Prediction method and system for optimizing frequency modulation instruction of hybrid energy storage system

Abstract

The invention relates to the technical field of power grid frequency modulation, in particular to a prediction method and system for optimizing a frequency modulation instruction of a hybrid energy storage system, and the method comprises the steps: obtaining a proportion increment sequence and a second-order proportion increment sequence according to the ratio of adjacent data in a frequency modulation instruction sequence; obtaining a difference value increment sequence and a second-order difference value increment sequence according to a difference value between adjacent data in the frequency modulation instruction sequence; acquiring a frequency modulation instruction data range corresponding to each piece of data in the frequency modulation instruction sequence; sequentially and randomly selecting a plurality of frequency modulation instruction random sequences through a frequency modulation instruction data range corresponding to each piece of data in the frequency modulation instruction sequence, and obtaining an optimal frequency modulation instruction random sequence according to the proportion increment sequence, the second-order proportion increment sequence, the difference value increment sequence and the second-order difference value increment sequence; and performing subsequent prediction on the optimal frequency modulation instruction random sequence, and performing frequency modulation control of hybrid energy storage through predicted data. According to the invention, the accuracy of hybrid energy storage frequency modulation control is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of power grid frequency modulation, and particularly to a method and system for optimizing the prediction of frequency modulation commands for a hybrid energy storage system. Background Art

[0002] Frequency modulation command prediction for energy storage refers to predicting the changes in frequency modulation commands when using an energy storage system to perform frequency regulation (frequency modulation) tasks in a power system, so as to optimize the scheduling and response of the energy storage system. Frequency regulation in a power system is very important. Especially with the increasing proportion of renewable energy sources (such as wind energy and solar energy), the instability of frequency increases, and the energy storage system plays an increasingly important role in this context.

[0003] The frequency modulation command refers to a signal sent by a power system dispatching center or automation equipment, telling the energy storage system how to adjust the charge and discharge power to maintain the stability of the power grid frequency. The energy storage system needs to quickly respond to emergencies and faults according to these frequency modulation commands to ensure frequency stability.

[0004] Traditional thermal power units require the assistance of a hybrid energy storage (ultracapacitor and lithium battery) system to meet certain requirements; therefore, when there is a difference between the output of the thermal power unit and the frequency modulation command, due to the slow response speed of the thermal power unit, at this time, the hybrid energy storage system is needed to assist the thermal power unit to keep the system stable. Since the hybrid energy storage contains both ultracapacitors and lithium batteries, when using the frequency modulation command to control the hybrid energy storage; the transmission of the frequency modulation command signal takes time. Therefore, the frequency modulation command signal in historical data can be used to predict the signal at subsequent moments, so as to reduce the delay caused by the transmission time; however, due to various noises interfering with the frequency modulation command signal during transmission, there are errors in the frequency modulation command signal in the obtained historical data. Therefore, when using the signal with errors to predict subsequent signals, it will cause large errors, resulting in a decrease in the accuracy of the hybrid energy storage frequency modulation control and affecting the steady state of the system. Summary of the Invention

[0005] The present invention provides a method and system for optimizing the prediction of frequency modulation commands for a hybrid energy storage system, which is used to solve the problem of noise interference in the frequency modulation command signal.

[0006] The object of the present invention can be achieved by the following technical solutions: The first aspect of the present invention is to provide a method for optimizing the prediction of frequency modulation commands for a hybrid energy storage system, including: Obtain the frequency modulation command signal; Divide the frequency modulation command signal to obtain a frequency modulation command sequence; obtain a proportional increment sequence according to the ratio between adjacent data in the frequency modulation command sequence; obtain a difference increment sequence according to the difference between adjacent data in the frequency modulation command sequence; obtain a second-order proportional increment sequence according to the ratio between adjacent data in the proportional increment sequence; obtain a second-order difference increment sequence according to the difference between adjacent data in the difference increment sequence; Obtain the frequency modulation command data range corresponding to each data in the frequency modulation command sequence; randomly select several frequency modulation command random sequences in turn through the frequency modulation command data range corresponding to each data in the frequency modulation command sequence, and perform iterative analysis on the several frequency modulation command random sequences in turn according to the proportional increment sequence, the difference increment sequence, the second-order proportional increment sequence, and the second-order difference increment sequence to obtain an optimal frequency modulation command random sequence; According to the optimal frequency modulation command random sequence, perform subsequent prediction through a GRU neural network, and perform frequency modulation control of the hybrid energy storage through the predicted data.

