Method for processing power generation, electronic device and storage medium

Abstract

The application discloses a power generation power processing method, an electronic device and a storage medium. The method comprises the following steps: acquiring a weather prediction result of a position where a wind turbine is located; correcting a first prediction result in the weather prediction result to obtain a weather correction result; and predicting power generation power of the wind turbine based on a second prediction result in the weather prediction result and the weather correction result, wherein the second prediction result is used to represent a prediction result other than the first prediction result in the weather prediction result. The application solves the technical problem of low prediction accuracy when predicting the power generation power of the wind turbine in the related art.

Description

Technical Field

[0001] This application relates to the field of data processing in power systems, and more specifically, to a method for processing power generation, electronic equipment, and storage medium. Background Technology

[0002] To achieve a dual-carbon strategy (carbon neutrality and carbon peaking), an increasing number of power systems are based on new energy sources, such as wind and hydropower, to achieve low-carbon emissions and energy conservation. However, new energy sources are often characterized by randomness and instability. For example, wind power is not fixed but usually varies. Currently, when using traditional forecasting models to predict the power generation of power systems based on new energy sources, the entire forecasting process is cumbersome, requires a lot of manpower to adjust the forecast results, and the forecast accuracy is relatively low.

[0003] There is currently no effective solution to the above problems. Summary of the Invention

[0004] This application provides a method for processing power generation, an electronic device, and a storage medium to at least solve the technical problem of low prediction accuracy when predicting the power generation of wind turbines in related technologies.

[0005] According to one aspect of the embodiments of this application, a method for processing power generation is provided, comprising: obtaining a meteorological forecast result of the location of a wind turbine generator; correcting a first forecast result in the meteorological forecast result to obtain a meteorological correction result; and predicting the power generation of the wind turbine generator based on a second forecast result and the meteorological correction result in the meteorological forecast result, wherein the second forecast result is used to characterize the forecast results in the meteorological forecast result other than the first forecast result.

[0006] According to another aspect of the embodiments of this application, a method for processing power generation is also provided, comprising: responding to an input command applied to an operation interface, displaying a weather forecast result of the location of a wind turbine on the operation interface; and responding to a power forecast command applied to the operation interface, displaying the power generation of the wind turbine on the operation interface, wherein the power generation is predicted based on a second forecast result and a weather correction result in the weather forecast result, the weather correction result is obtained by correcting a first forecast result in the weather forecast result, and the second forecast result is used to characterize forecast results other than the first forecast result in the weather forecast result.

[0007] According to another aspect of the embodiments of this application, a method for processing power generation is also provided, comprising: obtaining a meteorological forecast result of the location of a wind turbine generator by calling a first interface, wherein the first interface includes a first parameter, and the parameter value of the first parameter is the meteorological forecast result; correcting a first forecast result in the meteorological forecast result to obtain a meteorological correction result; predicting the power generation of the wind turbine generator based on a second forecast result and the meteorological correction result in the meteorological forecast result, wherein the second forecast result is used to characterize the forecast results in the meteorological forecast result other than the first forecast result; and outputting the power generation by calling a second interface, wherein the second interface includes a second parameter, and the parameter value of the second parameter is the power generation.

[0008] According to another aspect of the embodiments of this application, a method for processing power generation is also provided, comprising: a cloud server receiving location information sent by a client, wherein the location information is used to characterize the location of a wind turbine; the cloud server obtaining a meteorological forecast result corresponding to the location information; the cloud server correcting a first forecast result in the meteorological forecast result to obtain a corrected meteorological result; the cloud server predicting the power generation of the wind turbine based on a second forecast result and the corrected meteorological result in the meteorological forecast result, wherein the second forecast result is used to characterize forecast results other than the first forecast result in the meteorological forecast result; and the cloud server sending the power generation to the client, wherein the power generation is used to control the wind turbine.

[0009] According to another aspect of the embodiments of this application, a power generation processing apparatus is also provided, comprising: an acquisition module for acquiring meteorological forecast results of the location of a wind turbine generator; a correction module for correcting a first forecast result in the meteorological forecast results to obtain a meteorological correction result; and a prediction module for predicting the power generation of the wind turbine generator based on a second forecast result and the meteorological correction result in the meteorological forecast results, wherein the second forecast result is used to characterize the forecast results in the meteorological forecast results other than the first forecast result.

[0010] According to another aspect of the embodiments of this application, a power generation processing device is also provided, comprising: a first display module, configured to display a weather forecast result of the location of a wind turbine generator on the operation interface in response to an input command applied to the operation interface; and a second display module, configured to display the power generation of the wind turbine generator on the operation interface in response to a power prediction command applied to the operation interface, wherein the power generation is predicted based on a second prediction result and a weather correction result in the weather forecast result, the weather correction result being obtained by correcting the first prediction result in the weather forecast result, and the second prediction result being used to characterize the prediction results in the weather forecast result other than the first prediction result.

[0011] According to another aspect of the embodiments of this application, a power generation processing apparatus is also provided, comprising: a result acquisition module, configured to acquire a meteorological forecast result of the location of a wind turbine generator by calling a first interface, wherein the first interface includes a first parameter, and the parameter value of the first parameter is the meteorological forecast result; a result correction module, configured to correct a first forecast result in the meteorological forecast result to obtain a meteorological correction result; a power prediction module, configured to predict the power generation of the wind turbine generator based on a second forecast result and the meteorological correction result in the meteorological forecast result, wherein the second forecast result is used to characterize forecast results other than the first forecast result in the meteorological forecast result; and an output module, configured to output the power generation by calling a second interface, wherein the second interface includes a second parameter, and the parameter value of the second parameter is the power generation.

[0012] According to another aspect of the embodiments of this application, a power generation processing apparatus is also provided, comprising: a receiving module for a cloud server to receive location information sent by a client, wherein the location information is used to characterize the location of a wind turbine; an acquisition module for the cloud server to acquire a meteorological forecast result corresponding to the location information; a correction module for the cloud server to correct a first forecast result in the meteorological forecast result to obtain a meteorological correction result; a prediction module for the cloud server to predict the power generation of the wind turbine based on a second forecast result and the meteorological correction result in the meteorological forecast result, wherein the second forecast result is used to characterize forecast results other than the first forecast result in the meteorological forecast result; and a sending module for the cloud server to send the power generation to the client, wherein the power generation is used to control the wind turbine.

[0013] According to another aspect of the embodiments of this application, an electronic device is also provided, including: a memory storing an executable program; and a processor for running the program, wherein the program runs a method for processing the power generation of any one of the above-mentioned methods.

[0014] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, characterized in that the computer-readable storage medium includes a stored executable program, wherein, when the executable program is running, the device where the computer-readable storage medium is located executes the power generation processing method of any one of the above-mentioned methods.

[0015] In this embodiment, the method involves obtaining meteorological forecast results of the location of the wind turbine; correcting the first forecast result in the meteorological forecast results to obtain a corrected meteorological result; and predicting the power generation of the wind turbine based on the second forecast result and the corrected meteorological result. By correcting the first forecast result in the meteorological forecast results, which can be monitored for changes in real time, and using the corrected meteorological result in combination with the second forecast result in the meteorological forecast results to predict the power generation of the wind turbine, the prediction accuracy of the power generation of the wind turbine is improved, thereby solving the technical problem of low prediction accuracy when predicting the power generation of wind turbines in related technologies.

[0016] It is worth noting that the general description above and the detailed description that follow are merely for illustrative purposes and do not constitute a limitation on this application. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0018] Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing a power generation processing method is shown.

[0019] Figure 2 This is a flowchart of a method for processing power generation according to Embodiment 1 of this application;

[0020] Figure 3 This is a schematic diagram of a directed graph corresponding to preset meteorological elements according to Embodiment 1 of this application;

[0021] Figure 4 This is a schematic diagram of a conditional distribution solution process according to Embodiment 1 of this application;

[0022] Figure 5 This is a flowchart of a processing system for offline operation according to Embodiment 1 of this application;

[0023] Figure 6 This is a flowchart illustrating the online operation of a processing system according to Embodiment 1 of this application;

[0024] Figure 7 This is a flowchart of a method for processing power generation according to Embodiment 2 of this application;

[0025] Figure 8 This is a schematic diagram of an operation interface according to Embodiment 2 of this application;

[0026] Figure 9 This is a flowchart of a method for processing power generation according to Embodiment 3 of this application;

[0027] Figure 10 This is a flowchart of a method for processing power generation according to Embodiment 4 of this application;

[0028] Figure 11 This is a schematic diagram of a power prediction server interaction according to Embodiment 4 of this application;

[0029] Figure 12 This is a structural block diagram of a power generation processing device according to Embodiment 5 of this application;

[0030] Figure 13 This is a structural block diagram of a power generation processing device according to Embodiment 6 of this application;

[0031] Figure 14 This is a structural block diagram of a power generation processing device according to Embodiment 7 of this application;

[0032] Figure 15 This is a structural block diagram of a power generation processing device according to Embodiment 8 of this application;

[0033] Figure 16 This is a structural block diagram of an electronic device according to Embodiment 9 of this application. Detailed Implementation

[0034] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0035] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application 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 this application 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 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.

