A vector-based wind speed prediction method for supercapacity energy storage and related products

Abstract

This invention relates to the field of wind speed prediction technology, specifically to a wind speed prediction method for supercapacity energy storage based on the vector method and related products. The method involves acquiring historical wind speed sequences; the length of the historical wind speed sequence is... N The preset length of the predicted future wind speed sequence is... M ; will the first N + j Vectorize the historical wind speed sequence corresponding to time 1 to obtain the first... N + j The first wind speed vector sequence corresponding to time t; for the t... N + j Perform a sum-vector orthogonal decomposition on the first wind speed vector sequence corresponding to time t, and obtain the first... N + j The predicted wind speed at that moment; repeat this step. M This process is repeated until the prediction of the future wind speed sequence is completed, resulting in the predicted future wind speed sequence. The predicted future wind speed sequence is then vectorized to obtain the predicted future wind speed vector sequence. Based on the predicted future wind speed vector sequence, the predicted future wind speed sequence is corrected to obtain the final predicted future wind speed sequence. This improves the accuracy of wind speed prediction and enhances the precision and stability of power grid dispatching.

Description

Technical Field

[0001] This invention relates to the field of wind speed prediction technology, specifically to a wind speed prediction method for supercapacity energy storage based on vector method and related products. Background Technology

[0002] Due to the randomness of wind speed variations, large-scale wind farm grid connection poses challenges to grid dispatching, thus affecting system stability. To improve the dispatchability of wind farms, a common approach is to use neural networks to predict wind speeds for the next day. The predicted wind speed value is then used to calculate the power transmitted from the wind farm to the grid, and this prediction is submitted to the grid dispatching system. Simultaneously, an overcapacity energy storage system is connected at the wind farm's output point to quickly compensate for discrepancies between the actual and predicted power output. This enhances the reliability of grid dispatching based on wind speed predictions and improves the coordinated operation between the wind farm and the power system.

[0003] However, traditional forecasting is based on neural networks. But when using neural networks for short-term forecasting, if the input data is only historical wind speed data, it cannot accurately capture the complexity and randomness of wind speed changes. Therefore, it is necessary to introduce other relevant factors (such as meteorological data, topographic data, etc.) into the neural network to improve the accuracy of the forecasting model. However, other factors, such as meteorological data, are relatively complex to process, and these related factors are prone to errors during processing. This leads to a decrease in forecast accuracy and also increases the operating cost of the system. Summary of the Invention

[0004] To address the problem of low prediction accuracy caused by the complexity of wind speed influence in existing technologies, this invention provides a wind speed prediction method for supercapacity energy storage based on the vector method and related products.

[0005] The objective of this invention is achieved through the following technical solutions:

[0006] The first aspect of this invention provides a method for predicting wind speed in supercapacity energy storage based on the vector method, comprising the following steps:

[0007] Obtain the historical wind speed sequence; the length of the historical wind speed sequence is N The preset length of the predicted future wind speed sequence is... M ;

[0008] The first N + j Vectorize the historical wind speed sequence corresponding to time 1 to obtain the first... N + j The first wind speed vector sequence corresponding to time t; for the t... N + jPerform a sum-vector orthogonal decomposition on the first wind speed vector sequence corresponding to time t, and obtain the first... N + j The predicted wind speed at that moment; repeat this step. M This process continues until the prediction of the future wind speed sequence is completed, resulting in the predicted future wind speed sequence. , This represents the first number corresponding to the predicted future wind speed sequence. time;

[0009] The predicted future wind speed sequence is vectorized to obtain the predicted future wind speed vector sequence; based on the predicted future wind speed vector sequence, the predicted future wind speed sequence is corrected to obtain the final predicted future wind speed sequence.