[0007] Further, the dividing the frequency modulation command signal to obtain a frequency modulation command sequence includes: At a preset time interval divide the frequency modulation command signal to obtain several corresponding data after the division of the frequency modulation command signal, and form a group of sequences in chronological order, denoted as the frequency modulation command sequence.

[0008] Further, the obtaining a proportional increment sequence according to the ratio between adjacent data in the frequency modulation command sequence; obtaining a difference increment sequence according to the difference between adjacent data in the frequency modulation command sequence includes:

[0009] wherein, represents the th data in the frequency modulation command sequence, represents the th data in the frequency modulation command sequence, represents the data value corresponding to the th element in the proportional increment sequence;

[0010] wherein, represents the exponential function with the natural constant as the base, represents the data value corresponding to the th element in the difference increment sequence.

[0011] Further, the obtaining a second-order proportional increment sequence according to the ratio between adjacent data in the proportional increment sequence; obtaining a second-order difference increment sequence according to the difference between adjacent data in the difference increment sequence includes:

[0012] In the formula, represents the data value corresponding to the th element in the proportional increment sequence, represents the logarithmic function with the natural constant as the base, represents the absolute value symbol, represents the data value corresponding to the th element in the second-order proportional increment sequence;

[0013] In the formula, represents the data value corresponding to the th element in the difference increment sequence, represents the data value corresponding to the th element in the second-order difference increment sequence, represents the absolute value symbol.

[0014] Furthermore, obtaining the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence includes:

[0015] In the formula, represents the th data in the frequency modulation instruction sequence, represents the natural constant, represents the minimum value function, represents the maximum value function.

[0016] Furthermore, randomly selecting a number of frequency modulation instruction random sequences in turn according to the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence, and iteratively analyzing the number of frequency modulation instruction random sequences in turn according to the proportional increment sequence, difference increment sequence, second-order proportional increment sequence and second-order difference increment sequence to obtain the optimal frequency modulation instruction random sequence, includes: For the first time, randomly select all data within the FM command data range corresponding to each data in the FM command sequence to obtain the first FM command random sequence. Determine whether the first FM command random sequence meets the requirements. If it does, use the first FM command random sequence as the optimal FM command random sequence and stop the iteration; if not, continue to randomly select all data within the FM command data range corresponding to each data in the FM command sequence for the second time to obtain the second FM command random sequence. Determine whether the second FM command random sequence meets the requirements. If it does, use the second FM command random sequence as the optimal FM command random sequence and stop the iteration; if not, continue to randomly select all data within the FM command data range corresponding to each data in the FM command sequence for the third time to obtain the third FM command random sequence. Determine whether the third FM command random sequence meets the requirements. If it does, use the third FM command random sequence as the optimal FM command random sequence and stop the iteration; if not, continue with subsequent selections and determinations in this way until the optimal FM command random sequence is selected.

[0017] Further, the conditions for whether the FM command random sequence meets the requirements specifically include: The first condition is that for each FM command random sequence and the FM command sequence, the data values corresponding to each element in the corresponding ratio increment sequence and difference increment sequence must be between ; where represents the first low threshold, represents the first high threshold; The second condition is to calculate the ratio between the average value of the data values corresponding to all elements in each FM command random sequence and the average value of the data values corresponding to all elements in the FM command sequence. The ratio must be between ; where represents the second low threshold, represents the second high threshold; The third condition is to calculate the difference between the serial number corresponding to the maximum value in each FM command random sequence and the serial number corresponding to the maximum value in the FM command sequence. The difference must be less than or equal to , where is the number of all data in the FM command sequence, represents rounding to an integer; where represents the first preset parameter; The fourth condition is that the maximum value in each FM command random sequence is less than or equal to times the maximum value in the FM command sequence; where represents the second preset parameter; Among them, in the process of obtaining the proportional increment sequence, the difference increment sequence, the second-order proportional increment sequence, and the second-order difference increment sequence according to the frequency modulation instruction sequence, the proportional increment sequence, the difference increment sequence, the second-order proportional increment sequence, and the second-order difference increment sequence corresponding to each frequency modulation instruction random sequence are obtained.

