A method, device and medium for predicting ultra-short-term wind power
By obtaining wind measurement data of wind farms and determining the relevant parameters of the wind farm, the problems of complexity and uncertainty of the power prediction system of wind farms in the existing technology are solved, and more accurate ultra-short-term wind power prediction is achieved, reducing the power grid and the operating pressure of power generation companies.
Patent Information
- Application Number
- CN202210378893.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-04-12
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2042-04-12
AI Technical Summary
The existing wind farm power prediction system needs to conduct model training for each prediction period, resulting in an increase in system complexity and uncertainty. When there is a problem with the data, all the data needs to be re-determined to affect the prediction accuracy.
By obtaining the wind measurement data of the target wind farm and the remaining wind farms, determine the correlation coefficient between the actual wind speed sequence and the wind direction sequence of the target wind farm and the upwind wind farm, determine whether there is a reference sequence, and according to the relevant parameters, including time offset and wind The prediction wind power is determined by the data and the straight line distance, avoid repeated data determination, and improve prediction accuracy.
It reduces system complexity and uncertainty, improves the accuracy of ultra-short-term wind power prediction, conforms to meteorological laws, and reduces peak and frequency regulation pressures of power grids and power generation companies.
Smart Images

Figure CN114707734B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of wind power technology, and in particular to a method, device and medium for predicting ultra-short-term wind power. Background Art
[0002] As a new energy source, wind power is more suitable for large-scale development. Accurate wind power forecast data can alleviate the peak load and frequency regulation pressure of the power system and maximize the benefits of spot power trading. Reasonable arrangements for wind turbine maintenance can reduce unnecessary downtime and power generation losses, thereby reducing safety hazards. Therefore, power grids and power generation companies attach great importance to wind power forecasting, and the requirements are getting higher and higher. At present, the wind farm power forecasting system is generally based on short-term forecast power data and actual operating power, using the continuous method, sliding average method or machine learning algorithm to establish an ultra-short-term power forecasting model, and the power is predicted in the short term through the forecasting model.
[0003] However, model training is required for each prediction period. That is, if the power is predicted for the next four hours and the prediction is made every 15 minutes, model training is required every 15 minutes. The power prediction for the next four hours will appear every 15 minutes. If there is a problem with one of the data, all the data needs to be re-determined, which increases the complexity and uncertainty of the system.
[0004] In view of the above technical problems, seeking a wind power prediction method is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention
[0005] The purpose of the present application is to provide a method, device and medium for predicting ultra-short-term wind power, which are used to predict the wind power of a target wind farm according to the specific wind conditions of the wind farm.
[0006] In order to solve the above technical problems, the present application provides a method for predicting ultra-short-term wind power, comprising:
[0007] Obtain wind measurement data of the target wind farm and other wind farms;
[0008] Determine, based on the wind measurement data, a correlation coefficient of an actual wind speed sequence and a correlation coefficient of an actual wind direction sequence between the target wind farm and the upwind wind farm;
[0009] Determine whether both of the two correlation coefficients are greater than a preset threshold;
[0010] If so, taking the actual wind speed sequence or the actual wind direction sequence of the upwind wind farm as a reference sequence;
[0011] Determining relevant parameters according to the reference sequence;
[0012] Determining predicted wind power according to the relevant parameters;
[0013] The relevant parameters include at least the time offset between the upwind wind farm and the target wind farm, wind condition data of the area where all the wind farms are located, and the straight-line distance between the target wind farm and the remaining wind farms.
[0014] Preferably, determining the time offset comprises:
[0015] Acquire the time points of the peaks and troughs of the actual wind speed sequence and the reference sequence of the target wind farm;
[0016] Determining whether the actual wind speed sequence of the target wind farm and the reference sequence only have the peak or the trough;
[0017] If yes, select the time between the two peaks or the time between the two troughs as the time offset;
[0018] If not, the average of the time between the two peaks and the time between the two troughs is selected as the time offset.
[0019] Preferably, after determining the time offset, the method further includes:
[0020] Determine a wind speed sequence of the target wind farm in a corresponding time period according to the time offset;
[0021] Determining an average relative error between the actual wind speed sequence of the upwind wind farm and the wind speed sequence of the target wind farm as a wind speed amplitude deviation between the target wind farm and the upwind wind farm;
[0022] Determining the predicted wind power according to the relevant parameters includes:
[0023] The predicted wind power is determined according to the time offset, the wind speed amplitude deviation, the wind condition data and the straight-line distance.
