A method and system for predicting energy storage frequency modulation instructions based on symmetrical adjustment

Abstract

The present invention relates to the technical field of power grid frequency regulation, and more specifically to a method and system for predicting energy storage frequency regulation instructions based on symmetric adjustment, comprising: decomposing a frequency regulation instruction signal to obtain a plurality of component signals, then discretely dividing each component signal to obtain a subsequence corresponding to each component signal; determining a target symmetry line for each subsequence based on the distribution of all original data points of each subsequence; symmetrically mapping each original data point based on the target symmetry line of each subsequence to obtain a symmetric data point for each original data point; fusing the original data point and the symmetric data point to obtain a final adjusted adjusted data point; predicting each adjusted data point corresponding to each subsequence to obtain each predicted subsequence; and superimposing all predicted subsequences to obtain predicted signal data for the final frequency regulation instruction. The present invention reduces the impact of nonlinearity and improves prediction accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid frequency regulation, and in particular to a method and system for predicting energy storage frequency regulation instructions based on symmetrical adjustment. Background Art

[0002] Energy storage frequency regulation command prediction refers to predicting frequency regulation command changes when energy storage is used to implement frequency regulation (frequency regulation) tasks in power systems, thereby optimizing the energy storage system's scheduling and response. Frequency regulation in power systems is crucial, especially as the proportion of renewable energy (such as wind and solar power) increases, increasing frequency instability. Energy storage systems play an increasingly important role in this context.

[0003] Frequency regulation commands are signals sent by the power system dispatch center or automated equipment, telling the energy storage system how to adjust charging and discharging power to maintain grid frequency stability. The energy storage system needs to respond quickly to these frequency regulation commands to ensure frequency stability.

[0004] The traditional method for predicting energy storage frequency modulation commands involves decomposing the original signal corresponding to the frequency modulation command using the VMD (Variational Mode Decomposition) algorithm to obtain multiple component signals. Each component is then predicted separately, and the predicted results for all components are superimposed to obtain the final frequency modulation command prediction. However, because some component signals are highly nonlinear, even more so than the original signal, using these highly nonlinear components increases the difficulty of prediction and reduces the accuracy of the prediction results. Summary of the Invention

[0005] The present invention provides a method and system for predicting energy storage frequency modulation instructions based on symmetrical adjustment, which are used to solve existing problems.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] The first aspect of the present invention is to provide a method for predicting energy storage frequency modulation instructions based on symmetric adjustment, comprising:

[0008] Obtain frequency modulation command signal;

[0009] Decompose the frequency modulation command signal to obtain several component signals, then discretely divide each component signal to obtain a subsequence corresponding to each component signal; construct a coordinate system with time as the horizontal axis and the data in each subsequence as the vertical axis, and map all data in each subsequence into the coordinate system to obtain several original data points; determine the target symmetry line of each subsequence based on the distribution of all original data points in each subsequence; and perform symmetric mapping on each original data point based on the target symmetry line of each subsequence to obtain a symmetric data point for each original data point;

[0010] The original data points and the symmetric data points are merged to obtain the final adjusted data points; each subsequence is predicted using the adjusted data points corresponding to each subsequence to obtain each predicted subsequence;

[0011] All predicted subsequences are superimposed to obtain the predicted signal data of the final frequency modulation instruction.

[0012] Furthermore, the frequency modulation command signal is decomposed to obtain a plurality of component signals, and then each component signal is discretely divided to obtain a subsequence corresponding to each component signal, including:

[0013] The frequency modulation command signal is decomposed by VMD decomposition algorithm to obtain several component signals; Each component signal is divided to obtain a number of data corresponding to each component signal after division. The data are grouped into a set of sequences in chronological order, which are recorded as subsequences corresponding to each component signal.

