A method and device for allocating frequency modulation instructions for overcapacity energy storage considering unit life

Abstract

The disclosed embodiment provides a method and device for allocating frequency modulation instructions for super-capacity energy storage considering the life of the unit, the method comprising: obtaining a frequency modulation signal; performing multiple cycles, decomposing the frequency modulation signal according to the number of decomposition layers corresponding to each cycle, and obtaining subsequences of the number of decomposition layers; establishing a corresponding prediction model for each subsequence, training the prediction model using the data of the first period of the subsequence, and predicting the data of the second period; determining the ratio error and difference error of the data of the second period; summing the ratio error and difference error under the number of decomposition layers, respectively, to obtain the total ratio error and total difference error; determining whether the number of decomposition layers corresponding to the minimum values ​​of the total ratio error and the total difference error meet the preset conditions, and outputting the number of decomposition layers if they meet the conditions. Determine the number of decomposition layers that makes the sequence most stable and the load of the thermal power unit small, so that when the thermal power unit responds to the frequency modulation signal, it has less action, smaller load, and longer life.

Description

Technical Field

[0001] The present disclosure relates to the technical field of power grid frequency regulation, and in particular to a method and device for allocating frequency regulation instructions for overcapacity energy storage taking into account the life of a unit. Background Art

[0002] Under the dual pressure of energy crisis and environmental pollution, renewable energy represented by wind power and photovoltaic power has developed rapidly. The uncertainty of its power generation has brought many challenges to the operation of the power grid, among which the frequency regulation and peak regulation problem is particularly prominent. In order to improve the flexibility of power supply regulation, the country has taken measures such as building peak-shaving power sources such as thermal power and hydropower, carrying out flexibility transformation of thermal power units and building energy storage systems. Due to the rapid development of large-scale battery energy storage technology and the excellent regulation performance of energy storage systems, the use of energy storage systems to alleviate the pressure of power grid frequency regulation and peak regulation has received more and more attention. Balancing the frequency regulation performance of the system while considering the wear of thermal power units and the life loss of energy storage devices has become an urgent problem to be solved. Summary of the invention

[0003] The disclosed embodiments provide a method and device for allocating frequency modulation instructions for overcapacity energy storage taking into account the life of the unit, so as to solve the problem of frequent unit operation and short life due to poor stability of existing frequency modulation instructions.

[0004] Based on the above problems, in a first aspect, an embodiment of the present disclosure provides a method for allocating frequency modulation instructions for overcapacity energy storage considering the life of a unit, including:

[0005] Execute multiple cycles, and for the decomposition layer number corresponding to each cycle, decompose the frequency modulation signal based on the decomposition layer number to obtain subsequences of the decomposition layer number; establish a corresponding prediction model for each subsequence, train the prediction model based on the data of the first time period of the subsequence, and predict the data of the second time period of the subsequence through the trained prediction model; determine the ratio error and difference error between the predicted value and the actual value of the data of the second time period; and sum the ratio error and difference error corresponding to each subsequence under the decomposition layer number to obtain a total ratio error and a total difference error;

[0006] Determine the minimum value of the total ratio error and the total difference error corresponding to each decomposition level, and judge whether the decomposition level corresponding to the two minimum values ​​meets the preset conditions. If so, output the decomposition level.

[0007] In combination with the first aspect, in a possible implementation, the prediction model adopts a GRU (Gated Recurrent Unit) model, and the first time period is the first 80% of the time period of the corresponding subsequence; the second time period is the last 20% of the time period of the corresponding subsequence.

[0008] In combination with the first aspect, in a possible implementation manner, the ratio error is determined by the following formula: :

[0009] ,

[0010] The difference error is determined by the following formula: :

[0011] ,

[0012] Where N represents the sample size of any second period of data, represents the actual value at time n, Represents the predicted value at time n.