[0024] Preferably, determining the predicted wind power according to the time offset, the wind speed amplitude deviation, the wind condition data and the straight-line distance comprises:
[0025] Determine the predicted wind speed according to the time offset, the wind speed amplitude deviation, the wind condition data and the straight-line distance;
[0026] Obtaining an actual operating power curve of the target wind farm;
[0027] The predicted wind power is determined according to the predicted wind speed and the actual operating power curve.
[0028] Preferably, the wind condition levels corresponding to the wind condition data are level one wind condition, level two wind condition, level three wind condition and level four wind condition;
[0029] The first-level wind condition is when the wind speed in the area is within the first preset range, the second-level wind condition is when the wind speed in the area is within the second preset range, and the change rate of the wind speed is a preset change rate, the third-level wind condition is when the wind speed in the area is within the third preset range, and the rest are the fourth-level wind conditions;
[0030] The lower limit value of the second preset range is equal to the upper limit value of the first preset range, and the lower limit value of the third preset range is equal to the upper limit value of the second preset range.
[0031] Preferably, determining the predicted wind speed according to the time offset, the wind speed amplitude deviation, the wind condition data and the straight-line distance comprises:
[0032] When the area is in the level 1 wind condition, taking the current wind speed of the target wind farm as the predicted wind speed;
[0033] When the upwind wind farm is in the level 2 wind condition and the target wind farm is not in the level 2 wind condition, determining the time when the wind speed of the target wind farm changes significantly according to the straight-line distance and the wind speed;
[0034] Determine whether the moment is greater than a preset time;
[0035] If yes, taking the current wind speed of the target wind farm as the predicted wind speed;
[0036] If not, taking the current wind speed of the target wind farm as the predicted wind speed before the moment, and taking the current wind speed of the upwind wind farm as the predicted wind speed between the moment and the preset time;
[0037] When the target wind farm is in the level 2 wind condition and the upwind wind farm is not in the level 2 wind condition, a wind speed sequence of the upwind wind farm in a corresponding time period is determined according to the time offset and the wind speed amplitude deviation to serve as the predicted wind speed;
[0038] When the area is in the third-level wind condition, determining the historical wind speed sequence of the upwind wind farm, and determining the predicted wind speed according to the historical wind speed sequence of the upwind wind farm and the actual wind speed sequence of the target wind farm;
[0039] When the area is in the level 4 wind condition, the predicted wind speed is determined according to the actual wind speed sequence of the upwind wind farm and the actual wind speed sequence of the target wind farm.
[0040] In order to solve the above technical problems, the present application also provides an ultra-short-term wind power prediction device, comprising:
[0041] An acquisition module is used to acquire wind measurement data of the target wind farm and other wind farms;
[0042] A first determination module is used to determine the correlation coefficient of the actual wind speed sequence and the correlation coefficient of the actual wind direction sequence of the target wind farm and the upwind wind farm according to the wind measurement data;
[0043] A judging module, used for judging whether the two correlation coefficients are both greater than a preset threshold, and if so, triggering the module;
[0044] The module is used to use the actual wind speed sequence or the actual wind direction sequence of the upwind wind farm as a reference sequence;
[0045] A second determination module, configured to determine relevant parameters according to the reference sequence;
[0046] A third determination module, used to determine the predicted wind power according to the relevant parameters;
[0047] The relevant parameters include at least the time offset between the upwind wind farm and the target wind farm, wind condition data of the area where all the wind farms are located, and the straight-line distance between the target wind farm and the remaining wind farms.
[0048] In order to solve the above technical problems, the present application also provides an ultra-short-term wind power prediction device, comprising:
[0049] Memory for storing computer programs;
[0050] A processor is used to implement the steps of the ultra-short-term wind power prediction method as described above when executing the computer program.
[0051] In order to solve the above technical problems, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the ultra-short-term wind power prediction method as described above are implemented.
[0052] The present application provides a method for predicting ultra-short-term wind power, which obtains the wind measurement data of the target wind farm and the other wind farms, and determines the correlation coefficient of the actual wind speed sequence and the actual wind direction sequence of the target wind farm and the upwind wind farm based on the wind measurement data, thereby judging the correlation coefficient and determining whether there is a reference sequence. When there is a reference sequence, the relevant parameters of the wind farm are determined according to the reference sequence, and finally the predicted wind power is determined according to the relevant parameters. It can be seen that this method determines the relevant parameters of the wind farm through the reference sequence, wherein the relevant parameters include the wind conditions of all wind farms, and the wind power of the target wind farm can be predicted according to the specific wind conditions of the wind farm, thereby avoiding the need to redetermine all data when there is a problem with the data when predicting the wind power, thereby reducing the complexity and uncertainty of the system when predicting the wind power. Moreover, the wind conditions of the wind farm are more in line with meteorological laws, which improves the accuracy of ultra-short-term predicted power.
