Smooth processing method and system for wind power prediction curve based on time trend

Abstract

The invention discloses a wind power prediction curve smoothing method and system based on a time trend, and belongs to the technical field of wind power airport prediction. Original new energy day-ahead declaration curve data is adopted to determine fitting parameters of a sliding window suitable for the original new energy day-ahead declaration curve data, and then iterative operation is carried out based on a Savitzky-Golay filtering fitting method, so that the new energy day-ahead declaration curve data is obtained; and simulating the whole NDVI time sequence data to obtain a long-term change trend. According to the method, the low-frequency component in the original data at the abrupt increase or abrupt drop position is reserved, and the high-frequency component is smoothed, so that the phenomenon of abrupt increase or abrupt drop in a new energy day-ahead declaration curve is avoided, the basic trend and width of the original data can be ensured to be unchanged while noise is filtered, and the method is suitable for popularization and application. The method is suitable for a scene in which the profit effect of an original curve cannot be greatly changed, and meets the'inertia 'requirement of a transaction center on the power supply curve.

Description

Technical Field

[0001] This invention belongs to the field of wind power airport prediction technology, specifically involving a method and system for smoothing wind power prediction curves based on time trends. Background Technology

[0002] Day-ahead reporting by wind farms typically refers to the submission of their projected power generation and generation plans by the wind farm before the start of each day in the electricity market or power dispatch center. This process is a crucial component of electricity market operation and power dispatch, aiming to ensure the stable operation of the power system and optimize resource allocation. Accurate day-ahead reporting is paramount. Significant deviations between the reported and actual power generation can lead to power system instability and even power outages. Therefore, wind farms need to continuously improve the accuracy and reliability of their forecasts and reports to better participate in electricity market competition and power dispatch; site staff need to make day-ahead reports based on short-term wind power forecasts.

[0003] The 96-point curve submitted recently was derived from a manually processed curve generated by the power prediction model. To improve the accuracy of power predictions, power plants often adjust their submitted curves based on experience, such as increasing or decreasing output during certain periods. This can lead to sharp increases or decreases in the power curve. Such submitted curves do not meet the requirements of the trading center and require smoothing. However, existing new energy day-ahead submissions adjust short-term power predictions based on human experience. The resulting curves exhibit abrupt changes, which do not conform to the inertial characteristics of power generation. Summary of the Invention

[0004] The purpose of this invention is to solve the problems in the prior art by providing a method and system for smoothing wind power prediction curves based on time trends, so as to solve the technical problem that the power prediction curves generated by the prior art have "abrupt changes" and do not conform to the inertial characteristics of power generation.

[0005] To achieve the above objectives, the present invention employs the following technical solution:

[0006] A method for smoothing wind power prediction curves based on time trends, comprising:

[0007] Obtain a set of new energy vehicle application date curve data; determine the fitting parameters of the corresponding sliding window based on the set of new energy vehicle application date application curve data;

[0008] Based on the fitting parameters and the Savitzky-Golay filtering method, the fitted filtering model is obtained;

[0009] The remaining new energy daily declaration curve data are input into the fitting filter model to obtain the smoothed daily declaration curve.

[0010] Preferably, the fitting parameters include window length and fitting order.

[0011] Preferably, the step of obtaining the fitted filtering model based on the Savitzky-Golay filtering method according to the fitted parameters specifically includes:

[0012] Let x[i] be a set of new energy daily application curve data within a window, i = -m, ..., 0, ..., m, where i takes 2m+1 consecutive integer values. Now, construct an nth-order polynomial (n ≤ 2m+1) to fit the data:

[0013]

[0014] The sum of squared residuals between the fitted data points and the original data points is:

[0015]

[0016] Setting the partial derivative of the above equation to 0, we can solve for:

[0017]

[0018] Where 2m+1 is the window length, n is the fitting order, and E is the sum of squared residuals between the fitted data points and the original data points.

[0019] Preferably, the window length is a positive odd integer.

[0020] Preferably, the value of the fitting order is less than the window length.