[0014] Furthermore, determining the target symmetry line of each subsequence based on the distribution of all original data points of each subsequence includes:

[0015] The angle range of the symmetry line is determined by the distribution of all original data points in each subsequence. The angle range of the symmetry line is specifically expressed by the formula:

[0016]

[0017] The lower limit of the angle range of the symmetry line is specifically expressed by the formula:

[0018]

[0019] The upper limit of the angle range of the symmetry line is specifically expressed by the formula:

[0020]

[0021] Where, represents the set of all data in each subsequence, Represents the maximum absolute value of all data in each subsequence, Indicates the minimum absolute value of all data in each subsequence, Represents the minimum value of all data in each subsequence, Represents the maximum value of all data in each subsequence, is the absolute value symbol, represents the inverse tangent function, express Function, used for data normalization; Indicates the minimum angle of the symmetry line angle range, Indicates the maximum angle of the symmetry line angle range; It represents the angle between the line of symmetry and the horizontal line;

[0022] Minimum angle from the symmetry line Start from the maximum angle of the symmetry line angle range , each time the iteration is performed with the preset angle as the increment; each time the iteration reference angle is changed, a new iteration reference angle is determined; through each iteration reference angle, each reference symmetry line corresponding to each iteration reference angle is determined, and the number of original data points existing on each reference symmetry line is obtained, which is recorded as the reference data amount of each reference symmetry line;

[0023] The reference symmetry line with the largest amount of reference data is used as the target symmetry line for each subsequence.

[0024] Furthermore, performing symmetric mapping on each original data point according to the target symmetry line of each subsequence to obtain a symmetric data point for each original data point includes:

[0025]

[0026] Where, Represents the minimum value of all data in each subsequence, Represents the maximum absolute value of all data in each subsequence, is the absolute value symbol, represents the inverse tangent function, express Function, used for data normalization, Indicates the first The data value of the data, Indicates the The target angle of the original data point is the angle between the extension line of the original data point and the corresponding target symmetry line;

[0027] By using the target angle of each original data point, first determine the intersection point of the original data point extension line on the target symmetry line, and record it as the target symmetry line intersection point of each original data point; record the direction of each original data point pointing to the corresponding target symmetry line intersection point as the target extension direction of each original data point;

[0028] The original data points are then extended along the target extension direction to obtain symmetrical data points; wherein, in the process of adjusting and obtaining the symmetrical data points, the angle between the symmetrical data points and the target symmetry line is equal to the target angle of the original data points, and the distance from the symmetrical data points to the intersection of the target symmetry line is equal to the distance from the original data points to the intersection of the target symmetry line.

[0029] Furthermore, the fusing of the original data points and the symmetrical data points to obtain the final adjusted data points includes:

[0030] The formula for fusing the original data points with the symmetric data points is specifically expressed as:

[0031]

[0032] Among them, the adjustment coefficient of the coordinate value of the original data point in the fusion process is specifically expressed by the formula:

[0033]

[0034] Among them, the adjustment coefficient of the coordinate value of the symmetrical data point in the fusion process is specifically expressed by the formula:

[0035]

[0036] Where, Indicates the The coordinate values ​​of the original data points, Indicates the The coordinate value of the symmetrical data point corresponding to the original data point, Indicates the The adjustment coefficient of the coordinate value of the original data point, Indicates the The adjustment coefficient of the coordinate value of the symmetrical data point corresponding to the original data point, is a natural constant, For each subsequence data, It represents the angle between the target symmetry line and the horizontal line, Indicates the The target angle of the original data points; Indicates the The coordinate value of the adjusted data point after the final adjustment of the original data point; is the activation function; is a sine function;

[0037] Among them, through When adjusting data points, adjust the horizontal and vertical coordinate values ​​separately.

[0038] Furthermore, performing prediction by adjusting the data points corresponding to each subsequence to obtain each predicted subsequence includes:

[0039] All the adjusted data points after the final adjustment corresponding to each subsequence are sorted in chronological order to form a new set of sequences, which are recorded as each recombinant subsequence; the GRU neural network is used to make predictions based on each recombinant subsequence, and the predicted data are organized into each predicted subsequence in chronological order.

[0040] Furthermore, the superposition of all predicted subsequences to obtain predicted signal data of the final frequency modulation instruction includes:

[0041] Through the least squares method, curve fitting is performed on each prediction subsequence to obtain the prediction fitting curve of each prediction subsequence; through Fourier transform, the prediction fitting curves of all prediction subsequences are superimposed in the frequency domain to obtain the prediction signal data of the final frequency modulation instruction.