[0053] On this basis, the present application also provides an ultra-short-term wind power prediction device and medium, which have the same beneficial effects as the ultra-short-term wind power prediction method. BRIEF DESCRIPTION OF THE DRAWINGS
[0054] In order to more clearly illustrate the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0055] Figure 1 A flowchart of a method for predicting ultra-short-term wind power provided in an embodiment of the present application;
[0056] Figure 2 A structural diagram of an ultra-short-term wind power prediction device provided in an embodiment of the present application;
[0057] Figure 3 A structural diagram of an ultra-short-term wind power prediction device provided in another embodiment of the present application. DETAILED DESCRIPTION
[0058] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0059] The core of the present application is to provide an ultra-short-term wind power prediction method, device and medium, which are used to predict the wind power of a target wind farm according to the specific wind conditions of the wind farm.
[0060] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.
[0061] Figure 1 A flowchart of a method for predicting ultra-short-term wind power provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, the method for predicting ultra-short-term wind power includes the following steps.
[0062] S10: Obtain wind measurement data of the target wind farm and other wind farms.
[0063] S11: Determine the correlation coefficient of the actual wind speed sequence and the correlation coefficient of the actual wind direction sequence between the target wind farm and the upwind wind farm according to the wind measurement data.
[0064] S12: Determine whether both correlation coefficients are greater than a preset threshold. If so, proceed to step S13.
[0065] S13: Taking the actual wind speed sequence or the actual wind direction sequence of the upwind wind farm as a reference sequence.
[0066] S14: Determine relevant parameters according to the reference sequence.
[0067] S15: Determine the predicted wind power according to relevant parameters.
[0068] As a new energy source, wind power is more suitable for large-scale development. Accurate wind power forecast data can alleviate the peak load and frequency regulation pressure of the power system and maximize the benefits of spot power trading. Reasonable arrangement of wind turbine maintenance can reduce unnecessary downtime and power generation losses, thereby reducing safety hazards. Therefore, power grids and power generation companies attach great importance to wind power forecasting, and the requirements are getting higher and higher. At present, the wind farm power forecasting system generally uses the continuous method, sliding average method or machine learning algorithm to establish an ultra-short-term power forecasting model based on short-term forecast power data and actual operating power, and uses the forecasting model to make short-term power forecasts. However, it is necessary to train the model for each forecast period first, that is, if the power is predicted for the next four hours and it is predicted every 15 minutes, the model training needs to be performed every 15 minutes, and the power forecast for the next four hours will appear every 15 minutes. When there is a problem with one of the data, all the data need to be re-determined, which increases the complexity and uncertainty of the system. Therefore, a method for predicting ultra-short-term wind power is proposed.
[0069] As described in step S10, the wind measurement data of the target wind farm and the remaining wind farms are obtained, wherein the wind measurement data mentioned in this embodiment are the wind measurement data of the target wind farm and the remaining wind farms in a period of history and the current period. In addition, the specific content of the wind measurement data is not limited. This embodiment, as a preferred embodiment, describes the wind measurement data, including at least the average wind speed and the average wind direction of the whole field. In addition, there is no limitation on how to obtain the wind measurement data. It can be through a wind turbine or a wind tower. It only needs to be able to obtain the wind measurement data.
[0070] In step S11, it is mentioned that the correlation coefficient of the actual wind speed sequence and the correlation coefficient of the actual wind direction sequence of the target wind farm and the upwind wind farm are determined based on the wind measurement data. It can be understood that a correlation coefficient is determined by the actual wind speed sequence of the target wind farm and the actual wind speed sequence of the upwind wind farm, and then another correlation coefficient is determined by the actual wind direction sequence of the target wind farm and the actual wind direction sequence of the upwind wind farm. That is, two wind speed sequences determine one correlation coefficient, and two wind direction sequences determine another correlation coefficient. In step S12, it is mentioned that it is determined whether the two correlation coefficients are both greater than the preset threshold. This embodiment does not limit the preset threshold, and the specific size of the preset threshold can be selected according to the specific implementation method.
