Method and device for correcting a predicted wind speed

Abstract

The application discloses a correction method and device for predicting wind speed. The method comprises the following steps: correcting historical wind speed prediction data in each wind speed prediction validity period in each test time window by using a plurality of wind speed prediction deviation values, to obtain corrected historical wind speed prediction data in each test time window; selecting a wind speed correction time window of a target wind speed prediction date according to wind speed deviation values of the corrected historical wind speed prediction data and historical wind speed actual data in each wind speed prediction validity period in each test time window; and correcting wind speed prediction data in each wind speed prediction validity period in the target wind speed prediction date by using historical wind speed prediction data and historical wind speed actual data in each wind speed prediction validity period in the wind speed correction time window, to obtain corrected wind speed prediction data. The application solves the technical problem in the related art that wind speed data can only be obtained from batch-produced prediction products, and the precision requirement of a power system on wind speed data cannot be met.

Description

Technical Field

[0001] This invention relates to the field of data processing technology for power systems, and more specifically, to a method and apparatus for correcting predicted wind speed. Background Technology

[0002] Wind energy distribution exhibits strong spatial and temporal variations, and wind predictability is limited. Furthermore, wind power is significantly influenced by the geographical environment of the wind farm (including topography, roughness, tower shadows, and wake effects) and meteorological conditions (including wind speed, wind direction, air pressure, and temperature), resulting in highly fluctuating, uncertain, and intermittent wind power output. Currently, the meteorological information obtained by the power industry is mostly from mass-produced forecast products provided by meteorological departments, the accuracy of which is insufficient to meet the power industry's demand for meteorological services.

[0003] There is currently no effective solution to the problem that the aforementioned technologies can only obtain wind speed data from mass-produced forecast products, which cannot meet the accuracy requirements of power systems for wind speed data. Summary of the Invention

[0004] This invention provides a method and apparatus for correcting predicted wind speed, which at least solves the technical problem in related technologies that wind speed data can only be obtained from mass-produced forecast products, and cannot meet the accuracy requirements of power systems for wind speed data.

[0005] According to one aspect of the present invention, a method for correcting predicted wind speed is provided, comprising: acquiring historical wind speed forecast data and historical actual wind speed data for each wind speed forecast period within each time window, wherein the time window is a time period corresponding to a predetermined number of days before the target wind speed prediction date, each time window corresponds to multiple wind speed forecast periods, and the wind speed forecast period represents the validity time of the historical wind speed forecast data; determining a first wind speed deviation value for the historical wind speed forecast data and the historical actual wind speed data for each wind speed forecast period within each training time window, thereby obtaining multiple wind speed forecast deviation values ​​within each training time window, wherein each training time window is a portion of each time window; and correcting the historical wind speed forecast data for each wind speed forecast period within each test time window using the multiple wind speed forecast deviation values, thereby obtaining the corrected wind speed forecast data for each wind speed forecast period within each test time window. The system uses corrected historical wind speed forecast data for each forecast time, excluding the training time window portion of each time window. It selects a wind speed correction time window for the target wind speed prediction date based on the wind speed deviation between the corrected historical wind speed forecast data and the actual historical wind speed data for each forecast time within each test time window. The historical wind speed forecast data and actual historical wind speed data for each forecast time within the correction time window are used to correct the wind speed prediction data for each forecast time within the target wind speed prediction date. Finally, the system uses the historical wind speed forecast data and actual historical wind speed data for each forecast time within the correction time window to correct the wind speed prediction data for each forecast time within the target wind speed prediction date, resulting in corrected wind speed prediction data for each forecast time within the target wind speed prediction date.

[0006] Optionally, acquiring historical wind speed forecast data for each wind speed forecast period within each time window includes: after determining that the meteorological station will release meteorological data for each time window, collecting the meteorological data for each wind speed forecast period within each time window from the meteorological station, wherein the meteorological station, after receiving the station meteorological data fed back by each meteorological station, summarizes the station meteorological data to obtain the meteorological data, and each meteorological station is a station conducting meteorological observations; and acquiring the historical wind speed forecast data for each wind speed forecast period within each time window from the meteorological data.

[0007] Optionally, obtaining historical wind speed data for each wind speed forecast period within each time window includes: sending a wind speed data acquisition request to each meteorological station, wherein the wind speed data acquisition request includes the time window for requesting the acquisition of historical wind speed data; and obtaining the historical wind speed data for each wind speed forecast period within each time window as fed back by each meteorological station according to the wind speed data acquisition request.

[0008] Optionally, the historical wind speed forecast data for each wind speed forecast lead time within each test time window is corrected using the plurality of wind speed forecast deviation values ​​to obtain corrected historical wind speed forecast data for each wind speed forecast lead time within each test time window. This includes: determining the average forecast deviation value of the plurality of wind speed forecast deviation values; determining a test wind speed correction value based on the average forecast deviation value; and subtracting the historical wind speed forecast data for each wind speed forecast lead time within each test time window from the test wind speed correction value to correct the historical wind speed forecast data for each wind speed forecast lead time within each test time window, thereby obtaining corrected historical wind speed forecast data for each wind speed forecast lead time within each test time window.

[0009] Optionally, determining the test wind speed correction value based on the average forecast deviation value includes: determining the test wind speed correction value according to a predetermined formula and the average forecast deviation value, wherein the predetermined formula is: B(t) is the correction value for the tested wind speed. Let w be the average forecast deviation value, w be the weighting coefficient, t be a certain moment in the wind speed forecast lead time, and b be the wind speed forecast deviation value.

[0010] Optionally, selecting the wind speed correction time window for the target wind speed prediction date based on the wind speed deviation value between the corrected historical wind speed forecast data and the actual historical wind speed data for each wind speed forecast lead time within each test time window includes: determining each wind speed deviation value between the corrected historical wind speed forecast data and the actual historical wind speed data for each wind speed forecast lead time within each test time window; determining the average wind speed deviation value for each day within each test time window based on each wind speed deviation value; selecting the target wind speed deviation value that minimizes the average wind speed deviation value among the wind speed deviation values; determining the day corresponding to the target wind speed deviation value in the training time window as the starting point of the wind speed correction time window; and determining the time period between the starting point and the day before the target wind speed prediction date as the wind speed correction time window.

[0011] Optionally, the wind speed forecast data for each wind speed forecast period in the target wind speed forecast date is corrected using the historical wind speed forecast data and the historical actual wind speed data for each wind speed forecast period within the wind speed correction time window, to obtain the corrected wind speed forecast data for each wind speed forecast period in the target wind speed forecast date. This includes: determining a second wind speed deviation value between the historical wind speed forecast data and the historical actual wind speed data for each wind speed forecast period in each wind speed correction time window, obtaining multiple corrected wind speed forecast deviation values ​​within each wind speed correction time window; determining the average value of the multiple corrected wind speed forecast deviation values; and using the average value to correct the wind speed forecast data for each wind speed forecast period in the target wind speed forecast date, to obtain the corrected wind speed forecast data for each wind speed forecast period in the target wind speed forecast date.

[0012] Optionally, the wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date is corrected using the average value to obtain the corrected wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date, including: subtracting the wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date from the average value to obtain the corrected wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date.