[0042] A second aspect of the present invention is to provide an energy storage frequency modulation instruction prediction system based on symmetric adjustment, comprising:

[0043] Data acquisition module: used to obtain frequency modulation command signals;

[0044] Symmetry adjustment module: used to decompose the frequency modulation command signal to obtain several component signals, then discretely divide each component signal to obtain the subsequence corresponding to each component signal; construct a coordinate system with time as the horizontal axis and the data in each subsequence as the vertical axis, and map all data in each subsequence into the coordinate system to obtain several original data points; determine the target symmetry line of each subsequence based on the distribution of all original data points in each subsequence; and perform symmetric mapping on each original data point based on the target symmetry line of each subsequence to obtain the symmetric data point of each original data point;

[0045] Fusion prediction module: used to fuse the original data points and the symmetric data points to obtain the final adjusted data points; predict each subsequence by the adjusted data points corresponding to each subsequence to obtain each predicted subsequence;

[0046] Superposition module: used to superimpose all predicted subsequences to obtain the predicted signal data of the final frequency modulation instruction.

[0047] The third aspect of the present invention is to provide an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor, wherein the processor implements the energy storage frequency modulation instruction prediction method based on symmetrical adjustment when executing the computer program.

[0048] A fourth aspect of the present invention is to provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method for predicting energy storage frequency modulation instructions based on symmetric adjustment is implemented.

[0049] Compared with the prior art, the beneficial effects of the present invention are: decomposing the frequency modulation instruction signal to obtain several component signals, then discretely dividing each component signal to obtain a subsequence corresponding to each component signal, for subsequent analysis of the data distribution of each component; determining the target symmetry line of each subsequence according to the distribution of all original data points of each subsequence; symmetrically mapping each original data point according to the target symmetry line of each subsequence to obtain a symmetrical data point of each original data point, thereby reducing the influence of the nonlinearity in the component; fusing the original data point and the symmetrical data point to obtain the adjusted data point after the final adjustment; predicting through the adjusted data point corresponding to each subsequence to obtain each predicted subsequence, thereby improving the accuracy of the component signal prediction; superimposing all predicted subsequences to obtain the predicted signal data of the final frequency modulation instruction, thereby improving the response speed to emergencies and enhancing the stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 The present invention provides a schematic flow chart of the steps of a method for predicting energy storage frequency modulation instructions based on symmetrical adjustment;

[0052] Figure 2 The present invention provides a module flow diagram of an energy storage frequency modulation instruction prediction system based on symmetrical adjustment. DETAILED DESCRIPTION

[0053] 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.

[0054] 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.

[0055] In response to the problems existing in the background technology, a method and system for predicting energy storage frequency modulation instructions based on symmetrical adjustment are studied and designed, which has important practical significance.

[0056] like Figure 1 As shown, the first aspect of the present invention is to provide a method for predicting energy storage frequency modulation instructions based on symmetric adjustment, comprising the following steps:

[0057] Step S001: Collect frequency modulation instruction signals.

[0058] It should be noted that when there is a deviation in the balance between power supply and demand (such as load changes, power generation fluctuations, etc.), the power system's dispatch center or automation system generates frequency regulation instructions based on the system's frequency fluctuations, load demand, and power generation conditions. These frequency regulation instructions maintain frequency stability, respond to emergencies, and reduce the possibility of failures.

[0059] It should be further explained that in order to respond to emergencies more quickly, the frequency modulation instructions can be predicted to achieve a faster response. Therefore, the frequency modulation instructions are collected for prediction, so as to respond to emergencies or faults more quickly.

[0060] Specifically, get the preset time before the current moment The frequency modulation command signal of the power system dispatching center is set to 1 hour, wherein the preset time length in this embodiment is , wherein, in this embodiment, the preset time There is no specific limitation and implementers can decide based on specific circumstances.

[0061] At this point, the frequency modulation command signal is obtained.

[0062] Step S002: Decompose the frequency modulation command signal to obtain several component signals, then discretely divide each component signal to obtain a subsequence corresponding to each component signal; construct a coordinate system with time as the horizontal axis and the data in each subsequence as the vertical axis, map all data in each subsequence into the coordinate system, and obtain several original data points; determine the target symmetry line of each subsequence based on the distribution of all original data points in each subsequence; perform symmetrical mapping on each original data point based on the target symmetry line of each subsequence to obtain a symmetrical data point for each original data point.