[0010] Furthermore, the first N + j The first wind speed vector sequence corresponding to time point is described as follows:

[0011]

[0012] in, The first wind speed vector sequence is the first... i The wind speed value at that moment;

[0013] ; In the formula, The first in the historical wind speed series The wind speed value at that moment. N The length of the historical wind speed sequence. The first in the historical wind speed series i The wind speed value at that moment. For the historical wind speed sequence Wind speed at any time and the first i The angle between the wind speed values ​​at different times. For the historical wind speed sequence Wind speed at any time and the first i The length between instantaneous wind speed values, For the historical wind speed sequence Wind speed at any time and the first i The time interval between wind speed values ​​at any given moment is 1 ≤ i < N .

[0014] Furthermore, the aforementioned [context missing] N + j Perform a sum-vector orthogonal decomposition on the first wind speed vector sequence corresponding to time t, and obtain the first... N + j The predicted wind speed at each time point is as follows:

[0015] The first N + j Summing all terms of the first wind speed vector sequence corresponding to each time point yields the sum vector.

[0016] Decompose the sum vector orthogonally to obtain the first... N + j The predicted wind speed at that moment.

[0017] Furthermore, the first N + j The predicted wind speed at that time is:

[0018]

[0019] In the formula, For the first N + j The predicted wind speed at that moment For all in the first wind speed vector sequence sum; For the historical wind speed sequence Wind speed at any time and the first i The length between instantaneous wind speed values; Represents all of the first wind speed vector sequence sum; For the historical wind speed sequence Wind speed at any time and the first i The angle between the wind speed values ​​at different times. For the first The time corresponds to the last value of the historical wind speed sequence; Represents the sine function; This represents the cosine function.

[0020] Furthermore, the vectorization of the predicted future wind speed sequence specifically involves vectorizing the values ​​of two adjacent moments in the predicted future wind speed sequence.

[0021] Furthermore, the predicted future wind speed sequence is corrected based on the predicted future wind speed vector sequence to obtain the final predicted future wind speed sequence, specifically as follows:

[0022] The predicted future wind speed vector sequence is projected onto the X-axis and Y-axis respectively to obtain the X-axis projection sequence and the Y-axis projection sequence.

[0023] If the position of the maximum value in the X-axis projection sequence is the same as the position of the maximum value in the Y-axis projection sequence, then the value at the same position in the predicted future wind speed vector sequence corresponding to the position of the maximum value is corrected; otherwise, no correction is made.

[0024] Furthermore, the values ​​at the same positions in the predicted future wind speed vector sequence corresponding to the position of the maximum value are corrected, specifically as follows:

[0025]

[0026] In the formula, The minimum value in the predicted future wind speed sequence. The maximum value of the predicted future wind speed sequence. The first of the corrected final predicted future wind speed series Predicted wind speed at any time; The first of the corrected final predicted future wind speed series Real-time predicted wind speed, The predicted future wind speed sequence Predicted wind speed at any time; The first element in the predicted future wind speed vector sequence The value of the position; The first of the predicted future wind speed sequence Predicted wind speed at any time; The first of the predicted future wind speed sequence Predicted wind speed at any time; The first of the predicted future wind speed sequence Predicted wind speed at any time; Represents the maximum value function; Represents the minimum value function; It is the Euler number.

[0027] A second aspect of the present invention provides a wind speed prediction system for supercapacity energy storage based on the vector method, comprising:

[0028] The data initialization module is used to acquire historical wind speed sequences; the length of the historical wind speed sequence is... N The preset length of the predicted future wind speed sequence is... M ;

[0029] The prediction module will... N + j Vectorize the historical wind speed sequence corresponding to time 1 to obtain the first... N + j The first wind speed vector sequence corresponding to time t; for the t... N + j Perform a sum-vector orthogonal decomposition on the first wind speed vector sequence corresponding to time t, and obtain the first... N + j The predicted wind speed at that moment; repeat this step. M This process continues until the prediction of the future wind speed sequence is completed, resulting in the predicted future wind speed sequence. , Indicates the first time;

[0030] The correction module vectorizes the predicted future wind speed sequence to obtain the predicted future wind speed vector sequence; based on the predicted future wind speed vector sequence, the predicted future wind speed sequence is corrected to obtain the final predicted future wind speed sequence.

