Energy storage frequency modulation prediction method for identifying false subsequences and related equipment

Abstract

The invention relates to the technical field of frequency modulation sequence prediction, and discloses an energy storage frequency modulation prediction method for identifying false subsequences and related equipment, and the method comprises the steps: decomposing a frequency modulation instruction sequence into a plurality of subsequences, and determining a false parameter of each subsequence; determining the false degree of each sub-sequence according to the determined false parameters; based on the false degree identification of each sub-sequence, obtaining a sub-sequence corresponding to a false degree maximum value, taking the sub-sequence as a sub-sequence with a maximum false component, removing the sub-sequence, and generating a compensation sequence corresponding to the removed sub-sequence; and respectively inputting the sub-sequences which are not removed and the compensation sequence into a GRU model for prediction output to obtain a plurality of prediction results, and superposing the plurality of prediction results to generate a final prediction value. According to the method, the effective data after false information removal and the compensation sequence are comprehensively considered, so that the prediction result is more accurate and reliable, and the prediction precision is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of frequency modulation sequence prediction, and in particular to a method for predicting energy storage frequency modulation for identifying false subsequences and related equipment. Background Art

[0002] In power systems, a frequency regulation command sequence is a set of instructions used to regulate the power system's frequency. These instructions are typically generated based on factors such as the power system's frequency deviation, load variations, and the operating status of power generation equipment. The purpose of the frequency regulation command sequence is to maintain power system frequency stability and ensure power quality by adjusting the output power of power generation equipment (such as generators) or energy storage devices.

[0003] Traditional forecasting methods are often applied to predictive analysis of various types of sequence data to estimate future trends and support decision-making. Among them, the forecasting method based on variational mode decomposition (VMD) is a relatively common and valuable technical approach.

[0004] The basic principle of the VMD decomposition method is that it decomposes the original complex sequence into a series of subsequences. By predicting each of these subsequences separately and then superimposing the prediction results, the final prediction for the original sequence is obtained. This decomposition, separate prediction, and superposition method helps to extract characteristic information from different frequency components in the original sequence, providing a possible approach to improving prediction accuracy.

[0005] However, the VMD decomposition method has exposed significant flaws in practical applications. Specifically, it can generate spurious subsequences during the decomposition process. These spurious subsequences do not effectively reflect the true characteristics of the original sequence. Their presence not only fails to provide valuable information for prediction, but can also negatively impact prediction accuracy. The interference of spurious subsequences can cause deviations in the prediction model during training and prediction, resulting in significant discrepancies between the final prediction results and the actual situation, thereby compromising the scientific nature and accuracy of decisions based on the predictions.

[0006] Therefore, in view of the above-mentioned problems of the VMD decomposition method, it is necessary to develop a new prediction method or technical improvement solution that can overcome the interference of false subsequences and improve the prediction accuracy, so as to meet the demand for more accurate prediction results in practical applications. Summary of the Invention

[0007] In order to overcome the above-mentioned defects in the prior art, the purpose of the present invention is to provide a method and related equipment for energy storage frequency modulation prediction for identifying false subsequences, so as to solve the technical problem of how to overcome false subsequence interference and improve prediction accuracy in the prior art.

[0008] The present invention is achieved through the following technical solutions: In a first aspect, the present invention provides a method for predicting energy storage frequency modulation by identifying false subsequences, comprising: Decomposing the frequency modulation instruction sequence into a plurality of subsequences and determining the false parameters of each subsequence; determining the falsity of each subsequence based on the determined falsity parameter; Based on the falsehood of each subsequence, a subsequence corresponding to the maximum falsehood is obtained, the subsequence is removed as the subsequence with the largest falsehood component, and a compensating sequence is generated corresponding to the removed subsequence; The unremoved subsequences and the compensating sequence are respectively input into the GRU model for prediction and output to obtain multiple prediction results, which are then superimposed to generate the final prediction value.