[0063] It should be noted that due to the high nonlinearity of some component signals, the prediction results are very poor. Therefore, in order to solve this problem, a symmetry-based adjustment method is proposed to improve the smoothness of the data and reduce the impact of the nonlinearity of the component signals on the prediction results.

[0064] It should be further explained that, in order to perform symmetry adjustment, each component signal is discretized to obtain discrete data points, and the symmetry line is determined by the concentrated distribution of the data points, and the discrete data points are symmetrically adjusted through the symmetry line.

[0065] Specifically, the frequency modulation command signal is decomposed by the VMD decomposition algorithm to obtain several component signals; Each component signal is divided to obtain a number of data corresponding to each component signal after division. The data are grouped into a sequence in chronological order, which is recorded as a subsequence corresponding to each component signal. The VMD decomposition algorithm is a well-known technology and will not be described in detail here. In this embodiment, the time interval is preset. seconds, where the preset time interval There is no specific limitation and implementers can decide based on specific circumstances.

[0066] At this point, the subsequence corresponding to each component signal is obtained.

[0067] It should be noted that the selection of the symmetry line is equivalent to a mean line, so that more data points are on the symmetry line, and the remaining data points fluctuate on both sides of the symmetry line, so that the symmetry adjustment can be carried out well.

[0068] Specifically, a coordinate system is constructed with time as the horizontal axis and the data in each subsequence as the vertical axis. All data in each subsequence are mapped into the coordinate system to obtain a number of original data points. The angle range of the symmetry line is determined based on the distribution of all original data points in each subsequence. The angle range of the symmetry line is specifically expressed by the formula:

[0069]

[0070] The lower limit of the angle range of the symmetry line is specifically expressed by the formula:

[0071]

[0072] The upper limit of the angle range of the symmetry line is specifically expressed by the formula:

[0073]

[0074] Where, represents the set of all data in each subsequence, Represents the maximum absolute value of all data in each subsequence, Indicates the minimum absolute value of all data in each subsequence, Represents the minimum value of all data in each subsequence, Represents the maximum value of all data in each subsequence, is the absolute value symbol, represents the inverse tangent function, express Function, used for data normalization; Indicates the minimum angle of the symmetry line angle range, Indicates the maximum angle of the symmetry line angle range; It represents the angle between the line of symmetry and the horizontal line.

[0075] Minimum angle from the symmetry line Start from the maximum angle of the symmetry line angle range , each time the preset angle is used as the increment of the angle degree to perform the iteration; each time the iteration reference angle is changed, a new iteration reference angle is determined; through each iteration reference angle, each reference symmetry line corresponding to each iteration reference angle is determined (the iteration reference angle is the angle between the reference symmetry line and the horizontal line), and the number of original data points on each reference symmetry line is obtained, which is recorded as the reference data amount of each reference symmetry line. In this embodiment, the preset angle is used as For analysis, the preset angle is not specifically limited in this embodiment, and the implementer may determine it according to the specific situation.

[0076] The reference symmetry line with the largest amount of reference data is used as the target symmetry line for each subsequence.

[0077] It should be noted that the line of symmetry passes through the origin of the coordinate system.

[0078] Symmetrical mapping is performed on several original data points in the coordinate system through the target symmetry line. During the symmetric mapping process, the angle between the extension line of each original data point and the corresponding target symmetry line is first determined, and recorded as the target angle of each original data point; the symmetrical data point of each original data point is obtained according to the target angle of each original data point;

[0079] The target angle of each original data point is specifically expressed by the formula:

[0080]

[0081] Where, Represents the minimum value of all data in each subsequence, Represents the maximum absolute value of all data in each subsequence, is the absolute value symbol, represents the inverse tangent function, express Function, used for data normalization, Indicates the first The data value of the data, Indicates the The target angle of the original data points.

[0082] By using the target angle of each original data point, first determine the intersection point of the original data point extension line on the target symmetry line, and record it as the target symmetry line intersection point of each original data point; record the direction of each original data point pointing to the corresponding target symmetry line intersection point as the target extension direction of each original data point;

[0083] The original data points are then extended along the target extension direction to obtain symmetrical data points; wherein, in the process of adjusting and obtaining the symmetrical data points, the angle between the symmetrical data points and the target symmetry line is equal to the target angle of the original data points, and the distance from the symmetrical data points to the intersection of the target symmetry line is equal to the distance from the original data points to the intersection of the target symmetry line.

