A wind speed prediction method, system, device and storage medium
By combining background field and historical observation data with convolutional neural networks, the problem of low wind speed prediction accuracy caused by the large computational load of the NWP model is solved, achieving more accurate wind speed prediction and improving the economic benefits of wind energy utilization.
Patent Information
- Application Number
- CN202510196262.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-21
- Publication Date
- 2025-10-21
- Estimated Expiration
- 2045-02-21
AI Technical Summary
Existing wind speed prediction methods rely on the NWP model, which involves large computational loads and results in low accuracy, failing to meet the accuracy requirements for wind energy prediction.
A convolutional neural network (CNN) is used to combine background field data and historical wind speed data. By training and adjusting parameters, the accuracy of wind speed prediction is improved.
It improves the accuracy of wind speed forecasting, helps power companies optimize their electricity market strategies, reduce operating costs, and enhance the market competitiveness of wind energy.
Smart Images
Figure CN120044640B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of artificial intelligence technology, and in particular to a wind speed prediction method, system, device and storage medium. Background Art
[0002] As many countries incorporate wind energy into their national energy policies, wind energy forecasting is becoming increasingly important. Integrating wind energy into the power system requires changes to the scheduling and operation of other generators to address unpredictable discrepancies between supply and demand. Wind speed forecasting is crucial in wind energy forecasting, as it directly determines the volatility and predictability of wind power generation. Accurate wind speed forecasts can help power companies optimize their buying and selling strategies in the electricity market, avoiding financial losses caused by under- or over-generation. Furthermore, accurate forecasts can reduce grid dispatch pressure and the need for backup power, thereby lowering operating costs and improving the market competitiveness of wind energy. This is crucial for promoting the adoption of renewable energy and stabilizing the electricity market.
[0003] In related technologies, NWP models are the primary method for wind speed prediction. These models simulate atmospheric flows and physical processes to predict weather conditions. Commonly used numerical weather prediction models include the Global Forecast System (GFS) and the European Centre for Medium-Range Weather Forecasts (ECMWF). These models use partial differential equations to describe the behavior of atmospheric fluids, but this requires a large amount of computation, resulting in relatively low wind speed prediction accuracy. Therefore, there are still technical issues that need to be addressed in related technologies. Summary of the Invention
[0004] The purpose of this application is to solve one of the technical problems existing in the prior art to at least a certain extent.
[0005] To this end, an object of an embodiment of the present application is to provide a wind speed prediction method, system, device and storage medium, which can improve the accuracy of wind speed prediction.
[0006] In order to achieve the above-mentioned technical objectives, the technical solution adopted in the embodiment of the present application includes: a wind speed prediction method, comprising the following steps: obtaining a first historical observed wind speed data set and a second historical observed wind speed data set of a wind turbine head; wherein the first historical observed wind speed data set is a set of historical observed wind speed data of the wind turbine head before the current day; the second historical observed wind speed data set is a set of wind speed data of the wind turbine head before the current day and wind speed data of the current day; based on the background field data and the first historical observed wind speed data set, determining the first predicted data of the wind turbine head under the background field for the current day, and based on the background field data and the second historical observed wind speed data set, determining the second predicted data of the wind turbine head under the background field after the current day; inputting the first predicted data and the second historical observed wind speed data set into a convolutional neural network to obtain third predicted data after the current day; adjusting the parameters of the convolutional neural network according to the second predicted data and the third predicted data to obtain a trained convolutional neural network; inputting the observed wind speed of the wind turbine head before the prediction day into the trained convolutional neural network to obtain the target wind speed for the prediction day.
[0007] The present application can obtain a first historical observed wind speed data set and a second historical observed wind speed data set of a wind turbine head; wherein the first historical observed wind speed data set is a set of historical observed wind speed data of the wind turbine head before the current day; the second historical observed wind speed data set is a set of wind speed data of the wind turbine head before the current day and wind speed data of the current day; based on the background field data and the first historical observed wind speed data set, the first predicted data of the wind turbine head under the background field for the current day is determined, and based on the background field data and the second historical observed wind speed data set, the second predicted data of the wind turbine head under the background field after the current day is determined; the first predicted data and the second historical observed wind speed data set are input into a convolutional neural network to obtain third predicted data after the current day; according to the second predicted data and the third predicted data, the parameters of the convolutional neural network are adjusted to obtain a trained convolutional neural network; the observed wind speed of the wind turbine head before the prediction day is input into the trained convolutional neural network to obtain the target wind speed for the prediction day. This application proposes a new prediction method, which inputs the observed wind speed of the wind turbine head before the prediction day into an artificial intelligence model to obtain the wind speed on the prediction day. This method fully considers the historical observed wind speed data before the current day and the current day's wind speed data to predict the wind speed on the prediction day. This application can improve the prediction accuracy.