[0071] In addition, when both correlation coefficients are greater than a preset threshold, the actual wind speed sequence or the actual wind direction sequence of the upwind wind farm is used as a reference sequence, that is, when the subsequent sequence is related to wind speed, the reference sequence is the actual wind speed sequence of the upwind wind farm, and when the subsequent sequence is related to wind direction, the reference sequence is the actual wind direction sequence of the upwind wind farm. After confirming the reference sequence, it is also necessary to determine the relevant parameters of the wind farm through the reference sequence, wherein the relevant parameters at least include the time offset between the upwind wind farm and the target wind farm, the wind condition data of the area where all wind farms are located, and the straight-line distance between the target wind farm and the remaining wind farms. It is worth noting that the time offset between the upwind wind farm and the target wind farm refers to the time required for the upstream wind flow field to move from the upwind wind farm to the target wind farm. On this basis, this embodiment does not limit how to determine the relevant parameters, and how to determine the relevant parameters can be selected according to the specific implementation method.
[0072] In addition, the predicted wind power is determined according to the relevant parameters, that is, according to the time offset, wind condition data and straight-line distance, the predicted wind speed of the target wind farm can be preferentially determined through the relevant parameters, and the predicted wind power can be determined according to the relationship between wind speed and power. This embodiment does not limit this and can be selected according to the specific implementation situation. In addition, the ultra-short-term wind power prediction mentioned in this embodiment refers to the prediction of wind power within the next four hours, and after the predicted wind power is determined according to the relevant parameters, the ultra-short-term predicted power sequence with a time interval of 15 minutes will be displayed, with a total of 16 values.
[0073] The present embodiment provides a method for predicting ultra-short-term wind power, which obtains the wind measurement data of the target wind farm and the other wind farms, and determines the correlation coefficient of the actual wind speed sequence and the actual wind direction sequence of the target wind farm and the upwind wind farm based on the wind measurement data, thereby judging the correlation coefficient to determine whether there is a reference sequence. When there is a reference sequence, the relevant parameters of the wind farm are determined based on the reference sequence, and finally the predicted wind power is determined based on the relevant parameters. It can be seen that this method determines the relevant parameters of the wind farm through the reference sequence, wherein the relevant parameters include the wind conditions of all wind farms, and the wind power of the target wind farm can be predicted based on the specific wind conditions of the wind farm, thereby avoiding the need to re-determine all data when there is a problem with the data when predicting wind power, thereby reducing the complexity and uncertainty of the system when predicting wind power. Moreover, the wind conditions of the wind farm are more in line with meteorological laws, which improves the accuracy of ultra-short-term predicted power.
[0074] Based on the above embodiment, how to determine the time offset is described, wherein the specific steps of determining the time offset include:
[0075] Obtain the time points of the peaks and troughs of the actual wind speed sequence of the target wind farm and the reference sequence;
[0076] Determine whether the actual wind speed sequence of the target wind farm and the reference sequence only have peaks or troughs;
[0077] If so, select the time between two peaks or the time between two troughs as the time offset;
[0078] If not, the average of the time between two peaks and the time between two troughs is selected as the time offset.
[0079] It can be understood that the time points of the peaks and troughs of the actual wind speed sequence and the reference sequence of the target wind farm are obtained. Since the time offset is determined by wind speed in this embodiment, the reference sequence at this time is the actual wind speed sequence of the upwind wind farm. In a specific embodiment, the actual wind speed sequence and the reference sequence of the target wind farm may only have peaks or troughs, or both peaks and troughs may exist at the same time, so it is necessary to judge whether the actual wind speed sequence and the reference sequence of the target wind farm only have peaks or troughs. When only peaks or troughs exist, the time between the two peaks or the time between the two troughs is selected as the time offset, that is, when only peaks exist, the time between the two peaks is selected as the time offset, and when only troughs exist, the time between the two troughs is selected as the time offset.
[0080] In addition, when a peak and a trough exist at the same time, the time between the two peaks is determined, and the time between the two troughs is also determined, and the average of the two is calculated, and the average is used as the time offset. It is worth noting that this embodiment is only a preferred embodiment, and the time offset can also be determined by other methods, which will not be repeated in this embodiment.
[0081] The method for determining the time offset provided in this embodiment obtains the time points of the peaks and troughs of the actual wind speed sequence and the reference sequence of the target wind farm; determines whether the actual wind speed sequence and the reference sequence of the target wind farm only have peaks or troughs; if so, selects the time between the two peaks or the time between the two troughs as the time offset; if not, selects the average of the time between the two peaks and the time between the two troughs as the time offset. It can be seen that this method also determines the existence of peaks and troughs, making the determined time offset more accurate.
[0082] Based on the above embodiment, after determining the time offset, the method further includes:
[0083] Determine a wind speed sequence of a target wind farm in a corresponding time period according to the time offset;
[0084] Determine the average relative error between the actual wind speed sequence of the upwind wind farm and the wind speed sequence of the target wind farm as the wind speed amplitude deviation between the target wind farm and the upwind wind farm;
[0085] Determining the predicted wind power based on relevant parameters includes:
[0086] Determine the predicted wind power based on time offset, wind speed amplitude deviation, wind condition data and straight-line distance.