[0084] At this point, the symmetrical data points after symmetrical mapping of each original data point are obtained.

[0085] Step S003: The original data points and the symmetric data points are merged to obtain the final adjusted data points; prediction is performed using the adjusted data points corresponding to each subsequence to obtain each predicted subsequence.

[0086] It should be noted that, since the symmetrical data points have strong symmetry, their symmetrical data points are closer to the target symmetry line, so the symmetrical data points have a strong degree of linearity. Therefore, the original data points are adjusted by fusing the symmetrical data points with the previous original data points to obtain the final adjusted data points. This can retain the information of the original data and improve the linearity of the original data.

[0087] Specifically, the formula for fusing the original data points with the symmetric data points is expressed as:

[0088]

[0089] Among them, the adjustment coefficient of the coordinate value of the original data point in the fusion process is specifically expressed by the formula:

[0090]

[0091] Among them, the adjustment coefficient of the coordinate value of the symmetrical data point in the fusion process is specifically expressed by the formula:

[0092]

[0093] Where, Indicates the The coordinate values ​​of the original data points, Indicates the The coordinate value of the symmetrical data point corresponding to the original data point, Indicates the The adjustment coefficient of the coordinate value of the original data point, Indicates the The adjustment coefficient of the coordinate value of the symmetrical data point corresponding to the original data point, is a natural constant, For each subsequence data, It represents the angle between the target symmetry line and the horizontal line, Indicates the The target angle of the original data points; Indicates the The coordinate value of the adjusted data point after the final adjustment of the original data point; is the activation function; is a sine function.

[0094] Among them, through When adjusting data points, adjust the horizontal and vertical coordinate values ​​separately.

[0095] All the adjusted data points after the final adjustment corresponding to each subsequence are sorted in chronological order to form a new set of sequences, which are recorded as each recombinant subsequence; the GRU neural network is used to make predictions based on each recombinant subsequence, and the predicted data are organized into each predicted subsequence in chronological order.

[0096] When using a GRU neural network for prediction, the metrics MAE (Mean Absolute Error), SSE (Sum of Squared Errors), RMSE (Root Mean Square Error), and MAPE (Mean Absolute Percentage Error) are used to measure the prediction error. These metrics are used to evaluate the prediction results before and after the component signal adjustments. The loss function used in the GRU neural network is the cross-entropy loss function.

[0097] Among them, GRU neural network, MAE, SSE, RMSE, MAPE and cross entropy loss function are all well-known technologies and will not be described in detail here.

[0098] Step S004: superimpose all predicted subsequences to obtain predicted signal data of the final frequency modulation instruction.

[0099] The least squares method is used to perform curve fitting on each prediction subsequence to obtain the prediction fitting curve of each prediction subsequence. The prediction fitting curves of all prediction subsequences are superimposed in the frequency domain through Fourier transform to obtain the prediction signal data of the final frequency modulation instruction.

[0100] Among them, the above four indicators are used to perform prediction error analysis on the sequence after the FM command signal prediction and the predicted signal data of the final FM command; among them, the corresponding error indicators of the sequence after the FM command signal prediction are MAE 8.22, SSE 98.12, RMSE 0.97 and MAPE 16.02%; and the corresponding error indicators of each predicted subsequence after the adjusted prediction are MAE 0.56, SSE 10.01, RMSE 0.25 and MAPE 4.13%; from the results, the prediction error is significantly reduced, that is, the accuracy of the prediction is significantly improved.

[0101] Among them, the least square method and Fourier transform are both well-known technologies and will not be described in detail here.