[0036] First, some nouns or terms that appear in the description of the embodiments of this application shall be interpreted as follows:

[0037] Numerical weather prediction (NWP) refers to the prediction of weather for a certain period in the future, based on actual weather conditions and under certain initial and boundary conditions, by using large computers to solve the fluid dynamics and thermodynamics equations of the weather evolution process.

[0038] Feature engineering: Processing current meteorological data using historical meteorological data to optimize or reconstruct the data features of the current meteorological data, thereby making the power generation predicted using the current meteorological data more accurate.

[0039] Wind power generation forecast: Prediction of wind turbine power generation in wind farms.

[0040] A Gaussian process (GP) is a stochastic process in probability theory and statistics where observations occur within a continuous domain (e.g., time or space). Typically, a Gaussian process has a single-point output.

[0041] GPLAR: Gaussian Process Latent Autoregressive Regression, can refer to a self-developed autoregressive algorithm based on Gaussian processes with latent variables.

[0042] Variational inference (VI) is an approximate inference method that can be used to extract features from raw meteorological data to improve the quality of machine learning models built for power generation prediction.

[0043] TCN: Temporal Convolutional Network, a type of temporal convolutional network that can be used for sequence modeling tasks to build decoders.

[0044] MLP: Multilayer Perceptron, a type of multilayer perceptron that can be used to classify linear and nonlinear data and build decoders.

[0045] MSE: Mean Squared Error, a loss function that can make the output value of the constructed power prediction model closer to the true value.

[0046] Currently, power systems dominated by new energy sources involve the grid connection of large-scale new energy power generation. However, new energy power generation is typically characterized by randomness and instability, which can affect power dispatch and consequently grid security. Therefore, there are increasingly higher requirements for the accuracy and effectiveness of new energy power forecasting at all levels of the power grid, such as wind power forecasting. Traditional forecasting methods that rely solely on weather forecasts and wind power curve plotting are no longer sufficient to meet the current demands for accuracy and efficiency in power generation forecasting.

[0047] Example 1

[0048] According to an embodiment of this application, a method embodiment for processing power generation is also 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.

[0049] The method embodiment provided in Embodiment 1 of this application can be executed in a mobile terminal, computer terminal or similar computing device. Figure 1 A hardware block diagram of a computer terminal (or mobile device) for a processing method to realize power generation is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. 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 aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0050] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0051] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the power generation processing method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned power generation processing 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 computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0052] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0053] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).

[0054] In power systems that use wind energy as a new energy source, meteorological data from weather forecasts can usually be used to predict wind power generation. In this application, in order to improve the prediction effect when predicting power generation, such as improving prediction efficiency and prediction accuracy, it is proposed that multiple data in the meteorological data can be corrected, and the corrected data can be combined with the remaining uncorrected data to directly predict the power generation of the wind turbine. The specific method is as follows.

[0055] Under the aforementioned operating environment, this application provides the following: Figure 2 The method for processing the generated power is shown. Figure 2 This is a flowchart of a method for processing power generation according to Embodiment 1 of this application.

[0056] like Figure 2 As shown, the method may include the following steps:

[0057] Step S202: Obtain the meteorological forecast results for the location of the wind turbine.

[0058] The location of the aforementioned wind turbine may refer to the coordinates of the site where power generation prediction is performed.

[0059] The above meteorological forecast results may refer to weather forecast data within the vicinity of the coordinate location, such as within a range centered on the coordinate location and with a preset distance as the radius.

[0060] The above meteorological forecast results can generally include multiple meteorological elements, which may include, but are not limited to: wind speed, wind direction, temperature, air pressure, humidity, total surface irradiance, total surface precipitation, cloud cover, etc.

[0061] Currently, there are roughly two ways to obtain weather forecasts for the vicinity of traditional wind turbines. One is to directly purchase numerical weather predictions from meteorological service providers to predict the power generation of wind turbines. However, this method is costly and not very applicable. The other is to use feature engineering and tree models as their own weather forecast models to predict meteorological data. However, this method can only be applied to specific areas and requires a lot of manual parameter adjustment, which is not very applicable, has low efficiency in obtaining meteorological data, and puts a lot of pressure on staff.

[0062] Therefore, in one optional solution of this embodiment, meteorological data related to the coordinate location can be directly filtered from the nationwide weather forecast based on the coordinate location of the station, and used as the above-mentioned meteorological forecast result. This can improve the efficiency of obtaining meteorological forecast results, reduce the workload of staff and the cost of obtaining meteorological forecast results, and also improve the applicability of obtaining meteorological forecast data.

[0063] It should be noted that the nationwide weather forecast is just an example; it can also be a weather forecast for a province or city. The specific choice depends on the actual situation and is not limited here.

[0064] Step S204: Correct the first forecast result in the meteorological forecast results to obtain the corrected meteorological result.

[0065] The aforementioned first prediction result can refer to the meteorological elements that the station can monitor in real time, or it can be the prediction result corresponding to some meteorological elements in the meteorological prediction result, or it can be the prediction result corresponding to all meteorological elements.

[0066] Generally, the aforementioned first forecast result can refer to the forecast result corresponding to the element that can be corrected in real time among multiple meteorological elements, as shown in the following text. It should be noted that the selection of the first forecast result can be determined according to the actual situation, and can be some meteorological forecast results or all meteorological forecast results; there is no limitation here.

[0067] Because nationwide weather forecasts are obtained by solving the fluid dynamics and thermodynamics equations of weather evolution using large computers, and these numerical weather forecasts are adjusted by manual numerical calculations, they contain a certain degree of error. If meteorological forecasts selected from nationwide weather forecasts are used directly for wind power generation forecasts, the accuracy of the forecast results may be low.

[0068] Therefore, in one optional embodiment, meteorological data monitored in real time near the station can be used to correct the selected meteorological forecast results. However, since the types of meteorological data that the station can monitor in real time are limited, it may not be possible to correct all meteorological forecast results using the monitored meteorological data. Therefore, when correcting the data, it is only necessary to determine the forecast results with the same type of meteorological data that the station can monitor as the first forecast result, and then correct them to obtain the corrected meteorological result.

[0069] For example, if the meteorological elements corresponding to the meteorological forecast results related to the station's coordinate location selected in step S202 include: wind speed, wind direction, temperature, air pressure, humidity, total surface irradiance, total surface precipitation, cloud cover, etc., and the meteorological elements corresponding to the meteorological data that the station can monitor in real time include: wind speed, wind direction, temperature, air pressure, and humidity, then the forecast results corresponding to the meteorological elements such as wind speed, wind direction, temperature, air pressure, and humidity in the meteorological forecast results can be used as the first forecast result mentioned above. The first forecast result can then be corrected using the meteorological data monitored in real time by the station to obtain the meteorological correction result mentioned above.

[0070] Step S206: Based on the second forecast result and the weather correction result in the weather forecast results, the power generation capacity of the wind turbine is predicted.

[0071] The second forecast result is used to characterize the forecast results other than the first forecast result in the meteorological forecast results. That is, among the multiple elements corresponding to the meteorological forecast results, the forecast results corresponding to the elements that the station cannot monitor in real time.

[0072] Taking the example in step S204 above, the second prediction result mentioned above can refer to the prediction results corresponding to meteorological elements such as total surface irradiance, total surface precipitation, and cloud cover in the meteorological prediction results, but is not limited to this.

[0073] In one optional embodiment, after correcting the first prediction result to obtain the meteorological correction result, the meteorological correction result and the aforementioned second prediction result can be used to predict the power generation of the wind turbine using the power prediction model. That is, the first prediction result and the second prediction result are input into the power prediction model, and the output result of the power prediction model is the aforementioned power generation.

[0074] It should be noted that the power prediction model mentioned above can refer to a conventional wind power prediction model, such as a wind speed and wind power prediction model based on SVM (Support Vector Machine), or a prediction model based on a neural network model or a deep learning model trained on historical meteorological data.

[0075] In this embodiment, the method involves obtaining meteorological forecast results of the location of the wind turbine; correcting the first forecast result in the meteorological forecast results to obtain a corrected meteorological result; and predicting the power generation of the wind turbine based on the second forecast result and the corrected meteorological result. By correcting the first forecast result in the meteorological forecast results, which can be monitored for changes in real time, and using the corrected meteorological result in combination with the second forecast result in the meteorological forecast results to predict the power generation of the wind turbine, the prediction accuracy of the power generation of the wind turbine is improved, thereby solving the technical problem of low prediction accuracy when predicting the power generation of wind turbines in related technologies.