[0013] In combination with the first aspect, in a possible implementation manner, the method further includes:

[0014] If not, determine the first frequency division point under the decomposition layer number corresponding to the minimum total ratio error; divide the frequency modulation signal into a first high-frequency component and a first low-frequency component based on the first frequency division point; determine the first task amount undertaken by the thermal power unit based on the first low-frequency component; and

[0015] Determine a second frequency division point under the decomposition layer number corresponding to the minimum total difference error; divide the frequency modulation signal into a second high-frequency component and a second low-frequency component based on the second frequency division point; determine a second task amount undertaken by the thermal power unit based on the second low-frequency component;

[0016] The number of decomposition levels corresponding to the smaller one of the first task amount and the second task amount is determined and outputted.

[0017] In combination with the first aspect, in a possible implementation manner, a frequency division point is determined as follows:

[0018] Map all subsequences corresponding to the number of decomposition levels to the frequency domain;

[0019] The aliasing degrees between adjacent subsequences are determined respectively, and the point with the minimum aliasing degree is determined as the frequency division point.

[0020] In combination with the first aspect, in a possible implementation manner, the frequency modulation signal is divided into a high frequency component and a low frequency component based on a frequency division point and the task amount undertaken by the thermal power unit is determined based on the low frequency component as follows:

[0021] Determine that the subsequence before the frequency division point is a low-frequency component, and the subsequence after the frequency division point is a high-frequency component;

[0022] The task amount undertaken by the thermal power unit is obtained by adding up the subsequences contained in the low-frequency component.

[0023] In a second aspect, an embodiment of the present disclosure provides a frequency modulation instruction distribution device for super-capacity energy storage taking into account the life of a unit, comprising:

[0024] A signal acquisition module, used for acquiring a frequency modulation signal;

[0025] The signal processing module is used to execute multiple cycles, and for the number of decomposition layers corresponding to each cycle, the frequency modulation signal is decomposed based on the number of decomposition layers to obtain subsequences of the number of decomposition layers; a corresponding prediction model is established for each subsequence, the prediction model is trained based on the data of the first time period of the subsequence, and the data of the second time period of the subsequence is predicted by the trained prediction model; the ratio error and the difference error between the predicted value and the actual value of the data of the second time period are determined; and the ratio error and the difference error corresponding to each subsequence under the number of decomposition layers are summed up to obtain a total ratio error and a total difference error;

[0026] The judgment output module is used to determine the minimum value of the total ratio error and the total difference error corresponding to each decomposition layer number, and judge whether the decomposition layer number corresponding to the two minimum values ​​meets the preset conditions. If so, the decomposition layer number is output.

[0027] In combination with the second aspect, in a possible implementation, in the signal processing module, the prediction model adopts a GRU model, the first time period is the first 80% of the time period of the corresponding subsequence; the second time period is the last 20% of the time period of the corresponding subsequence.

[0028] In combination with the second aspect, in a possible implementation manner, the ratio error is determined using the following formula: :

[0029] ,

[0030] The difference error is determined by the following formula: :

[0031] ,

[0032] Where N represents the sample size of any second period of data, represents the actual value at time n, Represents the predicted value at time n.

[0033] In combination with the second aspect, in a possible implementation manner, the judgment output module further includes:

[0034] If not, determine the first frequency division point under the decomposition layer number corresponding to the minimum total ratio error; divide the frequency modulation signal into a first high-frequency component and a first low-frequency component based on the first frequency division point; determine the first task amount undertaken by the thermal power unit based on the first low-frequency component; and

[0035] Determine a second frequency division point under the decomposition layer number corresponding to the minimum total difference error; divide the frequency modulation signal into a second high-frequency component and a second low-frequency component based on the second frequency division point; determine a second task amount undertaken by the thermal power unit based on the second low-frequency component;

[0036] The number of decomposition levels corresponding to the smaller one of the first task amount and the second task amount is determined and outputted.

[0037] In conjunction with the second aspect, in a possible implementation manner, the frequency division point is determined as follows:

[0038] Map all subsequences corresponding to the number of decomposition levels to the frequency domain;

[0039] The aliasing degrees between adjacent subsequences are determined respectively, and the point with the minimum aliasing degree is determined as the frequency division point.