[0008] In addition, a wind speed prediction method according to the above embodiment of the present invention may also have the following additional technical features:
[0009] Furthermore, in an embodiment of the present application, determining the first forecast data of the wind turbine head under the background field for the current day based on the background field data and the first historical observed wind speed data set specifically includes:
[0010] configuring the configuration parameters of the weather research and forecasting model and sending background field data and physical boundary conditions to the weather research and forecasting model to obtain a simulation model;
[0011] The simulation model is run and the first historical observation wind speed data set is input into the simulation model to obtain the first prediction data.
[0012] Furthermore, in an embodiment of the present application, determining the second forecast data for the wind turbine head under the background field after the current day based on the background field data and the second historical observed wind speed data set specifically includes:
[0013] configuring the configuration parameters of the weather research and forecasting model and sending background field data and physical boundary conditions to the weather research and forecasting model to obtain a simulation model;
[0014] The simulation model is run and the second historical observation wind speed data set is input into the simulation model to obtain the second prediction data.
[0015] Furthermore, in an embodiment of the present application, the first forecast data and the second historical observed wind speed data set are input into a convolutional neural network to obtain third forecast data after the current day, specifically including:
[0016] Performing data preprocessing on the first prediction data and the second historical observation wind speed data set to obtain training data;
[0017] The training data is input into the convolutional neural network to obtain the third prediction data.
[0018] Furthermore, in an embodiment of the present application, the first prediction data and the second historical observation wind speed data set are subjected to data preprocessing to obtain training data, specifically including:
[0019] Perform data alignment processing on the first prediction data and the second historical observation wind speed data set,
[0020] Furthermore, the first prediction data and the second historical observation wind speed data set are subjected to data format adjustment processing to obtain training data.
[0021] Furthermore, in an embodiment of the present application, adjusting the parameters of the convolutional neural network according to the second prediction data and the third prediction data to obtain a trained convolutional neural network specifically includes:
[0022] determining a training error based on the second prediction data and the third prediction data;
[0023] When the training error is greater than the preset error, the parameters of the convolutional neural network are adjusted and the convolutional neural network is retrained until the training error is less than or equal to the preset error, thereby obtaining the trained convolutional neural network.
[0024] Furthermore, in the embodiment of the present application, determining the training error based on the second prediction data and the third prediction data specifically includes:
[0025] Subtracting the second predicted data from the third predicted data to obtain a first difference;
[0026] The first difference is used as the training error.
[0027] On the other hand, an embodiment of the present application further provides a wind speed prediction system, comprising:
[0028] a first processing unit, configured to obtain a first set of historical observed wind speed data and a second set of historical observed wind speed data for a wind turbine head; wherein the first set of historical observed wind speed data is a set of historical observed wind speed data for the wind turbine head before the current day; and the second set of historical observed wind speed data is a set of wind speed data for the wind turbine head before the current day and wind speed data for the current day;
[0029] a second processing unit, configured to determine first forecast data for a current day for a head of a wind turbine under the background field based on the background field data and the first set of historical observed wind speed data, and to determine second forecast data for a head of a wind turbine under the background field after the current day based on the background field data and the second set of historical observed wind speed data;
[0030] a third processing unit, configured to input the first forecast data and the second historical observed wind speed data set into a convolutional neural network to obtain third forecast data after the current day;
[0031] a fourth processing unit, configured to adjust parameters of the convolutional neural network according to the second prediction data and the third prediction data to obtain a trained convolutional neural network;
[0032] The fifth processing unit is used to input the wind speed observed at the wind turbine head before the forecast day into the trained convolutional neural network to obtain the target wind speed for the forecast day.