[0013] According to another aspect of the present invention, a wind speed prediction correction device is also provided, comprising: an acquisition unit, configured to acquire historical wind speed forecast data and historical actual wind speed data for each wind speed forecast time within each time window, wherein the time window is a time period corresponding to a predetermined number of days before the target wind speed prediction date, each time window corresponds to multiple wind speed forecast times, and the wind speed forecast time represents the effective time of the historical wind speed forecast data; a determination unit, configured to determine a first wind speed deviation value for the historical wind speed forecast data and the historical actual wind speed data for each wind speed forecast time within each training time window, thereby obtaining multiple wind speed forecast deviation values ​​within each training time window, wherein each training time window is a portion of each time window; and a first correction unit, configured to use the multiple wind speed forecast deviation values ​​to correct the historical wind speed forecast data for each wind speed forecast time within each test time window, thereby obtaining multiple wind speed forecast deviation values ​​within each test time window. The corrected historical wind speed forecast data for the wind speed forecast lead time includes the portion of each time window excluding each training time window; a selection unit is used to select the wind speed correction time window for the target wind speed prediction date based on the wind speed deviation value between the corrected historical wind speed forecast data and the actual historical wind speed data for each wind speed forecast lead time within each test time window, wherein the historical wind speed forecast data and the actual historical wind speed data for each wind speed forecast lead time within the wind speed correction time window are used to correct the wind speed prediction data for each wind speed forecast lead time within the target wind speed prediction date; a second correction unit is used to correct the wind speed prediction data for each wind speed forecast lead time within the target wind speed prediction date using the historical wind speed forecast data and the actual historical wind speed data for each wind speed forecast lead time within the wind speed correction time window, to obtain the corrected wind speed prediction data for each wind speed forecast lead time within the target wind speed prediction date.

[0014] Optionally, the acquisition unit includes: a collection module, configured to collect meteorological data for each wind speed forecast time within each time window from the meteorological station after determining that the meteorological station releases meteorological data for each time window, wherein the meteorological station summarizes the station meteorological data after receiving the station meteorological data fed back by each meteorological station to obtain the meteorological data, and each meteorological station is a station for conducting meteorological observations; and a first acquisition module, configured to acquire the historical wind speed forecast data for each wind speed forecast time within each time window from the meteorological data.

[0015] Optionally, the acquisition unit includes: a sending module, configured to send a wind speed data acquisition request to each meteorological station, wherein the wind speed data acquisition request includes a time window for the requested historical wind speed actual data; and a second acquisition module, configured to acquire the historical wind speed actual data for each wind speed forecast timeframe within each time window fed back by each of the meteorological stations according to the wind speed data acquisition request.

[0016] Optionally, the first correction unit includes: a first determining module, configured to determine the average forecast deviation value of the plurality of wind speed forecast deviation values; a second determining module, configured to determine a test wind speed correction value based on the average forecast deviation value; and a first correction module, configured to subtract the test wind speed correction value from the historical wind speed forecast data for each wind speed forecast lead time within each test time window, thereby correcting the historical wind speed forecast data for each wind speed forecast lead time within each test time window, to obtain the corrected historical wind speed forecast data for each wind speed forecast lead time within each test time window.

[0017] Optionally, the second determining module includes: a determining submodule, configured to determine the test wind speed correction value according to a predetermined formula and the average forecast deviation value, wherein the predetermined formula is: B(t) is the correction value for the tested wind speed. Let w be the average forecast deviation value, w be the weighting coefficient, t be a certain moment in the wind speed forecast lead time, and b be the wind speed forecast deviation value.

[0018] Optionally, the selection unit includes: a third determining module, used to determine each wind speed deviation value between the corrected historical wind speed forecast data and the actual historical wind speed data for each wind speed forecast time within each test time window; a fourth determining module, used to determine the average wind speed deviation value for each day within each test time window based on each wind speed deviation value; a selection module, used to select a target wind speed deviation value among the wind speed deviation values ​​that minimizes the average wind speed deviation values; a fifth determining module, used to determine the day corresponding to the target wind speed deviation value in the training time window as the starting point of the wind speed correction time window; and a sixth determining module, used to determine the time period between the starting point and the day before the target wind speed prediction date as the wind speed correction time window.

[0019] Optionally, the second correction unit includes: a seventh determining module, configured to determine a second wind speed deviation value between the historical wind speed forecast data and the historical wind speed actual data for each wind speed forecast lead time within each wind speed correction time window, thereby obtaining multiple corrected wind speed forecast deviation values ​​within each wind speed correction time window; an eighth determining module, configured to determine the average value of the multiple corrected wind speed forecast deviation values; and a second correction module, configured to use the average value to correct the wind speed forecast data for each wind speed forecast lead time within the target wind speed forecast date, thereby obtaining corrected wind speed forecast data for each wind speed forecast lead time within the target wind speed forecast date.

[0020] Optionally, the second correction module includes: an acquisition submodule, configured to subtract the wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date from the average value to obtain the corrected wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date.

[0021] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program performs the wind speed prediction correction method described in any one of the foregoing embodiments.

[0022] According to another aspect of the present invention, a processor is also provided, the processor being configured to run a program, wherein the program, when running, executes the wind speed prediction correction method described in any of the above embodiments.

[0023] In this embodiment of the invention, historical wind speed forecast data and historical actual wind speed data for each wind speed forecast period within each time window are obtained. A time window is a time period corresponding to a predetermined number of days before the target wind speed prediction date. Each time window corresponds to multiple wind speed forecast periods, and the wind speed forecast period represents the valid time of the historical wind speed forecast data. A first wind speed deviation value is determined for each wind speed forecast period within each training time window, based on the historical wind speed forecast data and historical actual wind speed data for each wind speed forecast period. This yields multiple wind speed forecast deviation values ​​within each training time window, where each training time window is a portion of each time window. The historical wind speed forecast data for each wind speed forecast period within each test time window is corrected using these multiple wind speed forecast deviation values, resulting in corrected wind speed forecast data for each wind speed forecast period within each test time window. The system uses historical wind speed forecast data, excluding the training time windows, for each time window. It selects a wind speed correction time window for the target wind speed prediction date based on the wind speed deviation between the corrected historical wind speed forecast data and the actual historical wind speed data for each forecast lead time within each test time window. The historical wind speed forecast data and actual historical wind speed data for each forecast lead time within the correction time window are used to correct the wind speed prediction data for each forecast lead time within the target wind speed prediction date. Finally, it uses the historical wind speed forecast data and actual historical wind speed data for each forecast lead time within the correction time window to correct the wind speed prediction data for each forecast lead time within the target wind speed prediction date, resulting in the corrected wind speed prediction data for each forecast lead time within the target wind speed prediction date. The wind speed prediction correction method provided by this invention divides each time window into a training time window and a test time window. It then uses the predicted wind speed data and actual wind speed data from both windows to select the day with the smallest deviation between the predicted and actual wind speed data as the starting point for correcting the wind speed prediction for the target date. The method further corrects the predicted wind speed for the target date using the wind speed prediction data and actual wind speed data from the starting point to the day before the target date. This achieves the technical effect of improving the accuracy of the wind speed prediction correction, thus providing a better data foundation for the power system's wind speed data needs. Furthermore, it solves the technical problem in related technologies where wind speed data can only be obtained from mass-produced forecast products, failing to meet the power system's accuracy requirements for wind speed data. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0025] Figure 1 This is a hardware structure block diagram of a mobile terminal for a wind speed prediction correction method according to an embodiment of the present invention.

