VMD-GRU control method.

[0098] Therefore, the present invention provides an energy storage frequency modulation command control method and system, aiming to solve the problems of large prediction difficulty and low accuracy caused by the too strong volatility of the frequency modulation command sequence in the prior art, and at the same time reduce the response delay to improve the frequency regulation effect and the economic benefits of the power plant. The present invention processes the frequency modulation command sequence of the hybrid energy storage system through the variational mode decomposition technology, effectively reducing the irregularity and volatility of the original sequence, combining the augmented sequence and the de-padding processing to generate a new subsequence set, and using the recurrent neural network to obtain the final control result, which not only significantly improves the prediction accuracy and response speed, reduces the prediction difficulty caused by the too strong volatility of the command sequence, but also realizes the early response to the frequency modulation demand, enhancing the stability and reliability of the power grid. In addition, the present invention greatly improves the economic benefits of the power plant in frequency modulation, providing strong technical support for the development of the smart grid.

[0099] Embodiment 3 provides an energy storage frequency modulation instruction control system, which includes an instruction decomposition module, a sequence processing module, and an instruction control module;

[0100] Specifically, the instruction decomposition module is used to obtain the energy storage frequency modulation instruction of the hybrid energy storage system and perform variational mode decomposition;

[0101] Specifically, the sequence processing module is used to calculate the balance value of the sequence after variational mode decomposition, generate an augmented sequence according to the balance value; obtain a de-padded sequence by processing the augmented sequence, and form a new set of subsequences by adding the sequence after variational mode decomposition and the augmented sequence corresponding to each other and then combining them with the de-padded sequence;

[0102] Specifically, the instruction control module is used to input the sequences in the new set of subsequences into the recurrent neural network respectively to obtain the final control result of the energy storage frequency modulation instruction.

[0103] It should be noted that the technical solution of this energy storage frequency modulation instruction control system belongs to the same concept as the technical solution of the above-mentioned energy storage frequency modulation instruction control method. For the details not described in detail in the technical solution of this energy storage frequency modulation instruction control system in this embodiment, reference can be made to the description of the technical solution of the above-mentioned energy storage frequency modulation instruction control method.

[0104] The above-mentioned each unit module can be embedded in the processor in the computer device in hardware form or be independent of the processor, or can be stored in the memory in the computer device in software form, so as to facilitate the processor to call and execute the operations corresponding to each above module.

[0105] This embodiment also provides an electronic device, which includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of this computer device is used to provide computing and control capabilities. The memory of this computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of this computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a carrier network, NFC (near field communication) or other technologies. The computer program, when executed by the processor, is used to implement an energy storage frequency modulation instruction control method. The display screen of this computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of this computer device can be a touch layer covered on the display screen, or can be a button, a trackball or a touchpad provided on the shell of the computer device, or can also be an external keyboard, a touchpad or a mouse, etc.

[0106] This embodiment also provides a computer-readable storage medium, on which a computer program is stored. When the program is executed by a processor, the method proposed in the above embodiment is implemented.

[0107] The storage medium proposed in this embodiment and the method proposed in the above embodiment belong to the same inventive concept. For the technical details not described in detail in this embodiment, reference can be made to the above embodiment, and this embodiment has the same beneficial effects as the above embodiment.

[0108] From the above description of the embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software and necessary general-purpose hardware. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a floppy disk, read-only memory (ROM), random access memory (RAM), flash memory (FLASH), hard disk, or optical disc of a computer, etc., including several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute the method of the embodiments of the present invention.

[0109] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

[0110] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented in various computer languages.

[0111] The present invention is described with reference to flowchart illustrations and / or block diagram illustrations of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each flow and / or block of the flowchart illustrations and / or block diagram illustrations, and combinations of flows and / or blocks in the flowchart illustrations and / or block diagram illustrations, can be implemented by computer program instructions. These computer program instructions may 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 executed by the processor of the computer or other programmable data processing apparatus create means for implementing the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 one or more blocks that specify the function.

[0112] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means that implement the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 one or more blocks that specify the function.

[0113] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in the flow Figure 1 one or more flows and / or blocks Figure 1 one or more blocks that specify the function.

[0114] Although the preferred embodiments of the present invention have been described, additional changes and modifications can be made by those skilled in the art once they learn of the basic inventive concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications that fall within the scope of the present invention.