[0076] Optionally, the meteorological forecast result includes forecast results corresponding to multiple meteorological elements. The first forecast result in the meteorological forecast result is corrected to obtain the meteorological correction result, which includes: obtaining the forecast result corresponding to the preset meteorological elements from the meteorological forecast result to obtain the first forecast result, wherein the preset meteorological elements are used to characterize the meteorological elements contained in the real-time monitored meteorological data; and correcting the first forecast result using a correction model to obtain the meteorological correction result, wherein the correction model is used to characterize the correlation between the first forecast result and the meteorological data.

[0077] The aforementioned preset meteorological elements can refer to multiple meteorological elements corresponding to the meteorological data that the wind turbine station can monitor in real time, such as the meteorological elements such as wind speed, wind direction, temperature, air pressure and humidity shown in the example in step S204 above.

[0078] The aforementioned correction model can refer to a model used to correct the first prediction result so that the first prediction result is close to the meteorological data monitored in real time by the station, or it can be used to represent the correlation between the first prediction result and the meteorological data monitored in real time by the station.

[0079] In one optional embodiment, the meteorological elements that the station can monitor can first be identified as the aforementioned preset meteorological elements. Then, the forecast results corresponding to the preset meteorological elements are selected from the aforementioned meteorological forecast results, and these forecast results are identified as the aforementioned first forecast result. Finally, the aforementioned correction model can be used to correct the first forecast result based on the meteorological data monitored by the station in real time, to obtain the aforementioned corrected meteorological result.

[0080] Optionally, the modified model is obtained by solving multiple conditional distributions separately. The multiple conditional distributions are obtained by decomposing the joint distribution probability corresponding to the preset meteorological elements. The joint distribution probability is constructed based on the directed graph, historical meteorological forecast results and historical meteorological data. The directed graph is used to represent the correlation between the preset meteorological elements, and the historical meteorological data is used to represent the meteorological data monitored at the historical time points corresponding to the historical meteorological forecast results.

[0081] The aforementioned conditional distribution can refer to the settings based on the correlation between various preset meteorological elements. The aforementioned directed graph can refer to an image used to represent the correlation between various preset meteorological elements. The aforementioned historical meteorological forecast results can refer to weather forecast data related to the station's coordinate location, selected from nationwide weather forecasts at multiple historical time points. The aforementioned historical meteorological data can refer to the meteorological data corresponding to the preset meteorological elements in the historical forecast results, monitored in real-time by the station at the aforementioned multiple historical time points.

[0082] In one optional embodiment, considering that the meteorological data actually monitored by the station may have problems such as high noise and many missing values, in order to improve the accuracy of correcting the first prediction result, the above-mentioned historical meteorological prediction results and historical meteorological data can be used to construct the above-mentioned correction model through the GPLAR method, and the correction model can be used to correct the first prediction result.

[0083] Specifically, firstly, a dataset can be constructed by obtaining the historical weather forecast results and historical weather data mentioned above. Based on the meteorological elements corresponding to the historical weather data, i.e. the aforementioned preset meteorological elements, a directed graph can be established. Next, the dataset can be input into the directed graph to determine the joint distribution probability corresponding to each preset meteorological element. Then, the joint distribution probability can be solved, decomposing the distribution probability into the product of several one-dimensional Gaussian functions, thereby determining the aforementioned conditional distribution, i.e., multiple one-dimensional Gaussian functions. Finally, the conditional distribution can be solved to determine the correction function used for data correction, and the aforementioned correction model can be constructed based on the correction function.

[0084] After constructing the correction model, the aforementioned first prediction result can be input into the correction model for correction, thereby obtaining the above-mentioned meteorological correction result.

[0085] Figure 3 This is a schematic diagram of a directed graph corresponding to preset meteorological elements according to Embodiment 1 of this application. Taking the preset meteorological elements as an example, these elements include temperature, humidity, air pressure, and wind speed. Figure 3 In this context, T represents temperature, R represents humidity, P represents air pressure, S represents wind speed, and x represents time. These meteorological elements are meteorological elements detected in real time at historical time points by the station.

[0086] like Figure 3 As shown, (1) represents the curve of temperature T changing with time x; (2) represents the curve of humidity R changing with time x; (3) represents the curve of air pressure P changing with time x; and (4) represents the curve of wind speed S changing with time x.

[0087] from Figure 3 As can be seen, a one-dimensional Gaussian function can be established for multiple preset meteorological elements based on the directed graph, and the joint distribution probability and the corresponding multiple conditional distributions can be determined to describe the correlation between different preset meteorological elements.

[0088] For example, we can establish a one-dimensional Gaussian function T(x) for temperature, a one-dimensional Gaussian function R(x) for humidity and temperature, a one-dimensional Gaussian function P(x) for air pressure and relative humidity and temperature, and a one-dimensional Gaussian function S(x) for wind speed and air pressure, humidity and temperature, etc.

[0089] like Figure 3 The formulas relating the various meteorological elements in the data can be:

[0090] R(x) = f1(T(x), x),

[0091] P(x) = f2(R(x), T(x), x),

[0092] S(x)=f3(P(x), R(x), T(x), x).

[0093] The corresponding joint probability distribution can be the product of the above multiple one-dimensional Gaussian functions, and the formula can be:

[0094] p(T(x), R(x), P(x), S(x))

[0095] =p(T(x))p(R(x)|T(x))p(P(x)|T(x), R(x))p(S(x)|T(x), R(x), P(x)),

[0096] It should be noted that the selection of the above-mentioned preset meteorological elements is only for illustrative purposes. The specific calculation process can be determined according to the actual situation and is not limited here.

[0097] Figure 4 This is a schematic diagram of a conditional distribution solution process according to Embodiment 1 of this application. This process can be a variational inference process. In an optional scheme of this embodiment, variational inference can be used to solve the above-mentioned conditional distribution. Figure 4 In this context, f1, f2, and f3 represent the specific formulas for calculating R(x), P(x), and S(x), while h1, h2, and h3 represent the operational parameters of each parameter in the formulas, such as operational relationships and operational coefficients. The specific solution process can adopt the solution process provided in related technologies, and this application does not impose any specific limitations on it.

[0098] Optionally, based on the second forecast result and the meteorological correction result in the meteorological forecast results, the power generation of the wind turbine is predicted, including: obtaining a first forecast time point; obtaining the forecast result corresponding to a preset time period from the second forecast result, and obtaining the correction result corresponding to the preset time period from the meteorological correction result, wherein the preset time period is determined based on the first forecast time point; inputting the forecast result corresponding to the preset time period and the correction result corresponding to the preset time period into the power prediction model to predict the power generation.

[0099] The aforementioned first prediction time point can refer to the time point at which wind power generation forecasting is needed. Generally, nationwide weather forecasts are sent at 2:00, 8:00, 14:00, and 20:00 Beijing time. Therefore, the first prediction time can be after these times, such as 21:00 Beijing time. The aforementioned preset time period can refer to the time interval corresponding to a preset time range before and after the first preset time point. For example, a preset time interval of 30 minutes before and after 21:00 Beijing time. The aforementioned power prediction model can refer to the prediction model trained based on historical meteorological data.

[0100] In one optional embodiment, the forecast results and correction results corresponding to the preset time period can be filtered out from the meteorological correction results and the second forecast results, and the forecast results and correction results after secondary filtering can be input into the power prediction model to predict the power generation of the wind turbine.

[0101] Specifically, in order to improve the efficiency and accuracy of power prediction, single-point prediction of power generation can be performed, that is, prediction is only made for the power generation at the first prediction time point. In order to further improve the accuracy of the prediction results, the second prediction results and correction results within the neighborhood before and after the first prediction time point, that is, within the aforementioned preset time period, can also be applied to the prediction of power generation.

[0102] Optionally, the power prediction model includes an encoder module and a decoder module. The prediction result and the correction result corresponding to the preset time period are input into the power prediction model to predict the power generation. This includes: using the encoder module to extract features from the prediction result and the correction result corresponding to the preset time period to obtain meteorological features; and using the decoder module to reconstruct the power generation based on the meteorological features to obtain the power generation.

[0103] The encoder module described above is based on a TCN (Temporal Convolutional Network) and features a multi-layer dilated convolutional structure. The decoder module described above is a decoder with a two-layer MLP (Multilayer Perceptron) structure.

[0104] In one optional embodiment, when processing the prediction and correction results corresponding to a preset time period using a power prediction model, the prediction and correction results can first be adjusted and extracted by an encoder based on a temporal convolutional network to determine their respective meteorological characteristics. Then, a decoder with a dual-layer mechanism can be used to reconstruct the power of the meteorological characteristics to obtain the aforementioned power generation.