[0087] It is understandable that after determining the time offset, the wind speed sequence of the target wind farm in the corresponding time period can be determined according to the time offset, and the average relative error between the actual wind speed sequence of the upwind wind farm and the wind speed sequence of the target wind farm is used as the wind speed amplitude difference between the target wind farm and the upwind wind farm. Then determining the predicted wind power according to the relevant parameters becomes determining the predicted wind power according to the time offset, wind speed amplitude deviation, wind condition data and straight-line distance.
[0088] It can be seen that after determining the time offset, this embodiment also determines the wind speed amplitude difference between the target wind farm and the upwind wind farm, so that the result obtained when determining the predicted wind power is more accurate.
[0089] Based on the above embodiment, how to determine the predicted wind power is described. The specific steps of determining the predicted wind power include:
[0090] Determine the predicted wind speed based on time offset, wind speed amplitude deviation, wind condition data and straight-line distance;
[0091] Obtain the actual operating power curve of the target wind farm;
[0092] The predicted wind power is determined based on the predicted wind speed and the actual operating power curve.
[0093] It can be understood that the predicted wind speed is first determined based on the event offset, wind speed amplitude deviation, wind condition data and straight-line distance, and then the actual operating power curve of the target wind farm is obtained. The actual operating power curve has wind speed as the horizontal axis and power as the vertical axis. The predicted wind power corresponding to the predicted wind speed can be found on the actual operating power curve based on the predicted wind speed.
[0094] It can be seen that the method for determining the predicted wind power provided in this embodiment first determines the predicted wind speed, and then determines the predicted wind power through the actual operating power curve. This method is more accurate in predicting wind power and also reduces the complexity of system prediction.
[0095] Based on the above embodiments, the wind condition data specifically includes level one wind conditions, level two wind conditions, level three wind conditions and level four wind conditions, wherein the level one wind condition refers to when the wind speed in the area is within the first preset range, the level two wind condition refers to when the wind speed in the area is within the second preset range, and the rate of change of the wind speed is the preset rate of change, the level three wind condition refers to when the wind speed in the area is within the third preset range, and the rest are level four wind conditions; the lower limit value of the second preset range is equal to the upper limit value of the first preset range, and the lower limit value of the third preset range is equal to the upper limit value of the second preset range.
[0096] How to determine the predicted wind speed is described below. The specific steps are as follows:
[0097] When the area is in level 1 wind condition, the current wind speed of the target wind farm is used as the predicted wind speed;
[0098] When the upwind wind farm is in the level 2 wind condition and the target wind farm is not in the level 2 wind condition, the time when the wind speed of the target wind farm changes significantly is determined based on the straight-line distance and wind speed;
[0099] Determine whether the moment is greater than the preset time;
[0100] If yes, the current wind speed of the target wind farm is used as the predicted wind speed;
[0101] If not, the current wind speed of the target wind farm is used as the predicted wind speed before the time, and the current wind speed of the upwind wind farm is used as the predicted wind speed between the time and the preset time;
[0102] When the target wind farm is in the level 2 wind condition and the upwind wind farm is not in the level 2 wind condition, the wind speed sequence of the upwind wind farm in the corresponding time period is determined according to the time offset and the wind speed amplitude deviation as the predicted wind speed;
[0103] When the area is in level 3 wind condition, determine the historical wind speed sequence of the upwind wind farm, and determine the predicted wind speed based on the historical wind speed sequence of the upwind wind farm and the actual wind speed sequence of the target wind farm;
[0104] When the area is in level 4 wind condition, the predicted wind speed is determined based on the actual wind speed sequence of the upwind wind farm and the actual wind speed sequence of the target wind farm.
[0105] It can be seen that the present embodiment divides the wind conditions of the wind farm in detail into four levels in total, and the level 4 wind condition is a situation other than the above situation. In addition, the present embodiment does not limit the first preset range, the second preset range and the third preset range, which can be determined according to the specific implementation situation. As a preferred implementation, the present embodiment describes the first preset range, the second preset range and the third preset range. Among them, the first preset range is 0-4m / s, the second preset range is 4m / s-9m / s, and the third preset range is greater than 9m / s. It is worth noting that the level 2 wind condition is when the wind speed in the area is in the second preset range, and the rate of change of the wind speed is the preset rate of change. The present embodiment does not limit the preset rate of change mentioned, which can be 2m / s or 3m / s, and the rate of change of the wind speed is greater than the preset rate of change. In addition, as a preferred embodiment, the present embodiment limits the preset time mentioned, and the preset time is four hours.
