A method and system for predicting frequency modulation instructions for optimizing hybrid energy storage systems

Abstract

The present invention relates to the field of power grid frequency regulation technology, and specifically to a method and system for optimizing frequency regulation instruction prediction for a hybrid energy storage system, comprising: obtaining a proportional increment sequence and a second-order proportional increment sequence based on the ratio between adjacent data in a frequency regulation instruction sequence; obtaining a differential increment sequence and a second-order differential increment sequence based on the difference between adjacent data in the frequency regulation instruction sequence; obtaining a frequency regulation instruction data range corresponding to each data in the frequency regulation instruction sequence; randomly selecting a plurality of frequency regulation instruction random sequences based on the frequency regulation instruction data range corresponding to each data in the frequency regulation instruction sequence, obtaining an optimal frequency regulation instruction random sequence based on the proportional increment sequence and the second-order proportional increment sequence, the differential increment sequence and the second-order differential increment sequence; and subsequently predicting the optimal frequency regulation instruction random sequence, and performing frequency regulation control of the hybrid energy storage using the predicted data. The present invention improves the accuracy of frequency regulation control of the hybrid energy storage.

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 frequency regulation instructions for optimizing a hybrid energy storage system. 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 must respond quickly to emergencies and faults based on these frequency regulation commands to ensure frequency stability.

[0004] Traditional thermal power units require the assistance of a hybrid energy storage system (supercapacitors and lithium batteries) to meet certain requirements. Therefore, when there is a difference between the output of a thermal power unit and the frequency modulation command, the thermal power unit's slow response speed requires the assistance of a hybrid energy storage system to maintain system stability. Since hybrid energy storage includes both supercapacitors and lithium batteries, when using frequency modulation commands 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 times to reduce delays caused by transmission time. However, due to various noise interference during the transmission of the frequency modulation command signal, the frequency modulation command signal in the acquired historical data contains errors. Therefore, using the erroneous signal to predict the subsequent signal will cause a large error, resulting in a decrease in the accuracy of the hybrid energy storage frequency modulation control and affecting the system's steady state. Summary of the Invention

[0005] The present invention provides a method and system for predicting frequency modulation instructions for optimizing a hybrid energy storage system, which are used to solve the problem of noise interference in frequency modulation instruction signals.

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

[0007] A first aspect of the present invention is to provide a method for predicting frequency modulation instructions for optimizing a hybrid energy storage system, comprising:

[0008] Obtain frequency modulation command signal;

[0009] The frequency modulation instruction signal is divided to obtain a frequency modulation instruction sequence; a proportional increment sequence is obtained according to the ratio between adjacent data in the frequency modulation instruction sequence; a differential increment sequence is obtained according to the difference between adjacent data in the frequency modulation instruction sequence; a second-order proportional increment sequence is obtained according to the ratio between adjacent data in the proportional increment sequence; a second-order differential increment sequence is obtained according to the difference between adjacent data in the differential increment sequence;

[0010] Obtaining a 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 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 according to a proportional increment sequence, a difference increment sequence, a second-order proportional increment sequence, and a second-order difference increment sequence to obtain an optimal frequency modulation instruction random sequence;

[0011] According to the random sequence of optimal frequency modulation instructions, subsequent predictions are made through the GRU neural network, and the frequency modulation control of the hybrid energy storage is carried out using the predicted data.

[0012] Furthermore, dividing the frequency modulation instruction signal to obtain the frequency modulation instruction sequence includes:

[0013] At preset time intervals The frequency modulation command signal is divided to obtain a number of data corresponding to the divided frequency modulation command signal. The data are grouped into a sequence in chronological order, which is recorded as a frequency modulation command sequence.

[0014] Furthermore, the method of obtaining a proportional increment sequence according to a ratio between adjacent data in the frequency modulation instruction sequence and obtaining a differential increment sequence according to a difference between adjacent data in the frequency modulation instruction sequence includes:

[0015]

[0016] Where, Indicates the first data, Indicates the first data, Indicates the first The data value corresponding to each element;

[0017]

[0018] Where, represents an exponential function with a natural constant as the base, Indicates the first The data value corresponding to each element.