[0105] Optionally, the power prediction model is trained using measured power at historical prediction time points and historical meteorological correction results, which are obtained by correcting the historical meteorological prediction results using the correction model.

[0106] The aforementioned historical forecast time points can refer to multiple times prior to the current time when meteorological forecast results were received, such as multiple time points corresponding to the previous 20 days. The aforementioned measured power can refer to the measured wind power generation capacity. The aforementioned historical meteorological correction results can refer to the results obtained by correcting historical meteorological forecast results using a correction model.

[0107] In one optional embodiment, multiple measured power values ​​corresponding to multiple historical time points, as well as historical meteorological correction results for multiple historical time points, can be used to train a preset prediction model to obtain the aforementioned power prediction model.

[0108] In one optional embodiment, when training the preset prediction model, the loss function used can be MSE (Mean Squared Error), so that the power generation output by the power prediction model is more consistent with the actual situation.

[0109] In other words, the meteorological correction results and measured power obtained in the previous period can be used to train the current prediction model for predicting power generation in the future in real time, so as to obtain the power prediction model mentioned above.

[0110] Optionally, obtaining the meteorological forecast results for the location of the wind turbine includes: obtaining a preset meteorological forecast result, a second preset time, and the geographical location of the wind turbine, wherein the preset meteorological forecast result includes forecast results for different regions within different time periods; and determining the meteorological forecast result from the preset meteorological forecast result based on the geographical location and the second preset time.

[0111] The aforementioned preset meteorological forecast results can refer to multiple meteorological forecast results corresponding to different times and different regions, such as the aforementioned nationwide weather forecast. The aforementioned different time periods can refer to the times when the preset meteorological forecasts are sent daily, such as the aforementioned 2:00 AM, 8:00 AM, 2:00 PM, and 8:00 PM Beijing time each day. The aforementioned second preset time can refer to the time when the power generation forecast results need to be reported, such as 8:00 AM Beijing time each day.

[0112] Generally, when obtaining the meteorological forecast results corresponding to the wind turbine, the above-mentioned meteorological forecast results can be selected from the preset meteorological forecast results, such as the weather forecast covering the whole country, based on the coordinate location of the wind turbine, i.e. the geographical location of the wind turbine, and the second preset time.

[0113] In one optional embodiment, in order to improve the accuracy of the predicted power generation, in addition to directly obtaining the meteorological forecast results corresponding to the geographical location of the wind turbine, the meteorological forecast results of the area near the wind turbine can also be obtained as input for predicting the power generation of the wind turbine.

[0114] For example, the surrounding area centered on the geographical location of the wind turbine and with a preset distance as the radius can be gridded, and the geographical locations of multiple grid points can be determined. When obtaining the above-mentioned meteorological forecast results, the meteorological forecast results corresponding to each grid point can be selected from the preset meteorological forecast results based on the geographical locations of multiple grid points and the second preset time mentioned above.

[0115] Optionally, based on geographical location and a second preset time, the meteorological forecast result is determined from the preset meteorological forecast results, including: generating screening conditions based on different time periods and the second preset time; determining the target forecast result that meets the screening conditions from the preset meteorological forecast results; and determining the forecast result corresponding to the geographical location area from the target forecast result to obtain the meteorological forecast result.

[0116] The above-mentioned screening criteria can refer to the conditions used to select meteorological forecast results from preset meteorological forecast results.

[0117] In one optional embodiment, the above-mentioned filtering conditions may include, but are not limited to: preset weather forecast results for a specified time period, specified meteorological elements, preset weather forecast results within a specified numerical range, etc.

[0118] For example, if the second preset time is the 5th, and the different time periods refer to the preset weather forecast results from 6 pm to 10 pm, then one of the above filtering conditions could be to obtain the weather forecast results at 8 pm on the 4th.

[0119] In one optional embodiment, when determining the weather forecast result from the preset weather forecast results, the above-mentioned filtering conditions can be generated first according to different time periods and a second preset time. Then, the target forecast result that meets the filtering conditions can be determined from the preset weather forecast results. Finally, the corresponding weather forecast result can be determined from the target forecast result according to the geographical location of the wind turbine.

[0120] Optionally, the method further includes: determining the difference between the first forecast result and the meteorological correction result; determining the display method of the meteorological correction result based on the difference; and outputting the meteorological correction result based on the display method.

[0121] The aforementioned display methods refer to those that clearly demonstrate changes in the weather correction results. For example, different colors, font sizes, and font backgrounds can be used to display the rise and fall of power generation. It should be noted that the above display methods are merely illustrative examples. In practical applications, it is sufficient to clearly demonstrate the difference between the weather correction results and the initial forecast results; no specific limitations are imposed here.

[0122] For example, the weather correction results when power generation increases can be displayed in large green font, while the weather correction results when power generation decreases can be displayed in small red font.

[0123] Specifically, to facilitate staff viewing of the correction results and improve their work efficiency, the first forecast result and the meteorological correction result can be compared to determine the difference between them. The display method of the meteorological correction result is determined according to the magnitude of the difference. For example, if the difference is positive, it means that the meteorological correction result is less than the first forecast result, and the current meteorological correction result can be displayed in the second color mentioned above, such as red. If the difference is negative or 0, it means that the meteorological correction result is greater than or equal to the first forecast result, and the current meteorological correction result can be displayed in the second color mentioned above, such as green.

[0124] For ease of understanding, the above-mentioned method for processing the entire power generation capacity can be divided into two parts. One part is the construction of the correction model and the training of the power prediction model. This part can be completed in the offline mode of the power generation capacity processing system to reduce the occupation of system resources. The other part is the prediction of power generation capacity using the correction model and the power prediction model. This part can be completed in the online mode of the power generation capacity processing system, so that staff can observe the power prediction results in real time and make manual judgments on the prediction results, thereby further improving the accuracy of the predicted power generation capacity of wind turbines.

[0125] In one optional embodiment, the offline components such as the modified model and the trained power prediction model can be deployed on a preset cloud server or client server. The server can train and update these models on a daily basis and use these models to predict the power generation of wind turbines.

[0126] In one optional embodiment, the processing system can predict power generation in both offline and online modes. Figure 5 This is a flowchart of a processing system for offline operation according to Embodiment 1 of this application, as follows: Figure 5 As shown, when the processing system is in offline mode, it can process parameters such as historical weather forecast results, actual monitored historical weather data, and historical measured power to obtain the corrected model and the power prediction model.

[0127] like Figure 5As shown, a dataset can be constructed first based on historical weather forecast results. A directed graph can be established based on the meteorological elements in the historical weather forecast results. The dataset can be input into the directed graph to determine the joint distribution probability corresponding to each meteorological element. Then, the joint distribution probability can be solved to obtain multiple conditional distributions. Finally, the multiple conditional distributions can be solved to determine the correction function used for data correction. Based on the correction function, the above correction model can be constructed.

[0128] After constructing the correction function, it can be used in conjunction with the historical meteorological data actually monitored above to correct the historical meteorological forecast results above, and then the historical meteorological correction results and the historical measured power above can be used to train the preset prediction model to obtain the power prediction model above.

[0129] Figure 6 This is a flowchart of an online processing system according to Embodiment 1 of this application, such as... Figure 6 As shown, when the processing system is in online mode, it can directly preprocess the acquired meteorological forecast results, determine the first forecast result and the second forecast result from the meteorological forecast results, and then use the correction model trained in offline mode to correct the first meteorological forecast result to obtain the meteorological correction result. Then, the meteorological correction result and the second meteorological forecast result can be further input into the power prediction model trained in offline mode to predict the power generation of the wind turbine.

[0130] 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.

[0131] 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, and of course, they can also be implemented by hardware. 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 of the various embodiments of this application.

[0132] Example 2

[0133] According to an embodiment of this application, a method for processing power generation is also 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.

[0134] Figure 7 This is a flowchart of a power generation processing method according to Embodiment 2 of this application, as shown below. Figure 7 As shown, the method may include the following steps:

[0135] Step S702: In response to the input command applied to the operation interface, display the weather forecast results of the location of the wind turbine on the operation interface.

[0136] The aforementioned input command may refer to a command used to obtain meteorological forecast results for the location of the wind turbine.

[0137] The location of the aforementioned wind turbine may refer to the coordinates of the site where power generation prediction is performed.

[0138] In one optional embodiment, in order to facilitate staff to check whether the obtained meteorological forecast results are valid and can be used to predict the power generation of wind turbines, the processing system can display the meteorological forecast results on the operation interface after obtaining the above-mentioned meteorological forecast results.

