Super-capacity energy storage grid connection method, system and equipment based on wind speed prediction and medium
By identifying and correcting the interruption points in the wind speed sequence, generating the uninterrupted wind speed sequence for prediction, the problem of insufficient accuracy of the existing wind speed prediction method is solved, and higher wind speed prediction accuracy and grid scheduling stability are achieved.
Patent Information
- Application Number
- CN202510260762.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-06
- Publication Date
- 2025-04-04
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Due to the discontinuity and randomness of the input data, existing wind speed prediction methods are difficult to fully capture the subtle characteristics and dynamic processes of wind speed changes, resulting in limited prediction accuracy and affecting the accuracy of power grid scheduling.
By obtaining the original wind speed sequence, the type of each two adjacent sampling points is judged, and corresponding correction strategies are adopted for different types of interruptions, including feedback linear compensation method and virtual compensation method interpolation processing, until the types of each two adjacent sampling points are uninterrupted points, and the uninterrupted point wind speed sequence is obtained. Then, the uninterrupted wind speed sequence is input to the prediction model, wind speed prediction is performed, and the grid-connected control of the supercapacity energy storage system is carried out based on the prediction results.
Through the improved wind speed prediction method, the accuracy of wind speed prediction is significantly improved, the accuracy and stability of power grid scheduling are enhanced, the volatility and uncertainty of wind power power are effectively compensated, and the efficiency and economicality of the energy storage system are optimized.
Smart Images
Figure CN119765474A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of wind power generation, and relates to a method, system, equipment and medium for super-capacity energy storage grid connection based on wind speed prediction. Background Art
[0002] As the global demand for renewable energy grows, wind energy, as a clean and renewable energy form, is rapidly expanding in development and utilization. The grid-connected operation of large-scale wind farms is of great significance for promoting energy structure transformation and reducing greenhouse gas emissions. However, the power generation characteristics of wind farms are highly dependent on natural wind speed, which itself has significant randomness, intermittency and uncontrollability, which brings great challenges to the dispatch and operation of the power grid.
[0003] Traditionally, grid dispatching agencies rely on accurate wind power forecasts to optimize resource allocation and ensure the stability and security of the power system. To achieve this goal, the industry widely uses advanced algorithms such as neural networks to predict wind speed and then deduce the output power of wind farms. There is often a deviation between the actual output power of wind farms and the predicted value. This deviation not only affects the accuracy of grid dispatching, but may also threaten the stability of the power system. To make up for this shortcoming, the industry usually adopts the method of connecting an ultra-capacity energy storage system at the outlet of the wind farm, and balances the difference between the actual output power and the predicted value through the rapid response capability of the energy storage system, thereby improving the dispatchability of the wind farm and the reliability of grid dispatching.
[0004] However, most existing wind speed prediction methods are based on historical wind speed data, which selects intermittent sampling values within a specific time period (such as every 15 minutes) as input and uses a neural network model for training and prediction. Although this method can reflect the changing trend of wind speed to a certain extent, it is difficult to fully capture the subtle characteristics and dynamic process of wind speed changes due to the discontinuity and randomness of the input data, resulting in limited prediction accuracy and affecting the accuracy of power grid dispatching. Summary of the invention
[0005] The purpose of the present invention is to provide a method, system, device and medium for super-capacity energy storage grid connection based on wind speed prediction, so as to solve the problem that due to the discontinuity and randomness of the input data of the existing wind speed prediction method, it is difficult to fully capture the subtle characteristics and dynamic process of wind speed changes, resulting in limited prediction accuracy and affecting the accuracy of power grid scheduling.
[0006] In order to achieve the above object, the present invention adopts the following technical solutions: A first aspect of the present invention provides a method for super-capacity energy storage grid connection based on wind speed prediction, comprising the following steps: S1, obtaining an original wind speed sequence; based on the original wind speed sequence, determining the type of every two adjacent sampling points in the original wind speed sequence; the types include uninterrupted points, first-type discontinuous points, and second-type discontinuous points; S2, the first type of discontinuity points are corrected by feedback linear compensation method, and the second type of discontinuity points are interpolated by virtual compensation method until the types of every two adjacent sampling points are uninterrupted points, and the wind speed sequence without discontinuity points is obtained; S3, inputting the uninterrupted point wind speed sequence into the prediction model to obtain the predicted wind speed sequence; converting the wind speed values of the predicted wind speed sequence into power values; based on the power values and the actual power generated by the wind farm, determining the shortfall that the over-capacity energy storage system needs to bear, and according to the shortfall, controlling the over-capacity energy storage system to be connected to the grid.