[0019] Furthermore, the method of obtaining a second-order proportional increment sequence based on the ratio between adjacent data in the proportional increment sequence and obtaining a second-order differential increment sequence based on the difference between adjacent data in the differential increment sequence includes:

[0020]

[0021] Where, Indicates the first The data value corresponding to the element, represents the logarithmic function with a natural constant as the base, Indicates the absolute value symbol, Indicates the first The data value corresponding to each element;

[0022]

[0023] Where, Indicates the first The data value corresponding to the element, Indicates the first The data value corresponding to the element, Indicates the absolute value symbol.

[0024] Furthermore, the step of obtaining the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence includes:

[0025]

[0026] Where, Indicates the first data, represents a natural constant, represents the minimum function, Represents the maximum value function.

[0027] Furthermore, the method randomly selects a plurality of random sequences of frequency modulation instructions according to the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence, and iteratively analyzes the plurality of random sequences of frequency modulation instructions in sequence 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 random sequence of frequency modulation instructions, including:

[0028] Perform a first random selection of all data in the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence to obtain a first frequency modulation instruction random sequence, and judge whether the first frequency modulation instruction random sequence meets the requirements. If so, take the first frequency modulation instruction random sequence as the optimal frequency modulation instruction random sequence, and stop the iteration; if not, continue to perform a second random selection of all data in the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence to obtain a second frequency modulation instruction random sequence, and judge whether the second frequency modulation instruction random sequence meets the requirements. If so, take the second frequency modulation instruction random sequence as the optimal frequency modulation instruction random sequence, and stop the iteration; if not, continue to perform a third random selection of all data in the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence to obtain a third frequency modulation instruction random sequence, and judge whether the third frequency modulation instruction random sequence meets the requirements. If so, take the third frequency modulation instruction random sequence as the optimal frequency modulation instruction random sequence, and stop the iteration; if not, continue the subsequent selection and judgment in this way until the optimal frequency modulation instruction random sequence is selected.

[0029] Furthermore, the conditions for whether the random sequence of frequency modulation instructions meets the requirements specifically include:

[0030] The first condition is that the data value range of each element in the corresponding proportional increment sequence and difference increment sequence of each frequency modulation instruction random sequence and frequency modulation instruction sequence must be between between; among them, represents the first low threshold, represents the first high threshold;

[0031] The second condition is to calculate the ratio between the average value of the data values ​​corresponding to all elements in each frequency modulation instruction random sequence and the average value of the data values ​​corresponding to all elements in the frequency modulation instruction sequence. The ratio must be between between; among them, represents the second lowest threshold, represents the second highest threshold;

[0032] The third condition is to calculate the difference between the serial number corresponding to the maximum value in each frequency modulation instruction random sequence and the serial number corresponding to the maximum value in the frequency modulation instruction sequence. The difference must be less than or equal to , where is the number of all data in the frequency modulation instruction sequence, Express Rounding is performed; where, represents the first preset parameter;

[0033] The fourth condition is that the maximum value in each FM instruction random sequence is less than or equal to the maximum value in the FM instruction sequence. times; among them, represents the second preset parameter;

[0034] Among them, according to 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.

[0035] A second aspect of the present invention is to provide a frequency modulation instruction prediction system for optimizing a hybrid energy storage system, comprising:

[0036] Data acquisition module: used to obtain frequency modulation command signals;

[0037] 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 differential 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 differential increment sequence according to the difference between adjacent data in the differential increment sequence;

[0038] 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 based on the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence, and iteratively analyze the several frequency modulation instruction random sequences in accordance with 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;

[0039] Predictive control module: used to make subsequent predictions through the GRU neural network based on the random sequence of optimal frequency modulation instructions, and to perform frequency modulation control of hybrid energy storage based on the predicted data.

[0040] The third aspect of the present invention is to provide an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements a method for predicting frequency modulation instructions for optimizing a hybrid energy storage system when executing the computer program.

[0041] 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 frequency modulation instructions for optimizing a hybrid energy storage system is implemented.