[0139] Figure 8 This is a schematic diagram of an operation interface according to Embodiment 2 of this application, as shown below. Figure 8 As shown, the operation interface 800 includes at least an instruction input interface 802 and a result display interface 804. The input interface 802 may also include multiple controls for inputting instructions, such as buttons 8022 and 8024 in the figure, as well as an area 8026 for inputting instruction information.

[0140] In one optional embodiment, after the user has entered the required operation command in area 8026, the operation command can be input into the processing system by pressing button 8022.

[0141] Step S704: In response to the power prediction command applied to the operation interface, the power generation of the wind turbine is displayed on the operation interface.

[0142] The power generation is predicted based on the second forecast result and the meteorological correction result in the meteorological forecast results. The meteorological correction result is obtained by correcting the first forecast result in the meteorological forecast results. The second forecast result is used to characterize the forecast results in the meteorological forecast results other than the first forecast result.

[0143] The aforementioned power forecasting command can refer to a command that predicts the power generation capacity of wind turbines based on meteorological forecasts. For example, such as... Figure 8 As shown, after a user inputs a power prediction command in area 8026, the command can be input into the processing system by pressing button 8024.

[0144] In one optional embodiment, to facilitate users to quickly predict and view power generation, button 8024 can be set as a shortcut button, and users can generate the above-mentioned power prediction command by directly pressing button 8024.

[0145] The aforementioned first forecast result can refer to the forecast result corresponding to some meteorological elements in the meteorological forecast result, or it can refer to the forecast result corresponding to all meteorological elements. The aforementioned second forecast result can refer to the result in the meteorological forecast result other than the first forecast result.

[0146] In one optional embodiment, to facilitate staff checking whether the predicted power generation is normal, the processing system can display the predicted power generation value on the operation interface after predicting the power generation.

[0147] In one optional embodiment, since the obtained meteorological forecast results are obtained through manual numerical calculations, there will be certain errors. Therefore, in order to improve the accuracy of the predicted power generation, the meteorological data monitored in real time at the wind turbine site can be used to correct the meteorological forecast results. However, since the number of meteorological elements corresponding to the meteorological data monitored in real time at the site is less than the number of meteorological elements in the meteorological forecast results, the meteorological data monitored in real time at the site may only be used to correct part of the meteorological forecast results. This part of the meteorological forecast results is the first forecast result mentioned above.

[0148] Therefore, the process of predicting the power generation of wind turbines can be as follows: First, the first prediction result is corrected based on the meteorological data monitored in real time at the wind farm, resulting in a corrected result. Then, using the corrected result and the second prediction result, a power prediction model is used to predict the power generation of the wind turbines. It should be noted that the aforementioned power prediction model can refer to a conventional wind power prediction model, such as a wind speed and wind power prediction model based on SVM (Support Vector Machine), or it can be a prediction model trained based on historical meteorological data. The specific process of using meteorological data to train the prediction model in real time to predict the starting power of wind turbines is shown in Example 1.

[0149] It should be noted that the preferred implementation schemes involved in the above embodiments of this application are the same as the schemes, application scenarios and implementation processes provided in Embodiment 1, but are not limited to the schemes provided in Embodiment 1.

[0150] Example 3

[0151] According to an embodiment of this application, a method for processing power generation is also 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.

[0152] Figure 9 This is a flowchart of a power generation processing method according to Embodiment 3 of this application, as shown below. Figure 9 As shown, the method may include the following steps:

[0153] Step S902: Obtain the meteorological forecast results of the location of the wind turbine by calling the first interface.

[0154] The first interface includes a first parameter, the value of which is the weather forecast result.

[0155] The first result mentioned above may refer to the interface used to obtain meteorological forecast results.

[0156] The location of the aforementioned wind turbine may refer to the coordinates of the site where power generation prediction is performed.

[0157] In one optional embodiment, the weather forecast for the location of the wind turbine can be obtained from preset weather forecast results via a first interface. The preset weather forecast results can refer to multiple weather forecasts corresponding to different times and regions, such as the aforementioned nationwide weather forecast.

[0158] Step S904: Correct the first forecast result in the meteorological forecast results to obtain the corrected meteorological result.

[0159] The aforementioned first forecast result can refer to the forecast result corresponding to some meteorological elements in the meteorological forecast result, or it can refer to the forecast result corresponding to all meteorological elements.

[0160] In one optional aspect of this embodiment, since the obtained meteorological forecast results are obtained through manual numerical calculations, there will be certain errors. Therefore, the meteorological data monitored in real time by the station can be used to correct the meteorological forecast results.

[0161] Since the number of meteorological elements in the real-time monitored meteorological data is less than the number of meteorological elements in the meteorological forecast results, the results in the meteorological forecast results that correspond to the meteorological elements in the real-time monitored meteorological data can be used as the first forecast result mentioned above. The first forecast result can then be corrected using the real-time monitored meteorological data to obtain the corrected meteorological result.

[0162] Step S906: Based on the second forecast result and the weather correction result in the weather forecast results, the power generation capacity of the wind turbine is predicted.

[0163] The second forecast result is used to characterize the forecast results other than the first forecast result in the meteorological forecast results.

[0164] The aforementioned second forecast result can refer to the result other than the first forecast result in the meteorological forecast result, that is, the forecast result corresponding to the element that the station cannot monitor in real time among the multiple elements corresponding to the meteorological forecast result.

[0165] In one optional embodiment, after correcting the first prediction result to obtain a meteorological correction result, the meteorological correction result and the aforementioned second prediction result can be used to predict the power generation of the wind turbine using a power prediction model. It should be noted that the aforementioned power prediction model can refer to a conventional wind power prediction model, such as a wind speed and wind power prediction model based on SVM (Support Vector Machine), or a prediction model trained based on historical meteorological data. The specific process of using meteorological data to train the prediction model in real time to predict the wind turbine's starting power is shown in Embodiment 1.

[0166] Step S908: Output power generation by calling the second interface.

[0167] The second interface includes a second parameter, the value of which is the power generation capacity.

[0168] The second interface mentioned above may refer to the interface used to output the predicted power generation.

[0169] In one alternative embodiment, after processing the second prediction result and the meteorological correction result to obtain the power generation of the wind turbine, the power generation can be output by calling the second result.

[0170] It should be noted that the preferred implementation schemes involved in the above embodiments of this application are the same as the schemes, application scenarios and implementation processes provided in Embodiment 1, but are not limited to the schemes provided in Embodiment 1.

[0171] Example 4

[0172] According to an embodiment of this application, a method for processing power generation is also 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.

[0173] Figure 10 This is a flowchart of a power generation processing method according to Embodiment 4 of this application, as shown below. Figure 10 As shown, the method may include the following steps:

[0174] In step S1002, the cloud server receives the location information sent by the client.

[0175] Location information is used to characterize the location of the wind turbine.

[0176] The location information sent by the aforementioned client may refer to the coordinates of the power plant where power generation prediction is performed.

[0177] In one optional embodiment, before predicting the power generation of the wind turbine, the cloud server can first send a location query command to the client, and then receive the location information sent by the client.

[0178] Step S1004: The cloud server obtains the weather forecast results corresponding to the location information.

[0179] The above meteorological forecast results may refer to weather forecast data within the vicinity of the coordinate location, such as within a range centered on the coordinate location and with a preset distance as the radius.

[0180] After receiving the location information sent by the client, the cloud server can obtain the corresponding weather forecast results based on the location information.

[0181] In one optional embodiment, meteorological data related to the coordinates of the station can be directly filtered from the nationwide weather forecast to serve as the meteorological forecast result. This can improve the efficiency of obtaining meteorological forecast results, reduce the workload of staff and the cost of obtaining meteorological forecast results, and also improve the applicability of the obtained meteorological forecast data.

[0182] Step S1006: The cloud server corrects the first forecast result in the weather forecast results to obtain the corrected weather forecast result.

[0183] The aforementioned first forecast result can refer to the forecast result corresponding to some meteorological elements in the meteorological forecast result, or it can refer to the forecast result corresponding to all meteorological elements.

[0184] In one optional solution of this embodiment, since the obtained meteorological forecast results are obtained by manual numerical calculation, there will be certain errors. Therefore, the meteorological forecast results can be corrected by using meteorological data monitored in real time by the station in the cloud server.

[0185] Since the number of meteorological elements in the real-time monitored meteorological data is less than the number of meteorological elements in the meteorological forecast results, the results in the meteorological forecast results that correspond to the meteorological elements in the real-time monitored meteorological data can be used as the first forecast result mentioned above. The first forecast result can then be corrected using the real-time monitored meteorological data to obtain the corrected meteorological result.

[0186] In step S1008, the cloud server predicts the power generation capacity of the wind turbine based on the second forecast result and the weather correction result in the weather forecast results.