[0007] The method of judging the type of every two adjacent sampling points in the original wind speed sequence based on the original wind speed sequence is as follows: Based on the original wind speed sequence, calculate the original wind speed sequence for every two adjacent sampling points and The first criterion And the second criterion :
[0008]
[0009] in, Represents the original wind speed series j The sampling point value of the position, Represents the original wind speed series i The sampling point value of the position, Represents the original wind speed series i+1 The sampling point value of the position, N Indicates the length of the original wind speed sequence; max() is the maximum value function; e is the Euler number; represents the summation symbol, and the summation interval is j = 1~( i -1); represents the summation symbol, and the summation interval is j =( i +2)~ N ; based on and Calculate the identification coefficient :
[0010] Among them, min() is the minimum function; based on The size of is used to determine the types of two adjacent sampling points in the original wind speed sequence.
[0011] The basis D The size of the original wind speed sequence is used to determine the type of two adjacent sampling points, specifically: if , then the two adjacent sampling points in the original wind speed sequence are uninterrupted points; if , then the two adjacent sampling points in the original wind speed sequence are the first type of discontinuity points; if , then the two adjacent sampling points in the original wind speed sequence are the second type of discontinuity points.
[0012] The first type of discontinuity points are corrected by using the feedback linear compensation method, and the specific method is: Based on the original wind speed sequence, update the sampling points of the original wind speed sequence ,until and These two adjacent sampling points are uninterrupted points; that is:
[0013] Among them, the second-order coefficient , the first-order coefficient B = , constant coefficient ; In the formula, and are two adjacent sampling points in the original wind speed sequence, As the first criterion, As the second criterion, D is the identification coefficient; rand() represents the random number function; min() represents the minimum value function; max() represents the maximum value function; express e of D Second power, e is the Euler number.
[0014] Preferably, the virtual compensation method is used for interpolation processing of the second type of discontinuity points, specifically: Based on the original wind speed sequence, at the second type of discontinuity and Insert several random values between to obtain a wind speed sequence with inserted random values; Based on the wind speed sequence with inserted random values, for every two adjacent sampling points with discontinuities, several random values are inserted until the types of every two adjacent sampling points are uninterrupted points; the discontinuities are first-type discontinuities or second-type discontinuities.
[0015] Furthermore, the random value is greater than or equal to the minimum value of the original wind speed sequence, and less than or equal to the maximum value of the original wind speed sequence.
[0016] A second 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 super-capacity energy storage grid-connected method based on wind speed prediction.
[0017] A third 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-capacity energy storage grid-connected method based on wind speed prediction when executing the computer program.
[0018] A fourth 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 above-mentioned super-capacity energy storage grid-connected method based on wind speed prediction is implemented.
[0019] A fifth aspect of the present invention provides a super-capacity energy storage grid-connected system based on wind speed prediction, comprising: A data classification module is used to obtain an original wind speed sequence; based on the original wind speed sequence, determine the type of every two adjacent sampling points in the original wind speed sequence; the types include uninterrupted points, first-type discontinuous points, and second-type discontinuous points; The data processing module is used to correct the first type of discontinuity points by using the feedback linear compensation method, and to interpolate the second type of discontinuity points by using the virtual compensation method, until the types of every two adjacent sampling points are uninterrupted points, thereby obtaining a wind speed sequence without discontinuity points; The grid-connected module inputs the uninterrupted wind speed sequence into the prediction model to obtain the predicted wind speed sequence; converts the wind speed values of the predicted wind speed sequence into power values; based on the power values and the actual power generated by the wind farm, determines the shortfall that the over-capacity energy storage system needs to bear, and controls the over-capacity energy storage system to be connected to the grid according to the shortfall.
[0020] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses a method for grid-connected supercapacity energy storage based on wind speed prediction. By identifying and classifying uninterrupted points, first-class discontinuity points, and second-class discontinuity points in the original wind speed sequence, the technology can accurately locate abnormal or missing parts in the data. Different correction strategies (feedback linear compensation method and virtual compensation method interpolation processing) are adopted for different types of discontinuity points, which effectively improves the continuity and accuracy of wind speed data; using the corrected uninterrupted point wind speed sequence as input, the prediction model can more accurately capture the trend and characteristics of wind speed changes, thereby significantly improving the accuracy of wind speed prediction; based on high-precision wind speed prediction results, the technology can more accurately calculate the shortfall between the actual power generated by the wind farm and the predicted power. By adjusting the charging and discharging strategy of the supercapacity energy storage system in real time, the volatility and uncertainty of wind power can be effectively compensated, and the stability and reliability of the power system can be improved.