[0042] Compared with the prior art, the present invention has the following beneficial effects: obtaining a proportional increment sequence based on the ratio between adjacent data in the frequency modulation instruction sequence; obtaining a differential increment sequence based on the difference between adjacent data in the frequency modulation instruction sequence; obtaining a second-order proportional increment sequence based on the ratio between adjacent data in the proportional increment sequence; obtaining a second-order differential increment sequence based on the difference between adjacent data in the differential increment sequence; improving the accuracy of analysis of all adjacent data in the frequency modulation instruction sequence; obtaining a 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 based on 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 based on the proportional increment sequence, the differential increment sequence, the second-order proportional increment sequence, and the second-order differential increment sequence to obtain an optimal frequency modulation instruction random sequence and reduce the influence of noise interference; performing subsequent prediction based on the optimal frequency modulation instruction random sequence using a Gated Recurrent Unit (GRU) neural network, and performing frequency modulation control of the hybrid energy storage using the predicted data, thereby improving the accuracy of the frequency modulation control of the hybrid energy storage and improving the steady state of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] 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.

[0044] Figure 1 The present invention provides a flowchart of the steps of a method for optimizing the frequency modulation instruction prediction of a hybrid energy storage system;

[0045] Figure 2 The present invention provides a module flow diagram for optimizing a frequency modulation instruction prediction system for a hybrid energy storage system. DETAILED DESCRIPTION

[0046] 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.

[0047] 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.

[0048] In response to the problems existing in the background technology, a method and system for optimizing the frequency modulation instruction prediction of the hybrid energy storage system is studied and designed, which has important practical significance.

[0049] like Figure 1 As shown, the first aspect of the present invention is to provide a method for optimizing the frequency modulation instruction prediction of a hybrid energy storage system, comprising the following steps:

[0050] Step S001: Collect frequency modulation instruction signals.

[0051] 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.

[0052] 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.

[0053] At this point, the frequency modulation command signal is obtained.

[0054] Step S002: Divide the frequency modulation instruction signal to obtain a frequency modulation instruction sequence; obtain a proportional increment sequence based on the ratio between adjacent data in the frequency modulation instruction sequence; obtain a differential increment sequence based on the difference between adjacent data in the frequency modulation instruction sequence; obtain a second-order proportional increment sequence based on the ratio between adjacent data in the proportional increment sequence; obtain a second-order differential increment sequence based on the difference between adjacent data in the differential increment sequence.

[0055] It should be noted that since the distribution of data in the frequency modulation command signal can reflect the changing characteristics of the signal data, and the changing 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.

[0056] Specifically, at a preset time interval To divide the frequency modulation command signal, obtain a number of data corresponding to the frequency modulation command signal after the division, and form a group of data into a sequence in time order, which is recorded as a frequency modulation command sequence. seconds, where the preset time interval There is no specific limitation and implementers can decide based on specific circumstances.

[0057] At this point, the frequency modulation instruction sequence is obtained.

[0058] It should be noted that, in a normal, noise-free environment, the frequency modulation instructions typically change continuously, and the frequency offset changes smoothly. Therefore, the differences between adjacent data points are typically smooth, without drastic fluctuations. Therefore, interference analysis can be performed by analyzing the differences between all adjacent data points in the frequency modulation instruction sequence.

[0059] Specifically, a proportional increment sequence and a difference increment sequence are constructed through a frequency modulation instruction sequence;

[0060] The process of constructing each element in the proportional increment sequence is specifically expressed by the formula:

[0061]

[0062] Where, Indicates the first data, Indicates the first data, Indicates the first The data value corresponding to each element.

[0063] The process of constructing each element in the difference increment sequence is specifically expressed by the formula:

[0064]

[0065] Where, Indicates the first data, Indicates the first data, represents an exponential function with a natural constant as the base, Indicates the first The data value corresponding to each element.

[0066] A second-order proportional increment sequence is constructed based on the proportional increment sequence. The process of constructing each element in the second-order proportional increment sequence is specifically expressed by the formula:

[0067]

[0068] Where, Indicates the first The data value corresponding to the element, Indicates the first The data value corresponding to the element, represents the logarithmic function with a natural constant as the base, Indicates the absolute value symbol, Indicates the first The data value corresponding to each element.

[0069] A second-order difference increment sequence is constructed based on the difference increment sequence. The process of constructing each element in the second-order difference increment sequence is specifically expressed by the formula:

[0070]

[0071] Where, Indicates the first The data value corresponding to the element, Indicates the first The data value corresponding to the element, Indicates the first The data value corresponding to the element, Indicates the absolute value symbol.

