Energy storage frequency modulation control method and system of super capacitor coupling lithium battery

Abstract

The invention discloses an energy storage frequency modulation control method and system for a super capacitor coupled lithium battery, and belongs to the technical field of energy storage and frequency modulation control, and the method comprises the steps: collecting data from an original frequency modulation instruction sequence, generating a substitution sequence through a search method, and generating a regular optimal substitution sequence through positive, negative and comprehensive optimization; training a GRU model by using the optimal substitution sequence, and optimizing hyper-parameters of a GRU neural network through an improved whale optimization algorithm; and inputting the optimal substitution sequence into the optimized GRU model to generate a preliminary prediction result, and correcting the prediction result in combination with the deviation between the prediction residual error and the original data to obtain a final prediction result. According to the method, prediction errors are remarkably reduced, the prediction precision of the frequency modulation control system is improved, the local optimum problem is effectively avoided, the globality of the optimization process is improved, and it is ensured that the generated optimal sequence has higher quality; the whale optimization algorithm is improved, the algorithm convergence efficiency is remarkably improved, and falling into a local optimal solution is avoided.

Description

Technical Field

[0001] The present invention relates to the technical field of energy storage and frequency modulation control, and particularly relates to a method and system for energy storage frequency modulation control of a supercapacitor coupled with a lithium battery. Background Art

[0002] In the traditional frequency modulation method of hybrid energy storage (supercapacitor + lithium battery) assisting a thermal power unit, the difference between the frequency modulation command and the thermal power unit is transmitted to the hybrid energy storage. However, the transmission of the signal (transmission of the frequency modulation command to the supercapacitor / lithium battery) takes time, and the supercapacitor or the lithium battery itself also takes time to respond, which will cause a certain response time difference. This not only affects the real-time performance of frequency modulation control, further affects the revenue value, and further affects the revenue of the power plant. For this reason, the present invention proposes a prediction method to predict the magnitude of the frequency modulation command in advance, enabling the supercapacitor / battery to act in advance to increase the revenue value.

[0003] Traditional prediction methods often directly put the original sequence into a neural network for prediction and directly obtain the prediction result. However, because the original sequence has nonlinearity and non-regularity, such a prediction method has a large prediction error, cannot meet the load demand in real time, and the prediction result has a large error, making it difficult to guarantee the economic benefits of the power plant. For this reason, the present invention proposes a prediction method of a search method. Summary of the Invention

[0004] In view of the above existing problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: the existing frequency modulation control method of the hybrid energy storage system has response delay, low prediction accuracy, reduced system revenue, and how to achieve higher-precision frequency modulation prediction and faster response by optimizing the prediction method and improving the algorithm.

[0006] To solve the above technical problems, the present invention provides the following technical solution: a method for energy storage frequency modulation control of a supercapacitor coupled with a lithium battery, which includes the following steps. Collect data from the original frequency modulation command sequence, generate an alternative sequence using the search method, and generate a regular optimal alternative sequence through forward, negative, and comprehensive optimization; train a GRU (Gated Recurrent Unit, a variant of the recurrent neural network) model using the optimal alternative sequence, and optimize the hyperparameters of the GRU neural network based on the training result through an improved whale optimization algorithm; input the optimal alternative sequence into the optimized GRU model to generate a preliminary prediction result, and correct the prediction result by combining the deviation between the prediction residual and the original data to obtain the final prediction result.

[0007] As a preferred solution of a method for energy storage frequency modulation control of a supercapacitor coupled with a lithium battery according to the present invention, wherein: the data collection includes Set the original frequency modulation sequence as , with a pre - length of ; Take the sequence of the pre - length as the input, and predict the value of the pre - test group and the value of the predicted unknown group ; Among them, collect all the errors generated by the actual value and the predicted value of the test group, is the sequence length, and i is the variable index.