[0040] In combination with the second aspect, in a possible implementation manner, the method of dividing the frequency modulation signal into a high frequency component and a low frequency component based on a frequency division point and determining the task amount undertaken by the thermal power unit based on the low frequency component is as follows:

[0041] Determine that the subsequence before the frequency division point is a low-frequency component, and the subsequence after the frequency division point is a high-frequency component;

[0042] The task amount undertaken by the thermal power unit is obtained by adding up the subsequences contained in the low-frequency component.

[0043] In a third aspect, a computer device is provided, comprising: a processor, a memory and a bus, the memory storing 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 allocating frequency modulation instructions for over-capacity energy storage taking into account the life of the unit are performed as described in the first aspect, or in combination with any possible implementation manner of the first aspect.

[0044] In a fourth aspect, a computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the method for allocating frequency modulation instructions for overcapacity energy storage taking into account the life of the unit as described in the first aspect, or in combination with any possible implementation of the first aspect.

[0045] The beneficial effects of the embodiments of the present disclosure include:

[0046] The method for allocating frequency modulation instructions for super-capacity energy storage considering the life of a unit provided by an embodiment of the present disclosure includes: obtaining a frequency modulation signal; executing multiple cycles, and decomposing the frequency modulation signal based on the decomposition layer number corresponding to each cycle to obtain subsequences of the decomposition layer number; establishing a corresponding prediction model for each subsequence, training the prediction model based on the data of the first time period of the subsequence, and predicting the data of the second time period of the subsequence through the trained prediction model; determining the ratio error and difference error between the predicted value and the actual value of the data of the second time period; and summing the ratio error and difference error corresponding to each subsequence under the decomposition layer number to obtain a total ratio error and a total difference error; respectively determining the minimum value of the total ratio error and the total difference error corresponding to each decomposition layer number, judging whether the decomposition layer number corresponding to the two minimum values ​​meets the preset conditions, and outputting the decomposition layer number if it meets the conditions. An overcapacity energy storage frequency regulation instruction allocation method considering the life of the unit provided in an embodiment of the present disclosure is applied to the frequency regulation of a power plant power grid. The frequency regulation signal is decomposed according to different decomposition levels, and the prediction error is judged by the result of model prediction to obtain the stationarity of the subsequence corresponding to the decomposition level. The decomposition level with the best stationarity is determined, so that when the thermal power unit responds to the frequency regulation signal, the unit action is reduced and the unit life is longer. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A flow chart of a method for allocating frequency modulation instructions for overcapacity energy storage taking into account the life of a unit provided in an embodiment of the present disclosure;

[0048] Figure 2 A schematic diagram of frequency domain distribution aliasing of modal quantities generated by decomposition provided in an embodiment of the present disclosure;

[0049] Figure 3 A specific flow chart of a method for allocating frequency modulation instructions for overcapacity energy storage taking into account the life of a unit provided in an embodiment of the present disclosure;

[0050] Figure 4 A flow chart of a frequency modulation instruction distribution device for overcapacity energy storage taking into account the life of the unit provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0051] The embodiments of the present disclosure provide a method and device for allocating frequency modulation instructions for super-capacity energy storage considering the life of the unit. The preferred embodiments of the present disclosure are described below in conjunction with the 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. In addition, the embodiments and features in the embodiments of the present application can be combined with each other if there is no conflict.

[0052] The embodiment of the present disclosure provides a method for allocating frequency modulation instructions of over-capacity energy storage considering the life of the unit, such as Figure 1As shown, including:

[0053] S101, obtaining a frequency modulation signal;

[0054] S102, executing multiple cycles, for the number of decomposition layers corresponding to each cycle, decomposing the frequency modulation signal based on the number of decomposition layers to obtain subsequences of the number of decomposition layers; establishing a corresponding prediction model for each subsequence, training the prediction model based on the data of the first time period of the subsequence, and predicting the data of the second time period of the subsequence through the trained prediction model; determining the ratio error and difference error between the predicted value and the actual value of the data of the second time period; and summing the ratio error and difference error corresponding to each subsequence under the number of decomposition layers to obtain a total ratio error and a total difference error;

[0055] S103, respectively determining the minimum values ​​of the total ratio error and the total difference error corresponding to each decomposition level number, judging whether the decomposition level number corresponding to the two minimum values ​​meets the preset conditions, and outputting the decomposition level number if it meets the conditions.

