Supercapacity energy storage grid-connected method based on wind speed prediction and related products

Abstract

The invention discloses a super-capacity energy storage grid-connected method based on wind speed prediction and related products, belonging to the technical field of wind power generation; firstly, the original wind speed sequence is divided into a prediction sequence and a feedback sequence; then, the prediction sequence is interpolated and input into a prediction model to obtain a feedback prediction, and the prediction sequence is corrected according to the prediction error; the model is input again to obtain the future wind speed prediction; finally, the wind speed prediction is converted into a power prediction, the power shortage of the super-capacity energy storage system is determined and dispatched and controlled; the accuracy of wind speed prediction is improved, the stability and economy of wind power grid connection are effectively enhanced, and the operating cost is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of wind power generation, and relates to a super-capacity energy storage grid-connected method based on wind speed prediction and related products. Background Art

[0002] With the growing global demand for renewable energy, wind power generation, as a clean and renewable energy form, has rapidly expanded its development and application. The grid connection of large-scale wind farms not only provides an important power supplement for the power system, but also poses new challenges to the dispatching and operation management of the power grid. Due to the high randomness, intermittentness and unpredictability of wind speed, the output power of wind farms is often difficult to accurately control, which directly affects the stability and reliability of the power grid.

[0003] In the existing technical system, in order to improve the dispatchability of wind farms, a widely used method is to use a neural network model to predict future wind speeds. By collecting historical wind speed data as input, the neural network can learn the inherent laws of wind speed changes and predict wind speed changes in the future. Based on these predicted wind speed values, the predicted power sent by the wind farm to the power grid can be further calculated, and this predicted value can be submitted to the power grid dispatch agency for more scientific and reasonable power generation dispatch.

[0004] However, the traditional wind speed prediction method has a significant limitation, that is, the historical wind speed data used for prediction is often collected intermittently, such as sampling every 15 minutes. This intermittent and discontinuous data sequence is difficult to fully reflect the continuity and dynamics of wind speed changes, thus reducing the accuracy of the prediction to a certain extent. Because in reality, wind speed changes continuously, its subtle fluctuations and changing trends are crucial for accurate prediction. Summary of the invention

[0005] The present invention provides a super-capacity energy storage grid-connected method based on wind speed prediction and related products to solve the technical problem that the historical wind speed data of the existing wind speed prediction is an intermittent and discontinuous data sequence, which is difficult to fully reflect the continuity and dynamics of wind speed changes, thereby reducing the accuracy of the prediction to a certain extent.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for super-capacity energy storage grid connection based on wind speed prediction, comprising the following steps:

[0008] S1, obtain the original wind speed sequence, and divide the original wind speed sequence into an original prediction sequence and an original feedback sequence;

[0009] S2, interpolate the original prediction sequence to obtain a prediction sequence containing insertion points;

[0010] S3, inputting the predicted sequence containing the insertion point into the prediction model to obtain the predicted feedback sequence;

[0011] S4, calculating the error between the predicted feedback sequence and the original feedback sequence; according to the error size, correcting the predicted sequence containing the insertion point until the error is less than a preset value, thereby obtaining a corrected predicted sequence containing the insertion point;

[0012] S5, inputting the corrected prediction sequence containing the insertion point into the prediction model to obtain the predicted future wind speed sequence;

[0013] S6, converts the predicted future wind speed sequence into a future power sequence, determines the shortfall that the excess energy storage system needs to bear based on the future power sequence and the actual power generation of the wind power plant, and dispatches and controls the excess energy storage system according to the shortfall.

[0014] Preferably, the interpolation process is performed on the original prediction sequence to obtain a prediction sequence containing insertion points, and the specific method is:

[0015] Based on the original prediction sequence, the insertion point value is obtained; the insertion point value is:

[0016]

[0017] in, To predict the sequence j The value of the position, For the i Insertion point values, For the i The proportional compensation coefficient of the insertion point value, For the i The difference compensation coefficient of the insertion point value;

[0018] Insert the insertion point value into the original prediction sequence to obtain the prediction sequence containing the insertion point.