[0031] A third aspect of the present invention provides an electronic device, including a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the vector-based supercapacity energy storage wind speed prediction method described above.

[0032] A fourth aspect of the present invention provides a computer-readable storage medium storing at least one instruction, which, when executed by a processor, implements the vector-based supercapacity energy storage wind speed prediction method.

[0033] The beneficial effects of this invention are as follows:

[0034] This invention provides a vector-based wind speed prediction method for supercapacity energy storage. By vectorizing historical wind speed sequences and using vector methods for analysis and prediction, it can more accurately capture the trends and patterns of wind speed changes, thereby improving prediction accuracy. This is achieved through iterative prediction. M This method progressively constructs a complete future wind speed sequence. This step-by-step prediction approach helps reduce the accumulation of errors from single predictions and enhances the stability of the prediction results. After obtaining the initial predicted future wind speed sequence, the method further vectorizes it and corrects the prediction results based on the predicted future wind speed vector sequence. This step can further eliminate biases in the prediction, making the final predicted future wind speed sequence closer to reality. This method is not only suitable for short-term wind speed prediction, but the length of the historical wind speed sequence can also be adjusted according to actual needs. N and the length of the future wind speed sequence M To adapt to the needs of wind speed forecasting at different time scales.

[0035] Furthermore, it not only considers the numerical value of each wind speed data point in the historical wind speed sequence, but also incorporates multi-dimensional information such as their angles, lengths, and time intervals. This refined vector construction method can more comprehensively and accurately reflect the complexity and dynamism of wind speed changes.

[0036] Furthermore, the present invention will by... N + j Summing all terms of the first wind speed vector sequence corresponding to time point 1, obtaining the sum vector, and then orthogonally decomposing it to obtain the first... N + jThe predicted wind speed at a given time point. This method not only considers the overall trend of wind speed data but also extracts key wind speed components through orthogonal decomposition, improving the accuracy and reliability of the prediction. By combining the length and angle information between various wind speed data points in the historical wind speed sequence, the predicted wind speed at the given time point is calculated. N + j The formula for predicting wind speeds at specific times is as follows. It fully considers the relationships between wind speed data, making the predictions more consistent with reality. The values ​​of adjacent positions in the predicted future wind speed sequence are vectorized. This representation not only preserves the numerical information of the wind speed data but also includes their relative positions and relationships, helping to capture the details and trends of wind speed changes. The predicted wind speed at the corresponding position is corrected by comparing the maximum value positions of the projection sequences of the predicted future wind speed vector sequence on the X and Y axes. This correction strategy eliminates biases and outliers in the prediction, making the final predicted future wind speed sequence smoother and more accurate. The correction formula fully considers the minimum and maximum values ​​in the predicted wind speed sequence, as well as the values ​​at corresponding positions in the predicted wind speed vector sequence. Through reasonable interpolation calculations, the corrected final predicted wind speed is obtained. This design makes the corrected wind speed sequence closer to reality, improving the accuracy and reliability of the prediction. Attached Figure Description

[0037] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0038] Figure 1 This is a schematic diagram of the wind speed prediction method for supercapacity energy storage based on vector method in an embodiment of the present invention;

[0039] Figure 2 This is a block diagram of a supercapacity energy storage wind speed prediction system based on the vector method in an embodiment of the present invention;

[0040] Figure 3 This is a schematic diagram of the structure of an electronic device in an embodiment of the present invention.

[0041] Among them, 100-electronic device; 101-memory; 102-processor; 103-computer program; 104-communication bus; 201-data initialization module; 202-prediction module; 203-correction module. Detailed Implementation

[0042] To make the objectives and technical solutions of this invention clearer and easier to understand, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. The specific embodiments described herein are for illustrative purposes only and are not intended to limit the invention.