[0008] As a preferred solution of a super - capacitor - coupled lithium - battery energy - storage frequency - modulation control method described in the present invention, wherein: the generation of the regular optimal alternative sequence includes generating a regular optimal alternative sequence from the original frequency modulation sequence by a search method; Randomly generate 90 groups of alternative sequences , let be any one of the first 30 groups of sequences for forward search, and substitute it into the forward search formula to obtain the random range of the i - th value of the current sequence. The forward search formula is as follows: , to is set as the middle sequence. At the same time, there are forward search and backward search. Let be any one of the sequences located in to and substitute it into the mixed - direction search formula to obtain the random range of the i - th value of the sequence. The mixed - direction search formula is as follows: , Let be any one of the last 30 groups of sequences for backward search, and substitute it into the forward search formula to obtain the random range of the i - th value of the current sequence. The backward search formula is as follows: , Among them, W is the error of the test group generated by , is the i - th value of the original frequency modulation instruction sequence, is the random range of the i - th value of the j - th group of alternative sequences. i and j are variable indexes, is the reference adjustment value of is a dynamic amplification factor, which adjusts the upper bound of the search range through the linear combination of the group number j and the error W; w is the weight parameter corresponding to the error, is the natural constant, is the dynamic contraction factor used to control the lower bound of the backward search range.

[0009] As a preferred solution of the energy storage frequency modulation control method for a supercapacitor-coupled lithium battery according to the present invention, wherein: the generation of the regular optimal substitution sequence further includes re-optimizing the generated sequence; Set the substitution sequence The error generated by the test group is ; When the error generated during the forward search reaches the error generated by the test group, the corresponding sequence at this time is , and the corresponding error is ; When the error generated during the mixed search reaches the error generated by the test group, the corresponding sequence at this time is The corresponding error is ; When the error generated during the negative search reaches the error generated by the test group, the corresponding sequence at this time is The corresponding error is ; Substitute the obtained , , into the following optimization formula to obtain the optimal substitution sequence , and the optimization formula is as follows: , wherein, , , are the minimum error values under the forward, mixed, and negative search strategies respectively, , , are the sequence values generated by different search strategies respectively, is the error correction term, is the error value corresponding to the i-th position.

[0010] As a preferred solution of the energy storage frequency modulation control method for a supercapacitor-coupled lithium battery according to the present invention, wherein: the improved whale optimization algorithm includes a first optimization and a second optimization; The first optimization is specifically to optimize the hyperparameters of the GRU neural network and improve the convergence factor using a non-linear decreasing strategy; Balance the global search and local search capabilities of the high whale optimization algorithm, and the convergence factor The improvement formula is as follows: , wherein, represents the maximum number of iterations of the whale algorithm, t is the current iteration number, represents the activation function; The improved whale optimization algorithm is used to optimize the hyperparameters of the GRU neural network, and the optimization formula is as follows: , where, represents the new hyperparameter combination, represents the optimal hyperparameter combination, represents the previous particle position, represents a random number.

[0011] As a preferred solution of the energy storage frequency modulation control method of the supercapacitor-coupled lithium battery described in the present invention, wherein: the second optimization includes optimizing the hyperparameters of the GRU neural network, setting the learning rate and the number of hidden layer neurons of the GRU neural network as the attributes of the search particles in the space, and taking the output error minimization as the objective function.

[0012] As a preferred solution of the energy storage frequency modulation control method of the supercapacitor-coupled lithium battery described in the present invention, wherein: the final prediction result includes inputting the optimal alternative sequence into the optimized GRU model; Using the improved whale optimization algorithm to make a prediction through the optimal alternative sequence, and the prediction result is ; Using the improved whale optimization algorithm to make a prediction through the difference sequence between the optimal alternative sequence and the original sequence, and the prediction result is ; Calculating the final prediction result based on the correlation of the two prediction results, wherein the correlation calculation is: , The final prediction result is ; wherein, represents the generated optimal alternative sequence, is the preliminary prediction value obtained by making a prediction, represents the difference prediction value obtained by using the improved whale optimization algorithm to make a prediction on the difference sequence between the optimal alternative sequence and the original sequence, is the sine function, and the input is π(N + i), which is used to introduce periodic correction.

[0013] Another object of the present invention is to provide an energy storage frequency modulation control system for a supercapacitor-coupled lithium battery.