[0033] On the other hand, the present application also provides a wind speed prediction device, comprising:
[0034] at least one processor;
[0035] at least one memory for storing at least one program;
[0036] When the at least one program is executed by the at least one processor, the at least one processor implements a wind speed prediction method as described in any one of the invention contents.
[0037] In addition, the present application also provides a computer-readable storage medium, which stores processor-executable instructions. When the processor executes the processor, the processor-executable instructions are used to execute a wind speed prediction method as described in any one of the above items.
[0038] The advantages and benefits of this application will be partially given in the following description, and partially become apparent from the following description, or learned through practice of this application:
[0039] The present application can obtain a first historical observed wind speed data set and a second historical observed wind speed data set of a wind turbine head; wherein the first historical observed wind speed data set is a set of historical observed wind speed data of the wind turbine head before the current day; the second historical observed wind speed data set is a set of wind speed data of the wind turbine head before the current day and wind speed data of the current day; based on the background field data and the first historical observed wind speed data set, the first predicted data of the wind turbine head under the background field for the current day is determined, and based on the background field data and the second historical observed wind speed data set, the second predicted data of the wind turbine head under the background field after the current day is determined; the first predicted data and the second historical observed wind speed data set are input into a convolutional neural network to obtain third predicted data after the current day; according to the second predicted data and the third predicted data, the parameters of the convolutional neural network are adjusted to obtain a trained convolutional neural network; the observed wind speed of the wind turbine head before the prediction day is input into the trained convolutional neural network to obtain the target wind speed for the prediction day. This application proposes a new prediction method, which inputs the observed wind speed of the wind turbine head before the prediction day into an artificial intelligence model to obtain the wind speed on the prediction day. This method fully considers the historical observed wind speed data before the current day and the current day's wind speed data to predict the wind speed on the prediction day. This application can improve the prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 A schematic diagram of the steps of a wind speed prediction method in a specific embodiment of the present invention;
[0041] Figure 2 A schematic diagram of a flow chart of a wind speed prediction method in a specific embodiment of the present invention
[0042] Figure 3 A schematic structural diagram of a wind speed prediction system in another specific embodiment of the present invention;
[0043] Figure 4 Schematic diagram of the structure of a wind speed prediction device in a specific embodiment of the present invention. DETAILED DESCRIPTION
[0044] The embodiments of the present invention are described in detail below with reference to the accompanying drawings to illustrate the principles and processes of the wind speed prediction method, system, device and storage medium in the embodiments of the present invention.
[0045] First, the nouns of this application are explained:
[0046] 1. NWP (Numerical Weather Prediction): Numerical weather prediction models are a general term for weather forecasting methods based on physics, mathematics, and computer science. They simulate future changes in atmospheric conditions by solving fundamental physical equations that describe atmospheric motion, such as fluid dynamics and thermodynamics. In wind energy forecasting, NWP models simulate physical processes to predict future wind speeds.
[0047] 2. RMSE (Root Mean Square Error): Root mean square error is a statistical indicator that measures the deviation between the predicted value and the actual observed value. It is calculated by taking the square root of the average of the squares of the prediction errors.
[0048] 3. WRF (Weather Research and Forecasting Model): A specific model within the NWP model, specifically designed for weather research and actual weather forecasting. DA: Data Assimilation: A method that combines observational data with numerical models to optimize model initial conditions and improve forecast accuracy.
[0049] 4. WRFDA (Weather Research and Forecasting Data Assimilation): This is the data assimilation system for the Weather Research and Forecasting (WRF) model. It combines observational data (such as from weather stations, satellites, and radar) with the numerical weather prediction model (WRF model) to optimize the model's initial conditions, thereby improving the accuracy and reliability of weather forecasts.
[0050] 5. ECMWF: European Centre for Medium-Range Weather Forecasts. Headquartered in Reading, UK, ECMWF is an international organization specializing in the research, development, and operation of medium-range weather forecasts (i.e., forecasts for the next 3-10 days). ECMWF is widely regarded as one of the world's most advanced numerical weather forecasting organizations.
[0051] 6. Machine Learning: Machine learning is a technology that allows computers to automatically learn patterns from data and make predictions or decisions without being explicitly programmed.