[0019] Preferably, the proportional compensation coefficient is described as:

[0020]

[0021] in, To predict the sequence The value of the position, To predict the sequence The value of the position, To predict the sequence The value of the position, , , Vis the prediction sequence, max( )express and The maximum value, min( )express and The minimum value, max( V )express V The maximum value, min( V )express V The minimum value of .

[0022] Preferably, the difference compensation coefficient is described as:

[0023]

[0024] in, To predict the sequence V of The value of the position, To predict the sequence V of The value of the position, represents a random value between 0.1 and 0.15, express arrive of sum.

[0025] Preferably, the error between the calculated predicted feedback sequence and the original feedback sequence is calculated; according to the error, the predicted sequence containing the insertion point is corrected until the error is less than a preset value, thereby obtaining a corrected predicted sequence containing the insertion point. The specific method is:

[0026] Calculate the error between the predicted feedback sequence and the original feedback sequence, and determine whether the error is less than a preset value;

[0027] When the error is greater than or equal to a preset value, the prediction sequence containing the insertion point is corrected to obtain a corrected prediction sequence containing the insertion point;

[0028] The specific method for correcting the prediction sequence containing the insertion point is: setting a compensation coefficient for the insertion point value of the prediction sequence containing the insertion point:

[0029]

[0030] in, To predict the sequence j The value of the position, for The insertion point value after the position of is the proportional compensation coefficient, is the difference compensation coefficient, To compensate for the coefficient,i Indicates i insertion points, the compensation coefficient is:

[0031]

[0032] In the formula, For the T The error corresponding to the correction is e is the Euler number;

[0033] The above steps are iterated until the error is less than the preset value.

[0034] Preferably, the error is:

[0035]

[0036] in, n is the length of the feedback sequence, Original Feedback Sequence i The value of the position, is the predicted feedback sequence i The value of the position.

[0037] In a second aspect, 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.

[0038] In a third aspect, 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.

[0039] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned super-capacity energy storage grid-connected method based on wind speed prediction.

[0040] In a fifth aspect, the present invention provides a super-capacity energy storage grid-connected system based on wind speed prediction, comprising:

[0041] A data acquisition module is used to acquire an original wind speed sequence and divide the original wind speed sequence into an original prediction sequence and an original feedback sequence;

[0042] An interpolation module is used to perform interpolation processing on the original prediction sequence to obtain a prediction sequence containing insertion points;

[0043] The correction module calculates the error between the predicted feedback sequence and the original feedback sequence; according to the error size, the predicted sequence containing the insertion point is corrected until the error is less than a preset value, thereby obtaining a corrected predicted sequence containing the insertion point;

[0044] The prediction module inputs the corrected prediction sequence containing the insertion point into the prediction model to obtain the predicted future wind speed sequence;

[0045] The grid-connected module converts the predicted future wind speed sequence into a future power sequence. Based on the future power sequence and the actual power generation of the wind power plant, it determines the shortfall that the excess energy storage system needs to bear, and dispatches and controls the excess energy storage system according to the shortfall.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] The present invention discloses a super-capacity energy storage grid-connected method based on wind speed prediction. By subdividing the original wind speed sequence into an original prediction sequence and an original feedback sequence, and introducing interpolation processing, the input data volume of the prediction model is effectively increased, so that the model can capture more details of wind speed changes. After receiving the prediction sequence containing insertion points, the prediction model can be trained and learned based on richer data, thereby improving the prediction accuracy of future wind speed sequences; the introduction of a feedback mechanism (i.e., calculating the prediction error and correcting the prediction sequence accordingly) forms a closed-loop control system, which can continuously iterate and optimize the prediction results until the error meets the preset standard, further ensuring the accuracy of the prediction.