[0021] The present invention discloses a super-capacity energy storage grid-connected system based on wind speed prediction. The data classification module accurately identifies the discontinuity points in the original wind speed sequence, and adopts specific correction and interpolation processing methods for different types of discontinuity points (such as first-type discontinuity points and second-type discontinuity points) in the data processing module, which effectively reduces the discontinuity and mutation in the wind speed data, thereby improving the smoothness and accuracy of the wind speed sequence. The accuracy of subsequent wind speed prediction is directly improved, so that the power output in the process of wind power grid connection is more stable, the power grid impact caused by wind speed fluctuations is reduced, and the overall stability of the power grid is enhanced. The grid-connected module uses the processed wind speed sequence without discontinuity points to predict the wind speed, and converts the predicted wind speed value into a power value. This conversion process provides an accurate power demand prediction for the dispatching control of the super-capacity energy storage system, so that the energy storage system can prepare in advance and accurately respond to the power fluctuation of the wind farm. By dynamically adjusting the charging and discharging strategy of the energy storage system, the system can effectively make up for the shortage or excess of the wind farm in power output, realize the "peak shaving and valley filling" of the wind farm output power, and optimize the use efficiency and economy of the energy storage system. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] 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.
[0023] Figure 1 The block diagram of the super-capacity energy storage grid-connected method based on wind speed prediction of the present invention; Figure 2 The present invention is a flow chart of a method for super-capacity energy storage grid connection based on wind speed prediction; Figure 3The block diagram of the super-capacity energy storage grid-connected system based on wind speed prediction of the present invention; Figure 4 This is a correction flow chart of the first type of discontinuity point feedback linear compensation method of the present invention.
[0024] Among them, 301-data classification module; 302-data processing module; 303-grid connection module. DETAILED DESCRIPTION
[0025] 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.
[0026] 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.
[0027] 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.
[0028] The present invention is further described in detail below in conjunction with the accompanying drawings: See also Figure 1 The present invention discloses a method for super-capacity energy storage grid connection based on wind speed prediction, comprising the following steps: S1, obtaining an original wind speed sequence; based on the original wind speed sequence, determining the type of every two adjacent sampling points in the original wind speed sequence; the types include uninterrupted points, first-type discontinuous points, and second-type discontinuous points; The wind speed measuring equipment installed in the wind farm is used to collect wind speed data at fixed time intervals (such as every 15 minutes) to form an original wind speed sequence.
[0029] Based on the original wind speed sequence, the type of every two adjacent sampling points in the original wind speed sequence is determined; according to a pre-set threshold, every two adjacent sampling points are determined to be uninterrupted points, first-type discontinuity points, and second-type discontinuity points.
[0030] The uninterrupted points are those where the wind speed changes between two adjacent points are within the threshold. The first type of discontinuity points are usually sudden jumps caused by sensor failure, data transmission errors, etc. The second type of discontinuity points are long-term data loss or extreme outliers.
[0031] S2, the first type of discontinuity points are corrected by the feedback linear compensation method, and the second type of discontinuity points are interpolated by the virtual compensation method until the types of every two adjacent sampling points are uninterrupted points, and a wind speed sequence without discontinuity points is obtained.
[0032] For the first type of discontinuity, the feedback linear compensation method is used. First, the linear relationship between the normal wind speed values before and after the discontinuity is determined; then, the reasonable wind speed value of the discontinuity is calculated based on the linear relationship, and this value is used to replace the original discontinuity value.
[0033] For the second type of discontinuity points, the virtual compensation method is used. The wind speed value of the discontinuity point is selected as a reference, and a random value between the minimum value of the original wind speed sequence and the maximum value of the original wind speed sequence is used for filling until the type of every two adjacent sampling points is an uninterrupted point.
[0034] S3, input the uninterrupted point wind speed sequence into the prediction model to obtain the predicted wind speed sequence; convert the wind speed values of the predicted wind speed sequence into power values; based on the power values and the actual power generated by the wind farm, determine the shortfall that the excess capacity energy storage system needs to bear, and dispatch and control the excess capacity energy storage system according to the shortfall.
[0035] The uninterrupted wind speed sequence is input into a pre-trained wind speed prediction model (such as a time series analysis model, a machine learning model, etc.). The model predicts the wind speed sequence in the future based on the historical wind speed data.