[0187] The second forecast result is used to characterize the forecast results other than the first forecast result in the meteorological forecast results. That is, among the multiple elements corresponding to the meteorological forecast results, the forecast results corresponding to the elements that the station cannot monitor in real time.

[0188] In one optional embodiment, after correcting the first prediction result to obtain a meteorological correction result, the meteorological correction result and the aforementioned second prediction result can be used to predict the power generation of the wind turbine using a power prediction model. It should be noted that the aforementioned power prediction model can refer to a conventional wind power prediction model, such as a wind speed and wind power prediction model based on SVM (Support Vector Machine), or a prediction model trained based on historical meteorological data. The specific process of using meteorological data to train the prediction model in real time to predict the wind turbine's starting power is shown in Embodiment 1.

[0189] In step S1010, the cloud server sends the power generation capacity to the client.

[0190] The generated power is used to control the wind turbine.

[0191] In one optional embodiment, after the cloud server predicts the power generation, it can send the power generation to the corresponding client, and the client can control the wind turbine to operate according to the power generation.

[0192] To clearly demonstrate the interaction between the cloud server and the client, Figure 11 This is a schematic diagram of a power prediction server interaction according to Embodiment 4 of this application.

[0193] like Figure 11 As shown, for wind turbines that require power generation prediction, the cloud server can first send a first instruction to the client to obtain location information. After receiving the first instruction, the client can collect the location information of the wind turbine site for predicting the power generation of the wind turbine, and then send the location information to the cloud server.

[0194] After receiving location information, the cloud server can first retrieve the corresponding weather forecast from a pre-set database. For example, it can directly filter out meteorological data related to the coordinates from nationwide weather forecasts as the weather forecast result. Then, the cloud server can use historical meteorological data to correct the meteorological data corresponding to the meteorological elements that the stations can monitor in real time in the weather forecast result, i.e., the first forecast result, to obtain the corrected weather forecast result. Finally, it uses the time periods corresponding to other meteorological elements in the weather forecast result, i.e., the second forecast result, and combines it with the corrected weather forecast result to predict the power generation of the wind turbine.

[0195] After predicting the power output of the wind turbine, the cloud server can send the power output to the client, and the client can control the corresponding wind turbine to operate based on the power output.

[0196] Predicting the power output of wind turbines through multi-terminal interaction avoids the problem of inaccurate prediction results caused by limited prediction data obtained by a single client, thereby improving the accuracy of the predicted power output of wind turbines.

[0197] It should be noted that the preferred implementation schemes involved in the above embodiments of this application are the same as the schemes, application scenarios and implementation processes provided in Embodiment 1, but are not limited to the schemes provided in Embodiment 1.

[0198] Example 5

[0199] According to an embodiment of this application, a power generation processing apparatus for implementing the above-described power generation processing method is also provided, which can be deployed in a target client. Figure 12 This is a structural block diagram of a power generation processing device according to Embodiment 5 of this application, as shown below. Figure 12 As shown, the device 1200 includes: an acquisition module 1202, a correction module 1204, and a prediction module 1206.

[0200] The acquisition module 1202 is used to acquire the meteorological forecast results of the location of the wind turbine generator; the correction module 1204 is used to correct the first forecast result in the meteorological forecast results to obtain the meteorological correction result; the prediction module 1206 is used to predict the power generation of the wind turbine generator based on the second forecast result and the meteorological correction result in the meteorological forecast results, wherein the second forecast result is used to characterize the forecast results in the meteorological forecast results other than the first forecast result.

[0201] It should be noted that the acquisition module 1202, correction module 1204, and prediction module 1206 mentioned above correspond to steps S202 to S206 in Embodiment 1. The three modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 124) and processed by one or more processors (e.g., processors 122a, 122b, ..., 122n). The above modules can also be part of a device and run in the computer terminal 12 provided in Embodiment 1.

[0202] In the above embodiments of this application, the meteorological forecast result includes forecast results corresponding to multiple meteorological elements. The correction module 1204 includes: a first acquisition unit, used to acquire forecast results corresponding to preset meteorological elements from the meteorological forecast result to obtain a first forecast result, wherein the preset meteorological elements are used to characterize the meteorological elements contained in the real-time monitored meteorological data; and a meteorological correction unit, used to correct the first forecast result using a correction model to obtain a meteorological correction result, wherein the correction model is used to characterize the correlation between the first forecast result and the meteorological data.

[0203] In the above embodiments of this application, the correction model is obtained by solving multiple conditional distributions separately. The multiple conditional distributions are obtained by decomposing the joint distribution probability corresponding to the preset meteorological elements. The joint distribution probability is constructed based on the directed graph, historical meteorological forecast results and historical meteorological data. The directed graph is used to represent the correlation between the preset meteorological elements, and the historical meteorological data is used to represent the meteorological data monitored at the historical time points corresponding to the historical meteorological forecast results.

[0204] In the above embodiments of this application, the prediction module 1206 includes: a second acquisition unit, used to acquire a first prediction time point; a third acquisition unit, used to acquire the prediction result corresponding to a preset time period from the second prediction result, and acquire the correction result corresponding to the preset time period from the meteorological correction result, wherein the preset time period is determined based on the first prediction time point; and a power prediction unit, used to input the prediction result corresponding to the preset time period and the correction result corresponding to the preset time period into the power prediction model to predict the power generation.

[0205] In the above embodiments of this application, the power prediction model includes an encoder module and a decoder module. The power prediction unit is further used to: extract features from the prediction results and correction results corresponding to a preset time period using the encoder module to obtain meteorological features; and reconstruct power based on the meteorological features using the decoder module to obtain the power generation.

[0206] In the above embodiments of this application, the power prediction model is trained using the measured power at the historical prediction time points and the historical meteorological correction results. The historical meteorological correction results are obtained by correcting the historical meteorological prediction results using the correction model.

[0207] In the above embodiments of this application, the acquisition module 1202 includes: a fourth acquisition unit, used to acquire a preset weather forecast result, a second preset time, and the geographical location of the wind turbine, wherein the preset weather forecast result includes forecast results for different regions within different time periods; and a determination unit, used to determine a weather forecast result from the preset weather forecast result based on the geographical location and the second preset time.

[0208] In the above embodiments of this application, the determining unit is further configured to: generate filtering conditions based on different time periods and a second preset time; determine the target prediction results that meet the filtering conditions in the preset meteorological prediction results; determine the prediction results corresponding to the geographical location area from the target prediction results, and obtain the meteorological prediction results.

[0209] In the above embodiments of this application, the device further includes: a difference determination module, used to determine the difference between the first forecast result and the meteorological correction result; a display mode determination module, used to determine the display mode of the meteorological correction result based on the difference; and a result output module, used to output the meteorological correction result based on the display mode.

[0210] Example 6

[0211] According to an embodiment of this application, a power generation processing apparatus for implementing the above-described power generation processing method is also provided, which can be deployed in a target client. Figure 13 This is a structural block diagram of a power generation processing device according to Embodiment 6 of this application, as shown below. Figure 13As shown, the device 1300 includes: a first display module 1302 and a second display module 1304.

[0212] The first display module 1302 is used to respond to input commands applied to the operation interface and display the weather forecast results of the location of the wind turbine on the operation interface; the second display module 1304 is used to respond to power forecast commands applied to the operation interface and display the power generation of the wind turbine on the operation interface. The power generation is predicted based on the second forecast result and the weather correction result in the weather forecast results. The weather correction result is obtained by correcting the first forecast result in the weather forecast results. The second forecast result is used to characterize the forecast results other than the first forecast result in the weather forecast results.

[0213] It should be noted that the first display module 1302 and the second display module 1304 mentioned above correspond to steps S702 to S704 in Embodiment 2. The two modules and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware components or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above modules can also be part of the device and run in the computer terminal 10 provided in Embodiment 1.

[0214] Example 7

[0215] According to an embodiment of this application, a power generation processing apparatus for implementing the above-described power generation processing method is also provided, which can be deployed in a target client. Figure 14 This is a structural block diagram of a power generation processing device according to Embodiment 7 of this application, as shown below. Figure 14 As shown, the device 1400 includes: a result acquisition module 1402, a result correction module 1404, a power prediction module 1406, and an output module 1108.

[0216] The result acquisition module 1402 is used to acquire the meteorological forecast result of the location of the wind turbine by calling a first interface, wherein the first interface includes a first parameter and the parameter value of the first parameter is the meteorological forecast result; the result correction module 1404 is used to correct the first forecast result in the meteorological forecast result to obtain the meteorological correction result; the power prediction module 1406 is used to predict the power generation of the wind turbine based on the second forecast result and the meteorological correction result in the meteorological forecast result, wherein the second forecast result is used to characterize the forecast result other than the first forecast result in the meteorological forecast result; and the output module 1108 is used to output the power generation by calling a second interface, wherein the second interface includes a second parameter and the parameter value of the second parameter is the power generation.