[0026] Figure 2 This is a flowchart of a method for correcting predicted wind speed according to an embodiment of the present invention;

[0027] Figure 3 This is a schematic diagram of an optional method for correcting predicted wind speed according to an embodiment of the present invention;

[0028] Figure 4(a) is a schematic diagram of wind speed forecast deviation in Guangzhou under different forecast lead times according to an embodiment of the present invention;

[0029] Figure 4(b) is a schematic diagram of the reduction in wind speed forecast deviation in Guangzhou under different forecast lead times according to an embodiment of the present invention;

[0030] Figure 5(a) is a schematic diagram of wind speed forecast deviation in Nanning under different forecast lead times according to an embodiment of the present invention;

[0031] Figure 5(b) is a schematic diagram of the reduction in wind speed forecast deviation under different forecast lead times in Nanning according to an embodiment of the present invention;

[0032] Figure 6(a) is a schematic diagram of wind speed forecast deviation in Guiyang under different forecast lead times according to an embodiment of the present invention;

[0033] Figure 6(b) is a schematic diagram of the reduction in wind speed forecast deviation under different forecast lead times in Guiyang according to an embodiment of the present invention;

[0034] Figure 7(a) is a schematic diagram of wind speed forecast deviation in Kunming under different forecast lead times according to an embodiment of the present invention;

[0035] Figure 7(b) is a schematic diagram of the reduction in wind speed forecast deviation under different forecast lead times in Kunming according to an embodiment of the present invention;

[0036] Figure 8(a) is a schematic diagram of wind speed forecast deviation in Haikou under different forecast lead times according to an embodiment of the present invention;

[0037] Figure 8(b) is a schematic diagram of the reduction in wind speed forecast deviation in Haikou under different forecast lead times according to an embodiment of the present invention;

[0038] Figure 9 This is a schematic diagram of a wind speed prediction correction device according to an embodiment of the present invention. Detailed Implementation

[0039] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0040] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0041] As described in the background section, the meteorological information acquired by the power industry is mostly from mass-produced forecast products provided by meteorological departments. The accuracy of these forecasts is insufficient to meet the power industry's needs for meteorological services, especially in areas such as new energy power forecasting, which place higher demands on meteorological services. To address the shortcomings of related technologies that rely solely on mass-produced forecast products for wind speed data, failing to meet the power system's accuracy requirements for wind speed data, this invention provides a method and apparatus for correcting predicted wind speed, a computer-readable storage medium, and a processor in its embodiments.

[0042] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0043] The methods and embodiments provided in this invention can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a wind speed prediction correction method according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0044] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the wind speed prediction correction method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0045] According to an embodiment of the present invention, a method embodiment for correcting predicted wind speed is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0046] Figure 2 This is a flowchart of a method for correcting predicted wind speed according to an embodiment of the present invention, such as... Figure 2 As shown, the method for correcting predicted wind speed includes the following steps:

[0047] Step S202: Obtain historical wind speed forecast data and historical actual wind speed data for each wind speed forecast period within each time window. Here, a time window is a time period corresponding to a predetermined number of days before the target wind speed forecast date. Each time window corresponds to multiple wind speed forecast periods, and the wind speed forecast period represents the valid time of the historical wind speed forecast data.

[0048] Optionally, the time window mentioned above is the time period corresponding to the predetermined number of days between the selected date to be predicted. For example, the correction of the predicted wind speed data for the 31st day can be made by using the wind speed predicted data and actual wind speed data from the previous 30 days.

[0049] Optionally, the aforementioned wind speed forecast lead time can be the time period of the meteorological data forecasted by the meteorological station every day. For example, when the meteorological station makes a weather forecast every day, it forecasts the meteorological data for the next 7 days. Then the effective time of the meteorological data forecasted every day is 7 days. That is, the wind speed forecast lead time represents the time period corresponding to the predicted wind speed, and the predicted wind speed during this period is the predicted value for the corresponding time period.

[0050] Step S204: Determine the first wind speed deviation value between the historical wind speed forecast data and the historical wind speed actual data for each wind speed forecast lead time within each training time window, and obtain multiple wind speed forecast deviation values ​​within each training time window, wherein each training time window is a part of each time window.

[0051] In this embodiment, the time window in step S202 can be divided into a training time window and a testing time window.

[0052] For example, if the time window is 30 days, then 2, 3, 4, 5, 6, 7, 8, 9, 10, 15, and 20 days can be selected as the training time windows, and the remaining days can be used as the testing time windows. After determining the training time windows, the predicted wind speed data for each wind speed forecast lead time within each training time window can be subtracted from the actual wind speed data to determine the wind speed deviation between the predicted and actual wind speed data for each training time window.

[0053] Step S206: Use multiple wind speed forecast deviation values ​​to correct the historical wind speed forecast data for each wind speed forecast lead time in each test time window, and obtain the corrected historical wind speed forecast data for each wind speed forecast lead time in each test time window, wherein each time window is the part excluding each training time window.

[0054] In this embodiment, multiple wind speed forecast deviation values ​​within each training time window can be used to correct the wind speed forecast data for each wind speed forecast lead time within each prediction time window, so as to obtain corrected historical wind speed forecast data for each wind speed forecast lead time within each test time window.

[0055] Step S208: Select the wind speed correction time window for the target wind speed prediction date based on the wind speed deviation between the corrected historical wind speed forecast data and the historical wind speed actual data for each wind speed forecast period within each test time window. The historical wind speed forecast data and historical wind speed actual data for each wind speed forecast period within the wind speed correction time window are used to correct the wind speed forecast data for each wind speed forecast period in the target wind speed prediction date.

[0056] In this embodiment, the wind speed deviation between the corrected historical wind speed forecast data and the actual historical wind speed data for each wind speed forecast period within each test time window can be determined first. Then, the wind speed correction time window for the target wind speed prediction date can be determined based on the time deviation value obtained here. Thus, the historical wind speed forecast data and the actual historical wind speed data for each wind speed forecast period within the wind speed correction time window can be used to correct the wind speed prediction data for each wind speed forecast period on the target wind speed prediction date, making the obtained wind speed prediction data more accurate.

[0057] Step S210: Use historical wind speed forecast data and historical actual wind speed data for each wind speed forecast period within the wind speed correction time window to correct the wind speed forecast data for each wind speed forecast period in the target wind speed forecast date, and obtain the corrected wind speed forecast data for each wind speed forecast period in the target wind speed forecast date.

[0058] In this embodiment, the wind speed forecast data for each wind speed forecast period within the wind speed correction time window can be used to correct the wind speed forecast data for each wind speed forecast period in the target wind speed forecast date, thereby obtaining the corrected wind speed forecast data for each wind speed forecast period in the target wind speed forecast date.