[0043] The present invention provides a method, system, device, and medium for predicting wind speed in supercapacity energy storage based on the vector method. The method includes:

[0044] Obtain the historical wind speed sequence; the length of the historical wind speed sequence is N The preset length of the predicted future wind speed sequence is... M ;

[0045] The first N + j Vectorize the historical wind speed sequence corresponding to time 1 to obtain the first... N + j The first wind speed vector sequence corresponding to time t; for the t... N + j Perform a sum-vector orthogonal decomposition on the first wind speed vector sequence corresponding to time t, and obtain the first... N + j The predicted wind speed at that moment; repeat this step. M This process continues until the prediction of the future wind speed sequence is completed, resulting in the predicted future wind speed sequence. , Indicates the first time;

[0046] The predicted future wind speed sequence is vectorized to obtain the predicted future wind speed vector sequence; based on the predicted future wind speed vector sequence, the predicted future wind speed sequence is corrected to obtain the final predicted future wind speed sequence.

[0047] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings and specific embodiments. The described embodiments are only some embodiments of the present invention, and not all embodiments.

[0048] Example 1

[0049] like Figure 1 As shown in the figure, the wind speed prediction method for supercapacity energy storage based on vector method in this embodiment includes the following specific implementation methods.

[0050] S1, Obtain the historical wind speed sequence; the length of the historical wind speed sequence is... N The preset length of the predicted future wind speed sequence is... M First, obtain the historical wind speed sequence. This embodiment uses an existing historical wind speed sequence. x 1, x 2,x 3,..., x N To predict wind speed data at various times within a future time period. x N+1 ,..., x N+9 ]. In this embodiment M =9.

[0051] S2, will the first N + j Vectorize the historical wind speed sequence corresponding to time 1 to obtain the first... N + j The sequence of first wind speed vectors corresponding to each moment; j The value ranges from 1 to M .

[0052] Secondly, each wind speed data in the historical time wind speed sequence is vectorized and represented.

[0053] Specifically, the angle and length between each wind speed data point and the current wind speed data are calculated. A vectorized representation is then created based on the product of the length and angle, forming the first wind speed vector sequence. The angle and length between the wind speed data points and the current wind speed data, and their corresponding vector expressions, are as follows:

[0054]

[0055] in, For the first wind speed vector sequence i The value of the position;

[0056] in: ;

[0057] In the formula, The first in the historical wind speed series The wind speed value at that moment. N The length of the historical wind speed sequence. The first in the historical wind speed series i The wind speed value at that moment. For the historical wind speed sequence Wind speed at any time and the first i The angle between the wind speed values ​​at different times. For the historical wind speed sequence Wind speed at any time and the first i The length between instantaneous wind speed values, For the historical wind speed sequence Wind speed at any time and the first i The time interval between wind speed values ​​at any given moment is 1 ≤ i <N .

[0058] It should be noted that, in actual implementation, the values ​​in the historical wind speed sequence are processed by minimum-maximum normalization / Min-Max Scaling pairs when performing calculations with the time interval of the historical wind speed sequence, so that they can be added or subtracted.

[0059] Therefore, we can obtain the first wind speed vector sequence, namely:

[0060] In the formula, Represents the historical wind speed sequence number Wind speed at any time and the first N The length between instantaneous wind speed values; Represents the historical wind speed sequence number Wind speed at any time and the first N The angle between the wind speed values ​​at any given moment; Represents the historical wind speed sequence number Wind speed at any time and the first N The length between instantaneous wind speed values; Represents the historical wind speed sequence number Wind speed at any time and the first N The angle between the wind speed values ​​at any given moment; Represents the historical wind speed sequence number Wind speed at any time and the first N The length between instantaneous wind speed values; Represents the historical wind speed sequence number Wind speed at any time and the first N The angle between the wind speed values ​​at any given time.

[0061] For the N + j Perform a sum-vector orthogonal decomposition on the first wind speed vector sequence corresponding to time t, and obtain the first... N + j The predicted wind speed at that moment; N + j Summing all terms of the first wind speed vector sequence corresponding to each time point yields the sum vector.

[0062] Specifically, the vector is represented as: .