[0036] The predicted wind speed value is converted into the corresponding power value, usually through the power curve of the wind turbine, and the predicted power is compared with the actual power generation of the wind farm to determine the power shortfall that the excess capacity energy storage system needs to bear.
[0037] The super-capacity energy storage system formulates a charging and discharging plan for the super-capacity energy storage system based on the size and direction of the power shortage; when there is excess wind power, the energy storage system is controlled to charge and store excess electricity; when there is insufficient wind power, the electricity in the energy storage system is released to supplement the grid demand; the charging and discharging power of the energy storage system is adjusted in real time to maintain the balance of supply and demand in the grid and improve the stability and reliability of the power system.
[0038] See also Figure 2 The present invention discloses a method for super-capacity energy storage grid connection based on wind speed prediction, comprising the following steps: S1, obtaining an original wind speed sequence; based on the original wind speed sequence, determining the type of every two adjacent sampling points in the original wind speed sequence; the types include uninterrupted points, first-type discontinuous points, and second-type discontinuous points; The wind speed measuring equipment installed in the wind farm is used to collect wind speed data at fixed time intervals (such as every 15 minutes) to form an original wind speed sequence.
[0039] Based on the original wind speed sequence, calculate the original wind speed sequence for every two adjacent sampling points and The first criterion And the second criterion :
[0040]
[0041] in, Represents the original wind speed series j The sampling point value of the position, Represents the original wind speed series i The sampling point value of the position, Represents the original wind speed series i+1 The sampling point value of the position, N Indicates the length of the original wind speed sequence; based on and Calculate the identification coefficient :
[0042] based on The size of , determines the type of two adjacent sampling points in the original wind speed sequence: if , then the two adjacent sampling points in the original wind speed sequence are uninterrupted points; if , then the two adjacent sampling points in the original wind speed sequence are the first type of discontinuity points; if , then the two adjacent sampling points in the original wind speed sequence are the second type of discontinuity points.
[0043] S2, the first type of discontinuity points are corrected by the feedback linear compensation method, and the second type of discontinuity points are interpolated by the virtual compensation method until the types of every two adjacent sampling points are uninterrupted points, and the wind speed sequence without discontinuity points is obtained; The first type of discontinuity points are corrected by using the feedback linear compensation method, and the specific method is: Based on the original wind speed series, such as Figure 4 As shown, update the sampling points of the original wind speed sequence ,until and These two adjacent sampling points are uninterrupted points; that is:
[0044] in, ,B= , ; In the formula, and are two adjacent sampling points in the original wind speed sequence.
[0045] The virtual compensation method is used to interpolate the second type of discontinuity points, specifically: Based on the original wind speed sequence, at the second type of discontinuity and Insert several random values between to obtain a wind speed sequence with inserted random values; Based on the wind speed sequence with inserted random values, for every two adjacent sampling points with discontinuity points, several random values are inserted until the types of every two adjacent sampling points are all uninterrupted points.
[0046] S3, input the uninterrupted point wind speed sequence into the prediction model to obtain the predicted wind speed sequence; convert the wind speed values of the predicted wind speed sequence into power values; based on the power values and the actual power generated by the wind farm, determine the shortfall that the excess capacity energy storage system needs to bear, and dispatch and control the excess capacity energy storage system according to the shortfall.
[0047] The uninterrupted wind speed sequence is input into a pre-trained wind speed prediction model (such as a time series analysis model, a machine learning model, etc.). The model predicts the wind speed sequence in the future based on the historical wind speed data.
[0048] The predicted wind speed value is converted into the corresponding power value, usually through the power curve of the wind turbine, and the predicted power is compared with the actual power generation of the wind farm to determine the power shortfall that the excess capacity energy storage system needs to bear.
[0049] The super-capacity energy storage system formulates a charging and discharging plan for the super-capacity energy storage system based on the size and direction of the power shortage; when there is excess wind power, the energy storage system is controlled to charge and store excess electricity; when there is insufficient wind power, the electricity in the energy storage system is released to supplement the grid demand; the charging and discharging power of the energy storage system is adjusted in real time to maintain the balance of supply and demand in the grid and improve the stability and reliability of the power system.