[0106] It can be seen that this embodiment provides a method for determining the predicted wind speed by classifying the wind conditions of the wind farm and predicting the wind speed based on the specific wind conditions. This method can obtain a more accurate predicted wind speed, which conforms to the natural laws of meteorological physics and reduces the power grid assessment electricity.
[0107] In the above embodiments, the prediction method of ultra-short-term wind power is described in detail, and the present application also provides an embodiment corresponding to the prediction device of ultra-short-term wind power. It should be noted that the present application describes the embodiments of the device part from two perspectives, one is based on the perspective of functional modules, and the other is based on the perspective of hardware.
[0108] Figure 2 A structural diagram of an ultra-short-term wind power prediction device provided in an embodiment of the present application, such as Figure 2 As shown, the ultra-short-term wind power prediction device includes:
[0109] An acquisition module 14 is used to acquire wind measurement data of a target wind farm and other wind farms;
[0110] A first determination module 15 is used to determine the correlation coefficient of the actual wind speed sequence and the correlation coefficient of the actual wind direction sequence of the target wind farm and the upwind wind farm according to the wind measurement data;
[0111] A judging module 16, used to judge whether the two correlation coefficients are both greater than a preset threshold, and if so, triggering an operating module 17;
[0112] As module 17, it is used to use the actual wind speed sequence or the actual wind direction sequence of the upwind wind farm as a reference sequence;
[0113] A second determination module 18, configured to determine relevant parameters according to a reference sequence;
[0114] A third determination module 19, used to determine the predicted wind power according to relevant parameters;
[0115] The relevant parameters include at least the time offset between the upwind wind farm and the target wind farm, the wind condition data of the area where all wind farms are located, and the straight-line distance between the target wind farm and the remaining wind farms.
[0116] The present embodiment provides a prediction device for ultra-short-term wind power, including an acquisition module, a first determination module, a judgment module, a module, a second determination module, and a third determination module, which is used to implement an ultra-short-term wind power prediction method, which obtains the wind measurement data of the target wind farm and the remaining wind farms, and determines the correlation coefficient of the actual wind speed sequence and the actual wind direction sequence of the target wind farm and the upwind wind farm according to the wind measurement data, thereby judging the correlation coefficient, determining whether there is a reference sequence, and when there is a reference sequence, determining the relevant parameters of the wind farm according to the reference sequence, and finally determining the predicted wind power according to the relevant parameters. It can be seen that the relevant parameters of the wind farm are determined by the reference sequence, wherein the relevant parameters include the wind conditions of all wind farms, and the wind power of the target wind farm can be predicted according to the specific wind conditions of the wind farm, which avoids the need to re-determine all data when there is a problem with the data when predicting the wind power, and reduces the complexity and uncertainty of the system when predicting the wind power. Moreover, the wind conditions of the wind farm are more in line with meteorological laws, which improves the accuracy of ultra-short-term predicted power.
[0117] Figure 3 This is a structural diagram of an ultra-short-term wind power prediction device provided by another embodiment of the present application, such as Figure 3 As shown, the ultra-short-term wind power prediction device includes: a memory 20 for storing a computer program;
[0118] The processor 21 is used to implement the steps of the ultra-short-term wind power prediction method mentioned in the above embodiment when executing the computer program.
[0119] The ultra-short-term wind power prediction device provided in this embodiment may include but is not limited to a smart phone, a tablet computer, a laptop computer, or a desktop computer.
[0120] Among them, the processor 21 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 21 can be implemented in at least one hardware form of a digital signal processor (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA). The processor 21 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a central processing unit (CPU); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 21 may be integrated with a graphics processing unit (GPU), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 21 may also include an artificial intelligence (AI) processor, which is used to process computing operations related to machine learning.
[0121] The memory 20 may include one or more computer-readable storage media, which may be non-transitory. The memory 20 may also include a high-speed random access memory, and a non-volatile memory, such as one or more disk storage devices, flash memory storage devices. In this embodiment, the memory 20 is at least used to store the following computer program 201, wherein, after the computer program is loaded and executed by the processor 21, it can implement the relevant steps of the ultra-short-term wind power prediction method disclosed in any of the aforementioned embodiments. In addition, the resources stored in the memory 20 may also include an operating system 202 and data 203, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 202 may include Windows, Unix, Linux, etc. Data 203 may include but is not limited to data of the ultra-short-term wind power prediction method, etc.
[0122] In some embodiments, the ultra-short-term wind power prediction device may further include a display screen 22 , an input / output interface 23 , a communication interface 24 , a power supply 25 , and a communication bus 26 .