[0059] As can be seen from the above, in this embodiment of the invention, each time window of a predetermined time length can be divided into a training time window and a testing time window. Then, historical wind speed forecast data and historical actual wind speed data for each forecast period within the training and testing time windows are used to select the wind speed correction time window for the target wind speed prediction date. This allows the historical wind speed forecast data for each forecast period within the wind speed correction time window to be corrected for the wind speed prediction data for each forecast period on the target wind speed prediction date. Compared to the prior art, which uses a fixed sample to correct each day of the forecast period using the nearest predetermined number of days, this method employs dynamic correction... Using fixed sample data better reflects the recent forecast error characteristics. It divides each time window into training and testing time windows, and selects the day with the smallest deviation between the predicted and actual wind speed data from the training and testing time windows as the starting point for correcting the wind speed on the target wind speed prediction date. The predicted wind speed on the target wind speed prediction date is then corrected using the predicted wind speed data and actual wind speed data from the starting point to the day before the target wind speed prediction date. This achieves the technical effect of improving the accuracy of the predicted wind speed correction, and thus provides a better data foundation for the power system's demand for wind speed data.

[0060] Therefore, the technical solution provided by the above embodiments of the present invention solves the technical problem in the related art that wind speed data can only be obtained from mass-produced forecast products, which cannot meet the accuracy requirements of the power system for wind speed data.

[0061] According to the above embodiments of the present invention, obtaining historical wind speed forecast data for each wind speed forecast period within each time window includes: after determining that the meteorological station will release meteorological data for each time window, collecting meteorological data for each wind speed forecast period within each time window from the meteorological station, wherein the meteorological station, after receiving the station meteorological data fed back by each meteorological station, summarizes the station meteorological data to obtain meteorological data, and each meteorological station is a station for meteorological observation; and obtaining historical wind speed forecast data for each wind speed forecast period within each time window from the meteorological data.

[0062] In this embodiment, after determining the meteorological data for each time window issued by the meteorological station (e.g., the meteorological station issues a weather forecast at 08:00 every day), the system can collect the 3-hour wind speed forecast data for each station for the next 3-168 hours (the next seven days) issued by the meteorological station at 08:00 every day, as well as the 3-hour wind speed real-time data.

[0063] According to the above embodiments of the present invention, obtaining historical wind speed data for each wind speed forecast period within each time window includes: sending a wind speed data acquisition request to each meteorological station, wherein the wind speed data acquisition request includes the time window for requesting the acquisition of historical wind speed data; and acquiring the historical wind speed data for each wind speed forecast period within each time window as fed back by each meteorological station based on the wind speed data acquisition request.

[0064] In this embodiment, a wind speed data acquisition request can be sent to each meteorological station to request the actual wind speed data actually monitored by each meteorological station, thereby obtaining the historical wind speed data for each wind speed forecast period within each time window.

[0065] According to the above embodiments of the present invention, the historical wind speed forecast data for each wind speed forecast lead time within each test time window is corrected using multiple wind speed forecast deviation values ​​to obtain corrected historical wind speed forecast data for each wind speed forecast lead time within each test time window. This includes: determining the average forecast deviation value of the multiple wind speed forecast deviation values; determining a test wind speed correction value based on the average forecast deviation value; and subtracting the historical wind speed forecast data for each wind speed forecast lead time within each test time window from the test wind speed correction value to correct the historical wind speed forecast data for each wind speed forecast lead time within each test time window, thereby obtaining corrected historical wind speed forecast data for each wind speed forecast lead time within each test time window.

[0066] In this embodiment, corrected historical wind speed forecast data for each wind speed forecast lead time within each test time window can be determined. For example, the wind speed deviation value between the historical wind speed forecast data and the actual historical wind speed data for each wind speed forecast lead time within each training time window can be determined first, resulting in multiple wind speed forecast deviation values ​​within each training time window. Then, the average forecast deviation value is obtained by averaging the multiple wind speed forecast deviation values. Finally, the average forecast deviation value is subtracted from the wind speed forecast data for each wind speed forecast lead time within each test time window, thereby obtaining the corrected wind speed forecast data for each wind speed forecast lead time within each test time window, thus improving the accuracy of the wind speed forecast data for each wind speed forecast lead time within each test time window.

[0067] In the above embodiments, determining the test wind speed correction value based on the average forecast deviation value includes: determining the test wind speed correction value according to a predetermined formula and the average forecast deviation value, wherein the predetermined formula is: B(t) is the correction value for the test wind speed. denoted as the average forecast deviation, w as the weighting coefficient, t as a specific moment in the wind speed forecast lead time, and b as the wind speed forecast deviation.

[0068] Optionally, the weighting coefficient t can be the reciprocal of the length of the time window.

[0069] That is, an adjustment coefficient can be set for the average forecast deviation value to correct it; this coefficient can be determined by the reciprocal of the time window length, with the difference between this and 1 used as the adjustment coefficient. This approach makes the determined test wind speed correction value more reliable, improves the accuracy of the correction for the predicted wind speed on the target wind speed prediction date, and reduces the deviation between the corrected predicted wind speed and the actual wind speed, providing better data support for the power system and thus providing guidance for wind power plants.

[0070] For example, a wind power generation strategy for a target wind speed prediction date can be determined based on the revised predicted wind speed. This allows wind power plants to perform power generation operations according to the wind power generation strategy, resulting in higher and more stable wind power efficiency.

[0071] According to the above embodiments of the present invention, selecting the wind speed correction time window for the target wind speed prediction date based on the wind speed deviation value between the corrected historical wind speed forecast data and the historical wind speed actual data for each wind speed forecast lead time within each test time window includes: determining each wind speed deviation value between the corrected historical wind speed forecast data and the historical wind speed actual data for each wind speed forecast lead time within each test time window; determining the average wind speed deviation value for each day within each test time window based on each wind speed deviation value; selecting the target wind speed deviation value that minimizes the average wind speed deviation value among the wind speed deviation values; determining the day corresponding to the target wind speed deviation value in the training time window as the starting point of the wind speed correction time window; and determining the time period between the starting point and the day before the target wind speed prediction date as the wind speed correction time window.

[0072] In this embodiment, after obtaining the corrected historical wind speed forecast data, the wind speed deviation values ​​are compared with the actual historical wind speed data for each forecast period within each test time window. This allows the determination of the average wind speed deviation value for each day within each test time window. Then, the target wind speed deviation value, which minimizes the average wind speed deviation value, is selected. The day corresponding to the target wind speed deviation value in the training time window is used as the starting point of the wind speed correction time window, and the day before the target wind speed prediction date is used as the ending point. This determines the wind speed correction time window for the target wind speed prediction date. Using the wind speed data from the correction time window, the wind speed on the target wind speed prediction date is predicted, resulting in a smaller deviation between the predicted and actual wind speeds. This method is more reliable than the prior art, which uses wind speed data from a fixed number of days before the target prediction date as correction data.

[0073] According to the above embodiments of the present invention, the wind speed forecast data for each wind speed forecast period in the target wind speed forecast date is corrected using historical wind speed forecast data and historical actual wind speed data for each wind speed forecast period within each wind speed correction time window, to obtain corrected wind speed forecast data for each wind speed forecast period in the target wind speed forecast date. This includes: determining a second wind speed deviation value for historical wind speed forecast data and historical actual wind speed data for each wind speed forecast period in each wind speed correction time window, obtaining multiple corrected wind speed forecast deviation values ​​within each wind speed correction time window; determining the average value of the multiple corrected wind speed forecast deviation values; and using the average value to correct the wind speed forecast data for each wind speed forecast period in the target wind speed forecast date, to obtain corrected wind speed forecast data for each wind speed forecast period in the target wind speed forecast date.

