Method and device for determining accuracy rate of capacity allocation of supercapacitor energy storage system

Abstract

An embodiment of the present disclosure provides a method and device for determining the accuracy rate of capacity allocation of a supercapacitor energy storage system, which relates to the technical field of power grid frequency modulation. The method includes: obtaining a frequency modulation command and a decomposition layer number adopted for capacity allocation; performing multiple loops to correct the punishment factor until the second prediction error corresponding to the second predicted decomposition purity is less than the second prediction error obtained in the previous loop, and then ending the loop; determining that the second predicted decomposition purity obtained in the last loop represents the accuracy rate of capacity allocation of the supercapacitor energy storage system, and the smaller the second predicted decomposition purity, the higher the accuracy rate of capacity allocation. It provides an efficient and accurate evaluation and determination method for the accuracy rate of the capacity allocation of energy storage devices in a supercapacitor energy storage system.

Description

Technical Field

[0001] The present disclosure relates to the technical field of power grid frequency modulation, and particularly to a method and device for determining the accuracy rate of capacity allocation of a supercapacitor energy storage system. Background Art

[0002] There are various limitations in the frequency modulation of existing thermal power and hydropower units, and the energy storage scheme for thermal power plants is highly favored. At present, in major regional power grids in China, large-scale hydropower and thermal power units are mainly used as the power grid frequency modulation power sources, and the system frequency change is responded by adjusting the output of the frequency modulation power sources. However, there are certain limitations in the frequency modulation of hydropower and thermal power units. Energy storage frequency modulation has become a new type of frequency modulation auxiliary means with fast and accurate power response capabilities. However, limited by the cycle life of lithium batteries of about 5000 times, most existing energy storage frequency modulation projects only respond to the secondary frequency modulation of AGC (Automatic Generation Control), but do not respond to the primary frequency modulation. Supercapacitors, with high power and long life characteristics, are suitable for the short-term high-frequency and high-power frequency modulation requirements of the power grid, and can make up for the energy storage short board of ultra-short and short time. However, there is currently no efficient and accurate scheme for determining the accuracy rate of capacity allocation involved in the supercapacitor energy storage system. Summary of the Invention

[0003] Embodiments of the present disclosure provide a method and device for determining the accuracy rate of capacity allocation of a supercapacitor energy storage system, so as to solve the problem that there is no scheme for evaluating and determining the accuracy rate of capacity allocation in the existing supercapacitor energy storage system.

[0004] Based on the above problems, in a first aspect, a method for determining the accuracy rate of capacity allocation of a supercapacitor energy storage system is provided, including:

[0005] Obtain the frequency modulation instruction and the decomposition layer number adopted for capacity allocation;

[0006] Loop multiple times. In each loop, set the frequency modulation instruction and the decomposition layer number and input them into a pre-trained prediction model to obtain the first predicted decomposition purity and the corresponding first prediction error, and store them in historical data until the number of loops reaches a preset value;

[0007] Loop multiple times. In each loop, input the frequency modulation instruction and the decomposition layer number into a pre-trained prediction model and set the penalty factor of the model to obtain the second predicted decomposition purity and the corresponding second prediction error, and store them in historical data. Based on the historical data, determine the first average error coefficient corresponding to the first prediction error and the second average error coefficient corresponding to the second prediction error; correct the penalty factor based on the first average error coefficient and the second average error coefficient; until the second prediction error corresponding to the second predicted decomposition purity is less than the second prediction error obtained in the previous loop, then end the loop;

[0008] Determine that the second predicted decomposition purity obtained in the last cycle characterizes the accuracy of the capacity allocation of the supercapacitor energy storage system. The smaller the second predicted decomposition purity, the higher the capacity allocation accuracy.

[0009] Combined with the first aspect, in a possible implementation manner, the pre-trained prediction model takes the corresponding frequency modulation command and decomposition layer number in the historical data as inputs, and the predicted decomposition purity as the output, and trains the model based on the true value of the decomposition purity.