[0072] The data value of the last element in the proportional increment sequence, the difference increment sequence, the second-order proportional increment sequence, and the second-order difference increment sequence is equal to the data value of the second-to-last element.

[0073] At this point, the proportional increment sequence, differential increment sequence, second-order proportional increment sequence and second-order differential increment sequence of the frequency modulation instruction sequence are obtained.

[0074] Step S003: 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 according to the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence, and iteratively analyze the number of frequency modulation instruction random sequences 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.

[0075] It should be noted that in order to eliminate the interference effect of noise on the frequency modulation instruction sequence, a range is set and a group of data is randomly selected within the set range to simulate the frequency modulation instruction sequence. Finally, the final randomly selected group of data values ​​are determined by comparing the differences between the randomly selected group of data and the frequency modulation instruction sequence, the corresponding proportional increment sequence, the difference increment sequence, the second-order proportional increment sequence and the second-order difference increment sequence.

[0076] Specifically, the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence is set, and the frequency modulation instruction data range is specifically expressed as:

[0077]

[0078] Where, Indicates the first data, represents a natural constant, represents the minimum function, Represents the maximum value function.

[0079] A set of data is randomly selected in sequence from the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence, and a set of sequences is formed in the order of random selection, which is recorded as a frequency modulation instruction random sequence. The number of data in the frequency modulation instruction random sequence is the same as the number of data in the frequency modulation instruction sequence.

[0080] According to 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 from 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.

[0081] The optimal frequency modulation instruction random sequence is determined based on the differences among the frequency modulation instruction random sequence, the proportional increment sequence corresponding to the frequency modulation instruction sequence, the difference increment sequence, the second-order proportional increment sequence, and the second-order difference increment sequence. The specific process of determining the optimal frequency modulation instruction random sequence is as follows:

[0082] Perform a first random selection of all data in the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence to obtain a first frequency modulation instruction random sequence, and judge whether the first frequency modulation instruction random sequence meets the requirements. If so, take the first frequency modulation instruction random sequence as the optimal frequency modulation instruction random sequence, and stop the iteration; if not, continue to perform a second random selection of all data in the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence to obtain a second frequency modulation instruction random sequence, and judge whether the second frequency modulation instruction random sequence meets the requirements. If so, take the second frequency modulation instruction random sequence as the optimal frequency modulation instruction random sequence, and stop the iteration; if not, continue to perform a third random selection of all data in the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence to obtain a third frequency modulation instruction random sequence, and judge whether the third frequency modulation instruction random sequence meets the requirements. If so, take the third frequency modulation instruction random sequence as the optimal frequency modulation instruction random sequence, and stop the iteration; if not, continue the subsequent selection and judgment in this way until the optimal frequency modulation instruction random sequence is selected.

[0083] The specific conditions for whether each frequency modulation instruction random sequence meets the requirements are:

[0084] The first condition is that the data value range of each element in the corresponding proportional increment sequence and difference increment sequence of each frequency modulation instruction random sequence and frequency modulation instruction sequence must be between between; among them, represents the first low threshold, Indicates the first high threshold; wherein, in this embodiment, the first low threshold , the first high threshold , where in this embodiment the first low threshold and the first high threshold There is no specific limitation and implementers can decide based on specific circumstances.

[0085] The second condition is to calculate the ratio between the average value of the data values ​​corresponding to all elements in each frequency modulation instruction random sequence and the average value of the data values ​​corresponding to all elements in the frequency modulation instruction sequence. The ratio must be between between; among them, represents the second lowest threshold, Indicates the second high threshold; wherein, in this embodiment, the second low threshold , the second highest threshold , where in this embodiment the second lower threshold and the second highest threshold There is no specific limitation and implementers can decide based on specific circumstances.

[0086] The third condition is to calculate the difference between the serial number corresponding to the maximum value in each frequency modulation instruction random sequence and the serial number corresponding to the maximum value in the frequency modulation instruction sequence. The difference must be less than or equal to , where is the number of all data in the frequency modulation instruction sequence, Express Rounding is performed; where, Represents the first preset parameter, wherein, in this embodiment, the first preset parameter , wherein in this embodiment the first preset parameter There is no specific limitation and implementers can decide based on specific circumstances.