[0018] The second aspect of the present invention is to provide a system for optimizing the frequency modulation instruction prediction of a hybrid energy storage system, including: Data acquisition module: used to obtain the frequency modulation instruction signal; Sequence construction module: used to divide the frequency modulation instruction signal to obtain the frequency modulation instruction sequence; obtain the proportional increment sequence according to the ratio between adjacent data in the frequency modulation instruction sequence; obtain the difference increment sequence according to the difference between adjacent data in the frequency modulation instruction sequence; obtain the second-order proportional increment sequence according to the ratio between adjacent data in the proportional increment sequence; obtain the second-order difference increment sequence according to the difference between adjacent data in the difference increment sequence; Optimal analysis module: used to obtain the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence; randomly select a number of frequency modulation instruction random sequences in turn through the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence, and perform iterative analysis on the number of frequency modulation instruction random sequences in turn according to the proportional increment sequence, the difference increment sequence, the second-order proportional increment sequence, and the second-order difference increment sequence to obtain the optimal frequency modulation instruction random sequence; Prediction control module: used to perform subsequent prediction through the GRU neural network according to the optimal frequency modulation instruction random sequence, and perform frequency modulation control of the hybrid energy storage through the predicted data.

[0019] 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 executable on the processor. When the processor executes the computer program, it implements the method for optimizing the frequency modulation instruction prediction of a hybrid energy storage system.

[0020] The 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, it implements the method for optimizing the frequency modulation instruction prediction of a hybrid energy storage system.

[0021] Compared with the prior art, the beneficial effects of the present invention are as follows: obtaining a ratio increment sequence according to the ratio between adjacent data in the frequency modulation instruction sequence; obtaining a difference increment sequence according to the difference between adjacent data in the frequency modulation instruction sequence; obtaining a second-order ratio increment sequence according to the ratio between adjacent data in the ratio increment sequence; obtaining a second-order difference increment sequence according to the difference between adjacent data in the difference increment sequence; improving the accuracy of analyzing all adjacent data in the frequency modulation instruction sequence; obtaining the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence; randomly selecting a number of frequency modulation instruction random sequences in turn through the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence, and iteratively analyzing the number of frequency modulation instruction random sequences in turn according to the ratio increment sequence, the difference increment sequence, the second-order ratio increment sequence and the second-order difference increment sequence to obtain the optimal frequency modulation instruction random sequence, reducing the influence of noise interference; according to the optimal frequency modulation instruction random sequence, performing subsequent prediction through a GRU (Gated Recurrent Unit) neural network, and performing frequency modulation control of the hybrid energy storage through the predicted data, improving the accuracy of the frequency modulation control of the hybrid energy storage and improving the stability of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the 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 drawings can be obtained based on these drawings.

[0023] Figure 1 It is a schematic flow chart of the steps of a method for optimizing the frequency modulation instruction prediction of a hybrid energy storage system provided by the present invention; Figure 2 It is a schematic module flow chart of a system for optimizing the frequency modulation instruction prediction of a hybrid energy storage system provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] In order to enable those skilled in the art to better understand the solution of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0025] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, 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 "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0026] In view of the problems existing in the background technology, it is of great practical significance to research and design a method and system for optimizing the frequency modulation command prediction of a hybrid energy storage system.

[0027] As Figure 1 shown, the first aspect of the present invention is to provide a method for optimizing the frequency modulation command prediction of a hybrid energy storage system, including the following steps: Step S001: Collect frequency modulation command signals.