[0009] Preferably, the process of determining the false parameters of each subsequence includes: S1, setting a sine function, adjusting the sine function parameters to record the data points that fall within the sine function and the corresponding number of landing points in a subsequence of the frequency modulation instruction sequence according to the set landing point conditions, and determining the data points that do not fall within the sine function as false parameters in the corresponding subsequence; S2, determining the subsequences that are not eliminated in the frequency modulation instruction sequence in sequence according to S1 to obtain the false parameters in the corresponding subsequences; S3, forming a false parameter set corresponding to the false parameters determined by each subsequence in the frequency modulation instruction sequence.

[0010] Furthermore, in S1, the landing condition is to substitute the time series point into the sine function. If the calculated value of the sine function is equal to the data point of the subsequence corresponding to the time series point, it is judged that the data point falls on the sine function; otherwise, the data point does not fall on the sine function.

[0011] Preferably, the calculation formula of falseness is as follows:

[0012] in, 、 、 、 a false argument indicating a subsequence, Indicates the number of landing points; || indicates the absolute value.

[0013] Preferably, the generation process of the compensation sequence includes: Based on the frequency parameters of the eliminated subsequence, phase parameters are randomly generated within the preset phase offset range to construct a sine function sequence with the same frequency characteristics but different phases.

[0014] Preferably, the calculation formula for compensating for sequence generation includes:

[0015] in, Represents the parameters of the compensation sequence; Parameters representing the subsequence to be removed; Indicates the minimum falsehood; Indicates the maximum falsehood; || indicates the absolute value.

[0016] Preferably, multiple prediction results are fused and superimposed by weighted summation to generate a final prediction value.

[0017] In a second aspect, the present invention further provides an energy storage frequency modulation prediction system for identifying false subsequences, comprising: a false parameter determination module, configured to decompose the frequency modulation instruction sequence into a plurality of subsequences and determine a false parameter for each subsequence; a falseness calculation module, configured to determine the falseness of each subsequence according to the determined falseness parameter; A sequence processing module is used to identify the subsequence corresponding to the maximum falsehood based on the falsehood of each subsequence, remove the subsequence as the subsequence with the largest falsehood component, and generate a compensating sequence corresponding to the removed subsequence; The sequence prediction module is used to input the unremoved subsequences and the supplementary sequences into the GRU model for prediction and output to obtain multiple prediction results, and then superimpose the multiple prediction results to generate the final prediction value.

[0018] In a third aspect, the present invention further provides a mobile terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the energy storage frequency modulation prediction method for identifying false subsequences as described above are implemented.

[0019] In a fourth aspect, the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the energy storage frequency modulation prediction method for identifying false subsequences as described above.

[0020] Compared with the prior art, the present invention has the following beneficial technical effects: The present invention provides a method for energy storage frequency modulation prediction that identifies false subsequences. By decomposing the frequency modulation instruction sequence into multiple subsequences, determining the false parameters and falseness, identifying and eliminating the subsequence with the largest false component, the interference problem of the false subsequence on the prediction process is specifically solved, and the adverse effect of false information on the prediction accuracy is reduced. After eliminating the subsequence with the largest false component, a compensation sequence is generated, and the uneliminated subsequences and the compensation sequence are respectively input into the GRU model for prediction, and then the multiple prediction results are superimposed to generate the final prediction value. This method comprehensively considers the valid data after removing the false information and the compensation sequence, making the prediction result more accurate and reliable, and effectively improving the prediction accuracy.

[0021] Furthermore, by setting a sine function and recording the number of data points based on the landing conditions, we can quantitatively identify data points in the subsequence that do not conform to the sine function, namely, spurious parameters. By applying the same identification steps to each subsequence in the frequency modulation instruction sequence, we ensure the systematic and consistent nature of the entire process. By identifying and eliminating spurious data points corresponding to spurious parameters, we can reduce the interference of this spurious information on the prediction model, thereby improving prediction accuracy.

[0022] Furthermore, by substituting the time series points into the sine function and comparing the calculated sine function value with the value of the corresponding subsequence data point, it is possible to accurately determine whether the data point falls on the sine function. If they are not equal, the data point is clearly a false parameter. This precise positioning method can effectively identify data that does not conform to the sine function, avoiding ambiguous judgments and improving the accuracy of false information identification.