[0074] In this embodiment, multiple corrected wind speed forecast deviation values ​​can be obtained from the second wind speed deviation value between historical wind speed forecast data and historical actual wind speed data for each wind speed forecast lead time within each wind speed correction time window. The average value of the multiple corrected wind speed forecast deviation values ​​is determined, and the wind speed forecast data for each wind speed forecast lead time in the target wind speed forecast date is corrected using the average wind speed deviation value for each wind speed forecast lead time in each wind speed correction time window, so that the corrected wind speed forecast data for each wind speed forecast lead time in the target wind speed forecast date is closer to the actual wind speed.

[0075] According to the above embodiments of the present invention, the wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date is corrected using the average value to obtain the corrected wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date, including: subtracting the wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date from the average value to obtain the corrected wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date.

[0076] In this embodiment, the difference between the wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date and the average value can be used as the corrected wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date.

[0077] Figure 3 This is a schematic diagram of an optional method for correcting predicted wind speed according to an embodiment of the present invention, such as... Figure 3As shown, with wind speed forecast lead time set at 3-hour intervals, we first acquire daily 3-hour 2-minute average wind speed forecast data and daily 3-hour 2-minute average wind speed observation data from automatic weather stations. Using daily forecast and actual samples from the 30 days prior to the forecast date as the training and test sets, we first calculate the forecast error for each forecast lead time within the training period for each station. We then set up a series of training time windows, calculating the 2-minute average wind speed forecast error for different forecast leads within each time window as the error estimate for the test set. The error estimate for each lead time each day in the test set is obtained from the training period closest to it. We calculate the mean absolute error after bias correction within different test periods. By comparing the temperature forecast bias of the test set corresponding to each training time window, we select the training time window with the smallest bias as the bias estimation time window for the first day of the forecast period. Then, we repeat the above process for each day of the forecast period using the samples from the 30 days closest to it for correction.

[0078] In the above embodiments, the wind speed deviation correction method corrects the station's wind speed forecast daily by calculating the deviation estimate of the average wind speed over 3 hours and 2 minutes for the next 1-168 hours, thus achieving the purpose of deviation correction. First, the system collects 3-hourly wind speed forecast data and actual 3-hourly wind speed data for each station within the 3-168 hour forecast period, as well as the actual wind speed data, issued by the meteorological observatory at 08:00 daily. For each forecast period on the 31st day (i.e., the first day after the forecast expires on the 1st day of the forecast period), the forecast and actual data samples from each of the 30 days prior to the forecast date are used as the training and test sets to calculate the wind speed forecast deviation for different start times for each forecast period. Next, 2, 3, 4, 5, 6, 7, 8, 9, 10, 15, and 20 days can be set as training time windows. The length of the test set is the remaining time length within the 30 days after deducting the training time windows. The average error of the wind speed forecast for different forecast periods within different time windows is calculated as the error estimate for the test set, and then this error is subtracted from the test set. The error estimate for each forecast period within the test set is calculated using the period closest to its training time. The specific algorithm is as follows: b(t) = f(t) - o(t), where f(t) is the forecast value of the station over t forecast periods, O(t) is the observation value of the station over t forecast periods, and b(t) is the forecast error of the station over t forecast periods. Then, the error estimate for the correction date (i.e., the date of the target wind speed prediction) is calculated: Where B(t) is the estimation error of the station at time t. Let f(t) be the mean absolute error of the station during the training period, w be the weighting coefficient, and b be the reciprocal of the training period length. Finally, subtract the estimated error obtained during the training period from the forecast for the next day to complete the forecast correction: F(t) = f(t) - B(t). This not only takes into account the characteristics of the average forecast error in the early stage of the model, ensuring the overall stability of the estimated error, but also incorporates the error information b(t-1) at the near time, making the error estimation more reasonable.

[0079] This includes calculating the forecast deviation index after deviation correction for different testing periods. The skill score for wind speed at the testing sites includes: mean absolute error. In the mean absolute error F i O represents the wind speed forecast value. i denoted by , where represents the actual wind speed value, and N represents the total number of days in the statistics. By comparing the temperature forecast deviations of the test set corresponding to each training time window, the training time window with the smallest deviation is selected as the deviation estimation time window for the first day of the forecast period. Furthermore, the above process is repeated for each day of the forecast period using samples from the 30 days closest to it for correction.

[0080] For example, wind speed forecast data can be selected from the 2-minute average wind speed forecasts issued daily from 08:00 on July 14, 2020 to August 8, 2022 by meteorological observatories in Guangzhou, Shenzhen, Nanning, Guiyang, Kunming, and Haikou, covering 56 forecast periods (1-168 hours ahead). Actual wind speed data: 2-minute average wind speeds were selected daily from July 14, 2020 to August 15, 2022 by meteorological observatories in Guangzhou, Shenzhen, Nanning, Guiyang, Kunming, and Haikou. Evaluation period: August 13, 2020 to August 8, 2022. A bias correction experiment was conducted on the wind speed forecast. Taking Guangzhou station as an example, the deviation correction within the forecast period has a good correction effect on most forecast lead times, indicating that there is a significant systematic error in the original wind speed forecast. As shown in Figures 4(a) and 4(b) (Figure 4(a) is a schematic diagram of wind speed forecast deviation under different forecast lead times in Guangzhou according to an embodiment of the present invention, and Figure 4(b) is a schematic diagram of the reduction magnitude of wind speed forecast deviation under different forecast lead times in Guangzhou according to an embodiment of the present invention), the deviation of 28 forecast lead times is reduced by more than 10%, with the maximum reduction of 18.3% for 18h and 90h. In addition, wind speed forecast deviation correction experiments were conducted in Nanning, Guiyang, Kunming, and Haikou, as illustrated in the following figures. Figures 5(a) and 5(b) show the wind speed forecast deviations at different forecast lead times in Nanning (Figure 5(a) is a schematic diagram of the wind speed forecast deviations at different forecast lead times in Nanning according to an embodiment of the present invention, and Figure 5(b) is a schematic diagram of the reduction in wind speed forecast deviations at different forecast lead times in Nanning according to an embodiment of the present invention); Figures 6(a) and 6(b) show the wind speed forecast deviations at different forecast lead times in Guiyang according to an embodiment of the present invention, and Figure 6(b) is a schematic diagram of the reduction in wind speed forecast deviations at different forecast lead times in Guiyang according to an embodiment of the present invention); Figures 6(a) and 6(b) show the wind speed forecast deviations at different forecast lead times in Kunming. The reduction magnitude is shown in Figures 7(a) and 7(b) (Figure 7(a) is a schematic diagram of the wind speed forecast deviation under different forecast lead times in Kunming according to an embodiment of the present invention, and Figure 7(b) is a schematic diagram of the reduction magnitude of the wind speed forecast deviation under different forecast lead times in Kunming according to an embodiment of the present invention); the wind speed forecast deviation under different forecast lead times in Haikou and the reduction magnitude of the corrected deviation are shown in Figures 8(a) and 8(b) (Figure 8(a) is a schematic diagram of the wind speed forecast deviation under different forecast lead times in Haikou according to an embodiment of the present invention, and Figure 8(b) is a schematic diagram of the reduction magnitude of the wind speed forecast deviation under different forecast lead times in Haikou according to an embodiment of the present invention); as can be seen from the figures, except for Nanning, where there was no significant improvement after the deviation correction, the wind speed deviations in Guiyang, Kunming, and Haikou were all significantly reduced after correction, by 1%–17.3%, 1%–24.4%, and 3.4%–20.3%, respectively.