[0014] To solve the above technical problems, the present invention provides the following technical solutions: an energy storage frequency modulation control system for a supercapacitor-coupled lithium battery, including an acquisition and adjustment module, an algorithm optimization module, and a prediction and correction module; The acquisition and adjustment module collects data from the original frequency modulation instruction sequence, generates an alternative sequence using a search method, and generates a regular optimal alternative sequence through positive, negative, and comprehensive optimization; The algorithm optimization module trains a GRU model using the optimal alternative sequence. Based on the training results, it optimizes the hyperparameters of the GRU neural network through an improved whale optimization algorithm; The prediction correction module inputs the optimal alternative sequence into the optimized GRU model to generate a preliminary prediction result, and modifies the prediction result by combining the deviation between the prediction residual and the original data to obtain the final prediction result.

[0015] The present invention provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the energy storage frequency modulation control method of a supercapacitor-coupled lithium battery are implemented.

[0016] The present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the energy storage frequency modulation control method of a supercapacitor-coupled lithium battery are implemented.

[0017] The beneficial effects of the present invention: The energy storage frequency modulation method of the supercapacitor-coupled lithium battery provided by the present invention uses a search method to generate an optimal alternative sequence, significantly reducing the prediction error and improving the prediction accuracy of the frequency modulation control system. In addition, by optimizing the sequence generation method, the system can more effectively respond to changes in frequency modulation instructions in advance, thereby improving the real-time performance of frequency modulation response and maximizing the economic benefits of the power plant.

[0018] Through positive, negative, and comprehensive optimization search of random sequences, the problem of local optimum is effectively avoided, the global nature of the optimization process is improved, ensuring that the generated optimal sequence has higher quality, enhancing the regularity of the sequence, reducing the non-linear interference of the prediction algorithm, and ensuring higher prediction accuracy.

[0019] The improved whale optimization algorithm significantly improves the algorithm convergence efficiency and model training effect, avoiding falling into local optimal solutions. The GRU neural network optimized by IWOA (whale optimization algorithm) improves the performance of energy storage frequency modulation control. The prediction error correction method reduces error accumulation and the risk of falling into local optimal solutions, enhancing the stability of the execution effect. The present invention achieves better results in terms of frequency modulation prediction accuracy, response efficiency, and power plant economic benefits. Description of the Drawings

[0020] To more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0021] Figure 1 It is the overall flowchart of an energy storage frequency modulation method for a supercapacitor-coupled lithium battery provided by the first embodiment of the present invention. Specific embodiments

[0022] To make the above objects, features, and advantages of the present invention more obvious and understandable, the following will describe the specific embodiments of the present invention in detail with reference to the accompanying drawings of the specification. Obviously, the described embodiments are some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0023] Example 1, refer to Figure 1 , which is the first embodiment of the present invention. This embodiment provides an energy storage frequency modulation control method for a supercapacitor-coupled lithium battery, including: S1: Collect data from the original frequency modulation instruction sequence, generate an alternative sequence using the search method, and generate a regular optimal alternative sequence through positive, negative, and comprehensive optimization.

[0024] Specifically, set the original frequency modulation sequence as , and the sequence with the previous length of .

[0025] Take the sequence with the previous length as the input, and predict the values of the pre-test group and the predicted unknown group .

[0026] Among them, the actual values and predicted values of the test group are used to generate all the subsequent errors (MAPE) of the present invention. What the present invention truly predicts is the value of the unknown group.

[0027] Among them, is the sequence length, and i is the variable index.

[0028] It should be noted that since the original frequency modulation sequence has strong non-periodicity and non-regularity, directly putting it into the upgrade network will result in a large prediction error. Therefore, the present invention generates a regular optimal alternative sequence through the search method (this sequence has strong periodicity and is more suitable for the prediction of neural networks).

[0029] Randomly generate 90 groups of alternative sequences , set Perform a forward search on any one of the first 30 sequences and substitute it into the forward search formula to obtain the random range of the i-th value of the current sequence. The forward search formula is as follows: , to Set it as the middle sequence. There are both forward search and backward search. Let be any sequence located between to Substitute it into the mixed search formula to obtain the random range of the i-th value of the sequence. The mixed search formula is as follows: , Let Perform a backward search on any one of the last 30 sequences and substitute it into the forward search formula to obtain the random range of the i-th value of the current sequence. The backward search formula is as follows: , where W is the error generated by the test group, is the i-th value of the original frequency modulation command sequence, is the random range of the i-th value of the j-th substitution sequence. i and j are variable indices, is the reference adjustment value of is a dynamic amplification factor. Through the linear combination of the group number j and the error W, it adjusts the upper bound of the search range; w is the weight parameter corresponding to the error, is the natural constant, is the dynamic contraction factor used to control the lower bound of the backward search range.