[0021] A wind power prediction curve smoothing system based on time trends, comprising:

[0022] The preprocessing unit is used to acquire a set of new energy vehicle application date curve data; and to determine the fitting parameters of the corresponding sliding window based on the set of new energy vehicle application date application curve data.

[0023] The model building unit is used to obtain the fitted filtering model based on the Savitzky-Golay filtering method according to the fitting parameters;

[0024] The fitting and filtering unit is used to input the remaining new energy daily declaration curve data into the fitting and filtering model to obtain a smooth daily declaration curve.

[0025] Preferably, the fitting parameters include window length and fitting order.

[0026] Preferably, the window length is a positive odd integer, and the fitting order is less than the window length.

[0027] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the time-trend-based wind power prediction curve smoothing method described above.

[0028] A computer-readable storage medium storing a computer program, characterized in that, when executed by a processor, the computer program implements the steps of the time-trend-based wind power prediction curve smoothing method described above.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] This invention proposes a time-trend-based wind power forecast curve smoothing method. It uses the original new energy day-ahead declaration curve data, determines the fitting parameters for a suitable sliding window, and then performs iterative calculations based on the Savitzky-Golay filtering fitting method to simulate the long-term trend of the entire NDVI time series data. Low-frequency components in the original data at "sharp increases" or "sharp decreases" are retained, while high-frequency components are smoothed, avoiding the "sharp increases" or "sharp decreases" phenomenon present in the new energy day-ahead declaration curve. While filtering out noise, it ensures that the basic trend and width of the original data remain unchanged. This method is suitable for scenarios where the profitability of the original curve cannot be significantly altered, and it meets the "inertia" requirements of trading centers for power curves. Attached Figure Description

[0031] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation on the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0032] Figure 1 This is a flowchart of the method of the present invention;

[0033] Figure 2 Figure A illustrates the effect of an embodiment of the present invention;

[0034] Figure 3 Figure B illustrates the effect of an embodiment of the present invention;

[0035] Figure 4 Figure C illustrates the effect of an embodiment of the present invention;

[0036] Figure 5 Figure D illustrates the effect of an embodiment of the present invention. Detailed Implementation

[0037] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0038] Therefore, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the claimed invention, but merely to illustrate selected embodiments of the invention. All other embodiments obtained by those skilled in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0039] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0040] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper," "lower," "horizontal," or "inner" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, or the orientation or positional relationship commonly used when the product of the invention is in use, they are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. Furthermore, terms such as "first" and "second" are only used to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0041] Furthermore, the use of the term "horizontal" does not imply that the component must be absolutely horizontal, but rather that it can be slightly tilted. For example, "horizontal" simply means that its direction is more horizontal than "vertical," and does not mean that the structure must be completely horizontal, but can be slightly tilted.

[0042] In the description of the embodiments of the present invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention according to the specific circumstances.

[0043] The present invention will now be described in further detail with reference to the accompanying drawings:

[0044] See Figure 1 This invention proposes a time-trend-based wind power forecast curve smoothing method. This method, based on the Savitzky-Golay filtering fitting method, aims to smooth the original new energy day-ahead reporting curve, thereby optimizing it to meet the requirements of the trading center. Specifically, it includes:

[0045] S1: Obtain a set of new energy vehicle application date curve data; determine the fitting parameters of the corresponding sliding window based on the set of new energy vehicle application date curve data;

[0046] S2: Based on the fitting parameters and the Savitzky-Golay filtering method, obtain the fitted filtering model;

[0047] S3: Input the remaining new energy day-ahead declaration curve data into the fitting filter model to obtain the smoothed day-ahead declaration curve.

[0048] In some embodiments, the fitting parameters include window length and fitting order.

[0049] In some embodiments, obtaining the fitted filtering model based on the Savitzky-Golay filtering method according to the fitted parameters specifically includes:

[0050] Let x[i] be a set of new energy daily application curve data within a window, i = -m, ..., 0, ..., m, where i takes 2m+1 consecutive integer values. Now, construct an nth-order polynomial (n ≤ 2m+1) to fit the data:

[0051]

[0052] The sum of squared residuals between the fitted data points and the original data points is:

[0053]

[0054] Setting the partial derivative of the above equation to 0, we can solve for:

[0055]

[0056] Where 2m+1 is the window length, n is the fitting order, and E is the sum of squared residuals between the fitted data points and the original data points.

