Ultra-capacitor coupled lithium battery energy storage method and related products based on frequency modulation instruction prediction

Abstract

The present invention discloses a supercapacitor coupled lithium battery energy storage method and related products based on frequency modulation instruction prediction, which belongs to the field of energy storage technology; stable control of power grid frequency is achieved by predicting frequency modulation instructions. First, the original frequency modulation instruction sequence of the power grid system is obtained, and it is input into a pre-constructed frequency modulation instruction prediction model for prediction processing to obtain a predicted frequency modulation instruction sequence. The model construction method includes approximate integrable decomposition of the original frequency modulation instruction sequence, separating approximate integrable quantities and integrable quantities, and performing periodic processing on the approximate integrable quantities, and then converting them into linear merging terms through similarity merging transformation, and calculating residual terms. The linear merging terms, residual terms and integrable quantities are input into the prediction model for prediction. This method effectively improves the prediction accuracy of the frequency modulation instruction, so that the supercapacitor-lithium battery hybrid energy storage system can more accurately and dynamically adjust the charging and discharging power distribution, thereby achieving stable control of the power grid frequency and efficient use of energy.

Description

Technical Field

[0001] The present invention belongs to the technical field of energy storage, and relates to a super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction and related products. Background Art

[0002] With the transformation of the global energy structure and the growing demand for electricity, the stable operation and efficient dispatch of the power system have become one of the major challenges facing the power industry. As the main force of current power supply, thermal power units, while bearing the basic load, also need to frequently participate in the frequency regulation of the power grid to cope with the grid fluctuations caused by the intermittent and uncertain power generation of new energy (such as wind power and solar energy). However, long-term high-intensity frequency regulation operations have brought significant adverse effects on thermal power units, including a significant increase in coal consumption, a decrease in equipment reliability, and a shortened operating life of the units, which not only increases operating costs, but also affects the overall stability and economy of the power system.

[0003] At the same time, high-quality and efficient frequency-modulating power resources are relatively scarce. Although the scale of renewable energy power generation is gradually expanding, its volatility after grid connection has increased the frequency modulation demand of the power grid. Especially in the heating season, the heating units are constrained by the principle of "heat determines electricity", and their frequency modulation capabilities are further restricted, which doubles the frequency modulation pressure of the power grid.

[0004] To solve the above problems, coal-fired power units have traditionally been relied on as the main frequency regulation power source, but this is in stark contradiction with environmental pressure. In order to alleviate this contradiction and improve the flexibility and efficiency of power frequency regulation, it is imperative to develop new frequency regulation technologies and equipment. However, the auxiliary frequency regulation energy storage equipment currently used in thermal power plants, such as conventional energy storage batteries, is still unable to meet the real-time, high efficiency and reliability requirements of unit frequency regulation, which limits its effectiveness in practical applications and also affects the implementation of grid subsidy policies and the improvement of economic benefits.

[0005] In the development of power frequency modulation technology, the introduction of prediction technology is regarded as a key means to improve the efficiency and accuracy of frequency modulation. Traditional frequency modulation instruction prediction methods often directly use machine learning models such as neural networks to predict the original frequency modulation instructions. However, due to the strong nonlinearity and irregularity of the frequency modulation instructions themselves, this method often has large prediction errors in practical applications and is difficult to meet the precise needs of power frequency modulation. Summary of the invention

[0006] The purpose of the present invention is to solve the technical problem in the prior art that the frequency modulation instruction prediction error is large and it is difficult to meet the precise requirements of power frequency modulation, and to provide an ultra-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction and related products.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] The first aspect of the present invention provides a super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction, comprising the following steps:

[0009] Obtaining the original frequency modulation instruction sequence of the power grid system;

[0010] Inputting the original frequency modulation instruction sequence into a pre-built frequency modulation instruction prediction model for prediction processing to obtain a predicted frequency modulation instruction sequence;

[0011] Generate a control signal based on the predicted frequency modulation instruction sequence to dynamically adjust the charging and discharging power distribution of the ultracapacitor-lithium battery hybrid energy storage system;

[0012] The method for constructing the frequency modulation instruction prediction model includes:

[0013] The original frequency modulation instruction sequence is approximately integrable decomposed to separate the approximately integrable quantity and the integrable quantity;

[0014] Performing periodic processing on the approximate integrable quantity to generate a periodic formula of the approximate integrable quantity;

[0015] The periodic formula of the approximate integrable quantity is converted into a linear combination term by similarity combination transformation, and the residual term is calculated;

[0016] The linear merging term, the residual term and the integrable quantity are input into the prediction model to predict and obtain the predicted frequency modulation instruction sequence.