[0028] It should be noted that when there is a deviation in the power supply and demand balance (such as load changes, power generation fluctuations, etc.). The dispatching center or automation system of the power system generates frequency modulation commands according to the frequency fluctuation conditions, load demands and power generation conditions of the system, and maintains frequency stability through the frequency modulation commands, which can respond to emergencies and reduce the possibility of failures.

[0029] Specifically, obtain the frequency modulation command signals of the power system dispatching center for a preset duration hours before the current moment. Among them, in this embodiment, the preset duration , and in this embodiment, the preset duration is not specifically limited, and the implementer can determine it according to the specific situation.

[0030] Thus, the frequency modulation command signal is obtained.

[0031] Step S002: Divide the frequency modulation command signal to obtain a frequency modulation command sequence; obtain a proportional increment sequence according to the ratio between adjacent data in the frequency modulation command sequence; obtain a difference increment sequence according to the difference between adjacent data in the frequency modulation command sequence; obtain a second-order proportional increment sequence according to the ratio between adjacent data in the proportional increment sequence; obtain a second-order difference increment sequence according to the difference between adjacent data in the difference increment sequence.

[0032] It should be noted that since the distribution of data in the frequency modulation command signal can reflect the change characteristics of the signal data, and the change and fluctuation differences of the signal data can reflect the error characteristics of the data, the frequency modulation command signal is divided into data points to analyze the data error situation.

[0033] Specifically, at a preset time interval the frequency modulation command signal is divided to obtain a number of corresponding data after the division of the frequency modulation command signal. According to the time sequence, the number of data is composed into a group of sequences, denoted as the frequency modulation command sequence. Among them, in this embodiment, the preset time interval is seconds. Among them, the preset time interval

[0034] is not specifically limited, and the implementer can determine it according to the specific situation.

[0035] It should be noted that in the case of normal absence of noise interference, the change of the frequency modulation command is usually continuous, and the change of the frequency offset will transition smoothly. Therefore, the difference between adjacent data is usually smooth and there will be no violent fluctuations; therefore, the interference situation can be analyzed by the difference between all adjacent data in the frequency modulation command sequence.

[0036] Specifically, a proportional increment sequence and a difference increment sequence are constructed through the frequency modulation command sequence; Among them, the process of constructing each element in the proportional increment sequence is specifically expressed by the formula:

[0037] In the formula, represents the th data in the frequency modulation command sequence, represents the th data in the frequency modulation command sequence, represents the data value corresponding to the th element in the proportional increment sequence.

[0038] Among them, the process of constructing each element in the difference increment sequence is specifically expressed by the formula:

[0039] In the formula, represents the th data in the frequency modulation command sequence, represents the th data in the frequency modulation command sequence, represents the exponential function with the natural constant as the base, represents the data value corresponding to the th element in the difference increment sequence.

[0040] Construct a second-order proportional increment sequence according to the proportional increment sequence; the process of constructing each element in the second-order proportional increment sequence is specifically expressed by the formula:

[0041] In the formula, represents the data value corresponding to the -th element in the proportional increment sequence, represents the data value corresponding to the -th element in the proportional increment sequence, represents the logarithmic function with the natural constant as the base, represents the absolute value symbol, represents the data value corresponding to the -th element in the second-order proportional increment sequence.

[0042] Construct a second-order difference increment sequence according to the difference increment sequence; the process of constructing each element in the second-order difference increment sequence is specifically expressed by the formula:

[0043] In the formula, represents the data value corresponding to the -th element in the difference increment sequence, represents the data value corresponding to the -th element in the difference increment sequence, represents the data value corresponding to the -th element in the second-order difference increment sequence, represents the absolute value symbol.

[0044] Among them, the data values of the last element in the proportional increment sequence, difference increment sequence, second-order proportional increment sequence, and second-order difference increment sequence are equal to the data values of the penultimate element.

[0045] Thus, the proportional increment sequence, difference increment sequence, second-order proportional increment sequence, and second-order difference increment sequence of the frequency modulation command sequence are obtained.