[0030] Furthermore, re-optimize the generated sequence; Set the error generated by the test group of the substitution sequence as ; When the error generated during the forward search reaches the error generated by the test group, the corresponding sequence at this time is , and the corresponding error is ; When the error generated during the mixed search reaches the error generated by the test group, the corresponding sequence at this time is and the corresponding error is ; When the error generated during the backward search reaches the error generated by the test group, the corresponding sequence at this time is and the corresponding error is .

[0031] The obtained , , Substitute into the following optimization formula to obtain the optimal substitution sequence , and the optimization formula is as follows: , where , , are the minimum error values under the forward, mixed, and backward search strategies respectively, , , are the sequence values generated by different search strategies respectively, is the error correction term, is the error value corresponding to the i-th position.

[0032] S2: Train the GRU model using the optimal substitution sequence. Based on the training results, optimize the hyperparameters of the GRU neural network through the improved whale optimization algorithm.

[0033] Specifically, the disadvantages of the whale algorithm are low solution accuracy and slow convergence speed when dealing with complex global optimization problems. The present invention proposes a non-linear decreasing strategy, which better balances the global search and local search capabilities of the whale optimization algorithm, so that the search method of the whale population for prey is not easily changed from global search to local search prematurely, thus preventing the algorithm from falling into a local optimal solution.

[0034] Therefore, the improved whale optimization algorithm includes the first optimization (improvement of the convergence factor) and the second optimization.

[0035] The first optimization is specifically to optimize the hyperparameters of the GRU neural network, and improve the convergence factor using a non-linear decreasing strategy; Balance the global search and local search capabilities of the high whale optimization algorithm, and the convergence factor The improvement formula is as follows: , where represents the maximum number of iterations of the whale algorithm, t is the current iteration number, represents the activation function; Optimize the hyperparameters of the GRU neural network using the improved whale optimization algorithm, and the optimization formula is as follows: , where represents the new hyperparameter combination, represents the best hyperparameter combination, represents the previous particle position, represents a random number.

[0036] Further, the second optimization includes optimizing the hyperparameters of the GRU neural network, setting the learning rate and the number of hidden layer neurons of the GRU neural network as the attributes of the search particles in the space, and taking the minimization of the output error as the objective function.

[0037] S3: Input the optimal alternative sequence into the optimized GRU model to generate a preliminary prediction result, and correct the prediction result by combining the deviation between the prediction residual and the original data to obtain the final prediction result.

[0038] It should be noted that the optimal alternative sequence is input into the optimized GRU model; The improved whale optimization algorithm is used to make a prediction through the optimal alternative sequence, and the prediction result is ; The improved whale optimization algorithm is used to make a prediction through the difference sequence between the optimal alternative sequence and the original sequence, and the prediction result is ; The two prediction results are used to obtain the final prediction result through correlation calculation, where the correlation calculation is: , The final prediction result is ; Among them, represents the generated optimal alternative sequence, is the preliminary predicted value obtained by making a prediction, represents the difference predicted value obtained by using the improved whale optimization algorithm to predict the difference sequence between the optimal alternative sequence and the original sequence, is the sine function, and the input is π(N + i), which is used to introduce periodic correction.

[0039] Embodiment 2 is an embodiment of the present invention, which provides an energy storage frequency modulation method for a supercapacitor-coupled lithium battery. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0040] First, verify the effectiveness of the energy storage frequency modulation prediction control method of the search method combined with the decomposition optimization algorithm and the improved whale optimization algorithm (IWOA-GRU) of the present invention in improving the prediction accuracy and response speed.

[0041] In order to further verify the advantages of the present invention, the present invention respectively uses the method of the present invention and the prediction method of VMD-WOA-GRU to predict the frequency modulation sequence, and the results are as follows.

[0042] Compare the prediction performances of the following methods: VMD-WOA-ELM model (whale optimization algorithm of variational mode decomposition), the search method of the present invention combined with the IWOA-GRU (improved whale algorithm optimization) model, and the prediction data is shown in Table 1.