[0123] Those skilled in the art will understand that Figure 3 The structure shown in the figure does not constitute a limitation on the ultra-short-term wind power prediction device, and may include more or fewer components than those shown in the figure.
[0124] The ultra-short-term wind power prediction device provided in this embodiment includes a memory and a processor, wherein the memory is used to store a program of an ultra-short-term wind power prediction method, and the processor is used to execute the stored program, which obtains the wind measurement data of the target wind farm and the other wind farms, and determines the correlation coefficient of the actual wind speed sequence and the actual wind direction sequence of the target wind farm and the upwind wind farm according to the wind measurement data, thereby judging the correlation coefficient, determining whether there is a reference sequence, and when there is a reference sequence, determining the relevant parameters of the wind farm according to the reference sequence, and finally determining the predicted wind power according to the relevant parameters. It can be seen that the relevant parameters of the wind farm are determined by the reference sequence, wherein the relevant parameters include the wind conditions of all wind farms, and the wind power of the target wind farm can be predicted according to the specific wind conditions of the wind farm, thereby avoiding the need to re-determine all data when there is a problem with the data when predicting the wind power, and reducing the complexity and uncertainty of the system when predicting the wind power. Moreover, the wind conditions of the wind farm are more in line with meteorological laws, which improves the accuracy of the ultra-short-term predicted power.
[0125] Finally, the present application also provides an embodiment corresponding to a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps recorded in the above method embodiment are implemented.
[0126] It is understandable that if the method in the above embodiment is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.
[0127] The computer-readable storage medium provided in this embodiment stores the program of the ultra-short-term wind power prediction method in the computer-readable storage medium, and is used to implement the steps of the ultra-short-term wind power prediction method. The method obtains the wind measurement data of the target wind farm and the other wind farms, and determines the correlation coefficient of the actual wind speed sequence and the actual wind direction sequence of the target wind farm and the upwind wind farm according to the wind measurement data, thereby judging the correlation coefficient, determining whether there is a reference sequence, and when there is a reference sequence, determining the relevant parameters of the wind farm according to the reference sequence, and finally determining the predicted wind power according to the relevant parameters. It can be seen that the relevant parameters of the wind farm are determined by the reference sequence, wherein the relevant parameters include the wind conditions of all wind farms, and the wind power of the target wind farm can be predicted according to the specific wind conditions of the wind farm, which avoids the need to re-determine all data when there is a problem with the data when predicting the wind power, and reduces the complexity and uncertainty of the system when predicting the wind power. Moreover, the wind conditions of the wind farm are more in line with meteorological laws, which improves the accuracy of the ultra-short-term predicted power.
[0128] The above is a detailed introduction to the ultra-short-term wind power prediction method, device and medium provided by the present application. The various embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same and similar parts between the embodiments can refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can refer to the method part description. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the claims of the present application.
[0129] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.
Claims
1. A method for predicting ultra-short-term wind power, characterized in that: include: Acquiring wind measurement data of a target wind farm and other wind farms except the target wind farm; the wind measurement data includes an average wind speed and an average wind direction of the entire wind farm; Determine, based on the wind measurement data, a correlation coefficient of an actual wind speed sequence and a correlation coefficient of an actual wind direction sequence between the target wind farm and the upwind wind farm; Determine whether both of the two correlation coefficients are greater than a preset threshold; If so, taking the actual wind speed sequence or the actual wind direction sequence of the upwind wind farm as a reference sequence; Determining relevant parameters according to the reference sequence; Determining predicted wind power according to the relevant parameters; The relevant parameters include at least the time offset between the upwind wind farm and the target wind farm, the wind condition data of the area where all the wind farms are located, and the straight-line distance between the target wind farm and the remaining wind farms; The time offset between the upwind wind farm and the target wind farm represents the time required for the upstream wind flow field to move from the upwind wind farm to the target wind farm; the wind condition data includes level 1 wind condition, level 2 wind condition, level 3 wind condition and level 4 wind condition.
2. The method for predicting ultra-short-term wind power according to claim 1, characterized in that: Determining the time offset includes: Acquire the time points of the peaks and troughs of the actual wind speed sequence and the reference sequence of the target wind farm; Determining whether the actual wind speed sequence of the target wind farm and the reference sequence only have the peak or the trough; If only the peak exists, the time between the two peaks is selected as the time offset; If only the trough exists, the time between the two troughs is selected as the time offset; If not, the average of the time between the two peaks and the time between the two troughs is selected as the time offset.