[0017] Furthermore, the original frequency modulation instruction sequence is approximately integrable decomposed to separate the approximately integrable quantity and the integrable quantity, specifically:

[0018] The original frequency modulation instruction sequence is processed by smooth function to be approximately integrable, and the approximate integrable quantity is extracted;

[0019] The non-integrable quantity is calculated by time domain difference operation, and the non-integrable quantity is the time domain difference between the frequency modulation instruction sequence and the approximate integrable quantity.

[0020] Further, the periodic processing of the approximate integrable quantity is specifically performed as follows:

[0021]

[0022] in, ; is the approximate first-order compensation coefficient;

[0023] ; is the approximate quadratic compensation coefficient; j is the length of the original frequency modulation instruction sequence; k is the coefficient to be determined;cos () is the cosine function; express arrive Integration of intervals; represents the sum function; represents factorial; A periodic formula for an approximately integrable quantity.

[0024] Furthermore, the periodic formula of the approximate integrable quantity is converted into a linear merging term through similarity merging transformation, and the residual term is calculated, specifically:

[0025] The periodic formula of the approximate integrable quantity is linearly combined through similarity combination transformation to obtain the linear combination term;

[0026] The residual term is obtained by subtracting the periodic formula of the approximately integrable quantity from the linear combination term.

[0027] Further, the linear merging term is described as:

[0028]

[0029] Among them, the rotation matrix ; j is the length of the original frequency modulation instruction sequence; ... The first to the second bits of the approximate integrable quantity of the original frequency modulation instruction sequence j The approximate first-order compensation coefficient of the bit; ... The first to the second bits of the approximate integrable quantity of the original frequency modulation instruction sequence j The approximate quadratic compensation coefficient of the bit; sin() represents the sine function; cos() represents the cosine function; is the phase angle parameter.

[0030] Furthermore, the linear combination term, the residual term and the integrable quantity are input into the prediction model for prediction to obtain the predicted frequency modulation instruction, which is specifically:

[0031] Inputting the linear combination item, the residual item and the integrable quantity into the prediction model for prediction, and obtaining the predicted linear combination item, the predicted residual item and the predicted integrable quantity;

[0032] The predicted linear combination term, the predicted residual term and the predicted integrable quantity are superimposed to obtain the predicted frequency modulation instruction.

[0033] A second aspect of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction when executing the computer program.

[0034] A third aspect of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction is implemented.

[0035] A fourth aspect of the present invention provides a computer program product, which includes computer instructions, and the computer instructions instruct a computer to execute the above-mentioned ultra-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction.

[0036] A fifth aspect of the present invention provides a super-capacitor coupled lithium battery energy storage system based on frequency modulation instruction prediction, comprising:

[0037] A data acquisition module, used to acquire the original frequency modulation instruction sequence of the power grid system;

[0038] A frequency modulation instruction prediction module is used to input the original frequency modulation instruction sequence into a pre-built frequency modulation instruction prediction model for prediction processing to obtain a predicted frequency modulation instruction sequence;

[0039] An energy storage adjustment module, used to generate a control signal based on the predicted frequency modulation instruction sequence to dynamically adjust the charging and discharging power distribution of the ultracapacitor-lithium battery hybrid energy storage system;

[0040] The method for constructing the frequency modulation instruction prediction model includes:

[0041] The original frequency modulation instruction sequence is approximately integrable decomposed to separate the approximately integrable quantity and the integrable quantity;

[0042] Performing periodic processing on the approximate integrable quantity to generate a periodic formula of the approximate integrable quantity;

[0043] The periodic formula of the approximate integrable quantity is converted into a linear combination term by similarity combination transformation, and the residual term is calculated;

[0044] The linear merging term, the residual term and the integrable quantity are input into the prediction model to predict and obtain the predicted frequency modulation instruction sequence.