[0048] Furthermore, based on the high-precision forecast of future wind speed, it can be more accurately converted into the future power sequence, and then the change in the power generation of the wind power plant in the future period can be accurately calculated; by comparing with the actual power generation of the wind power plant, the shortfall between the power generation of the wind power plant and the grid demand can be determined in real time, providing a scientific basis for the dispatch of the super-capacity energy storage system; the super-capacity energy storage system is dispatched in advance according to the predicted shortfall, and can respond quickly when wind power fluctuates, balance the supply and demand of the grid, and reduce the impact of wind power fluctuations on grid stability.

[0049] Furthermore, a computer program product provides strong support for the intelligent and efficient wind power grid connection technology by integrating and executing computer instructions of the super-capacity energy storage grid connection method based on wind speed prediction; the program product can predict future wind speed changes in advance through an accurate wind speed prediction model, thereby accurately calculating the power generation of the wind power plant in the future period; this prediction result not only provides a scientific basis for the operation and dispatch of the wind power plant, but also enables the super-capacity energy storage system to prepare in advance, perform intelligent dispatch according to the fluctuation of wind power, effectively balance the supply and demand of the power grid, reduce the impact of wind power fluctuations on the stability of the power grid, and significantly improve the efficiency and stability of wind power grid connection; by integrating advanced wind speed prediction algorithms and super-capacity energy storage system dispatching strategies, the program product can perceive the power grid status in real time, quickly respond to wind power fluctuations, and realize intelligent interaction between wind power and the power grid.

[0050] Furthermore, the present invention discloses an electronic device with an advanced computer program built in, which can obtain wind speed data in real time and make high-precision predictions, and at the same time, combined with the intelligent dispatching strategy of the ultra-capacity energy storage system, realizes the intelligent management of the wind power grid connection process. This intelligent management not only improves the efficiency of wind power grid connection, but also significantly enhances the stability and reliability of the power grid.

[0051] Furthermore, the present invention provides a computer-readable storage medium, which provides key data storage support for the intelligence and efficiency of wind power grid-connected technology by storing a computer program for executing a super-capacity energy storage grid-connected method based on wind speed prediction; the computer-readable storage medium has the characteristics of high speed, high reliability and large capacity, and can quickly respond to data read and write requests of the computer system to ensure the smoothness and real-time performance of the wind power prediction and energy storage scheduling process; the use of computer-readable storage media as a data storage solution provides good scalability and flexibility for the wind power grid-connected system, and the system can easily adapt to new needs and challenges by updating the computer program in the storage medium.

[0052] Furthermore, the present invention provides a super-capacity energy storage grid-connected system based on wind speed prediction, which realizes precise control and efficient management of the wind power grid-connected process by integrating multiple functional modules such as data acquisition, interpolation processing, error correction, wind speed prediction and grid-connected scheduling, thereby improving the accuracy of wind speed prediction and enhancing the stability of wind power grid-connected. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] 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.

[0054] Figure 1 The block diagram of the super-capacity energy storage grid-connected method based on wind speed prediction of the present invention;

[0055] Figure 2 The present invention is a flow chart of a method for super-capacity energy storage grid connection based on wind speed prediction;

[0056] Figure 3 The block diagram of the super-capacity energy storage grid-connected system based on wind speed prediction of the present invention is shown.

[0057] Among them, 301 is a data acquisition module, 302 is an interpolation module, 303 is a correction module, 304 is a prediction module, and 305 is a grid connection module. DETAILED DESCRIPTION

[0058] 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.

[0059] 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.

[0060] 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.

[0061] In the description of the embodiments of the present invention, it should be noted that if the terms "upper", "lower", "horizontal", "inner", etc. indicate an orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the product of the invention is usually placed when in use, it is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. In addition, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance.

[0062] In addition, if the term "horizontal" appears, it does not mean that the component must be absolutely horizontal, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", which does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0063] In the description of the embodiments of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0064] Terminology explanation:

[0065] 1. Back propagation, the English name is Back Propagation, abbreviated as BP.

[0066] 2. Extreme Learning Machine, the English name is Extreme Learning Machine, abbreviated as ELM.