[0010] Combined with the first aspect, in a possible implementation manner, the inputting the frequency modulation command and the decomposition layer number into the pre-trained prediction model to obtain the first predicted decomposition purity and the corresponding first prediction error includes:

[0011] Input the frequency modulation command and the decomposition layer number into the pre-trained prediction model to obtain the first predicted decomposition purity;

[0012] Calculate the actual decomposition purity based on the frequency modulation command and the decomposition layer number;

[0013] Subtract the first predicted decomposition purity from the actual decomposition purity to obtain the first prediction error.

[0014] Combined with the first aspect, in a possible implementation manner, the actual decomposition purity is calculated by the following formula:

[0015]

[0016] where represents the actual decomposition purity, represents the decomposition layer number, represents the th peak frequency when the subsequence generated by the decomposition is mapped to the frequency domain, represents the linear independence analysis function in the time domain case, represents the th subsequence generated by the decomposition.

[0017] Combined with the first aspect, in a possible implementation manner, the determining the first average error coefficient corresponding to the first prediction error and the second average error coefficient corresponding to the second prediction error based on the historical data includes:

[0018] Average the first prediction errors stored in the historical data in multiple cycles to obtain the first average error coefficient;

[0019] Average the second prediction errors stored in the historical data in multiple cycles to obtain the second average error coefficient.

[0020] In combination with the first aspect, in a possible implementation manner, the correction of the disciplinary factor based on the first average error coefficient and the second average error coefficient includes:

[0021] If the first average error coefficient is greater than the second average error coefficient, correct the disciplinary factor; otherwise, directly use the disciplinary factor as the corrected disciplinary factor.

[0022] The correction formula is as follows:

[0023]

[0024] Wherein, represents the disciplinary factor, represents the first average error coefficient, represents the second average error coefficient, represents the number of correction times, represents the natural constant, represents the Padé approximation.

[0025] In the second aspect, a device for determining the capacity allocation accuracy rate of a supercapacitor energy storage system is provided, including:

[0026] A data acquisition module for acquiring the frequency modulation command and the decomposition layer number used for capacity allocation;

[0027] A loop value-taking module for looping multiple times. Each time a loop is set, the frequency modulation command and the decomposition layer number are set and input into a pre-trained prediction model to obtain the first predicted decomposition purity and the corresponding first prediction error, which are stored in historical data until the number of loops reaches a preset value;

[0028] A loop correction module for looping multiple times. Each time a loop is set, the frequency modulation command and the decomposition layer number are input into a pre-trained prediction model and the disciplinary factor of the model is set to obtain the second predicted decomposition purity and the corresponding second prediction error, which are stored in historical data. Based on the historical data, the first average error coefficient corresponding to the first prediction error and the second average error coefficient corresponding to the second prediction error are determined; the disciplinary factor is corrected based on the first average error coefficient and the second average error coefficient; until the second prediction error corresponding to the second predicted decomposition purity is less than the second prediction error obtained in the previous loop, the loop ends;

[0029] An accuracy rate determination module for determining that the second predicted decomposition purity obtained in the last loop represents the capacity allocation accuracy rate of the supercapacitor energy storage system. The smaller the second predicted decomposition purity, the higher the capacity allocation accuracy rate.

[0030] In combination with the second aspect, in a possible implementation, in the loop value-taking module, the pre-trained prediction model takes the corresponding frequency modulation command and decomposition level in the historical data as inputs and the predicted decomposition purity as the output, and the model is trained based on the true value of the decomposition purity.

[0031] In combination with the second aspect, in a possible implementation, in the loop value-taking module, inputting the frequency modulation command and the decomposition level into the pre-trained prediction model to obtain a first predicted decomposition purity and a corresponding first prediction error includes:

[0032] Input the frequency modulation command and the decomposition level into the pre-trained prediction model to obtain a first predicted decomposition purity;

[0033] Calculate the actual decomposition purity based on the frequency modulation command and the decomposition level;

[0034] Subtract the first predicted decomposition purity from the actual decomposition purity to obtain the first prediction error.