[0052] 7. Deep learning: Deep learning is a machine learning method that automatically learns features and patterns in data through multi-layer neural networks to perform classification, regression, or generation tasks.
[0053] 8. CNN (Convolutional Neural Network): A convolutional neural network is a deep learning model that is particularly good at processing images and spatiotemporal data.
[0054] 9.3DVAR and 4DVAR: Two data assimilation algorithms that use a variational approach to assimilate data. They are used in numerical weather forecasting and other applications involving complex dynamical systems, combining observational data with background fields to optimize initial conditions.
[0055] In the 3DVAR algorithm, WRFDA generates an analysis to perform data assimilation by minimizing a scalar objective function:
[0056]
[0057] In the 4DVAR algorithm, WRFDA performs data assimilation by minimizing the scalar objective function J(x):
[0058]
[0059] The difference between 3DVAR and 4DVAR is that 4DVAR takes the time factor into consideration, so the result is more accurate, but it also increases the computational cost.
[0060] As many countries incorporate wind energy into their national energy policies, wind energy forecasting is becoming increasingly important. Integrating wind energy into the power system requires changes to the scheduling and operation of other generators to address unpredictable discrepancies between supply and demand. Wind speed forecasting is crucial in wind energy forecasting, as it directly determines the volatility and predictability of wind power generation. Accurate wind speed forecasts can help power companies optimize their buying and selling strategies in the electricity market, avoiding financial losses caused by under- or over-generation. Furthermore, accurate forecasts can reduce grid dispatch pressure and the need for backup power, thereby lowering operating costs and improving the market competitiveness of wind energy. This is crucial for promoting the adoption of renewable energy and stabilizing the electricity market.
[0061] In related technologies, NWP models are the primary method for wind speed prediction. These models simulate atmospheric flows and physical processes to predict weather conditions. Commonly used numerical weather prediction models include the Global Forecast System (GFS) and the European Centre for Medium-Range Weather Forecasts (ECMWF). These models use partial differential equations to describe the behavior of atmospheric fluids, but this requires a large amount of computation, resulting in relatively low wind speed prediction accuracy. Therefore, there are still technical issues that need to be addressed in related technologies.
[0062] In view of the above-mentioned defects of the prior art, Figure 1 , this application provides a wind speed prediction method. Figure 1 In the method, the method may include the following steps S101-S105.
[0063] S101. Obtain a first historical observation wind speed data set and a second historical observation wind speed data set of the wind turbine head; wherein the first historical observation wind speed data set is a set of historical observation wind speed data of the wind turbine head before the current day; the second historical observation wind speed data set is a set of wind speed data of the wind turbine head before the current day and wind speed data of the current day.
[0064] S102. Determine the first forecast data of the wind turbine head under the background field for the current day based on the background field data and the first historical observed wind speed data set, and determine the second forecast data of the wind turbine head under the background field after the current day based on the background field data and the second historical observed wind speed data set.
[0065] S103: Input the first prediction data and the second historical observation wind speed data set into a convolutional neural network to obtain third prediction data after the current day.
[0066] S104: Adjust the parameters of the convolutional neural network according to the second prediction data and the third prediction data to obtain a trained convolutional neural network.
[0067] S105: Input the wind speed observed at the wind turbine head before the forecast day into the trained convolutional neural network to obtain the target wind speed for the forecast day.
[0068] It is understood that the predicted day is the day after the current day, and the predicted day and the current day are two adjacent days. The current day can be any day.
[0069] In some feasible embodiments of the present application, the processor can be connected to the acquisition unit via a wired or wireless connection. After the connection is established, the processor can obtain a first historical observed wind speed data set and a second historical observed wind speed data set of the wind turbine head from the acquisition unit; wherein the first historical observed wind speed data set is a set of historical observed wind speed data of the wind turbine head before the current day; the second historical observed wind speed data set is a set of wind speed data of the wind turbine head before the current day and wind speed data of the current day; based on the background field data and the first historical observed wind speed data set, the processor can determine the first prediction data of the wind turbine head under the background field for the current day, and based on the background field data and the second historical observed wind speed data set, the processor can determine the second prediction data of the wind turbine head under the background field after the current day; the first prediction data and the second historical observed wind speed data set are input into the convolutional neural network, and the processor can obtain the third prediction data after the current day; based on the second prediction data and the third prediction data, the processor can adjust the parameters of the convolutional neural network to obtain a trained convolutional neural network; the observed wind speed of the wind turbine head before the prediction day is input into the trained convolutional neural network, and the processor can obtain the target wind speed for the prediction day.