[0057] In some embodiments, the window length is a positive odd integer. The smaller the window length, the closer the curve is to the real curve; the larger the window length, the more powerful the smoothing effect.

[0058] In some embodiments, the value of the fitting order is less than the window length. The larger the value of the fitting order, the closer the curve is to the true curve; the smaller the value of the fitting order, the smoother the curve is, that is, only the low-frequency part of the original data is retained.

[0059]

Example

[0060] Filtering method verification:

[0061] The Savitzky-Golay filtering fitting method determines appropriate filtering parameters based on the average trend of the NDVI time series curve, and uses polynomials to achieve least squares fitting within the sliding window. Iterative calculations are then performed using the Savitzky-Golay filtering method (based on the least squares convolution fitting algorithm) to simulate the long-term trend of the entire NDVI time series data.

[0062] This method fits a k-th order polynomial to data points within a certain window to obtain the fitted result. After discretization, the Savitzky-Golay filter fitting method is a moving window weighted average algorithm, but its weighting coefficients are not simple constant windows, but are obtained by least-squares fitting of a given high-order polynomial within the sliding window.

[0063] In the scenario addressed by this invention, adjustment spikes occur for two main reasons: first, to improve the accuracy of power prediction, staff may significantly increase or decrease the output value at a given time point based on historical experience; second, the power prediction system may perceive a sudden increase or decrease in wind / solar resources at a certain point in time. The first reason is generally more common, while the second is less so. Regardless of the reason, a steep "peak" or "trough" will be introduced into the original data. From a frequency domain perspective, such sudden spikes introduce a high-frequency signal. The Savitzky-Golay filtering fitting method tends to retain the low-frequency components in the original data while smoothing the high-frequency components. The biggest advantage of this method is that it can ensure the basic trend and width of the original data remain unchanged while filtering out noise, making it suitable for scenarios where this invention cannot significantly alter the benefit effect of the original curve.

[0064] Parameters determined:

[0065] Let x[i] be a set of new energy application data within a window, i = -m, ..., 0, ..., m, where i takes 2m+1 consecutive integer values. Now, construct an nth-order polynomial (n ≤ 2m+1) to fit the data:

[0066]

[0067] The sum of squared residuals between the fitted data points and the original data points is:

[0068]

[0069] To ensure a good fit, the sum of squares of the residuals should be minimized, so the partial derivative of the above equation should be 0. Solving for this, we get:

[0070]

[0071] In this invention, the window length to be fitted is 2m+1, the order of the polynomial is n, and the data to be fitted x[i] is known (user-defined). The polynomial can be calculated according to the above formula. The fitted polynomial is used to obtain the estimated value of the center point within the window. For subsequent reported data points, the operation can be repeated by continuously moving the window.

[0072] The Savitzky-Golay smoothing filter mainly has two parameters: window_length and n.

[0073] (1) window_length, which is the window length (2m+1), represents the range of reference before and after the smoothing point. The smaller the value of window_length, the closer the curve is to the real curve; the larger the value of window_length, the more powerful the smoothing effect (Note: This value must be a positive odd integer).

[0074] (2) n value: The data points within the window are fitted with an nth-order polynomial, and the value of n needs to be less than window_length. The larger the value of n, the closer the curve is to the true curve; the smaller the value of n, the smoother the curve is, that is, only the low-frequency part of the original data is retained. In addition, when the value of n is large, the fitting will have problems due to the limitation of window length, and the high-frequency curve will become a straight line.

[0075] Because the smoothing quantification index is unknown, when performing parameter tuning, it is necessary to provide the smoothing effect of multiple parameter combinations and determine the final parameter scheme based on the actual working conditions.

[0076] In a preferred embodiment of the present invention, the values ​​are: window_length = 9 or 11; k = 3.