[0035] In combination with the second aspect, in a possible implementation, in the loop value-taking module and the loop correction module, the actual decomposition purity is calculated by the following formula:

[0036]

[0037] where represents the actual decomposition purity, represents the decomposition level, represents the th subsequence generated by decomposition mapped to the peak frequency in the frequency domain, represents the linear independence analysis function in the time domain case, represents the th subsequence generated by decomposition.

[0038] In combination with the second aspect, in a possible implementation, in the loop correction module, determining the first average error coefficient corresponding to the first prediction error and the second average error coefficient corresponding to the second prediction error based on the historical data includes:

[0039] Average the first prediction errors stored in the historical data for multiple loops to obtain the first average error coefficient;

[0040] Average the second prediction errors stored in the historical data for multiple loops to obtain the second average error coefficient.

[0041] In combination with the second aspect, in a possible implementation manner, in the loop correction module, the penalty factor is corrected based on the first average error coefficient and the second average error coefficient; the method includes:

[0042] If the first average error coefficient is greater than the second average error coefficient, correct the penalty factor; otherwise, directly use the penalty factor as the corrected penalty factor.

[0043] The correction formula is as follows:

[0044]

[0045] Wherein, represents the penalty factor, represents the first average error coefficient, represents the second average error coefficient, represents the number of correction times, represents the natural constant, represents the Padé approximation.

[0046] In a third aspect, a computer device is provided, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device runs, the processor communicates with the memory through the bus. When the machine-readable instructions are executed by the processor, the steps of a method for determining the capacity allocation accuracy rate of a supercapacitor energy storage system as described in the first aspect or any possible implementation manner in combination with the first aspect are executed.

[0047] In a fourth aspect, a computer-readable storage medium is provided. A computer program is stored on the computer-readable storage medium. When the computer program is run by a processor, the steps of a method for determining the capacity allocation accuracy rate of a supercapacitor energy storage system as described in the first aspect or any possible implementation manner in combination with the first aspect are executed.

[0048] The beneficial effects of the embodiments of the present disclosure include:

[0049] An embodiment of the present disclosure provides a method and device for determining the accuracy rate of capacity allocation of a supercapacitor energy storage system, which is applied to the supercapacitor energy storage system to evaluate the allocation result of the energy storage capacity and determine the accuracy rate of the capacity allocation. In the embodiment of the present disclosure, a prediction model is used to predict the decomposition purity during the decomposition of the frequency modulation command before allocation, and by introducing a disciplinary factor and using the first prediction error and the second prediction error in the historical data to determine the first average error coefficient and the second average error coefficient, the disciplinary factor is continuously corrected, so as to correct the prediction result, make the predicted decomposition purity more accurate, and at the same time make the determination of the accuracy rate of capacity allocation more precise. It provides an efficient and accurate evaluation and determination method for the accuracy rate of the capacity allocation of energy storage devices in the supercapacitor energy storage system. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 FIG. is a flowchart of a method for determining the accuracy rate of capacity allocation of a supercapacitor energy storage system provided by an embodiment of the present disclosure;

[0051] Figure 2 FIG. is a structural diagram of a device for determining the accuracy rate of capacity allocation of a supercapacitor energy storage system provided by an embodiment of the present disclosure;

[0052] Figure 3 FIG. is a flowchart of a method for determining the accuracy rate of capacity allocation of a supercapacitor energy storage system provided by an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] An embodiment of the present disclosure provides a method and device for determining the accuracy rate of capacity allocation of a supercapacitor energy storage system. The following describes the preferred embodiments of the present disclosure with reference to the accompanying drawings of the specification. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present disclosure, and are not used to limit the present disclosure. And without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