3. The method for predicting ultra-short-term wind power according to claim 1, characterized in that: After determining the time offset, the method further includes: Determine a wind speed sequence of the target wind farm in a corresponding time period according to the time offset; Determining an average relative error between the actual wind speed sequence of the upwind wind farm and the wind speed sequence of the target wind farm as a wind speed amplitude deviation between the target wind farm and the upwind wind farm; Determining the predicted wind power according to the relevant parameters includes: The predicted wind power is determined according to the time offset, the wind speed amplitude deviation, the wind condition data and the straight-line distance.
4. The method for predicting ultra-short-term wind power according to claim 3, characterized in that: Determining the predicted wind power according to the time offset, the wind speed amplitude deviation, the wind condition data and the straight-line distance comprises: Determine the predicted wind speed according to the time offset, the wind speed amplitude deviation, the wind condition data and the straight-line distance; Obtaining an actual operating power curve of the target wind farm; The predicted wind power is determined according to the predicted wind speed and the actual operating power curve.
5. The method for predicting ultra-short-term wind power according to claim 4, characterized in that: The wind condition levels corresponding to the wind condition data are level one wind condition, level two wind condition, level three wind condition and level four wind condition; The first-level wind condition is when the wind speed in the area is within the first preset range, the second-level wind condition is when the wind speed in the area is within the second preset range, and the change rate of the wind speed is the preset change rate, the third-level wind condition is when the wind speed in the area is within the third preset range, and the rest are the fourth-level wind conditions; the first preset range is 0-4m / s, the second preset range is 4m / s-9m / s, and the third preset range is greater than 9m / s; The lower limit value of the second preset range is equal to the upper limit value of the first preset range, and the lower limit value of the third preset range is equal to the upper limit value of the second preset range.
6. The method for predicting ultra-short-term wind power according to claim 5, characterized in that: Determining the predicted wind speed according to the time offset, the wind speed amplitude deviation, the wind condition data and the straight-line distance comprises: When the area is in the level 1 wind condition, taking the current wind speed of the target wind farm as the predicted wind speed; When the upwind wind farm is in the level 2 wind condition and the target wind farm is not in the level 2 wind condition, determining the time when the wind speed of the target wind farm changes significantly according to the straight-line distance and the wind speed; Determine whether the time is greater than a preset time; If yes, taking the current wind speed of the target wind farm as the predicted wind speed; If not, taking the current wind speed of the target wind farm as the predicted wind speed before the moment, and taking the current wind speed of the upwind wind farm as the predicted wind speed between the moment and the preset time; When the target wind farm is in the level 2 wind condition and the upwind wind farm is not in the level 2 wind condition, a wind speed sequence of the upwind wind farm in a corresponding time period is determined according to the time offset and the wind speed amplitude deviation to serve as the predicted wind speed; When the area is in the third-level wind condition, determining the historical wind speed sequence of the upwind wind farm, and determining the predicted wind speed according to the historical wind speed sequence of the upwind wind farm and the actual wind speed sequence of the target wind farm; When the area is in the level 4 wind condition, the predicted wind speed is determined according to the actual wind speed sequence of the upwind wind farm and the actual wind speed sequence of the target wind farm.
7. An ultra-short-term wind power prediction device, characterized in that: include: An acquisition module is used to acquire wind measurement data of a target wind farm and other wind farms except the target wind farm; the wind measurement data includes an average wind speed and an average wind direction of the entire wind farm; A first determination module is used to determine the correlation coefficient of the actual wind speed sequence and the correlation coefficient of the actual wind direction sequence of the target wind farm and the upwind wind farm according to the wind measurement data; A judging module, used for judging whether the two correlation coefficients are both greater than a preset threshold, and if so, triggering the module; The module is used to use the actual wind speed sequence or the actual wind direction sequence of the upwind wind farm as a reference sequence; A second determination module, configured to determine relevant parameters according to the reference sequence; A third determination module, used to determine the predicted wind power according to the relevant parameters; The relevant parameters include at least the time offset between the upwind wind farm and the target wind farm, the wind condition data of the area where all the wind farms are located, and the straight-line distance between the target wind farm and the remaining wind farms; The time offset between the upwind wind farm and the target wind farm represents the time required for the upstream wind flow field to move from the upwind wind farm to the target wind farm; the wind condition data includes level 1 wind condition, level 2 wind condition, level 3 wind condition and level 4 wind condition.
8. An ultra-short-term wind power prediction device, characterized in that: comprising a memory for storing a computer program; A processor, configured to implement the steps of the method for predicting ultra-short-term wind power as claimed in any one of claims 1 to 6 when executing the computer program.
9. 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 steps of the method for predicting ultra-short-term wind power according to any one of claims 1 to 6 are implemented.