[0056] In the disclosed embodiment, for the frequency modulation of the power grid of the power plant, the frequency modulation is completed by using a combined energy storage system of supercapacitor-coupled thermal power units. This solution uses the VMD (Variational mode decomposition) algorithm to decompose the frequency modulation signal to obtain subsequences corresponding to the number of decomposition layers, and based on the GRU model principle, a prediction model is established for each subsequence, and the prediction model is trained using the data of the first period in the subsequence, and the data of the second period of the subsequence is predicted by the trained prediction model. The ratio error and difference error between the predicted value and the actual value of the data of the second period are obtained by calculating, and all the ratio errors and difference errors obtained by all subsequences under the number of decomposition layers are summed up respectively to obtain the total ratio error and total difference error corresponding to the number of decomposition layers. After all cycles are completed, the minimum total ratio error and the minimum total difference error are obtained by comparing the size of the error corresponding to each number of decomposition layers. When the number of decomposition layers corresponding to the smallest total ratio error and the number of decomposition layers corresponding to the smallest total difference error meet the preset conditions, that is, the number of decomposition layers corresponding to the smallest total ratio error and the number of decomposition layers corresponding to the smallest total difference error are equal, the number of decomposition layers is output.

[0057] In another embodiment provided by the present disclosure, in the above step S102, the prediction model adopts a GRU model, the first time period is the first 80% time period of the corresponding subsequence; the second time period is the last 20% time period of the corresponding subsequence.

[0058] In the disclosed embodiment, the training of a single prediction model is completed in a separate subsequence, and the data of the first period in the subsequence, that is, the first 80% period in the subsequence, is input into the prediction model to train the model. The trained model is used to predict the data of the last 20% period in the subsequence, and the obtained prediction value is compared with the actual value in the subsequence to obtain the ratio error and the difference error. The smaller the prediction error of the trained prediction model, the better the stability of the subsequence generated by the decomposition method, which reduces the action of the thermal power unit and increases the life of the unit.

[0059] In another embodiment provided by the present disclosure, in the above step S102, the ratio error is determined by the following formula: :

[0060] ,

[0061] The difference error is determined by the following formula: :

[0062] ,

[0063] Where N represents the sample size of any second period of data, represents the actual value at time n, Represents the predicted value at time n.

[0064] In the disclosed embodiment, in each subsequence, the data of the last 20% of the time period in the entire time period are calculated using the formula to obtain the ratio error and the difference error respectively.

[0065] In another embodiment provided by the present disclosure, the above method further includes:

[0066] If not, determine the first frequency division point under the decomposition layer number corresponding to the minimum total ratio error; divide the frequency modulation signal into a first high-frequency component and a first low-frequency component based on the first frequency division point; determine the first task amount undertaken by the thermal power unit based on the first low-frequency component; and

[0067] Determine a second frequency division point under the decomposition layer number corresponding to the minimum total difference error; divide the frequency modulation signal into a second high-frequency component and a second low-frequency component based on the second frequency division point; determine a second task amount undertaken by the thermal power unit based on the second low-frequency component;

[0068] The number of decomposition levels corresponding to the smaller one of the first task amount and the second task amount is determined and outputted.

[0069] In the disclosed embodiment, if the number of decomposition layers corresponding to the minimum total ratio error is consistent with the number of decomposition layers corresponding to the minimum total difference error, the number of decomposition layers is directly output; if the number of decomposition layers corresponding to the above-mentioned minimum total ratio error is inconsistent with the number of decomposition layers corresponding to the minimum total difference error, it is necessary to compare the size of the task amount undertaken by the thermal power unit in the frequency modulation signal allocation results corresponding to the two decomposition layers, and obtain the decomposition layer number corresponding to the allocation method with a smaller task amount undertaken by the thermal power unit.