[0102] like Figure 2 As shown, the second aspect of the present invention is to provide an energy storage frequency modulation instruction prediction system based on symmetric adjustment, including the following modules:

[0103] Data acquisition module 101: used to obtain frequency modulation command signals;

[0104] Symmetry adjustment module 102: used to decompose the frequency modulation command signal to obtain several component signals, then discretely divide each component signal to obtain a subsequence corresponding to each component signal; construct a coordinate system with time as the horizontal axis and the data in each subsequence as the vertical axis, and map all data in each subsequence into the coordinate system to obtain several original data points; determine the target symmetry line of each subsequence based on the distribution of all original data points in each subsequence; and perform symmetric mapping on each original data point based on the target symmetry line of each subsequence to obtain a symmetric data point for each original data point;

[0105] Fusion prediction module 103: used to fuse the original data points and the symmetric data points to obtain the final adjusted data points; perform prediction based on the adjusted data points corresponding to each subsequence to obtain each predicted subsequence;

[0106] The superposition module 104 is used to superpose all the predicted subsequences to obtain the predicted signal data of the final frequency modulation instruction.

[0107] The third aspect of the present invention is to provide an electronic device, including a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, it implements a method for predicting energy storage frequency modulation instructions based on symmetrical adjustment.

[0108] A fourth aspect of the present invention is to provide a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, a method for predicting energy storage frequency modulation instructions based on symmetrical adjustment is implemented.

[0109] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, optical storage, etc.) containing computer-usable program code.

[0110] The present invention is described with reference to flowcharts and / or block diagrams of methods, systems, and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0111] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0112] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0113] 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 instructions based on symmetrical adjustment, characterized in that: include: Obtain frequency modulation command signal; Decomposing the frequency modulation command signal to obtain several component signals, and then discretely dividing each component signal to obtain a subsequence corresponding to each component signal; With time as the horizontal axis and the data in each subsequence as the vertical axis, a coordinate system is constructed, and all the data in each subsequence are mapped into the coordinate system to obtain several original data points; According to the distribution of all original data points of each subsequence, the target symmetry line of each subsequence is determined; According to the target symmetry line of each subsequence, each original data point is symmetrically mapped to obtain the symmetrical data point of each original data point; The original data points and the symmetrical data points are merged to obtain the final adjusted data points; Make predictions through the adjusted data points corresponding to each subsequence to obtain each predicted subsequence; All predicted subsequences are superimposed to obtain the predicted signal data of the final frequency modulation instruction.

2. The energy storage frequency modulation instruction prediction method based on symmetric adjustment according to claim 1 is characterized in that: The step of decomposing the frequency modulation command signal to obtain a plurality of component signals, and then discretely dividing each component signal to obtain a subsequence corresponding to each component signal includes: The frequency modulation command signal is decomposed by VMD decomposition algorithm to obtain several component signals; Each component signal is divided to obtain a number of data corresponding to each component signal after division. The data are grouped into a set of sequences in chronological order, which are recorded as subsequences corresponding to each component signal.

3. The energy storage frequency modulation instruction prediction method based on symmetric adjustment according to claim 1 is characterized in that: Determining the target symmetry line of each subsequence based on the distribution of all original data points of each subsequence includes: The angle range of the symmetry line is determined by the distribution of all original data points in each subsequence. The angle range of the symmetry line is specifically expressed by the formula: The lower limit of the angle range of the symmetry line is specifically expressed by the formula: The upper limit of the angle range of the symmetry line is specifically expressed by the formula: Where, represents the set of all data in each subsequence, Represents the maximum absolute value of all data in each subsequence, Indicates the minimum absolute value of all data in each subsequence, Represents the minimum value of all data in each subsequence, Represents the maximum value of all data in each subsequence, is the absolute value symbol, represents the inverse tangent function, express Function, used for data normalization; Indicates the minimum angle of the symmetry line angle range, Indicates the maximum angle of the symmetry line angle range; It represents the angle between the line of symmetry and the horizontal line; Minimum angle from the symmetry line Start from the maximum angle of the symmetry line angle range , each time the iteration is performed with the preset angle as the increment; each time the iteration reference angle is changed, a new iteration reference angle is determined; through each iteration reference angle, each reference symmetry line corresponding to each iteration reference angle is determined, and the number of original data points existing on each reference symmetry line is obtained, which is recorded as the reference data amount of each reference symmetry line; The reference symmetry line with the largest amount of reference data is used as the target symmetry line for each subsequence.