[0050] In order to further verify the advantages of the present invention, the present invention uses the method of the present invention and the general prediction method to predict the wind speed, and uses the mean absolute percentage error (MAPE, full name Mean Absolute Percentage Error) to measure the error between the dispatch instruction and the actual response. The results are as follows:
[0051] In the wind speed sequence 1 with large wind speed fluctuations and complex changes, the MAPE of the traditional prediction method is as high as 11.1%, showing its limitations when facing extreme or complex wind speed changes. The prediction method of the present invention significantly reduces the MAPE to 2.1%, showing extremely high prediction accuracy and stability; for the relatively stable and less volatile wind speed sequence 2, although the traditional prediction method also achieved a certain prediction effect (MAPE of 6.2%), the prediction method of the present invention still achieved further accuracy improvement (MAPE of 4.2%). This shows that no matter how the wind speed changes, the prediction method of the present invention can maintain stable prediction performance and has stronger adaptability and generalization ability.
[0052] It can be seen that no matter under complex or steadily changing wind speed conditions, the present invention can achieve more accurate prediction results, providing strong technical support for the optimal scheduling of wind farms, the stable operation of power systems and the efficient use of wind energy.
[0053] 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; the device is specially designed to execute a super-capacity energy storage grid-connected method based on wind speed prediction. The electronic device achieves accurate prediction of wind speed in a wind farm by integrating advanced hardware and software technologies, and accordingly efficiently dispatches the super-capacity energy storage system, thereby optimizing the power balance in the process of wind power grid-connected.
[0054] The device can be any device with computing power, such as a personal computer, workstation, server, embedded system, smart terminal, etc. When the electronic device is started, the processor loads and executes the computer program of the super-capacity energy storage grid-connected method based on wind speed prediction from the memory. The program first collects the original wind speed data through the data acquisition module, and performs preprocessing and division; then, the interpolation module is used to interpolate the prediction sequence; the correction module is used to correct the prediction result to improve the prediction accuracy; finally, the prediction module uses the optimized prediction sequence to generate future wind speed predictions, and the grid-connected module formulates and executes corresponding dispatching instructions based on the prediction results and the actual state of the super-capacity energy storage system to achieve the coordinated operation of wind power and energy storage system.
[0055] The present invention also discloses 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 above-mentioned super-capacity energy storage grid-connected method based on wind speed prediction is implemented; the storage medium of the present invention is a non-volatile or readable and writable data storage device, which is designed to store and retain computer program instructions. The storage medium can be, but is not limited to, a hard disk drive (HDD, full name Hard-Disk Drive), a solid-state drive (SSD, full name Solid State Disk), a flash drive (USB, full name Universal Serial Bus), a compact disc (CD, full name Compact Disc) (such as a read-only disc (CD-ROM, full name Compact Disc Read-Only Memory), a digital video disc (DVD, full name Digital Video Disc)), a virtual storage space in a cloud storage service, or any other medium that can store and allow a computer to access and execute program code.
[0056] One embodiment of the present invention provides a computer program product, which includes computer instructions for instructing a computer to execute a method for super-capacity energy storage grid connection based on wind speed prediction. The method aims to improve the stability and efficiency of wind power grid connection through accurate wind speed prediction and intelligent energy storage system control. The computer program product can exist in various forms, including but not limited to executable files, source code files, script files, installation packages, compressed packages, etc. The product can be stored on physical media, such as hard disks, optical disks, etc., and can also be transmitted and distributed over the network.
[0057] See also Figure 3 The present invention provides a super-capacity energy storage grid-connected system based on wind speed prediction, comprising: The data classification module 301 is used to obtain the original wind speed sequence; based on the original wind speed sequence, determine the type of every two adjacent sampling points in the original wind speed sequence; the types include uninterrupted points, first-type discontinuous points, and second-type discontinuous points; The data processing module 302 is used to correct the first type of discontinuity points by using the feedback linear compensation method and to interpolate the second type of discontinuity points by using the virtual compensation method until the types of every two adjacent sampling points are uninterrupted points, thereby obtaining a wind speed sequence without discontinuity points; The grid connection module 303 inputs the uninterrupted point wind speed sequence into the prediction model to obtain a predicted wind speed sequence; converts the wind speed values of the predicted wind speed sequence into power values; determines the shortfall that the excess capacity energy storage system needs to bear based on the power value and the actual power generated by the wind farm, and dispatches and controls the excess capacity energy storage system according to the shortfall.