[0070] In another embodiment provided by the present disclosure, in the above method, the frequency division point is determined as follows:

[0071] Step 1: Map all subsequences corresponding to the decomposition level to the frequency domain;

[0072] Step 2: Determine the aliasing degree between adjacent subsequences respectively, and determine the point with the minimum aliasing degree as the frequency division point.

[0073] In the embodiment of the present disclosure, according to the number of decomposition layers, the frequency modulation signal is decomposed to generate subsequences of the number of decomposition layers, such as Figure 2 As shown, all subsequences of the corresponding decomposition level are mapped to the frequency domain. The subsequences will be aliased in the frequency domain. Taking the aliased part between the modal quantity IMF1 and the modal quantity IMF2 as an example, the width of the aliased part is ω(i+1)-(1); the frequency band occupied by the modal quantity IMF2 and the modal quantity IMF1 is ω (i+1)max -ω (i)min , the distribution of subsequences in the frequency domain is used to obtain the aliasing degree between adjacent subsequences. The aliasing degree between all adjacent subsequences is obtained for comparison, and the adjacent subsequence with the smallest aliasing degree is obtained. The point between the two subsequences is the frequency division point.

[0074] In another embodiment provided by the present disclosure, in the above method, the frequency modulation signal is divided into a high frequency component and a low frequency component based on the frequency division point and the task amount undertaken by the thermal power unit is determined based on the low frequency component as follows:

[0075] Step 1: determine that the subsequence before the frequency division point is the low-frequency component, and the subsequence after the frequency division point is the high-frequency component;

[0076] Step 2: Add the subsequences contained in the low-frequency components to obtain the task amount undertaken by the thermal power unit.

[0077] In the disclosed embodiment, after the frequency division point is determined, the low-frequency component is before the frequency division point, and the high-frequency component is after the frequency division point. The subsequences before the frequency division point are summed to obtain the low-frequency component, which is the amount of task that the thermal power unit needs to undertake. Decomposing the two decomposition layers corresponding to the above minimum total ratio error and the minimum total difference error, it can be seen that the smaller the amount of task undertaken by the thermal power unit, the smaller the load of the thermal power unit, and the longer the life. Therefore, the amount of task undertaken by the thermal power unit obtained by the above method is compared to obtain the decomposition layer number that makes the amount of task undertaken by the thermal power unit smaller and output the decomposition layer number. At this time, the thermal power unit has small loss, small load, and long life.

[0078] To facilitate a better understanding of the solution, the specific process of a method for allocating frequency modulation instructions for overcapacity energy storage considering the life of the unit provided in the embodiment of the present disclosure is as follows: Figure 3 As shown in the figure, the FM signal X(t) is acquired; VMD decomposition is performed on the FM signal X(t) and the initial decomposition layer number is set to 5; the subsequences corresponding to the decomposition layer number generated by the decomposition are respectively input into the pre-trained prediction model to obtain the predicted total aliasing degree; the ratio error and difference error between the predicted total aliasing degree and the actual total aliasing degree are determined; the ratio errors corresponding to all subsequences are summed to obtain the total ratio error BE and the total difference error CE; the decomposition layer number is incremented by 1 and the decomposition is repeated to obtain the total ratio error BE and the total difference error CE corresponding to the decomposition layer number until the decomposition layer number is 13; and the total ratio error BE and the total difference error CE corresponding to each decomposition layer number are recorded. Difference CE; determine the decomposition number corresponding to the minimum value BEmin of all total ratio errors BE and the decomposition number corresponding to the minimum value CEmin of all total difference errors CE, and judge whether the decomposition number corresponding to BEmin and the decomposition number corresponding to CEmin are equal; if they are equal, directly output the decomposition number; if they are not equal, determine the corresponding frequency division points under the decomposition numbers corresponding to BEmin and CEmin respectively; and determine the smaller of the task amounts undertaken by the thermal power units obtained by the frequency division points corresponding to BEmin and CEmin respectively; output the decomposition number corresponding to BEmin or CEmin corresponding to the frequency division point with the smaller task amount undertaken by the thermal power unit.