4. The energy storage frequency modulation instruction prediction method based on symmetric adjustment according to claim 1 is characterized in that: The step of performing symmetric mapping on each original data point according to the target symmetry line of each subsequence to obtain a symmetric data point for each original data point includes: Where, Represents the minimum value of all data in each subsequence, Represents the maximum absolute value of all data in each subsequence, is the absolute value symbol, represents the inverse tangent function, express Function, used for data normalization, Indicates the first The data value of the data, Indicates the The target angle of the original data point is the angle between the extension line of the original data point and the corresponding target symmetry line; By using the target angle of each original data point, first determine the intersection point of the original data point extension line on the target symmetry line, and record it as the target symmetry line intersection point of each original data point; record the direction of each original data point pointing to the corresponding target symmetry line intersection point as the target extension direction of each original data point; The original data points are then extended along the target extension direction to obtain symmetrical data points; wherein, in the process of adjusting and obtaining the symmetrical data points, the angle between the symmetrical data points and the target symmetry line is equal to the target angle of the original data points, and the distance from the symmetrical data points to the intersection of the target symmetry line is equal to the distance from the original data points to the intersection of the target symmetry line.

5. The energy storage frequency modulation instruction prediction method based on symmetric adjustment according to claim 4 is characterized in that: The step of fusing the original data points with the symmetrical data points to obtain the final adjusted data points includes: The formula for fusing the original data points with the symmetric data points is specifically expressed as: Among them, the adjustment coefficient of the coordinate value of the original data point in the fusion process is specifically expressed by the formula: Among them, the adjustment coefficient of the coordinate value of the symmetrical data point in the fusion process is specifically expressed by the formula: Where, Indicates the The coordinate values ​​of the original data points, Indicates the The coordinate value of the symmetrical data point corresponding to the original data point, Indicates the The adjustment coefficient of the coordinate value of the original data point, Indicates the The adjustment coefficient of the coordinate value of the symmetrical data point corresponding to the original data point, is a natural constant, For each subsequence data, It represents the angle between the target symmetry line and the horizontal line, Indicates the The target angle of the original data points; Indicates the The coordinate value of the adjusted data point after the final adjustment of the original data point; is the activation function; is a sine function; Among them, through When adjusting data points, adjust the horizontal and vertical coordinate values ​​separately.

6. The energy storage frequency modulation instruction prediction method based on symmetric adjustment according to claim 1 is characterized in that: The step of performing prediction by adjusting the data points corresponding to each subsequence to obtain each predicted subsequence includes: All the adjusted data points after the final adjustment corresponding to each subsequence are sorted in chronological order to form a new set of sequences, which are recorded as each recombinant subsequence; the GRU neural network is used to make predictions based on each recombinant subsequence, and the predicted data are organized into each predicted subsequence in chronological order.

7. The energy storage frequency modulation instruction prediction method based on symmetric adjustment according to claim 1 is characterized in that: The step of superimposing all predicted subsequences to obtain predicted signal data of the final frequency modulation instruction includes: Through the least squares method, curve fitting is performed on each prediction subsequence to obtain the prediction fitting curve of each prediction subsequence; through Fourier transform, the prediction fitting curves of all prediction subsequences are superimposed in the frequency domain to obtain the prediction signal data of the final frequency modulation instruction.

8. A storage frequency modulation instruction prediction system based on symmetrical adjustment, characterized in that: include: Data acquisition module: used to obtain frequency modulation command signals; Symmetric adjustment module: used to decompose the frequency modulation command signal to obtain several component signals, and then discretely divide each component signal to obtain the subsequence corresponding to each component signal; With time as the horizontal axis and the data in each subsequence as the vertical axis, a coordinate system is constructed, and all the data in each subsequence are mapped into the coordinate system to obtain several original data points; According to the distribution of all original data points of each subsequence, the target symmetry line of each subsequence is determined; According to the target symmetry line of each subsequence, each original data point is symmetrically mapped to obtain the symmetrical data point of each original data point; Fusion prediction module: used to fuse the original data points and the symmetric data points to obtain the final adjusted data points; Make predictions through the adjusted data points corresponding to each subsequence to obtain each predicted subsequence; Superposition module: used to superimpose all predicted subsequences to obtain the predicted signal data of the final frequency modulation instruction.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for predicting energy storage frequency modulation instructions based on symmetrical adjustment as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements the energy storage frequency modulation instruction prediction method based on symmetric adjustment as described in any one of claims 1 to 7.

Images