[0070] It should be noted that the above-mentioned wired connection method may include the connection between the mobile device and the processing module, and may also include the connection between the processing module and the hardware device, as well as the wired connection between other currently known or future developed devices and the processing module; and the above-mentioned wireless connection method may include but is not limited to 3G / 4G / 5G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (Ultra Wide Band) connection and other currently known or future developed wireless connection methods.
[0071] The present application can obtain a first historical observed wind speed data set and a second historical observed wind speed data set of a wind turbine head; wherein the first historical observed wind speed data set is a set of historical observed wind speed data of the wind turbine head before the current day; the second historical observed wind speed data set is a set of wind speed data of the wind turbine head before the current day and wind speed data of the current day; based on the background field data and the first historical observed wind speed data set, the first predicted data of the wind turbine head under the background field for the current day is determined, and based on the background field data and the second historical observed wind speed data set, the second predicted data of the wind turbine head under the background field after the current day is determined; the first predicted data and the second historical observed wind speed data set are input into a convolutional neural network to obtain third predicted data after the current day; according to the second predicted data and the third predicted data, the parameters of the convolutional neural network are adjusted to obtain a trained convolutional neural network; the observed wind speed of the wind turbine head before the prediction day is input into the trained convolutional neural network to obtain the target wind speed for the prediction day. This application proposes a new prediction method, which inputs the observed wind speed of the wind turbine head before the prediction day into an artificial intelligence model to obtain the wind speed on the prediction day. This method fully considers the historical observed wind speed data before the current day and the current day's wind speed data to predict the wind speed on the prediction day. This application can improve the prediction accuracy.
[0072] Furthermore, in an embodiment of the present application, the process of determining the first forecast data of the wind turbine head under the background field for the current day based on the background field data and the first historical observed wind speed data set may include steps S201 and S202.
[0073] S201. Configure the configuration parameters of the weather research and forecast model and send the background field data and physical boundary conditions to the weather research and forecast model to obtain a simulation model.
[0074] S202: Run the simulation model and input a first historical observation wind speed data set into the simulation model to obtain first prediction data.
[0075] It is understandable that the simulation model may be a weather research and forecast model, and the first prediction data may be wind speed data of the current day obtained by running the weather research and forecast model.
[0076] Furthermore, in an embodiment of the present application, the process of determining the second predicted data after the current day of the wind turbine head under the background field based on the background field data and the second historical observed wind speed data set may include steps S301 and S302.
[0077] S301 , configuring the configuration parameters of the weather research and forecast model and sending the background field data and physical boundary conditions to the weather research and forecast model to obtain a simulation model.
[0078] S302: Run the simulation model and input a second historical observation wind speed data set into the simulation model to obtain second prediction data.
[0079] It is understandable that the simulation model may be a weather research and forecast model, and the second prediction data may be wind speed data on the forecast day obtained by running the weather research and forecast model.
[0080] Furthermore, in an embodiment of the present application, the process of inputting the first prediction data and the second historical observation wind speed data set into the convolutional neural network to obtain the third prediction data after the current day may include steps S401 and S402.
[0081] S401: Preprocess the first prediction data and the second historical observation wind speed data set to obtain training data.
[0082] S402: Input the training data into the convolutional neural network to obtain third prediction data.
[0083] Furthermore, in an embodiment of the present application, the process of performing data preprocessing on the first prediction data and the second historical observation wind speed data set to obtain training data may include step S501.
[0084] S501 : performing data alignment processing on the first prediction data and the second historical observation wind speed data set, and performing data format adjustment processing on the first prediction data and the second historical observation wind speed data set to obtain training data.
[0085] Furthermore, in an embodiment of the present application, the process of adjusting the parameters of the convolutional neural network according to the second prediction data and the third prediction data to obtain a trained convolutional neural network may include steps S601 and S602.
[0086] S601: Determine a training error based on the second prediction data and the third prediction data.