[0045] Compared with the prior art, the present invention has the following beneficial effects:

[0046] The present invention discloses a supercapacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction. The original frequency modulation instruction sequence is subjected to integrability decomposition to separate the approximate integrable quantities that are easy to predict and the non-integrable quantities that are difficult to predict, so that the prediction model can focus more on capturing the main trends. The periodic extension processing and linear combination algorithm are adopted, combined with the Fourier-Taylor hybrid expansion and rotation matrix transformation, to further enhance the prediction model's ability to identify and predict periodic components in the frequency modulation instruction sequence. Through the pre-constructed frequency modulation instruction prediction model, the present invention can accurately predict the frequency modulation instructions of the power grid system, thereby realizing the dynamic adjustment of the charging and discharging power of the supercapacitor-lithium battery hybrid energy storage system. This method significantly improves the response speed of the energy storage system to the frequency modulation demand of the power grid, while ensuring the accuracy of the adjustment, which helps to maintain the stable operation of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 It is a block diagram of the super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction of the present invention;

[0049] Figure 2 This is a flow chart of the frequency modulation instruction prediction model of the present invention;

[0050] Figure 3 This is a block diagram of the ultra-capacitor coupled lithium battery energy storage system based on frequency modulation instruction prediction of the present invention.

[0051] Among them: 301-data acquisition module; 302-frequency modulation instruction prediction module; 303-energy storage adjustment module. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention described and marked in the drawings here can be arranged and designed in various different configurations.

[0053] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0054] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, further definition and explanation thereof is not required in subsequent drawings.

[0055] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0056] See also Figure 1 The present invention discloses a super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction, comprising the following steps:

[0057] S1, obtaining the original frequency modulation instruction sequence of the power grid system;

[0058] Obtain real-time original frequency regulation instructions from the power grid dispatch center or related data sources. These instructions usually reflect the current frequency deviation and adjustment requirements of the power grid.

[0059] S2, inputting the original frequency modulation instruction sequence into a pre-built frequency modulation instruction prediction model for prediction processing to obtain a predicted frequency modulation instruction sequence;

[0060] The construction method of the pre-built frequency modulation instruction prediction model is:

[0061] S201, perform approximate integrable decomposition on the original frequency modulation instruction sequence to separate the approximate integrable quantities and the integrable quantities; process the original frequency modulation instruction sequence to identify and separate the approximate integrable quantities (i.e., the parts with obvious trends and regularities) and the integrable quantities (i.e., the parts with random fluctuations or difficult to predict).

[0062] S202, performing periodic processing on the approximate integrable quantity to generate a periodic formula of the approximate integrable quantity; for the approximate integrable quantity, using methods such as Fourier transform and time series analysis to identify and extract its periodic components to obtain a periodic approximate integrable quantity.

[0063] S203, converting the periodic formula of the approximate integrable quantity into a linear combination term through a similarity merging transformation, and calculating the residual term; further linearizing the periodic formula of the approximate integrable quantity, and decomposing it into a linear combination term (main trend) and a residual term (remaining fluctuations that cannot be fully explained by the linear model) through linear regression or other linear models.

[0064] S204, input the linear combination terms, residual terms and integrable quantities into the prediction model for prediction, and obtain the predicted frequency modulation instructions. Select a suitable prediction algorithm, such as support vector machine, random forest or deep learning model in machine learning, to build a frequency modulation instruction prediction model. Use the linear combination terms, residual terms and integrable quantities as input features of the model, and use historical data to train the model to learn the mapping relationship between these features and future frequency modulation instructions. After the above preprocessing steps, the original frequency modulation instructions obtained in real time are input into the trained prediction model. Based on the input features, the model outputs a predicted frequency modulation instruction, which reflects the frequency adjustment demand of the power grid in the future.

[0065] S3, based on the predicted frequency modulation instruction sequence, a control signal is generated to dynamically adjust the charge and discharge power distribution of the ultracapacitor-lithium battery hybrid energy storage system; according to the predicted frequency modulation instruction, the current state and available capacity of the energy storage system are evaluated to formulate or adjust the charge and discharge plan of the energy storage system to ensure that sufficient power support can be provided or excess electric energy can be absorbed when the power grid needs it. According to the evaluation results, the charge and discharge plan is executed to achieve effective regulation of the power grid frequency by controlling the charge and discharge process of the ultracapacitor coupled lithium battery.

[0066] By implementing this method, the response speed and accuracy of the energy storage system to the grid frequency modulation instructions can be significantly improved. Compared with the traditional energy storage control method based on real-time instructions, this method can predict and prepare for the frequency fluctuations of the grid in advance, reducing the frequency deviation caused by delayed response. At the same time, by optimizing the charging and discharging plan of the energy storage system, the operating efficiency and economy of the energy storage system can be further improved, and the service life of the battery can be extended.

[0067] See also Figure 2 An embodiment of the present invention discloses a super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction, comprising the following steps:

[0068] S1, obtain the original frequency modulation instruction sequence of the power grid system; obtain the frequency modulation instruction data from the power grid dispatching center in real time, which reflects the current frequency deviation and adjustment requirements of the power grid.