[0046] Step S003: Obtain the frequency modulation command data range corresponding to each data in the frequency modulation command sequence; randomly select several frequency modulation command random sequences in turn through the frequency modulation command data range corresponding to each data in the frequency modulation command sequence, and perform iterative analysis on the several frequency modulation command random sequences in turn according to the proportional increment sequence, difference increment sequence, second-order proportional increment sequence, and second-order difference increment sequence to obtain the optimal frequency modulation command random sequence.

[0047] It should be noted that in order to remove the interference effect of noise on the frequency modulation command sequence, by setting a range, a set of data is randomly selected within the set range to simulate the frequency modulation command sequence, and finally, based on the differences between the randomly selected set of data and the frequency modulation command sequence, the corresponding ratio increment sequence, difference increment sequence, second-order ratio increment sequence, and second-order difference increment sequence, the final value of the randomly selected set of data is determined.

[0048] Specifically, set the frequency modulation command data range corresponding to each data in the frequency modulation command sequence, and the frequency modulation command data range is specifically expressed as:

[0049] In the formula, represents the th data in the frequency modulation command sequence, represents the natural constant, represents the minimum value function, represents the maximum value function.

[0050] Randomly select a set of data in turn according to the frequency modulation command data range corresponding to each data in the frequency modulation command sequence, and form a set of sequences in the selected order, denoted as the frequency modulation command random sequence. Among them, the number of data in the frequency modulation command random sequence is the same as the number of data in the frequency modulation command sequence.

[0051] Obtain the ratio increment sequence, difference increment sequence, second-order ratio increment sequence, and second-order difference increment sequence corresponding to each frequency modulation command random sequence according to the process of obtaining the ratio increment sequence, difference increment sequence, second-order ratio increment sequence, and second-order difference increment sequence from the frequency modulation command sequence.

[0052] Determine the optimal frequency modulation command random sequence according to the differences between the frequency modulation command random sequence, the ratio increment sequence, difference increment sequence, second-order ratio increment sequence, and second-order difference increment sequence corresponding to the frequency modulation command sequence; the specific process of determining the optimal frequency modulation command random sequence is as follows: Perform a first random selection of all data within the FM command data range corresponding to each data in the FM command sequence to obtain the first FM command random sequence. Determine whether the first FM command random sequence meets the requirements. If it does, use the first FM command random sequence as the optimal FM command random sequence and stop the iteration. If it does not, continue to perform a second random selection of all data within the FM command data range corresponding to each data in the FM command sequence to obtain the second FM command random sequence. Determine whether the second FM command random sequence meets the requirements. If it does, use the second FM command random sequence as the optimal FM command random sequence and stop the iteration. If it does not, continue to perform a third random selection of all data within the FM command data range corresponding to each data in the FM command sequence to obtain the third FM command random sequence. Determine whether the third FM command random sequence meets the requirements. If it does, use the third FM command random sequence as the optimal FM command random sequence and stop the iteration. If it does not, continue the subsequent selection and determination in this way until the optimal FM command random sequence is selected.

[0053] Among them, the condition for whether each FM command random sequence meets the requirements is specifically as follows: The first condition is that for each FM command random sequence and the FM command sequence, the data value range of each element in the corresponding ratio increment sequence and difference increment sequence must be between ; among them, represents the first low threshold, represents the first high threshold; among them, in this embodiment, the first low threshold , the first high threshold , where in this embodiment, the first low threshold and the first high threshold are not specifically limited, and the implementer can determine according to the specific situation.

[0054] The second condition is to calculate the ratio between the average value of the data values corresponding to all elements in each FM command random sequence and the average value of the data values corresponding to all elements in the FM command sequence. The ratio must be between ; among them, represents the second low threshold, represents the second high threshold; among them, in this embodiment, the second low threshold , the second high threshold , where in this embodiment, the second low threshold and the second high threshold are not specifically limited, and the implementer can determine according to the specific situation.