[0043] Table 1 Prediction Data Table , The following four evaluation metrics are used to evaluate the prediction performance: MAE, SSE, RMSE, MAPE, and the adaptability and robustness of the model are verified for multiple scenarios. The search method of the present invention combined with the improved whale optimization algorithm (IWOA-GRU) model is superior to other methods in terms of prediction accuracy and response speed. In multiple experimental scenarios, it shows lower prediction errors (MAE, SSE, RMSE, MAPE) and has good adaptability. The practicality and effectiveness of the method of the present invention in energy storage frequency modulation prediction control are proven as shown in Table 2.

[0044] Table 2 Evaluation Index Table , where M represents the sample size, and respectively represent the actual value and the predicted value at time n.

[0045] Compared with the traditional method, the present invention has significant advantages in the following aspects. The whale algorithm is optimized by a non-linear decreasing strategy, balancing the global search and local search capabilities, with a faster optimization convergence speed and more reasonable prediction model parameters. Combining the long short-term memory characteristics of GRU, the learning ability of complex time series data is improved, especially in the case of multi-dimensional feature input, showing higher robustness. The error of the prediction result is dynamically corrected to ensure the practical application value of the prediction result, which is more practical in the frequency modulation control scenario.

[0046] Example 3 is the third example of the present invention, which is different from the previous two examples in that: If the described function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0047] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0048] More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0049] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following techniques well known in the art and combinations thereof can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0050] Embodiment 4 is the fourth embodiment of the present invention. This embodiment provides an energy storage frequency modulation control system for a supercapacitor-coupled lithium battery, including an acquisition and adjustment module, an algorithm optimization module, and a prediction and correction module; The acquisition and adjustment module collects data from the original frequency modulation instruction sequence, generates an alternative sequence using a search method, and generates a regular optimal alternative sequence through forward, backward, and comprehensive optimization; The algorithm optimization module trains a GRU model using the optimal alternative sequence, and based on the training results, optimizes the hyperparameters of the GRU neural network through an improved whale optimization algorithm; The prediction correction module inputs the optimal alternative sequence into the optimized GRU model to generate a preliminary prediction result, and corrects the prediction result by combining the deviation between the prediction residual and the original data to obtain the final prediction result.

[0051] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than 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 by the scope of the claims of the present invention.

Claims

1. A storage frequency modulation control method for a supercapacitor-coupled lithium battery, characterized in that: including, collecting data from the original frequency modulation instruction sequence, generating an alternative sequence using a search method, and generating a regular optimal alternative sequence through positive, negative, and comprehensive optimization; training a GRU model using the optimal alternative sequence, and based on the training results, optimizing the hyperparameters of the GRU neural network through an improved whale optimization algorithm; inputting the optimal alternative sequence into the optimized GRU model to generate a preliminary prediction result, and correcting the prediction result by combining the deviation between the prediction residual and the original data to obtain the final prediction result.

2. The energy storage frequency modulation control method of a supercapacitor-coupled lithium battery according to claim 1, characterized in that: The data collection includes, Set the original frequency modulation sequence as , with a previous length of sequence; Use the sequence of the previous length as the input, the pre-test experimental group value and the predicted unknown group value; Among them, all the errors generated by collecting the actual values and predicted values of the test group, is the sequence length, and i is the variable index.

3. The energy storage frequency modulation control method of a supercapacitor-coupled lithium battery according to claim 2, characterized in that: The generation of the regular optimal alternative sequence includes the original frequency modulation sequence generating a regular optimal alternative sequence by a search method; Randomly generate 90 sets of alternative sequences , let be any one of the first 30 sets of sequences for forward search, and substitute it into the forward search formula to obtain the random range of the i-th value of the current sequence. The forward search formula is as follows: ， to Set to the middle sequence, with both forward search and backward search existing. Let be located at to Any sequence from is substituted into the mixed search formula to obtain the random range of the i-th value of the sequence. The mixed search formula is as follows: ， Let be any one of the last 30 sequences for negative search, and substitute it into the positive search formula to obtain the random range of the i-th value of the current sequence. The negative search formula is as follows: ， where W is the error of the test group generated, the i-th value of the original frequency modulation command sequence, the random range of the i-th value of the j-th alternative sequence, where i and j are variable indices, the reference adjustment value of, is a dynamic amplification factor that adjusts the upper bound of the search range through the linear combination of the group number j and the error W; w is the weight parameter corresponding to the error, is the natural constant, is the dynamic contraction factor used to control the lower bound of the negative search range.