[0054] An embodiment of the present disclosure provides a method for determining the accuracy rate of capacity allocation of a supercapacitor energy storage system, as Figure 1 shown, including:

[0055] S101. Obtain the frequency modulation command and the decomposition layer number used for capacity allocation;

[0056] S102. Loop multiple times. Each time, set the frequency modulation command and the decomposition layer number and input them into a pre-trained prediction model to obtain the first predicted decomposition purity and the corresponding first prediction error, and store them in the historical data until the number of loops reaches a preset value;

[0057] S103. Repeat the process multiple times. In each iteration, input the obtained frequency modulation command and the decomposition level into a pre-trained prediction model and set the penalty factor of the model to obtain the second predicted decomposition purity and the corresponding second predicted error, and store them in the historical data. Determine the first average error coefficient corresponding to the first predicted error and the second average error coefficient corresponding to the second predicted error based on the historical data; correct the penalty factor based on the first average error coefficient and the second average error coefficient; stop the loop until the second predicted error corresponding to the second predicted decomposition purity is less than the second predicted error obtained in the previous iteration.

[0058] S104. Determine that the second predicted decomposition purity obtained in the last iteration represents the capacity allocation accuracy rate of the supercapacitor energy storage system. The smaller the second predicted decomposition purity, the higher the capacity allocation accuracy rate.

[0059] In the embodiments of the present disclosure, when allocating the energy storage capacity of the supercapacitor energy storage system, first, the frequency modulation command is decomposed by the VMD algorithm to obtain , where is the total power that the frequency modulation command needs to compensate, is the i-th modal component (IMF) after decomposition, and the number of modal components is the decomposition level K1, is the residual component after decomposition; after obtaining the high-frequency power component and the low-frequency power component , send the high-frequency power component and the low-frequency power component to the corresponding energy storage device. However, aliasing will occur between the modal components generated by the decomposition, which affects the accuracy rate of capacity allocation. The decomposition purity is a criterion for defining whether each modal component is independent after VMD decomposition. The smaller the decomposition purity, the more independent each modal component is, and the less aliasing there is between the modal components, which means the higher the accuracy rate of capacity allocation. Therefore, by continuously correcting the penalty factor of the model, the accuracy of the decomposition purity prediction is continuously improved, so as to make the determination of the accuracy rate of the energy storage system capacity allocation more accurate.

[0060] In the embodiments of the present disclosure, the first average error coefficient and the second average error coefficient corresponding to the first predicted error without the penalty factor and the second predicted error with the penalty factor stored in the historical data in each iteration are used to judge the correction effect of the added penalty factor on the model prediction result, and the penalty factor is continuously corrected and adjusted through multiple iterations, so that the prediction result of the model, that is, the second predicted decomposition purity, continuously approaches the actual decomposition accuracy, and the prediction effect of the model is better. Among them, the penalty factor is a parameter of VMD, and its value can be set artificially.

[0061] In the embodiments of the present disclosure, in step S102, the frequency modulation instruction and the decomposition level are set randomly each time the loop is executed, or they can be set randomly according to a preset distribution, such as a normal distribution, a uniform distribution, etc.

[0062] In another embodiment provided by the present disclosure, the above-mentioned pre-trained prediction model takes the corresponding frequency modulation instruction and decomposition level in the historical data as inputs and the predicted decomposition purity as the output, and the model is trained based on the true value of the decomposition purity.

[0063] In the embodiments of the present disclosure, during the training process of the above-mentioned pre-trained prediction model, the corresponding frequency modulation instruction and decomposition level in the historical data are used as inputs, the predicted decomposition purity is used as the output, and the actual decomposition purity is used as the true value.