[0067] 3. Root mean square error, the English name is Root Mean Square Error, abbreviated as RMSE.

[0068] 4. Mean absolute error, the English name is Mean Absolute Error, abbreviated as MAE.

[0069] 5. Mean Absolute Percentage Error, abbreviated as MAPE.

[0070] 6. Hard disk drive, the English name is Hard-Disk Drive, abbreviated as HDD.

[0071] 7. Solid State Drive, the English name is Solid State Disk, abbreviated as SSD.

[0072] 8. Flash drive, the English name is Universal Serial Bus, abbreviated as USB.

[0073] 9. Compact Disc, abbreviated as CD.

[0074] 10. Compact Disc Read-Only Memory, abbreviated as CD-ROM.

[0075] 11. Digital Video Disc, abbreviated as DVD.

[0076] The present invention is further described in detail below in conjunction with the accompanying drawings:

[0077] Embodiment 1:

[0078] 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:

[0079] S1, obtaining an original wind speed sequence, and dividing the original wind speed sequence into an original prediction sequence and an original feedback sequence; the prediction sequence is used to predict the feedback sequence;

[0080] Collect historical wind speed data for a certain period of time from the wind farm meteorological station or wind turbine sensor to form an original wind speed sequence; divide the original wind speed sequence into two parts in chronological order: the one at the front is used as the prediction sequence for prediction; the one at the back is used as the feedback sequence for verifying the prediction accuracy; the length of the prediction sequence and the feedback sequence can be set as needed.

[0081] S2, interpolate the original prediction sequence to obtain a prediction sequence containing insertion points;

[0082] Use linear interpolation or more advanced interpolation methods to process the forecast sequence to increase the density of data points and improve the generalization ability of the forecast model. Insert several points between the original data points of the forecast sequence to generate a forecast sequence containing the inserted points.

[0083] S3, inputting the predicted sequence containing the insertion point into the prediction model to obtain the predicted feedback sequence;

[0084] The back propagation (BP) neural network in the time series prediction model or the extreme learning machine (ELM) in the machine learning model is selected as the prediction model; the prediction sequence containing the insertion point is input into the prediction model to obtain the predicted feedback sequence (that is, the future wind speed in the time period corresponding to the prediction sequence).

[0085] S4, calculating the error between the predicted feedback sequence and the original feedback sequence; according to the error size, correcting the predicted sequence containing the insertion point until the error is less than a preset value, thereby obtaining a corrected predicted sequence containing the insertion point;

[0086] The error between the predicted feedback sequence and the actual feedback sequence can be calculated using the Root Mean Square Error (RMSE) or Mean Absolute Error (MAE). If the error is greater than the preset value, the predicted sequence containing the interpolation points is adjusted until the error meets the requirements.

[0087] S5, inputting the corrected prediction sequence containing the insertion point into the prediction model to obtain the predicted future wind speed sequence;

[0088] The corrected forecast sequence containing the insertion points is input into the forecast model again to obtain the wind speed forecast sequence for a longer period of time in the future (such as the next 24 hours).

[0089] S6, converting the predicted future wind speed sequence into a future power sequence, determining the shortfall that the excess capacity energy storage system needs to bear based on the future power sequence and the actual power generation of the wind power plant, and dispatching and controlling the excess capacity energy storage system according to the shortfall;

[0090] According to the wind speed-power conversion curve (which can be provided by the wind turbine manufacturer), the future wind speed sequence is converted into the future power sequence; based on the future power sequence and the actual power data of the wind power plant, the power shortage that the over-capacity energy storage system needs to bear is calculated; when the predicted power is lower than the actual power, the energy storage system is controlled to discharge and supplement the power grid; when the predicted power is higher than the actual power, the energy storage system is controlled to charge and store excess electric energy; the energy storage system charging and discharging strategy is adjusted in real time to ensure the balance of supply and demand of the power grid and reduce the impact of wind power fluctuations on the power grid.