[0081] The technical solution provided by the above embodiments of the present invention has the following advantages: 1) Each day of the forecast period is corrected using the nearest predetermined day sample, which better reflects the recent forecast error characteristics compared to fixed samples; 2) It can correct not only the 3-hourly wind speed forecasts of stations, but also the gridded wind speed forecasts and hourly wind speed forecasts, and has strong portability and universality; 3) The temperature correction model does not require large sample training, and achieves good bias correction with less computing resources.

[0082] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0083] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0084] According to an embodiment of the present invention, a wind speed correction device for implementing the above-described wind speed prediction correction method is also provided. Figure 9 This is a schematic diagram of a wind speed prediction correction device according to an embodiment of the present invention, such as... Figure 9 As shown, the device includes: an acquisition unit 91, a determination unit 93, a first correction unit 95, a selection unit 97, and a second correction unit 99. Wherein,

[0085] The acquisition unit 91 is used to acquire historical wind speed forecast data and historical actual wind speed data for each wind speed forecast period within each time window. The time window is the time period corresponding to the number of days before the target wind speed forecast date. Each time window corresponds to multiple wind speed forecast periods, and the wind speed forecast period represents the valid time of the historical wind speed forecast data.

[0086] Unit 93 is used to determine the first wind speed deviation value between the historical wind speed forecast data and the historical wind speed actual data for each wind speed forecast lead time within each training time window, thereby obtaining multiple wind speed forecast deviation values ​​within each training time window, wherein each training time window is a part of each time window.

[0087] The first correction unit 95 is used to correct the historical wind speed forecast data for each wind speed forecast lead time in each test time window using multiple wind speed forecast deviation values, so as to obtain the corrected historical wind speed forecast data for each wind speed forecast lead time in each test time window, wherein each time window is a portion excluding each training time window.

[0088] Selection unit 97 is used to select the wind speed correction time window for the target wind speed prediction date based on the wind speed deviation between the corrected historical wind speed forecast data and the historical wind speed actual data for each wind speed forecast lead time within each test time window. The historical wind speed forecast data and historical wind speed actual data for each wind speed forecast lead time within the wind speed correction time window are used to correct the wind speed forecast data for each wind speed forecast lead time within the target wind speed prediction date.

[0089] The second correction unit 99 is used to correct the wind speed prediction data for each wind speed forecast period in the target wind speed prediction date by using the historical wind speed forecast data and historical actual wind speed data for each wind speed forecast period in the wind speed correction time window, so as to obtain the corrected wind speed prediction data for each wind speed forecast period in the target wind speed prediction date.

[0090] It should be noted that the above-mentioned acquisition unit 91, determination unit 93, first correction unit 95, selection unit 97 and second correction unit 99 correspond to steps S202 to S210 in the above embodiments. The five units and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments.

[0091] As can be seen from the above, in the scheme described in the above embodiments of the present invention, the acquisition unit can be used to acquire historical wind speed forecast data and historical actual wind speed data for each wind speed forecast period within each time window. Here, a time window is a time period corresponding to a predetermined number of days before the target wind speed prediction date, and each time window corresponds to multiple wind speed forecast periods. The wind speed forecast period represents the valid time of the historical wind speed forecast data. The determination unit uses a first wind speed deviation value to determine the historical wind speed forecast data and historical actual wind speed data for each wind speed forecast period within each training time window, thereby obtaining multiple wind speed forecast periods within each training time window. The wind speed forecast deviation value is used, where each training time window is a portion of each time window. The first correction unit uses multiple wind speed forecast deviation values ​​to correct the historical wind speed forecast data for each wind speed forecast lead time within each test time window, obtaining corrected historical wind speed forecast data for each wind speed forecast lead time within each test time window, where each time window includes the portion excluding the training time window. The selection unit uses the wind speed deviation value between the corrected historical wind speed forecast data and the actual historical wind speed data for each wind speed forecast lead time within each test time window to select the wind speed correction value for the target wind speed prediction date. The time window is divided into several parts. Within the corrected wind speed time window, historical wind speed forecast data and actual historical wind speed data for each forecast period are used to correct the wind speed forecast data for each forecast period on the target wind speed forecast date. A second correction unit uses historical wind speed forecast data and actual historical wind speed data for each forecast period on the target wind speed forecast date to correct the wind speed forecast data for each forecast period, resulting in corrected wind speed forecast data for each forecast period on the target wind speed forecast date. This process effectively divides the time window into... The training and testing time windows are used to select the day with the smallest deviation between the predicted and actual wind speed data from the training and testing time windows as the starting point for correcting the wind speed on the target wind speed prediction date. The predicted wind speed on the target wind speed prediction date is then corrected using the predicted wind speed data from the starting point and the day before the target wind speed prediction date, as well as the actual wind speed data. This achieves the technical effect of improving the accuracy of the predicted wind speed correction, and thus provides a better data foundation for the power system's demand for wind speed data.

[0092] Therefore, the technical solution provided by the above embodiments of the present invention solves the technical problem in the related art that wind speed data can only be obtained from mass-produced forecast products, which cannot meet the accuracy requirements of the power system for wind speed data.

[0093] Optionally, the acquisition unit includes: a collection module, used to collect meteorological data for each wind speed forecast time within each time window after determining the meteorological data to be released by the meteorological station for each time window, wherein the meteorological station summarizes the meteorological data from each meteorological station after receiving the meteorological data from each meteorological station to obtain meteorological data, and each meteorological station is a station for conducting meteorological observations; and a first acquisition module, used to acquire historical wind speed forecast data for each wind speed forecast time within each time window from the meteorological data.

[0094] Optionally, the acquisition unit includes: a sending module, used to send wind speed data acquisition requests to each meteorological station, wherein the wind speed data acquisition request includes a time window for the requested historical wind speed actual data; and a second acquisition module, used to acquire historical wind speed actual data for each wind speed forecast period within each time window fed back by each meteorological station according to the wind speed data acquisition request.

[0095] Optionally, the first correction unit includes: a first determining module, used to determine the average forecast deviation value of multiple wind speed forecast deviation values; a second determining module, used to determine the test wind speed correction value based on the average forecast deviation value; and a first correction module, used to subtract the test wind speed correction value from the historical wind speed forecast data for each wind speed forecast lead time within each test time window, so as to correct the historical wind speed forecast data for each wind speed forecast lead time within each test time window, thereby obtaining the corrected historical wind speed forecast data for each wind speed forecast lead time within each test time window.