[0079] In order to further verify the advantages of the method proposed in the present invention, the present invention uses the method of the present invention and the traditional algorithm for prediction, and the indicators are shown in the following table:

[0080]

[0081] It can be seen that the error of the predicted aliasing degree D obtained by the method of the present invention is significantly smaller than the error of the predicted aliasing degree D by the traditional model, and the method of the present invention is superior to the traditional method.

[0082] The method / system and related devices provided by the present disclosure are described in detail below with reference to specific embodiments in conjunction with the accompanying drawings.

[0083] Based on the same disclosed concept, the embodiments of the present disclosure also provide an apparatus and device for allocating frequency modulation instructions for overcapacity energy storage taking into account the life of the unit. Since the principles of the problems solved by these apparatus and devices are similar to the aforementioned method for allocating frequency modulation instructions for overcapacity energy storage taking into account the life of the unit, the implementation of the apparatus and device can refer to the implementation of the aforementioned method, and the repeated parts will not be repeated.

[0084] The embodiment of the present disclosure provides a frequency modulation instruction distribution device for super-capacity energy storage considering the life of the unit, such as Figure 4 As shown, including:

[0085] A signal acquisition module 401 is used to acquire a frequency modulation signal;

[0086] The signal processing module 402 is used to execute multiple cycles, and for the number of decomposition layers corresponding to each cycle, the frequency modulation signal is decomposed based on the number of decomposition layers to obtain subsequences of the number of decomposition layers; a corresponding prediction model is established for each subsequence, the prediction model is trained based on the data of the first time period of the subsequence, and the data of the second time period of the subsequence is predicted by the trained prediction model; the ratio error and the difference error between the predicted value and the actual value of the data of the second time period are determined; and the ratio error and the difference error corresponding to each subsequence under the number of decomposition layers are summed up to obtain a total ratio error and a total difference error;

[0087] The judgment output module 403 is used to determine the minimum value of the total ratio error and the total difference error corresponding to each decomposition level, and judge whether the decomposition level corresponding to the two minimum values ​​meets the preset conditions. If so, the decomposition level is output.

[0088] In another embodiment provided by the present disclosure, in the signal processing module 402, the prediction model adopts a GRU model, the first time period is the first 80% time period of the corresponding subsequence; the second time period is the last 20% time period of the corresponding subsequence.

[0089] In another embodiment provided by the present disclosure, in the signal processing module 402, the ratio error is determined by the following formula: :

[0090] ,

[0091] The difference error is determined by the following formula: :

[0092] ,

[0093] Where N represents the sample size of any second period of data, represents the actual value at time n, Represents the predicted value at time n.

[0094] In another embodiment provided by the present disclosure, the above-mentioned determination output module 403 further includes:

[0095] If not, determine the first frequency division point under the decomposition layer number corresponding to the minimum total ratio error; divide the frequency modulation signal into a first high-frequency component and a first low-frequency component based on the first frequency division point; determine the first task amount undertaken by the thermal power unit based on the first low-frequency component; and

[0096] Determine a second frequency division point under the decomposition layer number corresponding to the minimum total difference error; divide the frequency modulation signal into a second high-frequency component and a second low-frequency component based on the second frequency division point; determine a second task amount undertaken by the thermal power unit based on the second low-frequency component;

[0097] The number of decomposition levels corresponding to the smaller one of the first task amount and the second task amount is determined and outputted.

[0098] In another embodiment provided by the present disclosure, in the above-mentioned determination output module 403, the method of determining the frequency division point is as follows:

[0099] Map all subsequences corresponding to the number of decomposition levels to the frequency domain;

[0100] The aliasing degrees between adjacent subsequences are determined respectively, and the point with the minimum aliasing degree is determined as the frequency division point.