[0087] S602: When the training error is greater than the preset error, adjust the parameters of the convolutional neural network and retrain the convolutional neural network until the training error is less than or equal to the preset error, thereby obtaining a trained convolutional neural network.
[0088] Furthermore, in an embodiment of the present application, the process of determining the training error based on the second prediction data and the third prediction data may include steps S701 and S702.
[0089] S701 , performing a subtraction between the second prediction data and the third prediction data to obtain a first difference.
[0090] S702: Use the first difference as a training error.
[0091] The following is combined with Figure 2 The principle of this application is explained.
[0092] Reference Figure 2 The specific steps of this embodiment include S11-S16.
[0093] S11. Data Preparation: Collect wind speed data from wind turbines in each region. Download background field data from the ECMWF database. If necessary, perform temporal and spatial interpolation on the data to ensure coverage of the study area and timeframe, and remove outliers.
[0094] S12. Configure the WRF model: determine the scope and grid resolution of the study area, and set model parameters, including dynamics, physical scheme, operating environment, etc.
[0095] S13. Data assimilation (innovation): Use the WRFDA module, select 3DVAR and / or 4DVAR, and input the observed wind speed and background field data to assimilate the initial wind field.
[0096] S14. Run the WRF model: Configure the simulation timeframe, set the boundary conditions and the initial conditions obtained from data assimilation, and define the output frequency. After the relevant parameters are set, perform the numerical simulation on the supercomputing platform based on the assimilated data.
[0097] S15. Build and train a CNN model (innovation):
[0098] ① Data preparation: Align the WRF output data with the observed wind speed as input and label; and convert the data into a format supported by the CNN model.
[0099] ②Build the model architecture: The CNN model of this technical solution consists of five convolutional layers, one fully connected layer, and an output layer. Each convolutional layer contains 32 filters and uses ReLu as the activation function. The input of the first layer consists of various physical parameters extracted from the WRF model and the grid resolution. In the convolution operation, a randomly initialized convolution kernel is used to act on the input features. The feature map is obtained through the output of the first layer, and then these feature maps are used as the input of the second layer. In subsequent layers, this process is repeated. The output of the fifth convolutional layer is passed to the fully connected layer. The last layer generates the wind speed prediction result and outputs it.
[0100] ③Model training: Divide the data into training set, validation set and test set. During the training process, hyperparameters (such as learning rate, batch size and number of iterations) need to be set, and the validation set should be used to prevent overfitting.
[0101] S16. Result evaluation: Use the validation set data to make predictions and compare them with the observed data. Use evaluation indicators such as Bias and RMSE to evaluate the performance gap and improvement between this technical solution and traditional methods.
[0102] In addition, refer to Figure 3 ,and Figure 1 Corresponding to the method, an embodiment of the present application further provides a wind speed prediction system. The system may include a first processing unit 1001, a second processing unit 1002, a third processing unit 1003, a fourth processing unit 1004 and a fifth processing unit 1005. The first processing unit 1001 can be used to obtain a first historical observation wind speed data set and a second historical observation wind speed data set of the wind turbine head; wherein the first historical observation wind speed data set is a set of historical observation wind speed data of the wind turbine head before the current day; the second historical observation wind speed data set is a set of wind speed data of the wind turbine head before the current day and wind speed data of the current day. The second processing unit 1002 can determine the first prediction data of the wind turbine head under the background field on the current day based on the background field data and the first historical observation wind speed data set, and determine the second prediction data of the wind turbine head under the background field after the current day based on the background field data and the second historical observation wind speed data set. The third processing unit 1003 can be used to input the first forecast data and the second historical observed wind speed data set into a convolutional neural network to obtain third forecast data for the day after the current day. The fourth processing unit 1004 can be used to adjust the parameters of the convolutional neural network based on the second forecast data and the third forecast data to obtain a trained convolutional neural network. The fifth processing unit 1005 can be used to input the wind speed observed at the wind turbine head before the forecast day into the trained convolutional neural network to obtain the target wind speed for the forecast day.
[0103] It should be noted that the first processing unit may be any integrated circuit unit or microprocessor unit obtained by integrating a processing chip and its peripheral circuits using existing integration technologies. The first and second processing units may also be any integrated circuit modules or microprocessor modules obtained by integrating a processing chip and its peripheral circuits using existing integration technologies. The first and second processing units may also include one or more memories.