[0217] It should be noted that the result acquisition module 1402, result correction module 1404, power prediction module 1406, and output module 1408 mentioned above correspond to steps S902 to S904 in Embodiment 3. The two modules and the corresponding steps implement the same examples and application scenarios, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware components or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above modules can also be part of the device and run in the computer terminal 10 provided in Embodiment 1.

[0218] Example 8

[0219] According to an embodiment of this application, a power generation processing apparatus for implementing the above-described power generation processing method is also provided, which can be deployed in a target client. Figure 15 This is a structural block diagram of a power generation processing device according to Embodiment 8 of this application, as shown below. Figure 15 As shown, the device 1500 includes: a receiving module 1502, an acquisition module 1504, a correction module 1506, a prediction module 1508, and a sending module 1510.

[0220] The cloud server receives location information sent by the client, where the location information represents the location of the wind turbine. The cloud server obtains the meteorological forecast result corresponding to the location information. The cloud server corrects the first forecast result in the meteorological forecast result to obtain the corrected meteorological result. The cloud server predicts the power generation of the wind turbine based on the second forecast result and the corrected meteorological result, where the second forecast result represents the forecast result other than the first forecast result. The cloud server sends the power generation to the client, where the power generation is used to control the wind turbine.

[0221] It should be noted that the receiving module 1502, acquiring module 1504, correcting module 1506, predicting module 1508, and sending module 1510 mentioned above correspond to steps S1002 to S1010 in Embodiment 4. The two modules and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware components or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above modules can also be part of the device and run in the computer terminal 10 provided in Embodiment 1.

[0222] Example 9

[0223] Embodiments of this application may provide an electronic device, which may be any one of a group of electronic devices. Optionally, in this embodiment, the aforementioned electronic device may also be replaced by a terminal device such as a mobile terminal.

[0224] Optionally, in this embodiment, the aforementioned electronic device may be located in at least one of a plurality of network devices in a computer network.

[0225] In this embodiment, the above-mentioned electronic device can execute the program code of the following steps in the design parameter adjustment method: obtaining the meteorological forecast result of the location of the wind turbine generator; correcting the first forecast result in the meteorological forecast result to obtain the meteorological correction result; and predicting the power generation of the wind turbine generator based on the second forecast result and the meteorological correction result in the meteorological forecast result, wherein the second forecast result is used to characterize the forecast results in the meteorological forecast result other than the first forecast result.

[0226] Optionally, Figure 16This is a structural block diagram of an electronic device according to Embodiment 9 of this application. As shown in the figure, the electronic device A may include: a processor 1602 and a memory 1604, wherein an executable program is stored; the processor is used to run the program, wherein the program executes the power generation processing method shown in Embodiment 1 when it runs.

[0227] Optionally, such as Figure 16 As shown, electronic device A may also include a storage controller and a peripheral interface, wherein the peripheral interface is connected to the radio frequency module, the audio module and the display.

[0228] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the power generation processing method and apparatus in this application embodiment. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned power generation processing method. The memory 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 may further include memory remotely located relative to the processor, and these remote memories can be connected to terminal A via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0229] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: obtain the weather forecast results of the location of the wind turbine; correct the first forecast result in the weather forecast results to obtain the weather correction result; predict the power generation of the wind turbine based on the second forecast result and the weather correction result in the weather forecast results, wherein the second forecast result is used to characterize the forecast results in the weather forecast results other than the first forecast result.

[0230] Optionally, the processor may also execute program code for the following steps: the meteorological forecast result contains forecast results corresponding to multiple meteorological elements, and the first forecast result in the meteorological forecast result is corrected to obtain a meteorological correction result, including: obtaining the forecast result corresponding to a preset meteorological element from the meteorological forecast result to obtain the first forecast result, wherein the preset meteorological element is used to characterize the meteorological elements contained in the real-time monitored meteorological data; and correcting the first forecast result using a correction model to obtain the meteorological correction result, wherein the correction model is used to characterize the correlation between the first forecast result and the meteorological data.

[0231] Optionally, the processor may also execute program code for the following steps: the modified model is obtained by solving multiple conditional distributions separately. The multiple conditional distributions are obtained by decomposing the joint distribution probability corresponding to the preset meteorological elements. The joint distribution probability is constructed based on the directed graph, historical meteorological forecast results and historical meteorological data. The directed graph is used to represent the correlation between the preset meteorological elements, and the historical meteorological data is used to represent the meteorological data monitored at the historical time points corresponding to the historical meteorological forecast results.

[0232] Optionally, the processor may also execute program code for the following steps: predicting the power generation of the wind turbine based on the second prediction result and the meteorological correction result in the meteorological forecast results, including: obtaining a first prediction time point; obtaining the prediction result corresponding to a preset time period from the second prediction result, and obtaining the correction result corresponding to the preset time period from the meteorological correction result, wherein the preset time period is determined based on the first prediction time point; inputting the prediction result corresponding to the preset time period and the correction result corresponding to the preset time period into the power prediction model to predict the power generation.

[0233] Optionally, the processor may also execute program code for the following steps: The power prediction model includes an encoder module and a decoder module, which input the prediction results and correction results corresponding to the preset time period into the power prediction model to predict the power generation, including: using the encoder module to extract features from the prediction results and correction results corresponding to the preset time period to obtain meteorological features; and using the decoder module to reconstruct the power based on the meteorological features to obtain the power generation.

[0234] Optionally, the processor may also execute program code for the following steps: the power prediction model is trained using measured power at historical prediction time points and historical meteorological correction results, and the historical meteorological correction results are obtained by correcting the historical meteorological prediction results using the correction model.

[0235] Optionally, the processor may also execute program code for the following steps: obtaining meteorological forecast results for the location of the wind turbine, including: obtaining a preset meteorological forecast result, a second preset time, and the geographical location of the wind turbine, wherein the preset meteorological forecast result includes forecast results for different regions within different time periods; and determining the meteorological forecast result from the preset meteorological forecast result based on the geographical location and the second preset time.

[0236] Optionally, the processor may also execute program code for the following steps: determining a meteorological forecast result from preset meteorological forecast results based on geographical location and a second preset time, including: generating filtering conditions based on different time periods and a second preset time; determining target forecast results that meet the filtering conditions from the preset meteorological forecast results; determining the forecast result corresponding to the geographical location from the target forecast results, and obtaining the meteorological forecast result.

[0237] Optionally, the processor may also execute program code that performs the following steps: determining the difference between the first forecast result and the weather correction result; determining the display method of the weather correction result based on the difference; and outputting the weather correction result based on the display method.

[0238] In this embodiment, the method involves obtaining meteorological forecast results of the location of the wind turbine; correcting the first forecast result in the meteorological forecast results to obtain a corrected meteorological result; and predicting the power generation of the wind turbine based on the second forecast result and the corrected meteorological result. By correcting the first forecast result in the meteorological forecast results, which can be monitored for changes in real time, and using the corrected meteorological result in combination with the second forecast result in the meteorological forecast results to predict the power generation of the wind turbine, the prediction accuracy of the power generation of the wind turbine is improved, thereby solving the technical problem of low prediction accuracy when predicting the power generation of wind turbines in related technologies.

[0239] Those skilled in the art will understand that Figure 16 The structure shown is for illustrative purposes only. The computer terminal can also be a smartphone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (MID), a PAD, and other terminal devices. Figure 16 This does not limit the structure of the aforementioned electronic device. For example, computer terminal A may also include components that are more... Figure 16 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 16 The different configurations shown.

[0240] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0241] Example 10

[0242] Embodiments of this application also provide a computer-readable storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the power generation processing method provided in Embodiment 1.

[0243] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0244] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: obtaining the meteorological forecast results of the location of the wind turbine; correcting the first forecast result in the meteorological forecast results to obtain the meteorological correction result; and predicting the power generation of the wind turbine based on the second forecast result and the meteorological correction result in the meteorological forecast results, wherein the second forecast result is used to characterize the forecast results in the meteorological forecast results other than the first forecast result.

[0245] Optionally, the aforementioned storage medium may also execute program code for the following steps: the meteorological forecast result contains forecast results corresponding to multiple meteorological elements; the first forecast result in the meteorological forecast result is corrected to obtain a meteorological correction result, including: obtaining the forecast result corresponding to a preset meteorological element from the meteorological forecast result to obtain the first forecast result, wherein the preset meteorological element is used to characterize the meteorological elements contained in the real-time monitored meteorological data; and correcting the first forecast result using a correction model to obtain the meteorological correction result, wherein the correction model is used to characterize the correlation between the first forecast result and the meteorological data.