[0055] The third condition is to calculate the difference between the serial number corresponding to the maximum value in each random sequence of frequency modulation commands and the serial number corresponding to the maximum value in the frequency modulation command sequence, and the difference must be less than or equal to , where is the number of all data in the frequency modulation command sequence, denotes rounding to the nearest integer; where represents the first preset parameter, where, in this embodiment, the first preset parameter , where, in this embodiment, for the first preset parameter no specific limitation is made, and the implementer can determine it according to the specific situation.

[0056] The fourth condition is that the maximum value in each random sequence of frequency modulation commands is less than or equal to times the maximum value in the frequency modulation command sequence; where represents the second preset parameter, where, in this embodiment, the second preset parameter , where, in this embodiment, for the second preset parameter no specific limitation is made, and the implementer can determine it according to the specific situation.

[0057] Thus, the optimal random sequence of frequency modulation commands is obtained.

[0058] Step S004: Perform subsequent prediction through the optimal random sequence of frequency modulation commands, and perform frequency modulation control of the hybrid energy storage through the predicted data.

[0059] According to the optimal random sequence of frequency modulation commands, perform subsequent prediction through the GRU neural network, and perform frequency modulation control of the supercapacitor and the battery through the predicted data; where the loss function in the GRU neural network is the cross-entropy loss function; and the GRU neural network is a well-known technology, so no specific elaboration will be made here. Among them, error analysis is performed on the sequence corresponding to the frequency modulation command signal and the optimal random sequence of frequency modulation commands through MAPE (Mean Absolute Percentage Error, average absolute percentage error); where the average absolute percentage error corresponding to the sequence after predicting the frequency modulation command signal is 9.6, while the average absolute percentage error corresponding to the sequence after predicting the optimal random sequence of frequency modulation commands is 6.9. It can be seen from the results that the error is reduced, which means that the accuracy of the prediction is improved.

[0060] As Figure 2 shown, the second aspect of the present invention is to provide a system for optimizing the prediction system of the frequency modulation commands of a hybrid energy storage system, including the following modules: Data acquisition module 101: used to obtain the frequency modulation command signal; Sequence construction module 102: used to divide the frequency modulation command signal to obtain a frequency modulation command sequence; obtain a proportional increment sequence according to the ratio between adjacent data in the frequency modulation command sequence; obtain a difference increment sequence according to the difference between adjacent data in the frequency modulation command sequence; obtain a second-order proportional increment sequence according to the ratio between adjacent data in the proportional increment sequence; obtain a second-order difference increment sequence according to the difference between adjacent data in the difference increment sequence. Optimal analysis module 103: used to obtain the frequency modulation command data range corresponding to each data in the frequency modulation command sequence; randomly select a number of frequency modulation command random sequences in turn through the frequency modulation command data range corresponding to each data in the frequency modulation command sequence, and perform iterative analysis on the number of frequency modulation command random sequences in turn according to the proportional increment sequence, difference increment sequence, second-order proportional increment sequence, and second-order difference increment sequence to obtain an optimal frequency modulation command random sequence. Prediction control module 104: used to perform subsequent prediction through a GRU neural network according to the optimal frequency modulation command random sequence, and perform frequency modulation control of the hybrid energy storage through the predicted data.

[0061] 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 executable on the processor. When the processor executes the computer program, it implements a method for optimizing the frequency modulation command prediction of a hybrid energy storage system.

[0062] The fourth aspect of the present invention is to provide a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, it implements a method for optimizing the frequency modulation command prediction of a hybrid energy storage system.

[0063] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) containing computer-usable program code.

[0064] The present invention is described with reference to the flowcharts and / or block diagrams of methods, systems, and computer program products according to the embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of the processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate for implementation in the processFigure 1 one process or multiple processes and / or boxes Figure 1 a device for the functions specified in one box or multiple boxes.

[0065] These computer program instructions can 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 a manufactured article including an instruction device, and the instruction device implements the process Figure 1 one process or multiple processes and / or boxes Figure 1 the functions specified in one box or multiple boxes.

[0066] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to produce a computer-implemented process. Therefore, the instructions executed on the computer or other programmable device provide for implementing the process Figure 1 one process or multiple processes and / or boxes Figure 1 the steps of the functions specified in one box or multiple boxes.