[0087] The fourth condition is that the maximum value in each FM instruction random sequence is less than or equal to the maximum value in the FM instruction sequence. times; among them, Indicates the second preset parameter, wherein in this embodiment, the second preset parameter , wherein in this embodiment the second preset parameter There is no specific limitation and implementers can decide based on specific circumstances.

[0088] At this point, the optimal frequency modulation instruction random sequence is obtained.

[0089] Step S004: Perform subsequent predictions using the optimal frequency modulation instruction random sequence, and use the predicted data to perform frequency modulation control of the hybrid energy storage.

[0090] Based on the optimal random sequence of frequency modulation instructions, a GRU neural network performs subsequent predictions, and the predicted data is used to control the frequency modulation of the supercapacitor and battery. The loss function in the GRU neural network is the cross-entropy loss function. GRU neural networks are well-known technology and will not be described in detail here. The mean absolute percentage error (MAPE) was used to analyze the error between the sequence corresponding to the frequency modulation instruction signal and the optimal random sequence of frequency modulation instructions. The mean absolute percentage error corresponding to the sequence predicted by the frequency modulation instruction signal was 9.6, while the mean absolute percentage error corresponding to the sequence predicted by the optimal random sequence of frequency modulation instructions was 6.9. The results show that the error has decreased, indicating that the accuracy of the prediction has improved.

[0091] like Figure 2 As shown, the second aspect of the present invention is to provide a frequency modulation instruction prediction system for optimizing a hybrid energy storage system, comprising the following modules:

[0092] Data acquisition module 101: used to obtain frequency modulation command signals;

[0093] Sequence construction module 102: used to divide the frequency modulation instruction signal to obtain a frequency modulation instruction sequence; obtain a proportional increment sequence based on the ratio between adjacent data in the frequency modulation instruction sequence; obtain a differential increment sequence based on the difference between adjacent data in the frequency modulation instruction sequence; obtain a second-order proportional increment sequence based on the ratio between adjacent data in the proportional increment sequence; obtain a second-order differential increment sequence based on the difference between adjacent data in the differential increment sequence;

[0094] Optimal analysis module 103: 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 based on the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence, and iteratively analyze the number of frequency modulation instruction random sequences based on 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;

[0095] Prediction control module 104: used to perform subsequent predictions through the GRU neural network based on the optimal frequency modulation instruction random sequence, and perform frequency modulation control of the hybrid energy storage based on the predicted data.

[0096] 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, a method for predicting frequency modulation instructions for optimizing a hybrid energy storage system is implemented.

[0097] A fourth aspect of the present invention is to provide a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, a method for predicting frequency modulation instructions for optimizing a hybrid energy storage system is implemented.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] 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 optimizing frequency modulation instruction prediction of a hybrid energy storage system, characterized in that: include: Obtain frequency modulation command signal; Dividing the frequency modulation command signal to obtain a frequency modulation command sequence; According to the ratio between adjacent data in the frequency modulation instruction sequence, a proportional increment sequence is obtained; according to the difference between adjacent data in the frequency modulation instruction sequence, a differential increment sequence is obtained; according to the ratio between adjacent data in the proportional increment sequence, a second-order proportional increment sequence is obtained; according to the difference between adjacent data in the differential increment sequence, a second-order differential increment sequence is obtained; Obtaining a 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 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 according to a proportional increment sequence, a difference increment sequence, a second-order proportional increment sequence, and a second-order difference increment sequence to obtain an optimal frequency modulation instruction random sequence; According to the random sequence of optimal frequency modulation instructions, subsequent predictions are made through the GRU neural network, and the frequency modulation control of the hybrid energy storage is carried out using the predicted data.

2. A method for predicting frequency modulation instructions for optimizing a hybrid energy storage system according to claim 1, characterized in that: The step of dividing the frequency modulation instruction signal to obtain the frequency modulation instruction sequence includes: At preset time intervals The frequency modulation command signal is divided to obtain a number of data corresponding to the divided frequency modulation command signal. The data are grouped into a sequence in chronological order, which is recorded as a frequency modulation command sequence.