[0096] Optionally, the second determining module includes: a determining submodule, used to determine the test wind speed correction value according to a predetermined formula and an average forecast deviation value, wherein the predetermined formula is: B(t) is the correction value for the test wind speed. denoted as the average forecast deviation, w as the weighting coefficient, t as a specific moment in the wind speed forecast lead time, and b as the wind speed forecast deviation.

[0097] Optionally, the selection unit includes: a third determining module, used to determine each wind speed deviation value between the corrected historical wind speed forecast data and the actual historical wind speed data for each wind speed forecast lead time within each test time window; a fourth determining module, used to determine the average wind speed deviation value for each day within each test time window based on each wind speed deviation value; a selection module, used to select the target wind speed deviation value among the wind speed deviation values ​​that minimizes the average wind speed deviation value; a fifth determining module, used to determine the day corresponding to the target wind speed deviation value in the training time window as the starting point of the wind speed correction time window; and a sixth determining module, used to determine the time period between the starting point and the day before the target wind speed prediction date as the wind speed correction time window.

[0098] Optionally, the second correction unit includes: a seventh determining module, used to determine the second wind speed deviation value of historical wind speed forecast data and historical actual wind speed data for each wind speed forecast lead time within each wind speed correction time window, to obtain multiple corrected wind speed forecast deviation values ​​within each wind speed correction time window; an eighth determining module, used to determine the average value of the multiple corrected wind speed forecast deviation values; and a second correction module, used to correct the wind speed forecast data for each wind speed forecast lead time within the target wind speed forecast date using the average value, to obtain the corrected wind speed forecast data for each wind speed forecast lead time within the target wind speed forecast date.

[0099] Optionally, the second correction module includes: an acquisition submodule, used to subtract the wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date from the average value, to obtain the corrected wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date.

[0100] According to another aspect of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored program, wherein the program executes the predicted wind speed correction method of any of the above.

[0101] Optionally, in this embodiment, the computer-readable storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any communication device in a group of communication devices.

[0102] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: acquiring historical wind speed forecast data and historical actual wind speed data for each wind speed forecast timeframe within each time window, wherein a time window is a time period corresponding to a predetermined number of days before the target wind speed prediction date, each time window corresponds to multiple wind speed forecast timesframes, and the wind speed forecast timeframe represents the valid time of the historical wind speed forecast data; determining a first wind speed deviation value for the historical wind speed forecast data and historical actual wind speed data for each wind speed forecast timeframe within each training time window, obtaining multiple wind speed forecast deviation values ​​within each training time window, wherein each training time window is a portion of each time window; using the multiple wind speed forecast deviation values ​​to correct the historical wind speed forecast data for each wind speed forecast timeframe within each test time window, obtaining each test timeframe... The corrected historical wind speed forecast data for each forecast lead time within a time window, excluding the portion of each training time window; the wind speed correction time window for the target wind speed prediction date is selected based on the wind speed deviation between the corrected historical wind speed forecast data and the actual historical wind speed data for each forecast lead time within each test time window; the historical wind speed forecast data and actual historical wind speed data for each forecast lead time within the wind speed correction time window are used to correct the wind speed prediction data for each forecast lead time within the target wind speed prediction date; the corrected wind speed prediction data for each forecast lead time within the target wind speed prediction date is obtained by using the historical wind speed forecast data and actual historical wind speed data for each forecast lead time within the wind speed correction time window.

[0103] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: after determining the meteorological data to be released by the meteorological station for each time window, collecting meteorological data for each wind speed forecast time within each time window from the meteorological station, wherein the meteorological station summarizes the station meteorological data after receiving the station meteorological data fed back by each meteorological station to obtain meteorological data, and each meteorological station is a station for meteorological observation; and obtaining historical wind speed forecast data for each wind speed forecast time within each time window from the meteorological data.

[0104] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: sending wind speed data acquisition requests to each meteorological station, wherein the wind speed data acquisition request includes a time window for requesting the acquisition of historical wind speed actual data; acquiring historical wind speed actual data for each wind speed forecast period within each time window fed back by each meteorological station according to the wind speed data acquisition request.

[0105] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: determining the average forecast deviation value of multiple wind speed forecast deviation values; determining a test wind speed correction value based on the average forecast deviation value; subtracting the test wind speed correction value from the historical wind speed forecast data for each wind speed forecast lead time within each test time window, so as to correct the historical wind speed forecast data for each wind speed forecast lead time within each test time window, and obtaining corrected historical wind speed forecast data for each wind speed forecast lead time within each test time window.

[0106] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: determining a test wind speed correction value according to a predetermined formula and an average forecast deviation value, wherein the predetermined formula is: B(t) is the correction value for the test wind speed. denoted as the average forecast deviation, w as the weighting coefficient, t as a specific moment in the wind speed forecast lead time, and b as the wind speed forecast deviation.

[0107] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: determining each wind speed deviation value between the corrected historical wind speed forecast data and the actual historical wind speed data for each wind speed forecast lead time within each test time window; determining the average wind speed deviation value for each day within each test time window based on each wind speed deviation value; selecting a target wind speed deviation value among the wind speed deviation values ​​that minimizes the average wind speed deviation values; determining the day corresponding to the target wind speed deviation value in the training time window as the starting point of the wind speed correction time window; and determining the time period between the starting point and the day before the target wind speed prediction date as the wind speed correction time window.

[0108] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: determining a second wind speed deviation value between historical wind speed forecast data and historical actual wind speed data for each wind speed forecast lead time within each wind speed correction time window, obtaining multiple corrected wind speed forecast deviation values ​​within each wind speed correction time window; determining the average value of the multiple corrected wind speed forecast deviation values; and using the average value to correct the wind speed forecast data for each wind speed forecast lead time in the target wind speed forecast date, obtaining corrected wind speed forecast data for each wind speed forecast lead time in the target wind speed forecast date.

[0109] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: subtracting the wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date from the average value to obtain the corrected wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date.

[0110] According to another aspect of the present invention, a processor is also provided, which is used to run a program, wherein the program executes the predicted wind speed correction method of any of the above-described embodiments.