[0023] Furthermore, by constructing a sine function sequence based on the frequency parameters of the eliminated subsequence, it is possible to ensure that the compensation sequence and the original frequency modulation instruction sequence remain consistent in the key characteristic of frequency. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 Flowchart of the energy storage frequency modulation prediction method for identifying false subsequences in an embodiment of the present invention; Figure 2 FIG. 1 is a diagram of a process for determining a false parameter of each subsequence in an embodiment of the present invention; Figure 3 This is a schematic diagram of an energy storage frequency modulation prediction system for identifying false subsequences in an embodiment of the present invention; In the figure: 1. False parameter determination module; 2. False degree calculation module; 3. Sequence processing module; 4. Sequence prediction module. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products or devices.

[0027] The purpose of the present invention is to provide a method for predicting energy storage frequency modulation by identifying false subsequences and related equipment, so as to solve the technical problem of how to overcome false subsequence interference and improve prediction accuracy in the prior art.

[0028] The terms involved in this invention are explained as follows: GRU model: Gated Recurrent Unit, gated recurrent unit; VMD decomposition: Variational Mode Decomposition, variational mode decomposition; IMF: Intrinsic Mode Function, intrinsic mode function; MAE: Mean Absolute Error, mean absolute prediction error; SSE: Sum of Squared Errors, the sum of squares within the group or the sum of squares of the residual; RMSE: Root Mean Squared Error, root mean square prediction error; MAPE: Mean Absolute Percentage Error, the mean of the absolute error.

[0029] The present invention is described in further detail below with reference to the accompanying drawings: Example 1 See also Figure 1 In one embodiment of the present invention, a method for predicting energy storage frequency modulation for identifying false subsequences is provided, comprising: Step 1: Decompose the frequency modulation instruction sequence into multiple subsequences and determine the false parameters of each subsequence; Specifically, according to Figure 2 As shown, the process of determining the false parameters of each subsequence includes: S1, setting a sine function, adjusting the sine function parameters to record the data points that fall within the sine function and the corresponding number of landing points in a subsequence of the frequency modulation instruction sequence according to the set landing point conditions, and determining the data points that do not fall within the sine function as false parameters in the corresponding subsequence; Among them, the landing condition is to substitute the time series point into the sine function. If the calculated value of the sine function is equal to the data point of the subsequence corresponding to the time series point, it is judged that the data point falls on the sine function; otherwise, the data point does not fall on the sine function.

[0030] S2, determining the subsequences that are not eliminated in the frequency modulation instruction sequence in sequence according to S1 to obtain the false parameters in the corresponding subsequences; S3, forming a false parameter set corresponding to the false parameters determined by each subsequence in the frequency modulation instruction sequence.

[0031] Step 2, determining the falseness of each subsequence based on the determined false parameter; Specifically, the calculation formula of falseness is as follows:

[0032] in, 、 、 、 a false argument indicating a subsequence, Indicates the number of landing points; || indicates the absolute value.

[0033] Step 3: Based on the falsehood of each subsequence, the subsequence corresponding to the maximum falsehood is identified, and the subsequence is removed as the subsequence with the largest falsehood component, and a compensation sequence is generated corresponding to the removed subsequence; Specifically, the generation process of the compensation sequence includes: Based on the frequency parameters of the eliminated subsequence, phase parameters are randomly generated within the preset phase offset range to construct a sine function sequence with the same frequency characteristics but different phases.

[0034] Specifically, the calculation formula for compensating sequence generation includes:

[0035] in, Represents the parameters of the compensation sequence; Parameters representing the subsequence to be removed; Indicates the minimum falsehood; Indicates the maximum falsehood; || indicates the absolute value.

[0036] In step 4, the unremoved subsequences and the supplementary sequence are respectively input into the GRU model for prediction output to obtain multiple prediction results, and the multiple prediction results are superimposed to generate the final prediction value.