3. A method for predicting frequency modulation instructions for optimizing a hybrid energy storage system according to claim 1, characterized in that: The method of obtaining a proportional increment sequence according to a ratio between adjacent data in a frequency modulation instruction sequence and obtaining a differential increment sequence according to a difference between adjacent data in a frequency modulation instruction sequence comprises: Where, Indicates the first data, Indicates the first data, Indicates the first The data value corresponding to each element; Where, represents an exponential function with a natural constant as the base, Indicates the first The data value corresponding to each element.

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

5. A method for predicting frequency modulation instructions for optimizing a hybrid energy storage system according to claim 4, characterized in that: The obtaining of the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence includes: Where, Indicates the first data, represents a natural constant, represents the minimum function, Represents the maximum value function.

6. A method for predicting frequency modulation instructions for optimizing a hybrid energy storage system according to claim 5, characterized in that: The method randomly selects a plurality of random frequency modulation instruction sequences according to the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence, and iteratively analyzes the plurality of random frequency modulation instruction sequences in sequence 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 random frequency modulation instruction sequence, including: Perform a first random selection of all data in the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence to obtain a first frequency modulation instruction random sequence, and judge whether the first frequency modulation instruction random sequence meets the requirements. If so, take the first frequency modulation instruction random sequence as the optimal frequency modulation instruction random sequence, and stop the iteration; if not, continue to perform a second random selection of all data in the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence to obtain a second frequency modulation instruction random sequence, and judge whether the second frequency modulation instruction random sequence meets the requirements. If so, take the second frequency modulation instruction random sequence as the optimal frequency modulation instruction random sequence, and stop the iteration; if not, continue to perform a third random selection of all data in the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence to obtain a third frequency modulation instruction random sequence, and judge whether the third frequency modulation instruction random sequence meets the requirements. If so, take the third frequency modulation instruction random sequence as the optimal frequency modulation instruction random sequence, and stop the iteration; if not, continue the subsequent selection and judgment in this way until the optimal frequency modulation instruction random sequence is selected.

7. A method for predicting frequency modulation instructions for optimizing a hybrid energy storage system according to claim 6, characterized in that: The conditions for whether the random sequence of frequency modulation instructions meets the requirements specifically include: The first condition is that the data value range of each element in the corresponding proportional increment sequence and difference increment sequence of each frequency modulation instruction random sequence and frequency modulation instruction sequence must be between between; among them, 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 frequency modulation instruction random sequence and the average value of the data values ​​corresponding to all elements in the frequency modulation instruction sequence. The ratio must be between between; among them, represents the second lowest threshold, represents the second highest threshold; The third condition is to calculate the difference between the serial number corresponding to the maximum value in each frequency modulation instruction random sequence and the serial number corresponding to the maximum value in the frequency modulation instruction sequence. The difference must be less than or equal to , where is the number of all data in the frequency modulation instruction sequence, Express Rounding is performed; where, represents the first preset parameter; The fourth condition is that the maximum value in each FM instruction random sequence is less than or equal to the maximum value in the FM instruction sequence. times; among them, represents the second preset parameter; Among them, according to 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.

8. A frequency modulation instruction prediction system for optimizing a hybrid energy storage system, characterized in that: include: Data acquisition module: used to obtain frequency modulation command signals; Sequence building module: used to divide the FM command signal and obtain the FM command sequence; According to the ratio between adjacent data in the frequency modulation instruction sequence, a proportional increment sequence is obtained; according to the difference between adjacent data in the frequency modulation instruction sequence, a differential increment sequence is obtained; according to the ratio between adjacent data in the proportional increment sequence, a second-order proportional increment sequence is obtained; according to the difference between adjacent data in the differential increment sequence, a second-order differential increment sequence is obtained; 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 based on the frequency modulation instruction data range corresponding to each data in the frequency modulation instruction sequence, and iteratively analyze the several frequency modulation instruction random sequences in accordance with 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; Predictive control module: used to make subsequent predictions through the GRU neural network based on the random sequence of optimal frequency modulation instructions, and to perform frequency modulation control of hybrid energy storage based on the predicted data.

9. An electronic device, characterized in that: It includes 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 predicting frequency modulation instructions for optimizing a hybrid energy storage system as described in any one of claims 1 to 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, the method for predicting frequency modulation instructions for optimizing a hybrid energy storage system according to any one of claims 1 to 7 is implemented.

Images