[0064] In another embodiment provided by the present disclosure, in step S102, each time the loop is executed, the frequency modulation instruction and the decomposition level are set and input into the pre-trained prediction model to obtain the first predicted decomposition purity and the corresponding first prediction error, including:

[0065] Input the frequency modulation instruction and the decomposition level into the pre-trained prediction model to obtain the first predicted decomposition purity;

[0066] Calculate the actual decomposition purity based on the frequency modulation instruction and the decomposition level;

[0067] Subtract the first predicted decomposition purity from the actual decomposition purity to obtain the first prediction error.

[0068] In the embodiments of the present disclosure, there will be an error between the first predicted decomposition purity obtained through the prediction model and the actual decomposition purity. The actual decomposition purity corresponding to the frequency modulation instruction and the decomposition level can be obtained through calculation, and subtracting the predicted decomposition purity from the actual decomposition purity can obtain the error of the prediction result, which is convenient for subsequently using this error to correct the penalty factor added to the model, and then correcting the prediction result.

[0069] In another embodiment provided by the present disclosure, the actual decomposition purity is calculated by the following formula:

[0070]

[0071] Where, represents the actual decomposition purity, represents the decomposition level, represents the th peak frequency in the frequency domain to which the subsequence generated by the decomposition is mapped, represents the linear independence analysis function in the time domain case, represents the th subsequence generated by the decomposition.

[0072] In another embodiment provided by the present disclosure, in step S103, determining a first average error coefficient corresponding to the first prediction error and a second average error coefficient corresponding to the second prediction error based on historical data includes:

[0073] Taking the average of the first prediction errors stored in the historical data in multiple loops to obtain the first average error coefficient;

[0074] Taking the average of the second prediction errors stored in the historical data in multiple loops to obtain the second average error coefficient.

[0075] In the embodiment of the present disclosure, the first prediction error and the second prediction error stored in the historical data in each loop before the current loop are respectively averaged to obtain the first average error coefficient and the second average error coefficient. By comparing between the first average error coefficient and the second average error coefficient, it can effectively characterize the correction effect on the model prediction result while continuously correcting the disciplinary factor.

[0076] In another embodiment provided by the present disclosure, in step S103, correcting the disciplinary factor based on the first average error coefficient and the second average error coefficient; includes:

[0077] If the first average error coefficient is greater than the second average error coefficient, correct the disciplinary factor, otherwise directly use the disciplinary factor as the corrected disciplinary factor;

[0078] The correction formula is as follows:

[0079]

[0080] Wherein, represents the disciplinary factor, represents the first average error coefficient, represents the second average error coefficient, represents the number of correction times, represents the natural constant, represents the Padé approximation.

[0081] In the embodiment of the present disclosure, if W1 < W2, it means that the improvement effect on the prediction accuracy of the model after adding the disciplinary factor is not good, and then the disciplinary factor needs to be corrected.

[0082] Based on the same inventive concept, the embodiment of the present disclosure also provides a device for determining the capacity allocation accuracy rate of a supercapacitor energy storage system. Since the principle of the problem solved by this device is similar to that of the foregoing method for determining the capacity allocation accuracy rate of a supercapacitor energy storage system, the implementation of this device can refer to the implementation of the foregoing method, and the repeated parts will not be described again.

[0083] For ease of understanding, the specific process of the present disclosure solution is as follows Figure 2 As shown, the decomposition purity is predicted through a prediction model, and during the process, a punishment factor is added and continuously mined and corrected to further improve the accuracy of the model prediction result. Finally, the capacity allocation accuracy rate of the system is evaluated and determined through the finally obtained predicted decomposition purity, that is, the second predicted decomposition purity.