[0069] S2, inputting the original frequency modulation instruction sequence into a pre-built frequency modulation instruction prediction model for prediction processing to obtain a predicted frequency modulation instruction sequence;

[0070] The method for constructing the frequency modulation instruction prediction model pre-constructed by the present invention comprises the following steps:

[0071] S201, perform approximate integrability decomposition on the original frequency modulation instruction sequence to separate the approximate integrable quantity and the integrable quantity; use the smooth function to perform approximate integrability processing on the original frequency modulation instruction sequence to separate the approximate integrable quantity with obvious trend and the integrable quantity with random fluctuation. The approximate integrable quantity is obtained after smoothing by the smooth function, and the integrable quantity is the difference between the original frequency modulation instruction sequence and the approximate integrable quantity.

[0072] S202, performing periodic processing on the approximate integrable quantity to generate a periodic formula of the approximate integrable quantity;

[0073] The approximate integrable quantity is periodized to extract its periodic components. Using the Fourier series expansion method, the periodic formula of the approximate integrable quantity can be expressed as the sum of a series of sine and cosine functions, that is:

[0074]

[0075] in, ; is the approximate first-order compensation coefficient;

[0076] ; is the approximate quadratic compensation coefficient; j is the length of the original frequency modulation instruction sequence; k is the coefficient to be determined; cos () is the cosine function; express arrive Integration of intervals; represents the sum function; Represents factorial.

[0077] S203, converting the periodic formula of the approximate integrable quantity into a linear combination term through similarity combination transformation, and calculating the residual term; the linear combination term is obtained through similarity combination transformation to describe its main trend. The linear combination term is described as:

[0078]

[0079] Among them, the rotation matrix ; j is the length of the original frequency modulation instruction sequence; ... The original frequency modulation instruction sequence is from the 1st to the j The approximate first-order compensation coefficient of the bit; ... The original frequency modulation instruction sequence is from the 1st to the j The approximate quadratic compensation coefficient of the bit; sin() represents the sine function; cos() represents the cosine function; is the phase angle parameter.

[0080] Based on the linear combination term and the periodic formula of the approximate integrable quantity, the residual term is calculated, that is, the remaining fluctuations that cannot be fully described by the linear combination term. The residual term is the difference between the linear combination term and the periodic approximate integrable quantity.

[0081] S204, input the linear combination term, residual term and integrable quantity into the prediction model for prediction, and obtain the predicted frequency modulation instruction. The linear combination term, residual term and integrable quantity are used as input features and input into the pre-trained prediction model. The prediction model can be a machine learning model (such as a support vector machine, a random forest) or a deep learning model. The prediction model outputs the predicted linear combination term, the predicted residual term and the predicted integrable quantity. These three are superimposed to obtain the predicted frequency modulation instruction.

[0082] S3, based on the predicted frequency modulation instruction sequence, a control signal is generated to dynamically adjust the charging and discharging power distribution of the ultracapacitor-lithium battery hybrid energy storage system; the energy storage system evaluates the current state and available capacity of the energy storage system according to the predicted frequency modulation instruction. Formulate or adjust the charging and discharging plan of the energy storage system to ensure that sufficient power support can be provided or excess electric energy can be absorbed when the power grid needs it. Execute the charging and discharging plan to achieve effective regulation of the power grid frequency by controlling the charging and discharging process of the ultracapacitor coupled lithium battery.

[0083] In order to verify the advantages of the prediction algorithm in the ultra-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction proposed in the present invention over the traditional model, this embodiment demonstrates the performance difference of the two algorithms in predicting frequency modulation instructions through comparative experiments. By calculating and comparing the root mean square error (RMSE), the performance of different algorithms in prediction accuracy can be intuitively evaluated. The results are as follows:

[0084]

[0085] It can be seen from the above experimental results that the algorithm of the present invention shows significant advantages in predicting frequency modulation instructions. On two different frequency modulation instruction sequences, the RMSE values ​​of the algorithm of the present invention are much lower than those of the traditional model, indicating that its prediction accuracy is higher and the error is smaller. Specifically, on frequency modulation instruction 1, the RMSE value of the algorithm of the present invention is only 1.2, which is about 88% lower than 9.9 of the traditional model; on frequency modulation instruction 2, although the RMSE value of the algorithm of the present invention is slightly higher than that of frequency modulation instruction 1, it is still much lower than 8.7 of the traditional model, which is about 62% lower. These results show that the algorithm of the present invention has stronger prediction ability and higher stability when dealing with complex and changeable frequency modulation instruction sequences.