[0037] Specifically, multiple prediction results are fused and superimposed through weighted summation to generate the final prediction value.

[0038] The specific operations in this embodiment are as follows: The frequency modulation instruction sequence is set to Pt, which is decomposed by VMD into IMF1, IMF2, IMF3, ...IMF i ,…,IMF K .

[0039] Set one of the subsequence IMFs of VMD decomposition i =[X i1 ,X i2 ,X i3 ,.X ii ..,X iN ]; and generates a sine function ; Continuously adjust parameters , so that [X i1 ,X i2 ,X i3 ,.X ii ..,X iN ] as many as possible The final parameters after adjustment are , falls on There are Mi points on it.

[0040] Among them, the landing condition is to substitute t=1 into ,if , then X i1 fall into Otherwise, it does not fall in.

[0041] According to the above method, the false parameters of each subsequence are sorted out: as subsequence IMF i Parameters For example, the calculation formula of false degree Di is:

[0042] When the subsequence falls approximately close to The more points there are on the function, the stronger the regularity of the sequence is, and the lower the falsehood is, and vice versa.

[0043] Calculated according to the above method , and find out The maximum value in .

[0044] set up The subsequence corresponding to the maximum value is the subsequence with the largest false component. This subsequence will have a negative impact on the prediction, so it is eliminated.

[0045] After removing the subsequences with the highest false degree, a set of compensatory sequences is generated.

[0046] Among them, suppose the subsequence to be eliminated is IMF s =[X s1 ,X s2 ,X s3 ,.X si ..,X sN ]; let the generated subsequence be IMF s 、 =[X s1 、 ,X s2 、 ,X s3 、 ,.X si 、 ..,X sN 、 ].

[0047] X si 、 For example, the compensation sequence formula is as follows:

[0048] From the above, we can see that the compensation sequence is a range and is randomly generated.

[0049] After generating the compensation sequence, the subsequences are put into GRU prediction respectively, and then the final prediction results are superimposed.

[0050] Assume the final sequence is IMF1,IMF2,IMF3,.IMF s 、 ..,IMF K Put these sequences into GRU for prediction, and then add up the final predicted values ​​to get the final result.

[0051] In order to further verify the advantages of the present invention, the present invention uses the method of the present invention and the VMD-GRU (K=7) prediction method to predict the frequency modulation sequence. The results are shown in Table 1: Frequency modulation sequence 1 comes from the frequency modulation data of a power plant in Hulunbuir from 0:00 to 20:00 on December 1, 2024.

[0052] Frequency modulation sequence 2 comes from the frequency modulation data of a power plant in Hulunbuir from 2:00 to 22:00 on December 2, 2024.

[0053] Table 1 shows the prediction results of FM sequences 1 and 2

[0054] Table 2 Four evaluation indicators

[0055] In the table, N represents the sample size. and represent the actual value and predicted value at time n respectively.

[0056] As shown in Table 2, the experimental results show that all four evaluation indicators have decreased, indicating that the decomposition method proposed in this paper is equivalent to the traditional VMD-GRU prediction method and can find the decomposition layer number K with the least false components. This avoids the inherent drawback of VMD decomposition, which contains false components, and further improves prediction accuracy. This helps power plants improve their frequency regulation responsiveness and further increases their profits.

[0057] In summary, the present invention provides a method for energy storage frequency modulation prediction for identifying false subsequences, which solves the problem of interference of false subsequences on the prediction process by decomposing the frequency modulation instruction sequence into multiple subsequences, determining false parameters and falseness, identifying and eliminating the subsequence with the largest false component, and reducing the adverse effects of false information on prediction accuracy. After eliminating the subsequence with the largest false component, a compensation sequence is generated, and the remaining subsequences and the compensation sequence are respectively input into the GRU model for prediction, and then the multiple prediction results are superimposed to generate the final prediction value. This method comprehensively considers the valid data after removing the false information and the compensation sequence, so that the prediction result is more accurate and reliable, and effectively improves the prediction accuracy.