[0084] Corresponding to the method shown above Figure 1 The embodiment of the present disclosure also provides a device for determining the capacity allocation accuracy rate of an over-capacity energy storage system, as Figure 3 shown, including:[[]]

[0085] A data acquisition module 301, configured to acquire the frequency modulation instruction and the decomposition layer number adopted for capacity allocation;

[0086] A loop value-taking module 302, configured to loop multiple times. Each time the loop is executed, the frequency modulation instruction and the decomposition layer number are set and input into a pre-trained prediction model to obtain the first predicted decomposition purity and the corresponding first prediction error, and store them in historical data until the number of loops reaches a preset value;

[0087] A loop correction module 303, configured to loop multiple times. Each time the loop is executed, the frequency modulation instruction and the decomposition layer number are input into a pre-trained prediction model and the punishment factor of the model is set to obtain the second predicted decomposition purity and the corresponding second prediction error, and store them in historical data. Based on the historical data, determine the first average error coefficient corresponding to the first prediction error and the second average error coefficient corresponding to the second prediction error; correct the punishment factor based on the first average error coefficient and the second average error coefficient; until the second prediction error corresponding to the second predicted decomposition purity is less than the second prediction error obtained in the previous loop, then end the loop;

[0088] An accuracy rate determination module 304, configured to determine that the second predicted decomposition purity obtained in the last loop represents the capacity allocation accuracy rate of the over-capacity energy storage system. The smaller the second predicted decomposition purity, the higher the capacity allocation accuracy rate.

[0089] In another embodiment provided by the present disclosure, in the above loop value-taking module 302 and loop correction module 303, the pre-trained prediction model takes the corresponding frequency modulation instruction and decomposition layer number in the historical data as inputs and the predicted decomposition purity as the output, and trains the model based on the true value of the decomposition purity.

[0090] In another embodiment provided by the present disclosure, in the above loop value-taking module 302, inputting the frequency modulation instruction and the decomposition layer number into a pre-trained prediction model to obtain the first predicted decomposition purity and the corresponding first prediction error includes:

[0091] Input the frequency modulation command and the number of decomposition layers into a pre-trained prediction model to obtain the first predicted decomposition purity;

[0092] Calculate the actual decomposition purity based on the frequency modulation command and the number of decomposition layers;

[0093] Subtract the first predicted decomposition purity from the actual decomposition purity to obtain the first prediction error.

[0094] In another embodiment provided by the present disclosure, in the above-mentioned loop value-taking module 302 and loop correction module 303, the actual decomposition purity is calculated by the following formula:

[0095]

[0096] where, represents the actual decomposition purity, represents the number of decomposition layers, represents the th subsequence generated by decomposition mapped to the peak frequency in the frequency domain, represents the linear independence analysis function in the time domain case, represents the th subsequence generated by decomposition.

[0097] In another embodiment provided by the present disclosure, in the above-mentioned loop correction module 303, determining the first average error coefficient corresponding to the first prediction error and the second average error coefficient corresponding to the second prediction error based on historical data includes:

[0098] Average the first prediction errors stored in the historical data for multiple loops to obtain the first average error coefficient;

[0099] Average the second prediction errors stored in the historical data for multiple loops to obtain the second average error coefficient.

[0100] In another embodiment provided by the present disclosure, in the above-mentioned loop correction module 303, correcting the disciplinary factor based on the first average error coefficient and the second average error coefficient; includes:

[0101] If the first average error coefficient is greater than the second average error coefficient, correct the disciplinary factor, otherwise directly use the disciplinary factor as the corrected disciplinary factor;

[0102] The correction formula is as follows:

[0103]

[0104] where, represents the disciplinary factor, represents the first average error coefficient, Characterize the second mean error coefficient, Characterize the number of correction times, Characterize the natural constant, Characterize the Padé approximation.

[0105] An embodiment of the present disclosure provides a computer device, including: a processor, a memory, and a bus. The memory stores machine-readable instructions executable by the processor. When the computer device runs, the processor communicates with the memory through the bus. When the machine-readable instructions are executed by the processor, the steps of the method for determining the capacity allocation accuracy rate of the supercapacitor energy storage system provided in any embodiment of the present disclosure are executed.