[0063] Decompose the sum vector orthogonally to obtain the first... N + j The predicted wind speed at that moment. For example... j When =1, the first N The predicted wind speed at time +1 is as follows:

[0064]

[0065] In the formula, For the first N + j The predicted wind speed at that moment For all in the first wind speed sequence sum; For the historical wind speed sequence Wind speed at any time and the first i The length between instantaneous wind speed values; Represents all in the first wind speed sequence sum; For the historical wind speed sequence Wind speed at any time and the first i The angle between the wind speed values ​​at different times. For the first The time corresponds to the last value of the historical wind speed sequence; Represents the sine function; This represents the cosine function.

[0066] Get the first N After the wind speed data at time +1, based on the next time (the... N The historical wind speed sequence corresponding to (+2 time) is recursively predicted to obtain the predicted wind speed data for each time within the set time period, and a predicted wind speed sequence is formed.

[0067] The predicted wind speed sequence in this embodiment is: This means predicting the wind speed data for a given moment based on the historical wind speed sequence. For example, The prediction method is as follows: Based on the above prediction method, the wind speed data at the first moment has been predicted. x N+1 ,but x N+2 The corresponding historical wind speed sequence is After vectorization, it is:

[0068]

[0069] In the formula, Represents the historical wind speed sequence number Wind speed at any time and the first N+ The length between wind speed values ​​at time 1; Represents the historical wind speed sequence number Wind speed at any time and the first N+ The angle between wind speed values ​​at time 1; Represents the historical wind speed sequence number Wind speed at any time and the first N+ The length between wind speed values ​​at time 1; Represents the historical wind speed sequence number Wind speed at any time and the first N+ The angle between wind speed values ​​at time 1; Represents the historical wind speed sequence number Wind speed at any time and the first N+ The length between wind speed values ​​at time 1; Represents the historical wind speed sequence number Wind speed at any time and the first N + The angle between the wind speed values ​​at time 1.

[0070] Summing all phases of the vector sequence yields a sum vector. The sum vector is orthogonally decomposed on a Cartesian coordinate axis, and the wind speed data for the next moment is predicted based on the sine and cosine components and the sum vector.

[0071]

[0072] in, For the first N The predicted wind speed at time +2 It is the sum of all lengths in the first wind speed sequence; This represents the sum of all angles in the first wind speed vector sequence; For the first The time corresponds to the last value of the historical wind speed sequence; Represents the sine function; This represents the cosine function.

[0073] The rest of x N+3 ,...,x N+9 And so on.

[0074] S3, vectorize the predicted future wind speed sequence to obtain the predicted future wind speed vector sequence; based on the predicted future wind speed vector sequence, correct the predicted future wind speed sequence to obtain the final predicted future wind speed sequence.

[0075] By vectorizing the values ​​of two adjacent positions in the predicted future wind speed sequence, we obtain the predicted future wind speed vector sequence:

[0076]

[0077] in, Represents the historical wind speed sequence number Wind speed at any time and the first N+ The length between the wind speed values ​​at two different times; Represents the historical wind speed sequence number Wind speed at any time and the first N+ The angle between the wind speed values ​​at two different times; Represents the historical wind speed sequence number Wind speed at any time and the first N+ The length between the wind speed values ​​at 3 moments; Represents the historical wind speed sequence number Wind speed at any time and the first N+ The angle between the wind speed values ​​at 3 moments; Represents the historical wind speed sequence number Wind speed at any time and the first N+ The length between the wind speed values ​​at 9 o'clock; Represents the historical wind speed sequence number Wind speed at any time and the first N+ The angle between the wind speed values ​​at 9 o'clock.