[0091] By implementing this solution, wind farms can predict and respond to wind speed fluctuations in advance, effectively reduce the volatility of wind power output, and improve wind power utilization and grid stability. At the same time, the reasonable dispatch and control of the ultra-capacity energy storage system further enhances the flexibility and reliability of the grid, providing strong support for the sustainable development of wind farms and grids.

[0092] Embodiment 2:

[0093] 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:

[0094] S1, obtaining an original wind speed sequence, and dividing the original wind speed sequence into an original prediction sequence and an original feedback sequence; the prediction sequence is used to predict the feedback sequence;

[0095] Historical wind speed data for a certain period of time is collected from the wind farm meteorological station or wind turbine sensor to form an original wind speed sequence, which is then divided into two parts in chronological order: the first 90% is used as a prediction sequence for prediction; the last 10% is used as a feedback sequence to verify the prediction accuracy.

[0096] S2, interpolate the original prediction sequence to obtain a prediction sequence containing insertion points;

[0097] Based on the original prediction sequence, the insertion point value is obtained; the insertion point value is:

[0098]

[0099] in, To predict the sequence j The value of the position, For the i Insertion point values, For the i The proportional compensation coefficient of the insertion point value, For the i The difference compensation coefficient of the insertion point value;

[0100] in, To predict the sequence V of j -1 position value, To predict the sequence V of j +2 position value, To predict the sequence V of j +1 position value, , ; V is the prediction sequence, max( )express and The maximum value, min( )express and The minimum value, max( V )express V The maximum value, min( V )express V The minimum value of .

[0101]

[0102] in, To predict the sequence V of The value of the position, To predict the sequence V of The value of the position; represents a random value between 0.1 and 0.15, express arrive of sum.

[0103] Insert the insertion point value into the original prediction sequence to obtain the prediction sequence containing the insertion point.

[0104] S3, inputting the predicted sequence containing the insertion point into the prediction model to obtain the predicted feedback sequence;

[0105] This embodiment uses the BP (Back Propagation) model as the prediction model.

[0106] S4, calculating the error between the predicted feedback sequence and the original feedback sequence; according to the error size, correcting the predicted sequence containing the insertion point until the error is less than a preset value, thereby obtaining a corrected predicted sequence containing the insertion point;

[0107] Calculate the error between the predicted feedback sequence and the original feedback sequence, and determine whether the error is less than a preset value;

[0108]

[0109] in, n is the length of the feedback sequence, Original Feedback Sequence i The value of the position, is the predicted feedback sequence i The value of the position, For the T The error corresponding to the correction;

[0110] When the error is greater than or equal to a preset value, the prediction sequence containing the insertion point is corrected to obtain a corrected prediction sequence containing the insertion point;

[0111] The specific method for correcting the prediction sequence containing the insertion point is: setting a compensation coefficient for the insertion point value of the prediction sequence containing the insertion point:

[0112]

[0113] in, To predict the sequence j The value of the position, for The insertion point value after the position of is the proportional compensation coefficient, is the difference compensation coefficient, To compensate for the coefficient, i Indicates i insertion points, the compensation coefficient is:

[0114]

[0115] in,T is the number of corrections, e is the Euler number;

[0116] The above steps are iterated until the error is less than the preset value.

[0117] S5, inputting the corrected prediction sequence containing the insertion point into the prediction model to obtain the predicted future wind speed sequence.

[0118] S6, converting the predicted future wind speed sequence into a future power sequence, determining the shortfall that the excess capacity energy storage system needs to bear based on the future power sequence and the actual power generation of the wind power plant, and dispatching and controlling the excess capacity energy storage system according to the shortfall;

[0119] According to the wind speed-power conversion curve (which can be provided by the wind turbine manufacturer), the future wind speed sequence is converted into the future power sequence; based on the future power sequence and the actual power data of the wind power plant, the power shortage that the over-capacity energy storage system needs to bear is calculated; when the predicted power is lower than the actual power, the energy storage system is controlled to discharge and supplement the power grid; when the predicted power is higher than the actual power, the energy storage system is controlled to charge and store excess electric energy; the energy storage system charging and discharging strategy is adjusted in real time to ensure the balance of supply and demand of the power grid and reduce the impact of wind power fluctuations on the power grid.