[0101] In another embodiment provided by the present disclosure, in the above-mentioned judgment output module 403, the method of dividing the frequency modulation signal into a high-frequency component and a low-frequency component based on the frequency division point and determining the task amount undertaken by the thermal power unit based on the low-frequency component is as follows:

[0102] Determine that the subsequence before the frequency division point is a low-frequency component, and the subsequence after the frequency division point is a high-frequency component;

[0103] The task amount undertaken by the thermal power unit is obtained by adding up the subsequences contained in the low-frequency component.

[0104] An embodiment of the present disclosure provides a computer device, including: 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 allocating frequency modulation instructions for over-capacity energy storage taking into account the life of the unit provided in any embodiment of the present disclosure are executed.

[0105] The computer device provided by the embodiment of the present disclosure includes a processor, a memory, and a bus. The memory is used to store execution instructions, including internal memory and external memory; the internal memory here is also called internal memory, which is used to temporarily store the operation data in the processor and the data exchanged with the external memory such as the hard disk. The processor exchanges data with the external memory through the internal memory. When the electronic device is running, the processor and the memory communicate through the bus, so that the processor executes the following instructions:

[0106] Get FM signal;

[0107] Execute multiple cycles, and for the decomposition layer number corresponding to each cycle, decompose the frequency modulation signal based on the decomposition layer number to obtain subsequences of the decomposition layer number; establish a corresponding prediction model for each subsequence, train the prediction model based on the data of the first time period of the subsequence, and predict the data of the second time period of the subsequence through the trained prediction model; determine the ratio error and difference error between the predicted value and the actual value of the data of the second time period; and sum the ratio error and difference error corresponding to each subsequence under the decomposition layer number to obtain a total ratio error and a total difference error;

[0108] Determine the minimum value of the total ratio error and the total difference error corresponding to each decomposition level, and judge whether the decomposition level corresponding to the two minimum values ​​meets the preset conditions. If so, output the decomposition level.

[0109] The embodiment of the present disclosure provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method for allocating frequency modulation instructions for overcapacity energy storage considering the life of the unit provided in any embodiment of the present disclosure are executed. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0110] Through the description of the above implementation methods, 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 solution 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 read-only CD, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present disclosure.

[0111] Those skilled in the art will appreciate that the accompanying drawings are merely schematic diagrams of a preferred embodiment, and the modules or processes in the accompanying drawings are not necessarily required for implementing the present disclosure.

[0112] Those skilled in the art can understand that the modules in the device in the embodiment can be distributed in the device in the embodiment according to the description of the embodiment, or can be changed accordingly and located in one or more devices different from the present embodiment. The modules in the above embodiment can be combined into one module, or can be further divided into multiple sub-modules.

[0113] The serial numbers of the above-mentioned embodiments of the present disclosure are only for description and do not represent the advantages or disadvantages of the embodiments.

[0114] 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 equivalents, the present disclosure is also intended to include these modifications and variations.

Claims

1. A method for allocating frequency modulation instructions for overcapacity energy storage considering the life of the unit, characterized in that: include: Get FM signal; Execute multiple cycles, and for the number of decomposition layers corresponding to each cycle, decompose the frequency modulation signal based on the number of decomposition layers to obtain subsequences of the number of decomposition layers; establish a corresponding prediction model for each subsequence, train the prediction model based on the data of the first period of the subsequence, and predict the data of the second period of the subsequence through the trained prediction model; Determine the ratio error and the difference error between the predicted value and the actual value of the data in the second period; and sum the ratio error and the difference error corresponding to each subsequence under the decomposition level to obtain a total ratio error and a total difference error; Determine the minimum value of the total ratio error and the total difference error corresponding to each decomposition level, and judge whether the decomposition level corresponding to the two minimum values ​​meets the preset conditions. If so, output the decomposition level; Among them, when the decomposition number corresponding to the smallest total ratio error and the decomposition number corresponding to the smallest total difference error meet the preset conditions, that is, the decomposition number corresponding to the smallest total ratio error and the decomposition number corresponding to the smallest total difference error are equal, the decomposition number is output; If it does not meet the requirement, then determine the first frequency division point under the decomposition layer number corresponding to the minimum total ratio error; divide the frequency modulation signal into a first high-frequency component and a first low-frequency component based on the first frequency division point; determine the first task amount undertaken by the thermal power unit based on the first low-frequency component; and Determine a second frequency division point under the decomposition layer number corresponding to the minimum total difference error; divide the frequency modulation signal into a second high-frequency component and a second low-frequency component based on the second frequency division point; determine a second task amount undertaken by the thermal power unit based on the second low-frequency component; The number of decomposition levels corresponding to the smaller one of the first task amount and the second task amount is determined and outputted.