[0067] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: the specific implementation manners of the present invention can still be modified or equivalently replaced, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the present invention.

Claims

1. A method for optimizing the prediction of frequency regulation commands for a hybrid energy storage system, characterized in that, Including: Obtain a frequency modulation command signal; Divide the frequency modulation command signal to obtain a frequency modulation command sequence; Obtain a proportional increment sequence according to the ratio between adjacent data in the frequency modulation command sequence; obtain a difference increment sequence according to the difference between adjacent data in the frequency modulation command sequence; obtain a second-order proportional increment sequence according to the ratio between adjacent data in the proportional increment sequence; obtain a second-order difference increment sequence according to the difference between adjacent data in the difference increment sequence; Obtain the frequency modulation command data range corresponding to each data in the frequency modulation command sequence; randomly select a number of frequency modulation random sequences in turn through the frequency modulation command data range corresponding to each data in the frequency modulation command sequence, and perform iterative analysis on the number of frequency modulation random sequences in turn according to the proportional increment sequence, the difference increment sequence, the second-order proportional increment sequence, and the second-order difference increment sequence to obtain an optimal frequency modulation random sequence; According to the optimal frequency modulation random sequence, perform subsequent prediction through a GRU neural network, and perform frequency modulation control of the hybrid energy storage through the predicted data.

2. The method for predicting frequency modulation commands of a hybrid energy storage system for optimization according to claim 1, wherein The dividing the frequency modulation command signal to obtain a frequency modulation command sequence includes: At a preset time interval divide the frequency modulation command signal to obtain a number of corresponding data after the division of the frequency modulation command signal, and form a group of sequences of the number of data in chronological order, denoted as the frequency modulation command sequence.

3. A method for predicting frequency modulation commands for optimizing a hybrid energy storage system according to claim 1, wherein The obtaining a proportional increment sequence according to the ratio between adjacent data in the frequency modulation command sequence; obtaining a difference increment sequence according to the difference between adjacent data in the frequency modulation command sequence includes: In the formula, represents the th data in the frequency modulation command sequence, represents the th data in the frequency modulation command sequence, represents the data value corresponding to the th element in the proportional increment sequence; In the formula, represents the exponential function with the natural constant as the base, represents the data value corresponding to the -th element in the difference increment sequence.

4. A method for predicting frequency modulation commands for optimizing a hybrid energy storage system according to claim 3, characterized in that, The obtaining a second-order proportional increment sequence according to the ratio between adjacent data in the proportional increment sequence; obtaining a second-order difference increment sequence according to the difference between adjacent data in the difference increment sequence includes: wherein, represents the data value corresponding to the -th element in the proportional increment sequence, represents the logarithmic function with the natural constant as the base, represents the absolute value symbol, represents the data value corresponding to the -th element in the second-order proportional increment sequence; In the formula, represents the data value corresponding to the -th element in the difference increment sequence, represents the data value corresponding to the -th element in the second-order difference increment sequence, represents the absolute value symbol.

5. A method for predicting frequency modulation commands for optimizing a hybrid energy storage system according to claim 4, characterized in that, The obtaining the frequency modulation command data range corresponding to each data in the frequency modulation command sequence includes: In the formula, represents the th data in the frequency modulation command sequence, represents the natural constant, represents the minimum value function, represents the maximum value function.