[0120] Embodiment 3:

[0121] In order to further verify the advantages of the present invention and demonstrate its accuracy and effectiveness in wind speed prediction and super-capacity energy storage grid-connected system scheduling, we designed a series of comparative experiments to conduct a comprehensive performance evaluation of the method proposed by the present invention and the currently widely used traditional prediction methods. The evaluation index used was the mean absolute percentage error (MAPE), which can intuitively reflect the degree of deviation between the predicted value and the actual value and is an important criterion for measuring prediction accuracy.

[0122] The present invention selected two wind speed sequences (wind speed sequence 1 and wind speed sequence 2) as test objects, and adopted the commonly used time series prediction method in the industry (BP (Back Propagation) model) as a benchmark. The two wind speed sequences were predicted using the traditional method and the method of the present invention, and the results are as follows:

[0123]

[0124] It can be seen from the experimental results that the MAPE values ​​of the method of the present invention are much lower than those of the traditional prediction methods, whether it is wind speed sequence 1 or wind speed sequence 2, indicating that the present invention has achieved a significant improvement in wind speed prediction accuracy. In particular, in sequence 1 with large wind speed fluctuations, the improvement percentage is as high as 73.2%, which fully demonstrates the superior performance of the present invention in complex environments; the test results of two different wind speed sequences show the high stability and good adaptability of the method of the present invention, indicating that the method can effectively cope with a variety of wind speed change modes and provide a reliable basis for the precise scheduling of ultra-capacity energy storage systems.

[0125] Based on high-precision wind speed prediction, the present invention can more accurately determine the power shortage that the super-capacity energy storage system needs to bear, thereby formulating a more reasonable charging and discharging scheduling plan, which helps to reduce power fluctuations in the power grid and improve the reliability and economy of wind power grid connection.

[0126] Embodiment 4:

[0127] See also Figure 3 The present invention discloses a super-capacity energy storage grid-connected system based on wind speed prediction, comprising:

[0128] The data acquisition module 301 is used to acquire an original wind speed sequence and divide the original wind speed sequence into an original prediction sequence and an original feedback sequence;

[0129] An interpolation module 302 is used to perform interpolation processing on the original prediction sequence to obtain a prediction sequence containing insertion points;

[0130] The correction module 303 calculates the error between the predicted feedback sequence and the original feedback sequence; according to the error, the predicted sequence containing the insertion point is corrected until the error is less than a preset value, thereby obtaining a corrected predicted sequence containing the insertion point;

[0131] Prediction module 304, inputs the corrected prediction sequence containing the insertion point into the prediction model to obtain the predicted future wind speed sequence;

[0132] The grid connection module 305 converts the predicted future wind speed sequence into a future power sequence, determines the shortfall that the excess energy storage system needs to bear based on the future power sequence and the actual power generated by the wind power plant, and dispatches and controls the excess energy storage system according to the shortfall.

[0133] Embodiment 5:

[0134] This embodiment provides an electronic device, including 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 during wind power grid-connected process.

[0135] 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.

[0136] The present invention also discloses a computer-readable storage medium, which stores a computer program. 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 realized; 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, Hard-Disk Drive), a solid-state hard disk (SSD, Solid State Disk), a flash drive (USB, Universal Serial Bus), an optical disk (such as CD-ROM (Compact Disc Read-Only Memory, read-only optical disk), DVD (Digital Video Disc, digital video optical disk)), 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.

[0137] Preferably, the present invention discloses a computer program product, which includes computer instructions, and the computer instructions instruct the computer to execute the above-mentioned super-capacity energy storage grid-connected method based on wind speed prediction; the computer program product runs in the computer system of the wind farm or the power grid control center respectively to implement the above-described super-capacity energy storage grid-connected method based on wind speed prediction.