[0058] Example 2 according to Figure 3 As shown, the present invention also provides an energy storage frequency modulation prediction system for identifying false subsequences, comprising: A false parameter determination module 1 is used to decompose the frequency modulation instruction sequence into multiple subsequences and determine the false parameters of each subsequence; a falseness calculation module 2, configured to determine the falseness of each subsequence according to the determined falseness parameter; Sequence processing module 3, for identifying the subsequence corresponding to the maximum falsehood based on the falsehood of each subsequence, removing the subsequence as the subsequence with the largest falsehood component, and generating a compensating sequence corresponding to the removed subsequence; The sequence prediction module 4 is used to input the non-eliminated subsequences and the supplementary sequence into the GRU model for prediction and output to obtain multiple prediction results, and superimpose the multiple prediction results to generate a final prediction value.

[0059] Example 3 The present invention also provides a mobile terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, such as an energy storage frequency modulation prediction program for identifying false subsequences.

[0060] When the processor executes the computer program, the steps of the energy storage frequency modulation prediction method for identifying false subsequences are implemented, for example: Decomposing the frequency modulation instruction sequence into a plurality of subsequences and determining the false parameters of each subsequence; determining the falsity of each subsequence based on the determined falsity parameter; Based on the falsehood of each subsequence, a subsequence corresponding to the maximum falsehood is obtained, the subsequence is removed as the subsequence with the largest falsehood component, and a compensating sequence is generated corresponding to the removed subsequence; The unremoved subsequences and the compensating sequence are respectively input into the GRU model for prediction and output to obtain multiple prediction results, which are then superimposed to generate the final prediction value.

[0061] Alternatively, when the processor executes the computer program, the functions of each module in the above system are realized, for example: A false parameter determination module 1 is used to decompose the frequency modulation instruction sequence into multiple subsequences and determine the false parameters of each subsequence; a falseness calculation module 2, configured to determine the falseness of each subsequence according to the determined falseness parameter; Sequence processing module 3, for identifying the subsequence corresponding to the maximum falsehood based on the falsehood of each subsequence, removing the subsequence as the subsequence with the largest falsehood component, and generating a compensating sequence corresponding to the removed subsequence; The sequence prediction module 4 is used to input the non-eliminated subsequences and the supplementary sequence into the GRU model for prediction and output to obtain multiple prediction results, and superimpose the multiple prediction results to generate a final prediction value.

[0062] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in the mobile terminal.

[0063] For example, the computer program may be divided into a false parameter determination module 1, a false degree calculation module 2, a sequence processing module 3, and a sequence prediction module 4; The specific functions of each module are as follows: A false parameter determination module 1 is used to decompose the frequency modulation instruction sequence into multiple subsequences and determine the false parameters of each subsequence; a falseness calculation module 2, configured to determine the falseness of each subsequence according to the determined falseness parameter; Sequence processing module 3, for identifying the subsequence corresponding to the maximum falsehood based on the falsehood of each subsequence, removing the subsequence as the subsequence with the largest falsehood component, and generating a compensating sequence corresponding to the removed subsequence; The sequence prediction module 4 is used to input the non-eliminated subsequences and the supplementary sequence into the GRU model for prediction and output to obtain multiple prediction results, and superimpose the multiple prediction results to generate a final prediction value.

[0064] The mobile terminal may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The mobile terminal may include, but is not limited to, a processor and a memory.

[0065] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the mobile terminal, connecting various parts of the entire mobile terminal using various interfaces and lines.

[0066] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the mobile terminal by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0067] The memory may primarily include a program storage area and a data storage area. The program storage area may store an operating system and at least one application required for a function (such as sound playback or image playback); the data storage area may store data generated based on the use of the mobile phone (such as audio data and a phone book). Furthermore, the memory may include high-speed random access memory (RAM) and non-volatile memory, such as a hard disk, internal memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0068] Example 4 The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the energy storage frequency modulation prediction method for identifying false subsequences are implemented.