[0058] 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 method for grid-connecting supercapacity energy storage based on wind speed prediction, characterized in that: The following steps are involved: S1, obtaining an original wind speed sequence; based on the original wind speed sequence, determining the type of every two adjacent sampling points in the original wind speed sequence; the types include uninterrupted points, first-type discontinuous points, and second-type discontinuous points; The method of judging the type of every two adjacent sampling points in the original wind speed sequence based on the original wind speed sequence is as follows: Based on the original wind speed sequence, calculate the original wind speed sequence for every two adjacent sampling points and The first criterion And the second criterion : in, Represents the original wind speed series j The sampling point value of the position, Represents the original wind speed series i The sampling point value of the position, Represents the original wind speed series i+1 The sampling point value of the position, N Indicates the length of the original wind speed sequence; max() is the maximum value function; e is the Euler number; represents the summation symbol, and the summation interval is j = 1~( i -1); represents the summation symbol, and the summation interval is j =( i +2)~ N ; based on and Calculate the identification coefficient : Among them, min() is the minimum function; based on The size of the original wind speed sequence is used to determine the type of two adjacent sampling points, specifically: if , then the two adjacent sampling points in the original wind speed sequence are uninterrupted points; if , then the two adjacent sampling points in the original wind speed sequence are the first type of discontinuity points; if , then the two adjacent sampling points in the original wind speed sequence are the second type of discontinuity points; S2, the first type of discontinuity points are corrected by feedback linear compensation method, and the second type of discontinuity points are interpolated by virtual compensation method until the types of every two adjacent sampling points are uninterrupted points, and the wind speed sequence without discontinuity points is obtained; The first type of discontinuity points are corrected by using the feedback linear compensation method, and the specific method is: Based on the original wind speed sequence, update the sampling points of the original wind speed sequence ,until and These two adjacent sampling points are uninterrupted points; that is: Among them, the second-order coefficient , the first-order coefficient B = , constant coefficient ; is the first i The sampling points of the location; is the first i +1 sampling point; As the first criterion, As the second criterion, D is the identification coefficient; rand() represents the random number function; min() represents the minimum value function; max() represents the maximum value function; express e of D Second power, e is the Euler number; S3, inputting the uninterrupted point wind speed sequence into the prediction model to obtain the predicted wind speed sequence; converting the wind speed values of the predicted wind speed sequence into power values; based on the power values and the actual power generated by the wind farm, determining the shortfall that the over-capacity energy storage system needs to bear, and according to the shortfall, controlling the over-capacity energy storage system to be connected to the grid.
2. The method for super-capacity energy storage grid connection based on wind speed prediction according to claim 1 is characterized in that: The virtual compensation method is used to interpolate the second type of discontinuity points, specifically: Based on the original wind speed sequence, at the second type of discontinuity and Insert several random values between to obtain a wind speed sequence with inserted random values; Based on the wind speed sequence with inserted random values, for every two adjacent sampling points with discontinuities, several random values are inserted until the types of every two adjacent sampling points are uninterrupted points; the discontinuities are first-type discontinuities or second-type discontinuities.
3. The method for super-capacity energy storage grid connection based on wind speed prediction according to claim 2 is characterized in that: The random value is greater than or equal to the minimum value of the original wind speed sequence, and less than or equal to the maximum value of the original wind speed sequence.
4. A computer program product, comprising computer instructions, characterized in that: The computer instructions instruct the computer to execute the super-capacity energy storage grid-connected method based on wind speed prediction as described in any one of claims 1-3.
5. An electronic device, characterized in that: The invention 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 method for grid-connecting super-capacity energy storage based on wind speed prediction as described in any one of claims 1 to 3 is implemented.
6. 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 super-capacity energy storage grid-connected method based on wind speed prediction according to any one of claims 1 to 3 is implemented.
7. A super capacity energy storage grid-connected system based on wind speed prediction, based on the super capacity energy storage grid-connected method based on wind speed prediction according to claim 1, characterized in that: include: Data classification module, used to obtain the original wind speed sequence; Based on the original wind speed sequence, determine the type of every two adjacent sampling points in the original wind speed sequence; The types include unbroken points, first-type discontinuities, and second-type discontinuities; The data processing module is used to correct the first type of discontinuity points by using the feedback linear compensation method, and to interpolate the second type of discontinuity points by using the virtual compensation method, until the types of every two adjacent sampling points are uninterrupted points, thereby obtaining a wind speed sequence without discontinuity points; The grid-connected module inputs the uninterrupted wind speed sequence into the prediction model to obtain the predicted wind speed sequence; converts the wind speed values of the predicted wind speed sequence into power values; based on the power values and the actual power generated by the wind farm, determines the shortfall that the over-capacity energy storage system needs to bear, and controls the over-capacity energy storage system to be connected to the grid according to the shortfall.