[0138] 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, obtain the original wind speed sequence, and divide the original wind speed sequence into an original prediction sequence and an original feedback sequence; S2, interpolate the original prediction sequence to obtain a prediction sequence containing insertion points. The specific method is: Based on the original prediction sequence, the insertion point value is obtained; the insertion point value is: in, To predict the sequence j The value of the position, For the i Insertion point values, For the i The proportional compensation coefficient of the insertion point value, For the i The difference compensation coefficient of the insertion point value; the proportional compensation coefficient is described as: in, To predict the sequence The value of the position, To predict the sequence The value of the position, To predict the sequence The value of the position, , , V is the prediction sequence, max( )express and The maximum value, min( )express and The minimum value, max( V )express V The maximum value, min( V )express V The minimum value of; the difference compensation coefficient is described as: in, To predict the sequence V of The value of the position, To predict the sequence V of The value of the position, represents a random value between 0.1 and 0.15, express arrive of sum; Insert the insertion point value into the original prediction sequence to obtain the prediction sequence containing the insertion point; S3, inputting the predicted sequence containing the insertion point into the prediction model to obtain the predicted feedback sequence; S4, calculating the error between the predicted feedback sequence and the original feedback sequence; according to the error size, correcting the predicted sequence containing the insertion point until the error is less than a preset value, thereby obtaining a corrected predicted sequence containing the insertion point; S5, inputting the corrected prediction sequence containing the insertion point into the prediction model to obtain the predicted future wind speed sequence; S6, converting the predicted future wind speed sequence into a future power sequence, determining the shortfall that the excess energy storage system needs to bear based on the future power sequence and the actual power generation of the wind power plant, and dispatching and controlling the excess energy storage system according to the shortfall.

2. The method for super-capacity energy storage grid connection based on wind speed prediction according to claim 1 is characterized in that: The error between the calculated predicted feedback sequence and the original feedback sequence is calculated; according to the error size, the predicted sequence containing the insertion point is corrected until the error is less than a preset value, and a corrected predicted sequence containing the insertion point is obtained. The specific method is: Calculate the error between the predicted feedback sequence and the original feedback sequence, and determine whether the error is less than a preset value; When the error is greater than or equal to a preset value, the prediction sequence containing the insertion point is corrected to obtain a corrected prediction sequence containing the insertion point; The specific method for correcting the prediction sequence containing the insertion point is: setting a compensation coefficient for the insertion point value of the prediction sequence containing the insertion point: in, To predict the sequence j The value of the position, for The insertion point value after the position of is the proportional compensation coefficient, is the difference compensation coefficient, To compensate for the coefficient, i Indicates i insertion points, the compensation coefficient is: In the formula, For the T The error corresponding to the correction is e is the Euler number; The above steps are iterated until the error is less than the preset value.

3. The method for super-capacity energy storage grid connection based on wind speed prediction according to claim 1 or 2, characterized in that: The error is: in, n is the length of the feedback sequence, Original Feedback Sequence i The value of the position, is the predicted feedback sequence i The value of the position.

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: A data acquisition module is used to acquire an original wind speed sequence and divide the original wind speed sequence into an original prediction sequence and an original feedback sequence; An interpolation module is used to perform interpolation processing on the original prediction sequence to obtain a prediction sequence containing insertion points; The correction module calculates the error between the predicted feedback sequence and the original feedback sequence; according to the error size, the predicted sequence containing the insertion point is corrected until the error is less than a preset value, thereby obtaining a corrected predicted sequence containing the insertion point; The prediction module inputs the corrected prediction sequence containing the insertion point into the prediction model to obtain the predicted future wind speed sequence; The grid-connected module converts the predicted future wind speed sequence into a future power sequence. Based on the future power sequence and the actual power generation of the wind power plant, it determines the shortfall that the excess energy storage system needs to bear, and dispatches and controls the excess energy storage system according to the shortfall.

Images