[0086] An embodiment of the present invention provides an electronic device, which realizes rapid response and precise control of power grid frequency modulation instructions by integrating advanced prediction algorithms and efficient energy management strategies, and effectively improves the overall performance and economic benefits of the energy storage system. The device is mainly composed of a memory, a processor, and a pre-written computer program, which work together to complete the prediction of frequency modulation instructions, the formulation and execution of energy storage strategies. The memory is responsible for storing the data and programs required for the operation of the device, including but not limited to the historical data of frequency modulation instructions, the status information of lithium batteries and supercapacitors, prediction model parameters, control algorithm logic, etc. The memory uses a high-speed, high-reliability storage medium to ensure the timeliness and security of data access. The processor, as the core control unit, is responsible for executing the computer program stored in the memory. The processor has powerful computing power and real-time processing capabilities, and can quickly parse frequency modulation instructions, run prediction models, formulate energy storage strategies, and adjust the charge and discharge status of lithium batteries and supercapacitors in real time. The computer program integrates a super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction.

[0087] One embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the above-mentioned super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction. It can be understood that the computer-readable storage medium here can include both built-in storage media in the terminal device and extended storage media supported by the terminal device. It can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, device or device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space. These instructions can be one or more computer programs (including program codes). It should be noted that more specific examples of computer-readable storage media here (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM, full name CompactDisc Read-Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0088] The computer-readable storage medium also includes a data signal propagated in the baseband or as part of a carrier wave, which carries a readable program code. Such propagated data signals can take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The readable storage medium can also be any readable medium other than a readable storage medium, which can send, propagate or transmit a program for use by or in combination with an instruction execution system, an apparatus or a device. The program code contained on the readable storage medium can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above. The program code for performing the operation of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and also conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code can be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on the remote computing device, or completely on the remote computing device or server. In cases involving remote computing devices, the remote computing devices can be connected to the user computing device through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or can be connected to an external computing device (for example, using an Internet service provider to connect through the Internet).

[0089] The processor may load and execute one or more instructions stored in a computer-readable storage medium to implement the corresponding steps of the ultra-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction in the above embodiment.

[0090] This embodiment provides a computer program product, which executes the corresponding steps of the above-mentioned super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction under the instruction of computer instructions. It aims to achieve stable regulation of power grid frequency and efficient use of energy by integrating advanced frequency modulation instruction prediction algorithm and super-capacitor coupled lithium battery energy storage technology. By executing specific computer instructions, the product automatically analyzes the real-time status of the power grid, predicts future frequency modulation needs, and optimizes the charging and discharging strategy of the super-capacitor coupled lithium battery energy storage system accordingly, thereby effectively responding to power grid frequency fluctuations and improving the stability and economy of the power system.

[0091] See also Figure 3 The present invention discloses a super-capacitor coupled lithium battery energy storage system based on frequency modulation instruction prediction, comprising:

[0092] The data acquisition module 301 is used to acquire the original frequency modulation instruction sequence of the power grid system;

[0093] The frequency modulation instruction prediction module 302 is used to input the original frequency modulation instruction sequence into a pre-built frequency modulation instruction prediction model for prediction processing to obtain a predicted frequency modulation instruction sequence;

[0094] The energy storage adjustment module 303 is used to generate a control signal based on the predicted frequency modulation instruction sequence to dynamically adjust the charging and discharging power distribution of the ultra-capacitor-lithium battery hybrid energy storage system;

[0095] The method for constructing the frequency modulation instruction prediction model includes:

[0096] The original frequency modulation instruction sequence is approximately integrable decomposed to separate the approximately integrable quantity and the integrable quantity;

[0097] Performing periodic processing on the approximate integrable quantity to generate a periodic formula of the approximate integrable quantity;

[0098] The periodic formula of the approximate integrable quantity is converted into a linear combination term by similarity combination transformation, and the residual term is calculated;

[0099] The linear merging term, the residual term and the integrable quantity are input into the prediction model to predict and obtain the predicted frequency modulation instruction sequence.