[0077] Application effect:

[0078] Figures 2-5 This diagram illustrates the actual effect of a simulation based on day-ahead reporting system data from a wind farm. The blue star-shaped line represents the wind power day-ahead reporting curve adjusted by the farm staff, while the red curve represents the reporting curve adjusted using the method of this invention. The vertical axis represents wind power output, and the horizontal axis represents 96 time points within a day. It can be seen that the smoothing process of this invention significantly reduces the "sharp increase" or "sharp decrease" phenomena in the day-ahead reporting curve. In conclusion, the Savitzky-Golay filtering fitting method exhibits good smoothing performance and is suitable for processing day-ahead reporting system data from wind farms.

[0079] This application also discloses a wind power prediction curve smoothing system based on time trends, characterized in that it includes:

[0080] The preprocessing unit is used to acquire a set of new energy vehicle application date curve data; and to determine the fitting parameters of the corresponding sliding window based on the set of new energy vehicle application date application curve data.

[0081] The model building unit is used to obtain the fitted filtering model based on the Savitzky-Golay filtering method according to the fitting parameters;

[0082] The fitting and filtering unit is used to input the remaining new energy daily declaration curve data into the fitting and filtering model to obtain a smooth daily declaration curve.

[0083] In some embodiments, the fitting parameters include window length and fitting order.

[0084] In some embodiments, the window length is a positive odd integer, and the fitting order is less than the window length.

[0085] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that the processor, when executing the computer program, implements the steps of the time-trend-based wind power prediction curve smoothing method described above.

[0086] A computer-readable storage medium storing a computer program, characterized in that, when executed by a processor, the computer program implements the steps of the time-trend-based wind power prediction curve smoothing method described above.

[0087] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0088] 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.

[0089] 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.

[0090] 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.

[0091] 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 protection scope of the claims of the present invention.

Claims

1. A method for smoothing wind power prediction curves based on time trends, characterized in that, include: Obtain a set of new energy vehicle pre-application curve data; The fitting parameters for the corresponding sliding window are determined based on the application curve data of the new energy application date. Based on the fitting parameters and the Savitzky-Golay filtering method, the fitted filtering model is obtained; The remaining new energy daily declaration curve data are input into the fitting filter model to obtain the smoothed daily declaration curve.

2. The method for smoothing wind power prediction curves based on time trends according to claim 1, characterized in that, The fitting parameters include window length and fitting order.

3. The method for smoothing wind power prediction curves based on time trends according to claim 2, characterized in that, The process of obtaining the fitted filtering model based on the Savitzky-Golay filtering method using the fitted parameters specifically includes: Let x[i] be a set of new energy daily application curve data within a window, i = -m, ..., 0, ..., m, where i takes 2m+1 consecutive integer values. Now, construct an nth-order polynomial (n ≤ 2m+1) to fit the data: The sum of squared residuals between the fitted data points and the original data points is: Setting the partial derivative of the above equation to 0, we can solve for: Where 2m+1 is the window length, n is the fitting order, and E is the sum of squared residuals between the fitted data points and the original data points.

4. The method for smoothing wind power prediction curves based on time trends according to claim 2, characterized in that, The window length is a positive odd integer.

5. The method for smoothing wind power prediction curves based on time trends according to claim 2, characterized in that, The value of the fitting order is less than the window length.

6. A wind power prediction curve smoothing system based on time trends, characterized in that, include: The preprocessing unit is used to acquire a set of new energy day-ahead declaration curve data; The fitting parameters for the corresponding sliding window are determined based on the application curve data of the new energy application date. The model building unit is used to obtain the fitted filtering model based on the Savitzky-Golay filtering method according to the fitting parameters; The fitting and filtering unit is used to input the remaining new energy daily declaration curve data into the fitting and filtering model to obtain a smooth daily declaration curve.

7. The wind power prediction curve smoothing system based on time trend according to claim 6, characterized in that, The fitting parameters include window length and fitting order.

8. The wind power prediction curve smoothing system based on time trend according to claim 7, characterized in that, The window length is a positive odd integer, and the fitting order is less than the window length.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the wind power prediction curve smoothing method based on any one of claims 1 to 5.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the wind power prediction curve smoothing method based on any one of claims 1 to 5.

Images