4. The energy storage frequency modulation control method of a supercapacitor-coupled lithium battery according to claim 3, characterized in that: The generation of the regular optimal alternative sequence further includes re-optimizing the generated sequence; Set the alternative sequence The error generated by the experimental group is ; When the error generated during the forward search reaches the error generated by the experimental group, the corresponding sequence at this time is , and the corresponding error is ; When the error generated during the mixed search reaches the error generated by the experimental group, the corresponding sequence at this time is The corresponding error is ; When the error generated during the negative search reaches the error generated by the experimental group, the corresponding sequence at this time is The corresponding error is ; The obtained , , are substituted into the following optimization formula to obtain the optimal substitution sequence . The optimization formula is as follows: ， Among them, , , are the minimum error values under the forward, mixed, and negative search strategies respectively, , , are the sequence values generated by different search strategies respectively, is the error correction term, is the error value corresponding to the i-th position.

5. The energy storage frequency modulation control method of a supercapacitor-coupled lithium battery according to claim 4, characterized in that: The improved whale optimization algorithm includes a first optimization and a second optimization; The first optimization is specifically to optimize the hyperparameters of the GRU neural network, and improve the convergence factor using a non-linear decreasing strategy; Balance the global search and local search capabilities of the high whale optimization algorithm, and the convergence factor The improved formula is as follows: ， Among them, represents the maximum number of iterations of the whale algorithm, \(t\) is the current iteration number, represents the activation function; Using the improved whale optimization algorithm to optimize the hyperparameters of the GRU neural network, and the optimization formula is as follows: ， Among them, represents a new combination of hyperparameters, represents the optimal combination of hyperparameters, represents the previous particle position, represents a random number.

6. The energy storage frequency modulation control method of a supercapacitor-coupled lithium battery according to claim 5, characterized in that: The second optimization includes optimizing the hyperparameters of the GRU neural network, setting the learning rate and the number of hidden layer neurons of the GRU neural network as the attributes of the search particles in the space, and taking the minimization of the output error as the objective function.

7. The energy storage frequency modulation control method of a supercapacitor-coupled lithium battery according to claim 6, characterized in that: The final prediction result includes inputting the optimal alternative sequence into the optimized GRU model; Using the improved whale optimization algorithm to make predictions through the optimal replacement sequence, the prediction result is ; The improved whale optimization algorithm is used to make predictions through the difference sequence between the optimal substitution sequence and the original sequence, and the prediction result is ; Obtaining the final prediction result by performing correlation calculation on the two prediction results, where the correlation calculation is: ， The final prediction result is ; Among them, represents the generated optimal alternative sequence, is the preliminary predicted value obtained by prediction, represents the difference predicted value obtained by predicting the difference sequence between the optimal alternative sequence and the original sequence using the improved whale optimization algorithm, is the sine function, with the input of π(N + i), which is used to introduce periodic correction.

8. A energy storage frequency modulation control system for supercapacitor-coupled lithium batteries, which applies the energy storage frequency modulation control method for supercapacitor-coupled lithium batteries according to any one of claims 1 to 7, characterized in that, including a data collection and adjustment module, an algorithm optimization module, and a prediction correction module; The data collection and adjustment module collects data from the original frequency modulation instruction sequence, generates an alternative sequence using a search method, and generates a regular optimal alternative sequence through positive, negative, and comprehensive optimization; The algorithm optimization module trains a GRU model using the optimal alternative sequence, and based on the training results, optimizes the hyperparameters of the GRU neural network through an improved whale optimization algorithm; The prediction correction module inputs the optimal alternative sequence into the optimized GRU model to generate a preliminary prediction result, and corrects the prediction result by combining the deviation between the prediction residual and the original data to obtain the final prediction result.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of a method for energy storage frequency modulation control of a supercapacitor-coupled lithium battery according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of a method for energy storage frequency modulation control of a supercapacitor-coupled lithium battery according to any one of claims 1 to 7.

Images