[0111] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0112] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0113] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0114] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0115] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0116] If the integrated unit is implemented as 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 invention, in essence, 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. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0117] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for correcting predicted wind speed, characterized in that, include: Obtain historical wind speed forecast data and historical actual wind speed data for each wind speed forecast period within each time window. The time window is a time period corresponding to a predetermined number of days before the target wind speed prediction date. Each time window corresponds to multiple wind speed forecast periods, and the wind speed forecast period represents the valid time of the historical wind speed forecast data. Determine the first wind speed deviation value between the historical wind speed forecast data and the historical wind speed actual data for each wind speed forecast time within each training time window, and obtain multiple wind speed forecast deviation values ​​within each training time window, wherein each training time window is a part of each time window; The historical wind speed forecast data for each wind speed forecast lead time within each test time window are corrected using the multiple wind speed forecast deviation values ​​to obtain the corrected historical wind speed forecast data for each wind speed forecast lead time within each test time window. Each test time window is a portion of each time window excluding each training time window. The wind speed correction time window for the target wind speed prediction date is selected based on the wind speed deviation value between the corrected historical wind speed forecast data and the historical wind speed actual data for each wind speed forecast period within each test time window. The historical wind speed forecast data and the historical wind speed actual data for each wind speed forecast period within the wind speed correction time window are used to correct the wind speed forecast data for each wind speed forecast period in the target wind speed prediction date. By using the historical wind speed forecast data and the historical actual wind speed data for each wind speed forecast period within the wind speed correction time window, the wind speed forecast data for each wind speed forecast period on the target wind speed forecast date is corrected to obtain the corrected wind speed forecast data for each wind speed forecast period on the target wind speed forecast date; The wind speed correction time window for the target wind speed prediction date is selected based on the wind speed deviation between the corrected historical wind speed forecast data and the actual historical wind speed data for each wind speed forecast lead time within each test time window, including: Determine the wind speed deviation values ​​between the corrected historical wind speed forecast data and the actual historical wind speed data for each wind speed forecast lead time within each test time window; The average wind speed deviation value for each day within each test time window is determined based on the wind speed deviation values ​​described above. Select the target wind speed deviation value that minimizes the average wind speed deviation value among the aforementioned wind speed deviation values; The starting point of the wind speed correction time window is determined as the day corresponding to the target wind speed deviation value in the training time window. The time period between the starting point and the day before the target wind speed prediction date is defined as the wind speed correction time window.

2. The method for correcting predicted wind speed according to claim 1, characterized in that, Obtain historical wind speed forecast data for each forecast lead time within each time window, including: After determining the meteorological data to be released by the meteorological station for each time window, the meteorological data for each wind speed forecast time within each time window is collected from the meteorological station. The meteorological station summarizes the meteorological data from each meteorological station after receiving the meteorological data from each meteorological station to obtain the meteorological data. Each meteorological station is a station that conducts meteorological observations. The historical wind speed forecast data for each wind speed forecast lead time within each of the aforementioned time windows are obtained from the meteorological data.

3. The method for correcting predicted wind speed according to claim 1, characterized in that, Obtain historical actual wind speed data for each wind speed forecast lead time within each time window, including: Send wind speed data acquisition requests to each meteorological station, wherein the wind speed data acquisition request includes the time window of the requested historical wind speed actual data; Obtain the historical wind speed data for each wind speed forecast timeframe within each of the time windows requested by each of the meteorological stations based on the wind speed data.

4. The method for correcting predicted wind speed according to claim 1, characterized in that, The historical wind speed forecast data for each forecast lead time within each test time window is corrected using the multiple wind speed forecast deviation values, resulting in corrected historical wind speed forecast data for each forecast lead time within each test time window, including: Determine the average forecast deviation value of the plurality of wind speed forecast deviation values; The test wind speed correction value is determined based on the average forecast deviation value; The historical wind speed forecast data for each wind speed forecast period within each test time window is subtracted from the test wind speed correction value to correct the historical wind speed forecast data for each wind speed forecast period within each test time window, thus obtaining the corrected historical wind speed forecast data for each wind speed forecast period within each test time window.

5. The method for correcting predicted wind speed according to claim 4, characterized in that, Determining the test wind speed correction value based on the average forecast deviation value includes: The test wind speed correction value is determined according to a predetermined formula and the average forecast deviation value, wherein the predetermined formula is: B(t) is the correction value for the tested wind speed. Let w be the average forecast deviation value, w be the weighting coefficient, t be a certain moment in the wind speed forecast lead time, and b be the wind speed forecast deviation value.

6. The method for correcting predicted wind speed according to claim 1, characterized in that, By using the historical wind speed forecast data and the historical actual wind speed data for each wind speed forecast period within the wind speed correction time window, the wind speed forecast data for each wind speed forecast period on the target wind speed forecast date is corrected to obtain the corrected wind speed forecast data for each wind speed forecast period on the target wind speed forecast date, including: Determine the second wind speed deviation value between the historical wind speed forecast data and the historical wind speed actual data for each wind speed forecast lead time within each wind speed correction time window, and obtain multiple corrected wind speed forecast deviation values ​​within each wind speed correction time window; Determine the average value of the plurality of corrected wind speed forecast deviations; The wind speed prediction data for each forecast lead time in the target wind speed prediction date is corrected using the average value to obtain the corrected wind speed prediction data for each forecast lead time in the target wind speed prediction date.

7. The method for correcting predicted wind speed according to claim 6, characterized in that, The wind speed forecast data for each forecast lead time within the target wind speed forecast date is corrected using the average value to obtain corrected wind speed forecast data for each forecast lead time within the target wind speed forecast date, including: The wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date is subtracted from the average value to obtain the corrected wind speed prediction data for each wind speed forecast lead time in the target wind speed prediction date.

8. A correction device for predicting wind speed, characterized in that, include: The acquisition unit is used to acquire historical wind speed forecast data and historical actual wind speed data for each wind speed forecast period within each time window. The time window is a time period corresponding to a predetermined number of days before the target wind speed prediction date. Each time window corresponds to multiple wind speed forecast periods, and the wind speed forecast period represents the valid time of the historical wind speed forecast data. The determining unit is used to determine the first wind speed deviation value between the historical wind speed forecast data and the historical wind speed actual data for each wind speed forecast time within each training time window, thereby obtaining multiple wind speed forecast deviation values ​​within each training time window, wherein each training time window is a part of each time window; The first correction unit is used to correct the historical wind speed forecast data for each wind speed forecast lead time in each test time window using the multiple wind speed forecast deviation values, so as to obtain the corrected historical wind speed forecast data for each wind speed forecast lead time in each test time window, wherein each test time window is a part of each time window excluding each training time window. The selection unit is used to select the wind speed correction time window for the target wind speed prediction date based on the wind speed deviation value between the corrected historical wind speed forecast data and the historical wind speed actual data for each wind speed forecast time within each test time window. The historical wind speed forecast data and the historical wind speed actual data for each wind speed forecast time within the wind speed correction time window are used to correct the wind speed forecast data for each wind speed forecast time within the target wind speed prediction date. The second correction unit is used to correct the wind speed prediction data for each wind speed forecast period in the target wind speed prediction date by using the historical wind speed forecast data and the historical wind speed actual data for each wind speed forecast period in the wind speed correction time window, so as to obtain the corrected wind speed prediction data for each wind speed forecast period in the target wind speed prediction date. The selection unit includes: a third determining module, used to determine the wind speed deviation values ​​between the corrected historical wind speed forecast data and the actual historical wind speed data for each wind speed forecast time within each test time window; a fourth determining module, used to determine the average wind speed deviation value for each day within each test time window based on the wind speed deviation values; a selection module, used to select a target wind speed deviation value that minimizes the average wind speed deviation values ​​among the wind speed deviation values; a fifth determining module, used to determine the day corresponding to the target wind speed deviation value in the training time window as the starting point of the wind speed correction time window; and a sixth determining module, used to determine the time period between the starting point and the day before the target wind speed prediction date as the wind speed correction time window.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program executes the method for correcting predicted wind speed as described in any one of claims 1 to 7.

10. A processor, characterized in that, The processor is used to run a program, wherein the program executes the method for correcting predicted wind speed as described in any one of claims 1 to 7.

Images