[0106] The computer device provided by the embodiment of the present disclosure includes a processor, a memory, and a bus. Among them, the memory is used to store execution instructions, including internal memory and external memory; the internal memory here is also called main memory, which is used to temporarily store the operation data in the processor and the data exchanged with external memories such as hard disks. The processor exchanges data with the external memory through the internal memory. When the electronic device runs, the processor communicates with the memory through the bus, so that the processor executes the following instructions:

[0107] Obtain the frequency modulation instruction and the decomposition layer number adopted for capacity allocation;

[0108] Loop multiple times. In each loop, input the frequency modulation instruction and the decomposition layer number into a pre-trained prediction model to obtain the first predicted decomposition purity and the corresponding first predicted error and store them in the historical data; input the frequency modulation instruction and the decomposition layer number into a pre-trained prediction model and set the penalty factor of the model to obtain the second predicted decomposition purity and the corresponding second predicted error and store them in the historical data; determine the first mean error coefficient corresponding to the first predicted error and the second mean error coefficient corresponding to the second predicted error based on the historical data; correct the penalty factor based on the first mean error coefficient and the second mean error coefficient; until the second predicted error corresponding to the second predicted decomposition purity is less than the second predicted error obtained in the previous loop, then end the loop;

[0109] Determine that the second predicted decomposition purity obtained in the last loop characterizes the capacity allocation accuracy rate of the supercapacitor energy storage system. The smaller the second predicted decomposition purity, the higher the capacity allocation accuracy rate.

[0110] An embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, the steps of the method for determining the capacity allocation accuracy rate of the supercapacitor energy storage system provided in any embodiment of the present disclosure are executed. Among them, the storage medium can be a volatile or non-volatile computer-readable storage medium.

[0111] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments of the present disclosure can be implemented by hardware or by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solutions of the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments of the present disclosure.

[0112] Those skilled in the art can understand that the drawings are only schematic diagrams of a preferred embodiment, and the modules or processes in the drawings are not necessarily essential for implementing the present disclosure.

[0113] Those skilled in the art can understand that the modules in the device in the embodiments can be distributed in the device in the embodiments according to the description of the embodiments, or can be correspondingly changed to be located in one or more devices different from the present embodiment. The modules of the above embodiments can be combined into one module, or can be further split into multiple sub-modules.

[0114] The serial numbers of the above embodiments of the present disclosure are only for description and do not represent the advantages or disadvantages of the embodiments.

[0115] Obviously, those skilled in the art can make various changes and modifications to the present disclosure without departing from the spirit and scope of the present disclosure. Thus, if these modifications and variations of the present disclosure fall within the scope of the claims of the present disclosure and their equivalent technologies, the present disclosure also intends to include these changes and modifications.

Claims

1. A method for determining the capacity allocation accuracy of an ultra-capacity energy storage system, characterized in that: include: Obtain frequency modulation instructions and decomposition layers used for capacity allocation; Repeat multiple times, each time setting the frequency modulation instruction and the number of decomposition layers and inputting them into the pre-trained prediction model, obtaining the first prediction decomposition purity and the corresponding first prediction error and storing them in the historical data, until the number of cycles reaches the preset value; Repeating the process multiple times, in each cycle, inputting the frequency modulation instruction and the number of decomposition layers into a pre-trained prediction model and setting the penalty factor of the model, obtaining a second prediction decomposition purity and a corresponding second prediction error and storing them in historical data, determining a first average error coefficient corresponding to the first prediction error and a second average error coefficient corresponding to the second prediction error based on the historical data; correcting the penalty factor based on the first average error coefficient and the second average error coefficient; if the first average error coefficient is greater than the second average error coefficient, correcting the penalty factor, otherwise using the penalty factor as the corrected penalty factor; The loop ends until the second prediction error corresponding to the second prediction decomposition purity is smaller than the second prediction error obtained in the previous loop; Determine that the second prediction decomposition purity obtained in the last cycle represents the capacity allocation accuracy of the super-capacity energy storage system, and the smaller the second prediction decomposition purity is, the higher the capacity allocation accuracy is; Among them, the formula used to correct the punishment factor is as follows: in, Characterizes the punishment factor, Characterizes the first average error coefficient, Characterizes the second mean error coefficient, Characterize the number of corrections, Characterizes the natural constants, Characterizing the PADE approximation.