[0078] The predicted future wind speed vector sequence is projected onto the X-axis and Y-axis respectively to obtain the X-axis projection sequence and the Y-axis projection sequence; the X-axis projection sequence is:

[0079]

[0080] The Y-axis projection sequence is:

[0081]

[0082] In the formula, This is the x-axis projection vector of the predicted power values ​​at the first and second time points. Let x be the projection vector of the predicted power values ​​at the second and third time points onto the x-axis, ..., The x-axis projection vectors of the predicted power values ​​at the eighth and ninth time points; This is the y-axis projection vector of the predicted power values ​​at the first and second time points. Let be the y-axis projection vectors of the predicted power values ​​at the second and third time points, ... This is the y-axis projection vector of the power values ​​corresponding to the eighth and ninth times.

[0083] Select the maximum vector from the x-axis projection sequence and the y-axis projection sequence respectively:

[0084]

[0085]

[0086] If the position of the maximum value in the X-axis projection sequence is the same as the position of the maximum value in the Y-axis projection sequence, then the value at the same position in the predicted future wind speed vector sequence corresponding to that position will be corrected.

[0087] The specific correction method is as follows:

[0088]

[0089] In the formula, To provide the minimum predicted data in the wind speed sequence, To predict the maximum forecast data in the wind speed sequence, The first of the corrected final predicted future wind speed series Predicted wind speed at any time; The first of the corrected final predicted future wind speed series Real-time predicted wind speed, The predicted future wind speed sequence Predicted wind speed at any time; The first element in the predicted future wind speed vector sequence The value of the position; The first of the predicted future wind speed sequence Predicted wind speed at any time; The first of the predicted future wind speed sequence Predicted wind speed at any time; The first of the predicted future wind speed sequence Predicted wind speed at any time; Represents the maximum value function; Represents the minimum value function; It is the Euler number.

[0090] For example, the largest Y-axis projection is The largest x-axis projection is At this point, the predicted value needs to be adjusted. and Make corrections, specifically:

[0091]

[0092] The prediction accuracy is further improved by correcting the predicted wind speed sequence. This method does not employ existing prediction models, thus eliminating the need for initial data processing and saving time in the prediction process. This allows for rapid prediction, and the vector-based prediction method also offers relatively high accuracy. Overall, this method is simple to implement and highly accurate.

[0093] To compare the performance of the method of this invention with general prediction methods, this embodiment selects two different wind speed sequences as test objects. These two wind speed sequences represent wind speed variations under different climatic conditions and geographical environments to ensure the broad applicability of the experimental results. This embodiment uses Mean Absolute Percentage Error (MAPE) as an indicator to measure prediction accuracy.

[0094] The experimental results are shown in the table below:

[0095]

[0096] As can be seen from the table, for both different wind speed sequences, the MAPE of the method of this invention is significantly lower than that of the traditional method. Specifically, in wind speed sequence 1, the MAPE of the method of this invention is reduced by approximately 13.2 percentage points compared to the traditional method; in wind speed sequence 2, it is also reduced by approximately 7.6 percentage points. This indicates that the method of this invention has significant advantages in wind speed prediction.

[0097] Example 2

[0098] like Figure 2 As shown, this embodiment also provides a wind speed prediction system for supercapacity energy storage based on the vector method, including:

[0099] Data initialization module 201 is used to acquire historical wind speed sequences; the length of the historical wind speed sequence is... N The preset length of the predicted future wind speed sequence is... M ;

[0100] Prediction module 202 will predict the first N + j Vectorize the historical wind speed sequence corresponding to time 1 to obtain the first... N + j The first wind speed vector sequence corresponding to time t; based on the t... N + j The first wind speed vector sequence corresponding to time t is obtained. N + j The predicted wind speed at that moment; repeat this step. M This process continues until the prediction of the future wind speed sequence is completed, resulting in the predicted future wind speed sequence.

[0101] The correction module 203 vectorizes the predicted future wind speed sequence to obtain the predicted future wind speed vector sequence; based on the predicted future wind speed vector sequence, it corrects the predicted future wind speed sequence to obtain the final predicted future wind speed sequence.