6. A method for predicting frequency modulation commands for optimizing a hybrid energy storage system according to claim 5, wherein The randomly selecting a number of frequency modulation random sequences in turn through the frequency modulation command data range corresponding to each data in the frequency modulation command sequence, and performing iterative analysis on the number of frequency modulation random sequences in turn according to the proportional increment sequence, the difference increment sequence, the second-order proportional increment sequence, and the second-order difference increment sequence to obtain an optimal frequency modulation random sequence includes: Perform a first random selection of all data within the frequency modulation command data range corresponding to each data in the frequency modulation command sequence to obtain a first random sequence of frequency modulation commands. Determine whether the first random sequence of frequency modulation commands meets the requirements. If it does, use the first random sequence of frequency modulation commands as the optimal random sequence of frequency modulation commands and stop the iteration; if it does not, continue to perform a second random selection of all data within the frequency modulation command data range corresponding to each data in the frequency modulation command sequence to obtain a second random sequence of frequency modulation commands. Determine whether the second random sequence of frequency modulation commands meets the requirements. If it does, use the second random sequence of frequency modulation commands as the optimal random sequence of frequency modulation commands and stop the iteration; if it does not, continue to perform a third random selection of all data within the frequency modulation command data range corresponding to each data in the frequency modulation command sequence to obtain a third random sequence of frequency modulation commands. Determine whether the third random sequence of frequency modulation commands meets the requirements. If it does, use the third random sequence of frequency modulation commands as the optimal random sequence of frequency modulation commands and stop the iteration; if it does not, continue in this way to perform subsequent selections and determinations until the optimal random sequence of frequency modulation commands is selected.

7. A method for optimizing the frequency modulation command prediction of a hybrid energy storage system according to claim 6, characterized in that, The conditions for whether the random sequence of frequency modulation commands meets the requirements specifically include: The first condition is that the range of the data value corresponding to each element in each frequency modulation instruction random sequence, frequency modulation instruction sequence, corresponding ratio increment sequence, and difference increment sequence must be between ; among them, represents the first low threshold, represents the first high threshold; Second condition, calculate the ratio between the average value of the data values corresponding to all elements in each random sequence of frequency modulation commands and the average value of the data values corresponding to all elements in the frequency modulation command sequence, and the ratio must be between ; where represents the second lowest threshold value, represents the second highest threshold value; The third condition is to calculate the difference between the serial number corresponding to the maximum value in each random sequence of frequency modulation commands and the serial number corresponding to the maximum value in the frequency modulation command sequence, and the difference must be less than or equal to , where is the number of all data in the frequency modulation command sequence, represents rounding to the nearest integer; among them, represents the first preset parameter; Fourth condition, the maximum value in each random sequence of frequency modulation commands is less than or equal to times the maximum value in the frequency modulation command sequence; where represents the second preset parameter. Among them, in the process of obtaining the ratio increment sequence, difference increment sequence, second-order ratio increment sequence, and second-order difference increment sequence according to the frequency modulation command sequence, obtain the ratio increment sequence, difference increment sequence, second-order ratio increment sequence, and second-order difference increment sequence corresponding to each random sequence of frequency modulation commands.

8. A frequency modulation command prediction system for optimizing a hybrid energy storage system, characterized in that, Include: Data acquisition module: used to obtain the frequency modulation command signal; Sequence construction module: used to divide the frequency modulation command signal to obtain the frequency modulation command sequence; Obtain the ratio increment sequence according to the ratio between adjacent data in the frequency modulation command sequence; obtain the difference increment sequence according to the difference between adjacent data in the frequency modulation command sequence; obtain the second-order ratio increment sequence according to the ratio between adjacent data in the ratio increment sequence; obtain the second-order difference increment sequence according to the difference between adjacent data in the difference increment sequence; Optimal analysis module: used to obtain the frequency modulation command data range corresponding to each data in the frequency modulation command sequence; randomly select a number of random sequences of frequency modulation commands in turn through the frequency modulation command data range corresponding to each data in the frequency modulation command sequence, and perform iterative analysis on the number of random sequences of frequency modulation commands in turn according to the ratio increment sequence, difference increment sequence, second-order ratio increment sequence, and second-order difference increment sequence to obtain the optimal random sequence of frequency modulation commands; Prediction control module: used to perform subsequent prediction through the GRU neural network according to the optimal random sequence of frequency modulation commands, and perform frequency modulation control of the hybrid energy storage through the predicted data.

9. An electronic device, characterized in that, Include a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method for optimizing the frequency modulation command prediction of the hybrid energy storage system according to any one of claims 1-7.

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 method for predicting frequency modulation instructions for optimizing a hybrid energy storage system according to any one of claims 1-7.

Images