[0069] If the module / unit integrated in the mobile terminal 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.

[0070] Based on this understanding, the present invention can implement all or part of the processes in the above-mentioned method by means of a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above-mentioned method for scheduling aggregated reinforcement learning resources. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form.

[0071] The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0072] It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0073] 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 it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the present invention.

Claims

1. A method for predicting energy storage frequency modulation by identifying false subsequences, characterized in that: include: Decomposing the frequency modulation instruction sequence into a plurality of subsequences and determining the false parameters of each subsequence; determining the falsity of each subsequence based on the determined falsity parameter; Based on the falsehood of each subsequence, a subsequence corresponding to the maximum falsehood is obtained, the subsequence is removed as the subsequence with the largest falsehood component, and a compensating sequence is generated corresponding to the removed subsequence; The unremoved subsequences and the compensating sequence are respectively input into the GRU model for prediction and output to obtain multiple prediction results, which are then superimposed to generate the final prediction value.

2. The energy storage frequency modulation prediction method for identifying false subsequences according to claim 1, characterized in that: The process of determining the false parameters of each subsequence includes: S1, setting a sine function, adjusting the sine function parameters to record the data points that fall within the sine function and the corresponding number of landing points in a subsequence of the frequency modulation instruction sequence according to the set landing point conditions, and determining the data points that do not fall within the sine function as false parameters in the corresponding subsequence; S2, determining the subsequences that are not eliminated in the frequency modulation instruction sequence in sequence according to S1 to obtain the false parameters in the corresponding subsequences; S3, forming a false parameter set corresponding to the false parameters determined by each subsequence in the frequency modulation instruction sequence.

3. The energy storage frequency modulation prediction method for identifying false subsequences according to claim 2, characterized in that: In S1, the landing condition is to substitute the time series point into the sine function. If the calculated value of the sine function is equal to the data point of the subsequence corresponding to the time series point, it is judged that the data point falls on the sine function; otherwise, the data point does not fall on the sine function.

4. The energy storage frequency modulation prediction method for identifying false subsequences according to claim 1, characterized in that: The calculation formula of the false degree is as follows: in, 、 、 、 a false argument indicating a subsequence, Indicates the number of landing points; || indicates the absolute value.

5. The energy storage frequency modulation prediction method for identifying false subsequences according to claim 1, characterized in that: The generation process of the compensation sequence includes: Based on the frequency parameters of the eliminated subsequence, phase parameters are randomly generated within a preset phase offset range to construct a sine function sequence with the same frequency characteristics and different phases. The sine function sequence is the compensation sequence.

6. The energy storage frequency modulation prediction method for identifying false subsequences according to claim 1, characterized in that: The calculation formula for generating the compensation sequence includes: in, Represents the parameters of the compensation sequence; Parameters representing the subsequence to be removed; Indicates the minimum falsehood; Indicates the maximum falsehood; || indicates the absolute value.

7. The energy storage frequency modulation prediction method for identifying false subsequences according to claim 1, characterized in that: The multiple prediction results are fused and superimposed in a weighted summation manner to generate a final prediction value.

8. A system for predicting energy storage frequency modulation for identifying false subsequences, characterized in that: include: a false parameter determination module, configured to decompose the frequency modulation instruction sequence into a plurality of subsequences and determine a false parameter for each subsequence; a falseness calculation module, configured to determine the falseness of each subsequence according to the determined falseness parameter; A sequence processing module is used to identify the subsequence corresponding to the maximum falsehood based on the falsehood of each subsequence, remove the subsequence as the subsequence with the largest falsehood component, and generate a compensating sequence corresponding to the removed subsequence; The sequence prediction module is used to input the unremoved subsequences and the supplementary sequences into the GRU model for prediction and output to obtain multiple prediction results, and then superimpose the multiple prediction results to generate the final prediction value.

9. A mobile terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the energy storage frequency modulation prediction method for identifying false subsequences as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the energy storage frequency modulation prediction method for identifying false subsequences as claimed in any one of claims 1 to 7 are implemented.

Images