[0102] Example 3

[0103] like Figure 3As shown, this embodiment provides an electronic device for implementing the vector-based wind speed prediction method for supercapacity energy storage in Embodiment 1. The electronic device 100 includes at least one processor 102, a memory 101, a computer program 103 stored in the memory 101 and executable on at least one processor 102, and at least one communication bus 104. The memory 101 can be used to store the computer program 103. The processor 102 implements the steps of the vector-based wind speed prediction method for supercapacity energy storage in Embodiment 1 by running or executing the computer program stored in the memory 101 and by calling data stored in the memory 101. The memory 101 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, at least one application program required for a function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created based on the use of the electronic device 100 (such as audio data), etc. In addition, memory 101 may include non-volatile memory, such as hard disk, memory, plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, at least one disk storage device, flash memory device, or other non-volatile solid-state storage device.

[0104] At least one processor 102 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Processor 102 may be a microprocessor or any conventional processor. Processor 102 is the control center of electronic device 100, connecting various parts of electronic device 100 via various interfaces and lines.

[0105] The memory 101 in the electronic device 100 stores multiple instructions to implement a vector-based supercapacity energy storage wind speed prediction method, and the processor 102 can execute multiple instructions to implement the above-mentioned vector-based supercapacity energy storage wind speed prediction method.

[0106] Example 4

[0107] If the modules / units integrated in the electronic device 100 are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, and read-only memory (ROM). Only Memory).

[0108] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0109] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0110] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0111] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A vector method based ultra capacity energy storage wind speed prediction method, characterized in that, The method comprises the following steps: obtaining a historical wind speed sequence; a length of the historical wind speed sequence is N ; a length of the preset predicted future wind speed sequence is M ; The first N + j Vectorize the historical wind speed sequence corresponding to time 1 to obtain the first... N + j The first wind speed vector sequence corresponding to time t; for the t... N + j Perform a sum-vector orthogonal decomposition on the first wind speed vector sequence corresponding to time t, and obtain the first... N + j The predicted wind speed at that moment; repeat this step. M This process continues until the prediction of the future wind speed sequence is completed, resulting in the predicted future wind speed sequence. , This represents the first number corresponding to the predicted future wind speed sequence. time; vectorizing the predicted future wind speed sequence to obtain a predicted future wind speed vector sequence; and correcting the predicted future wind speed sequence based on the predicted future wind speed vector sequence to obtain a final predicted future wind speed sequence; The step of correcting the predicted future wind speed sequence based on the predicted future wind speed vector sequence to obtain a final predicted future wind speed sequence comprises: projecting the predicted future wind speed vector sequence on the X-axis and the Y-axis respectively to obtain an X-axis projection sequence and a Y-axis projection sequence; if the position of the maximum value of the X-axis projection sequence is the same as the position of the maximum value of the Y-axis projection sequence, correcting the value at the same position in the predicted future wind speed vector sequence corresponding to the position of the maximum value; otherwise, not correcting; The step of correcting the value at the same position in the predicted future wind speed vector sequence corresponding to the position of the maximum value comprises: wherein is the minimum value in the predicted future wind speed sequence, is the maximum value in the predicted future wind speed sequence, is the predicted wind speed at time instant in the final predicted future wind speed sequence after correction; is the predicted wind speed at time instant in the final predicted future wind speed sequence after correction; is the predicted wind speed at time instant in the final predicted future wind speed sequence after correction, is the predicted wind speed at time instant in the final predicted future wind speed sequence after correction, is the predicted wind speed at time instant in the final predicted future wind speed sequence after correction; is the predicted wind speed at time instant in the final predicted future wind speed sequence after correction; is the value at position in the predicted future wind speed vector sequence; is the predicted wind speed at time instant in the final predicted future wind speed sequence after correction; is the predicted wind speed at time instant in the final predicted future wind speed sequence after correction; is the predicted wind speed at time instant in the final predicted future wind speed sequence after correction; is the predicted wind speed at time instant in the final predicted future wind speed sequence after correction; is the predicted wind speed at time instant in the final predicted future wind speed sequence after correction; is the predicted wind speed at time instant in the final predicted future wind speed sequence after correction; is the predicted wind speed at time instant in the final predicted future wind speed sequence after correction; denotes the maximum function; denotes the minimum function; is the Euler number.