[0100] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction, characterized in that: The following steps are involved: Obtaining the original frequency modulation instruction sequence of the power grid system; Inputting the original frequency modulation instruction sequence into a pre-built frequency modulation instruction prediction model for prediction processing to obtain a predicted frequency modulation instruction sequence; Generate a control signal based on the predicted frequency modulation instruction sequence to dynamically adjust the charging and discharging power distribution of the ultracapacitor-lithium battery hybrid energy storage system; The method for constructing the frequency modulation instruction prediction model includes: The original frequency modulation instruction sequence is approximately integrable decomposed to separate the approximately integrable quantity and the integrable quantity; Performing periodic processing on the approximate integrable quantity to generate a periodic formula of the approximate integrable quantity; The periodic formula of the approximate integrable quantity is converted into a linear combination term by similarity combination transformation, and the residual term is calculated; The linear merging term, the residual term and the integrable quantity are input into the prediction model to predict and obtain the predicted frequency modulation instruction sequence.

2. The super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction according to claim 1 is characterized in that: The original frequency modulation instruction sequence is approximately integrable decomposed to separate the approximately integrable quantity and the integrable quantity, specifically: The original frequency modulation instruction sequence is processed by smooth function to be approximately integrable, and the approximate integrable quantity is extracted; The non-integrable quantity is calculated by time domain difference operation, and the non-integrable quantity is the time domain difference between the frequency modulation instruction sequence and the approximate integrable quantity.

3. The super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction according to claim 1 is characterized in that: The periodic processing of the approximate integrable quantity is specifically: in, ; is the approximate first-order compensation coefficient; ; is the approximate quadratic compensation coefficient; j is the length of the original frequency modulation instruction sequence; k is the coefficient to be determined; cos () is the cosine function; express arrive Integration of intervals; represents the sum function; represents factorial; A periodic formula for an approximately integrable quantity.

4. The super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction according to claim 1 is characterized in that: The periodic formula of the approximate integrable quantity is converted into a linear merging term through similarity merging transformation, and the residual term is calculated, specifically: The periodic formula of the approximate integrable quantity is linearly combined through similarity combination transformation to obtain the linear combination term; The residual term is obtained by subtracting the periodic formula of the approximately integrable quantity from the linear combination term.

5. The ultra-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction according to claim 1 is characterized in that: The linear merging term is described as: Among them, the rotation matrix ; j is the length of the original frequency modulation instruction sequence; ... The first to the second bits of the approximate integrable quantity of the original frequency modulation instruction sequence j The approximate first-order compensation coefficient of the bit; ... The first to the second bits of the approximate integrable quantity of the original frequency modulation instruction sequence j The approximate quadratic compensation coefficient of the bit; sin() represents the sine function; cos() represents the cosine function; is the phase angle parameter.

6. The super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction according to claim 1 is characterized in that: The linear combination term, the residual term and the integrable quantity are input into the prediction model for prediction to obtain the predicted frequency modulation instruction, specifically: Inputting the linear combination item, the residual item and the integrable quantity into the prediction model for prediction, and obtaining the predicted linear combination item, the predicted residual item and the predicted integrable quantity; The predicted linear combination term, the predicted residual term and the predicted integrable quantity are superimposed to obtain the predicted frequency modulation instruction.

7. An electronic device, characterized in that: It comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the ultra-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction as described in any one of claims 1 to 6 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the ultra-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction according to any one of claims 1 to 6 is implemented.

9. A computer program product, comprising computer instructions, characterized in that: The computer instructions instruct the computer to execute the ultra-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction as described in any one of claims 1-6.

10. A super-capacitor coupled lithium battery energy storage system based on frequency modulation instruction prediction, based on the super-capacitor coupled lithium battery energy storage method based on frequency modulation instruction prediction according to claim 1, characterized in that: include: A data acquisition module, used to acquire the original frequency modulation instruction sequence of the power grid system; A frequency modulation instruction prediction module is used to input the original frequency modulation instruction sequence into a pre-built frequency modulation instruction prediction model for prediction processing to obtain a predicted frequency modulation instruction sequence; An energy storage adjustment module, used to generate a control signal based on the predicted frequency modulation instruction sequence to dynamically adjust the charging and discharging power distribution of the ultracapacitor-lithium battery hybrid energy storage system; The method for constructing the frequency modulation instruction prediction model includes: The original frequency modulation instruction sequence is approximately integrable decomposed to separate the approximately integrable quantity and the integrable quantity; Performing periodic processing on the approximate integrable quantity to generate a periodic formula of the approximate integrable quantity; The periodic formula of the approximate integrable quantity is converted into a linear combination term by similarity combination transformation, and the residual term is calculated; The linear merging term, the residual term and the integrable quantity are input into the prediction model to predict and obtain the predicted frequency modulation instruction sequence.

Images