[0115] It is apparent that those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention is also intended to include these modifications and variations.

Claims

1. A method for controlling energy storage frequency modulation instructions, characterized in that: include: Obtain the energy storage frequency modulation instructions of the hybrid energy storage system and perform variational mode decomposition; Calculating the equilibrium value of the sequence after the variational mode decomposition, and generating a supplementary sequence according to the equilibrium value; The calculation of the equilibrium value of the sequence after the variational mode decomposition includes: Obtain energy storage frequency modulation instructions, which are decomposed into ; Suppose a subsequence after variational mode decomposition is ,in, and Respectively represent the i-th element and the N-th element in the subsequence after variational mode decomposition; The average value of the subsequence after the variational mode decomposition is , the median value is , the maximum and minimum values ​​are and , then the subsequence of the variational mode decomposition is The equilibrium value is expressed as: in, Represents the subsequence after variational mode decomposition The balance value of Generating the supplementary sequence comprises: Traverse a subsequence that has undergone the variational mode decomposition ; If value , then the corresponding , the formula is: If value or , then the corresponding =0; If value , then the corresponding , the formula is: Generate the subsequence of the variational mode decomposition according to the above three situations Supplementary sequence ; Processing the supplemented sequence to obtain a defilled sequence, and adding the sequence after the variational mode decomposition and the supplemented sequence accordingly to form a new subsequence set with the defilled sequence; The sequences in the new subsequence set are respectively input into the recursive neural network to obtain the final control result of the energy storage frequency modulation instruction.

2. The energy storage frequency modulation instruction control method according to claim 1, characterized in that: Generating the supplementary sequence further comprises: According to the subsequence of the variational mode decomposition The method of obtaining the supplementary sequence of is similar to that of obtaining the supplementary sequence of all subsequences. .

3. A method for controlling energy storage frequency modulation instructions as claimed in claim 2, characterized in that: The obtaining of the defilled sequence by processing the supplemented sequence comprises: Add the complement of all subsequences together Get the defilled sequence ,in, and Respectively represent the i-th element and the N-th element in the defilled sequence; by The single value is close to 0 as the goal, and the supplementary sequence of all subsequences is continuously randomized. Each value of , and loops according to the set number of times, to find the random value supplement sequence that is closest to the target , where N represents the number of elements in the defilled sequence; The defilled sequence after random processing is: , ,in, and They respectively represent the i-th element and the N-th element in the de-filled sequence after random processing, and A represents the average value of the de-filled sequence.

4. The energy storage frequency modulation instruction control method according to claim 3, characterized in that: The obtaining of the defilled sequence by processing the supplemented sequence further comprises: If A>6, each value of the defilling sequence needs to be fine-tuned, and the formula is expressed as: in, Represents the fine-tuned value of the elements in the defilled sequence.

5. The energy storage frequency modulation instruction control method according to claim 4, characterized in that: The final control result of obtaining the energy storage frequency modulation instruction includes: By calculating the variational mode decomposition sequence The equilibrium value of the supplementary sequence is generated , add the corresponding terms of the variational mode decomposition sequence and the supplemented sequence to obtain ; The sequence after the variational mode decomposition and the supplemented sequence are added to the defilled sequence after random processing. A new subsequence set is formed, and each sequence in the new subsequence set is input into the recursive neural network respectively, and the value of the corresponding unknown group is output, and then the value of the unknown group corresponding to each subsequence output is added to obtain the final control result of the energy storage frequency modulation instruction.

6. An energy storage frequency modulation command control system, using the method according to any one of claims 1 to 5, characterized in that: include: An instruction decomposition module is used to obtain the energy storage frequency modulation instructions of the hybrid energy storage system and perform variational mode decomposition; A sequence processing module, used for calculating the equilibrium value of the sequence after the variational mode decomposition, generating a supplementary sequence according to the equilibrium value; obtaining a defilled sequence by processing the supplementary sequence, and forming a new subsequence set with the defilled sequence after adding the sequence after the variational mode decomposition and the supplementary sequence accordingly; The instruction control module is used to input the sequences in the new subsequence set into the recursive neural network respectively to obtain the final control result of the energy storage frequency modulation instruction.

7. An electronic device, comprising a memory and a processor, characterized in that: The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the computer-executable instructions are executed by the processor, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having computer-executable instructions stored thereon, characterized in that: When the computer executable instructions are executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images