2. The method according to claim 1, characterized in that The pre-trained prediction model takes the corresponding frequency modulation instructions and decomposition layer number in the historical data as input, predicts the decomposition purity as output, and trains the model based on the true value of the decomposition purity.

3. The method according to claim 1, characterized in that The step of inputting the frequency modulation instruction and the number of decomposition layers into a pre-trained prediction model to obtain a first prediction decomposition purity and a corresponding first prediction error includes: Inputting the frequency modulation instruction and the number of decomposition layers into a pre-trained prediction model to obtain a first prediction decomposition purity; The actual decomposition purity is calculated based on the frequency modulation instruction and the number of decomposition layers; The first prediction error is obtained by subtracting the first predicted decomposition purity from the actual decomposition purity.

4. The method according to claim 3, characterized in that The actual decomposition purity is calculated by the following formula: in, Characterizes the actual decomposition purity, Characterizes the number of decomposition levels, Characterize the decomposition The subsequences are mapped to the peak frequencies in the frequency domain, Characterize the linear independence analysis function in the time domain, Characterize the decomposition subsequences.

5. The method according to claim 1, characterized in that The determining, based on historical data, a first average error coefficient corresponding to the first prediction error and a second average error coefficient corresponding to the second prediction error includes: Averaging the first prediction errors stored in the historical data for multiple cycles to obtain the first average error coefficient; The second prediction error stored in the historical data in multiple cycles is averaged to obtain the second average error coefficient.

6. A device for determining the capacity allocation accuracy of an ultra-capacity energy storage system, characterized in that: include: A data acquisition module, used to obtain frequency modulation instructions and decomposition layers used for capacity allocation; A loop correction module is used to loop multiple times, each loop sets the frequency modulation instruction and the number of decomposition layers and inputs them into a pre-trained prediction model, obtains a first prediction decomposition purity and a corresponding first prediction error and stores them in historical data; inputs the frequency modulation instruction and the number of decomposition layers into the pre-trained prediction model and sets the penalty factor of the model, obtains a second prediction decomposition purity and a corresponding second prediction error and stores them in historical data; determines a first average error coefficient corresponding to the first prediction error and a second average error coefficient corresponding to the second prediction error based on historical data; if the first average error coefficient is greater than the second average error coefficient, corrects the penalty factor, otherwise the penalty factor is used as the corrected penalty factor; corrects the penalty factor based on the first average error coefficient and the second average error coefficient; until the second prediction error corresponding to the second prediction decomposition purity is less than the second prediction error obtained in the previous loop, the loop ends; An accuracy determination module, used to determine the second prediction decomposition purity obtained in the last cycle to characterize the accuracy of capacity allocation of the super-capacity energy storage system, the smaller the second prediction decomposition purity, the higher the capacity allocation accuracy; Among them, the formula used to correct the punishment factor is as follows: in, Characterizes the punishment factor, Characterizes the first average error coefficient, Characterizes the second mean error coefficient, Characterize the number of corrections, Characterizes the natural constants, Characterizing the PADE approximation.

7. The device according to claim 6, characterized in that In the cycle correction module, the pre-trained prediction model takes the corresponding frequency modulation instructions and decomposition layer number in the historical data as input, predicts the decomposition purity as output, and trains the model based on the true value of the decomposition purity.

8. A computer device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for determining the capacity allocation accuracy of the ultra-capacity energy storage system according to any one of claims 1 to 5 are performed.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the method for determining the capacity allocation accuracy of the ultra-capacity energy storage system according to any one of claims 1 to 5.

Images