2. The vector-based super-energized wind speed prediction method according to claim 1, wherein, The first N + j The first wind speed vector sequence corresponding to the time moment is described as: wherein, is the wind speed value corresponding to the time instant t in the first wind speed vector sequence i is the wind speed value corresponding to the time instant t in the first wind speed vector sequence ; ; wherein, is the wind speed value corresponding to the moment in the historical wind speed sequence, N is the length of the historical wind speed sequence, is the wind speed value corresponding to the i moment in the historical wind speed sequence, is the wind speed value of the moment in the historical wind speed sequence, i is the angle between the wind speed value of the moment and the wind speed value of the moment in the historical wind speed sequence, i is the length between the wind speed value of the moment and the wind speed value of the moment in the historical wind speed sequence, i is the time interval between the wind speed value of the i moment and the wind speed value of the N moment in the historical wind speed sequence.

3. The vector-based super-energized wind speed prediction method according to claim 1, wherein, The first wind speed vector sequence corresponding to the time moment is decomposed into a sum vector and a normal vector to obtain the first wind speed vector sequence corresponding to the time moment N j The first wind speed vector sequence corresponding to the time moment is decomposed into a sum vector and a normal vector to obtain the first wind speed vector sequence corresponding to the time moment N j The first wind speed vector sequence corresponding to the time moment is decomposed into a sum vector and a normal vector to obtain the first wind speed vector sequence corresponding to the time moment​​ The first N + j Summing all terms of the first wind speed vector sequence corresponding to each time point yields the sum vector. The and vector is orthogonally decomposed to obtain the first N + j corresponding to the prediction wind speed at the moment.

4. The vector-based super-energized wind speed prediction method according to claim 3, wherein, The first N + j The predicted wind speed corresponding to the time instant is: In the formula, is the first N j is the predicted wind speed corresponding to the time point t; is the sum of all wind speed values in the first wind speed vector sequence; is the length between the wind speed value at the time point t and the wind speed value at the time point t+1 in the historical wind speed sequence; i is the sum of all wind speed values in the first wind speed vector sequence; is the angle between the wind speed value at the time point t and the wind speed value at the time point t+1 in the historical wind speed sequence, i is the last value of the historical wind speed sequence corresponding to the time point t; represents a sine function; represents a cosine function.​​​​​​​​ 5. The vector-based super-energized wind speed prediction method according to claim 1, wherein, The step of vectorizing the predicted future wind speed sequence comprises vectorizing the values of two adjacent time points in the predicted future wind speed sequence.

6. A vector method based ultra capacity energy storage wind speed prediction system based on the vector method based ultra capacity energy storage wind speed prediction method of claim 1, characterized in that, The method comprises: The data initialization module is configured to acquire a historical wind speed sequence; the length of the historical wind speed sequence is N ; and the length of a preset predicted future wind speed sequence is M ; a prediction module, which vectorizes the historical wind speed sequence corresponding to the time point to obtain a first wind speed vector sequence corresponding to the time point; performs sum vector orthogonal decomposition on the first wind speed vector sequence corresponding to the time point to obtain a predicted wind speed corresponding to the time point; and repeats the step for times until the prediction of the future wind speed sequence is completed to obtain the predicted future wind speed sequence. N j N j N j N j M t represents the time point.​​​​​​​​​​​ a correction module configured to vectorize the predicted future wind speed sequence to obtain a predicted future wind speed vector sequence, and correct the predicted future wind speed sequence based on the predicted future wind speed vector sequence to obtain a final predicted future wind speed sequence.

7. An electronic device, comprising: The device comprises a processor and a memory, wherein the processor is configured to execute a computer program stored in the memory to implement the vector-based super-capacity energy storage wind speed prediction method according to any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium stores at least one instruction, and the at least one instruction is executed by the processor to implement the vector-based super-capacity energy storage wind speed prediction method according to any one of claims 1-5.

Images