2. The method according to claim 1, characterized in that The prediction model adopts the GRU model, the first time period is the first 80% time period of the corresponding subsequence; the second time period is the last 20% time period of the corresponding subsequence.

3. The method according to claim 1, characterized in that The ratio error is determined using the following formula: : ， The difference error is determined by the following formula: : ， Where N represents the sample size of any second period of data, represents the actual value at time n, Represents the predicted value at time n.

4. The method according to claim 1, characterized in that The method to determine the crossover frequency is as follows: Map all subsequences corresponding to the number of decomposition levels to the frequency domain; The aliasing degrees between adjacent subsequences are determined respectively, and the point with the minimum aliasing degree is determined as the frequency division point.

5. The method according to claim 1, characterized in that The method of dividing the frequency modulation signal into a high frequency component and a low frequency component based on the frequency division point and determining the task amount undertaken by the thermal power unit based on the low frequency component is as follows: Determine that the subsequence before the frequency division point is a low-frequency component, and the subsequence after the frequency division point is a high-frequency component; The task amount undertaken by the thermal power unit is obtained by adding up the subsequences contained in the low-frequency component.

6. An overcapacity energy storage frequency modulation instruction distribution device considering the life of the unit, comprising: A signal acquisition module, used for acquiring a frequency modulation signal; The signal processing module is used to execute multiple cycles, and for the number of decomposition layers corresponding to each cycle, the frequency modulation signal is decomposed based on the number of decomposition layers to obtain subsequences of the number of decomposition layers; a corresponding prediction model is established for each subsequence, the prediction model is trained based on the data of the first period of the subsequence, and the data of the second period of the subsequence is predicted by the trained prediction model; Determine the ratio error and the difference error between the predicted value and the actual value of the data in the second period; and sum the ratio error and the difference error corresponding to each subsequence under the decomposition level to obtain a total ratio error and a total difference error; The judgment output module is used to determine the minimum value of the total ratio error and the total difference error corresponding to each decomposition level, and judge whether the decomposition level corresponding to the two minimum values ​​meets the preset conditions. If so, the decomposition level is output; The judgment output module is used to output the decomposition number when the decomposition number corresponding to the minimum total ratio error and the decomposition number corresponding to the minimum total difference error meet the preset condition, that is, the decomposition number corresponding to the minimum total ratio error and the decomposition number corresponding to the minimum total difference error are equal; The judgment output module is used to determine the first frequency division point under the decomposition layer number corresponding to the minimum total ratio error if it does not meet the requirements; and divide the frequency modulation signal into a first high-frequency component and a first low-frequency component based on the first frequency division point; Determine a first task amount undertaken by the thermal power unit based on the first low-frequency component; and Determine the second frequency division point under the number of decomposition layers corresponding to the minimum total difference error; dividing the frequency modulation signal into a second high frequency component and a second low frequency component based on the second frequency division point; Determining a second task amount undertaken by the thermal power unit based on the second low-frequency component; The number of decomposition levels corresponding to the smaller one of the first task amount and the second task amount is determined and outputted.

7. 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 allocating frequency modulation instructions for over-capacity energy storage taking into account the life of the unit are performed as described in any one of claims 1 to 5.

8. 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 allocating frequency modulation instructions for overcapacity energy storage taking into account the life of the unit as described in any one of claims 1 to 5.

Images