[0246] Optionally, the above storage medium may also execute program code for the following steps: the modified model is obtained by solving multiple conditional distributions separately. The multiple conditional distributions are obtained by decomposing the joint distribution probability corresponding to the preset meteorological elements. The joint distribution probability is constructed based on the directed graph, historical meteorological forecast results and historical meteorological data. The directed graph is used to represent the correlation between the preset meteorological elements, and the historical meteorological data is used to represent the meteorological data monitored at the historical time points corresponding to the historical meteorological forecast results.

[0247] Optionally, the aforementioned storage medium may also execute program code for the following steps: predicting the power generation of the wind turbine based on the second prediction result and the meteorological correction result in the meteorological forecast results, including: obtaining a first prediction time point; obtaining the prediction result corresponding to a preset time period from the second prediction result, and obtaining the correction result corresponding to the preset time period from the meteorological correction result, wherein the preset time period is determined based on the first prediction time point; inputting the prediction result corresponding to the preset time period and the correction result corresponding to the preset time period into the power prediction model to predict the power generation.

[0248] Optionally, the above storage medium may also execute program code for the following steps: The power prediction model includes an encoder module and a decoder module, which input the prediction results and correction results corresponding to the preset time period into the power prediction model to predict the power generation, including: using the encoder module to extract features from the prediction results and correction results corresponding to the preset time period to obtain meteorological features; and using the decoder module to reconstruct the power based on the meteorological features to obtain the power generation.

[0249] Optionally, the aforementioned storage medium may also execute program code for the following steps: the power prediction model is trained using measured power at historical prediction time points and historical meteorological correction results, and the historical meteorological correction results are obtained by correcting the historical meteorological prediction results using the correction model.

[0250] Optionally, the storage medium may also execute program code for the following steps: obtaining meteorological forecast results for the location of the wind turbine, including: obtaining a preset meteorological forecast result, a second preset time, and the geographical location of the wind turbine, wherein the preset meteorological forecast result includes forecast results for different regions within different time periods; and determining the meteorological forecast result from the preset meteorological forecast result based on the geographical location and the second preset time.

[0251] Optionally, the storage medium may also execute program code for the following steps: determining a meteorological forecast result from preset meteorological forecast results based on geographical location and a second preset time, including: generating filtering conditions based on different time periods and the second preset time; determining target forecast results that meet the filtering conditions from the preset meteorological forecast results; determining the forecast result corresponding to the geographical location from the target forecast results, and obtaining the meteorological forecast result.

[0252] Optionally, the aforementioned storage medium may also execute program code that performs the following steps: determining the difference between the first forecast result and the meteorological correction result; determining the display method of the meteorological correction result based on the difference; and outputting the meteorological correction result based on the display method.

[0253] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0254] In the above embodiments of this application, 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.

[0255] 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 is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection of units or modules may be electrical or other forms.

[0256] 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 network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0257] Furthermore, the functional units in the various embodiments of this application 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.

[0258] 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 this application, 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 of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.

[0259] The above are merely preferred embodiments of this application. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for processing power generation capacity, characterized in that, include: Obtain meteorological forecasts for the location of the wind turbine; The first forecast result in the meteorological forecast results is corrected to obtain the meteorological correction result, wherein the meteorological element corresponding to the first forecast result is a meteorological element that can be monitored in real time. Based on the second forecast result and the weather correction result in the weather forecast results, the power generation of the wind turbine is predicted, wherein the second forecast result is used to characterize the forecast results in the weather forecast results other than the first forecast result.

2. The method according to claim 1, characterized in that, The meteorological forecast results include forecast results corresponding to multiple meteorological elements. The first forecast result in the meteorological forecast results is corrected to obtain the corrected meteorological results, including: The first prediction result is obtained by obtaining the prediction result corresponding to the preset meteorological elements from the meteorological prediction result, wherein the preset meteorological elements are used to characterize the meteorological elements contained in the real-time monitored meteorological data. The first forecast result is corrected using a correction model to obtain the meteorological correction result, wherein the correction model is used to characterize the correlation between the first forecast result and the meteorological data.

3. The method according to claim 2, characterized in that, The modified model is obtained by solving multiple conditional distributions separately. The multiple conditional distributions are obtained by decomposing the joint distribution probability corresponding to the preset meteorological elements. The joint distribution probability is constructed based on a directed graph, historical meteorological forecast results, and historical meteorological data. The directed graph is used to represent the correlation between the preset meteorological elements, and the historical meteorological data is used to represent the meteorological data monitored at the historical time points corresponding to the historical meteorological forecast results.

4. The method according to claim 1, characterized in that, Based on the second forecast result and the weather correction result in the weather forecast results, the power generation capacity of the wind turbine is predicted, including: Obtain the first prediction time point; The prediction result corresponding to the preset time period is obtained from the second prediction result, and the correction result corresponding to the preset time period is obtained from the meteorological correction result, wherein the preset time period is determined based on the first prediction time point; The prediction results and correction results corresponding to the preset time period are input into the power prediction model to predict the power generation.

5. The method according to claim 4, characterized in that, The power prediction model includes an encoder module and a decoder module, wherein the prediction result corresponding to the preset time period and the correction result corresponding to the preset time period are input into the power prediction model to predict the power generation, including: The encoder module is used to extract features from the prediction results and correction results corresponding to the preset time period to obtain meteorological features. The power generation capacity is obtained by using the decoder module to reconstruct the power based on the meteorological characteristics.

6. The method according to claim 4, characterized in that, The power prediction model is trained using measured power at historical prediction time points and historical meteorological correction results. The historical meteorological correction results are obtained by correcting the historical meteorological prediction results using the correction model.

7. The method according to claim 1, characterized in that, Obtain meteorological forecasts for the location of the wind turbine, including: Obtain a preset weather forecast result, a second preset time, and the geographical location of the wind turbine, wherein the preset weather forecast result includes forecast results for different regions within different time periods; Based on the geographical location and the second preset time, the weather forecast result is determined from the preset weather forecast result.

8. The method according to claim 7, characterized in that, Based on the geographical location and the second preset time, the weather forecast result is determined from the preset weather forecast result, including: Based on the different time periods and the second preset time, filter conditions are generated; Determine the target forecast results that meet the screening conditions from the preset meteorological forecast results; The meteorological forecast result is obtained by determining the forecast result corresponding to the region to which the geographical location belongs from the target forecast result.

9. The method according to claim 1, characterized in that, The method further includes: Determine the difference between the first forecast result and the meteorological correction result; Based on the difference, determine the display method of the meteorological correction result; The meteorological correction result is output based on the aforementioned display method.

10. A method for processing power generation capacity, characterized in that, include: In response to input commands applied to the operating interface, the weather forecast results for the location of the wind turbine are displayed on the operating interface. In response to a power prediction command applied to the operation interface, the power generation of the wind turbine is displayed on the operation interface. The power generation is predicted based on a second prediction result and a meteorological correction result in the meteorological prediction results. The meteorological correction result is obtained by correcting a first prediction result in the meteorological prediction results. The second prediction result is used to characterize the prediction results in the meteorological prediction results other than the first prediction result. The meteorological element corresponding to the first prediction result is a meteorological element that can be monitored in real time.

11. A method for processing power generation capacity, characterized in that, include: The weather forecast result of the location of the wind turbine is obtained by calling the first interface, wherein the first interface includes a first parameter and the parameter value of the first parameter is the weather forecast result; The first forecast result in the meteorological forecast results is corrected to obtain the meteorological correction result, wherein the meteorological element corresponding to the first forecast result is a meteorological element that can be monitored in real time. Based on the second forecast result and the weather correction result in the weather forecast results, the power generation of the wind turbine is predicted, wherein the second forecast result is used to characterize the forecast results in the weather forecast results other than the first forecast result; The power generation is output by calling a second interface, wherein the second interface includes a second parameter, and the parameter value of the second parameter is the power generation.

12. A method for processing power generation capacity, characterized in that, include: The cloud server receives location information sent by the client, wherein the location information is used to characterize the location of the wind turbine. The cloud server obtains the weather forecast results corresponding to the location information; The cloud server corrects the first forecast result in the meteorological forecast results to obtain a corrected meteorological result, wherein the meteorological element corresponding to the first forecast result is a meteorological element that can be monitored in real time. The cloud server predicts the power generation of the wind turbine based on the second prediction result and the meteorological correction result in the meteorological forecast results, wherein the second prediction result is used to characterize the prediction results in the meteorological forecast results other than the first prediction result; The cloud server sends the power generation to the client, wherein the power generation is used to control the wind turbine.

13. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the method according to any one of claims 1 to 12.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored executable program, wherein, when the executable program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1 to 12.

Images