[0104] It should be noted that the contents of the above-mentioned wind speed prediction method embodiment are all applicable to the present wind speed prediction system embodiment. The functions specifically implemented by the present wind speed prediction system embodiment are the same as those of the above-mentioned wind speed prediction method embodiment, and the beneficial effects achieved are also the same as those achieved by the above-mentioned wind speed prediction method embodiment.
[0105] and Figure 1Corresponding to the method, the embodiment of the present application also provides a wind speed prediction device, the specific structure of which can be referred to Figure 4 ,include:
[0106] at least one processor 1011;
[0107] at least one memory 1012, configured to store at least one program;
[0108] When the at least one program is executed by the at least one processor, the at least one processor implements the wind speed prediction method.
[0109] The contents of the above method embodiments are all applicable to the present device embodiments. The functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0110] and Figure 1 Corresponding to the method, an embodiment of the present application further provides a computer-readable storage medium, which stores instructions executable by a processor, and the processor-executable instructions are used to execute the wind speed prediction method when executed by the processor.
[0111] The contents of the above-mentioned wind speed prediction method embodiment are all applicable to the present storage medium embodiment. The functions specifically implemented by the present storage medium embodiment are the same as those of the above-mentioned wind speed prediction method embodiment, and the beneficial effects achieved are also the same as those achieved by the above-mentioned wind speed prediction method embodiment.
[0112] In some optional embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiments presented and described in the flow chart of the present application are provided in an exemplary manner for the purpose of providing a more comprehensive understanding of the technology. The disclosed method is not limited to the operations and logical flows presented herein. Optional embodiments are contemplated in which the order of the various operations is changed and the sub-operations described as a part of a larger operation are performed independently.
[0113] In addition, although the present application is described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present application. More specifically, given the properties, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the module will be understood within the routine skills of an engineer. Therefore, a person skilled in the art can implement the present application as set forth in the claims using ordinary techniques without undue experimentation. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present application, which is determined by the full scope of the appended claims and their equivalents.
[0114] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several programs for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0115] The logic and / or steps represented in a flowchart or otherwise described herein, for example, may be considered as an ordered list of executable programs for implementing the logical functions, and may be embodied in any computer-readable medium for use by, or in conjunction with, a program execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can retrieve and execute a program from a program execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" may be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, a program execution system, apparatus, or device.
[0116] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or more wires (electronic devices), a portable computer disk cartridge (magnetic devices), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.
[0117] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable program execution system. For example, if implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.
[0118] In the above description of this specification, reference to the terms "one embodiment / example," "another embodiment / example," or "certain embodiments / examples" means that the specific features, structures, materials, or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any appropriate manner in any one or more embodiments or examples.
[0119] Although the embodiments of the present application have been shown and described, those skilled in the art will appreciate that various changes, modifications, substitutions, and variations may be made to the embodiments without departing from the principles and intent of the present application, and that the scope of the present application is defined by the claims and their equivalents.
[0120] The above is a specific description of the preferred implementation of the present application, but the present application is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present application. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present application.
Claims
1. A wind speed prediction method, characterized in that: The following steps are involved: Obtaining a first historical observation wind speed data set and a second historical observation wind speed data set for a wind turbine head; wherein the first historical observation wind speed data set is a set of historical observation wind speed data of the wind turbine head before the current day; and the second historical observation wind speed data set is a set of wind speed data of the wind turbine head before the current day and wind speed data of the current day; Determining first forecast data for the wind turbine head under the background field on the current day based on the background field data and the first set of historical observed wind speed data, and determining second forecast data for the wind turbine head under the background field after the current day based on the background field data and the second set of historical observed wind speed data; Inputting the first forecast data and the second historical observation wind speed data set into a convolutional neural network to obtain third forecast data after the current day; Adjusting parameters of the convolutional neural network according to the second prediction data and the third prediction data to obtain a trained convolutional neural network; Inputting the wind speed observed at the wind turbine head before the forecast day into the trained convolutional neural network to obtain the target wind speed for the forecast day; The determining, based on the background field data and the first historical observed wind speed data set, first forecast data of the wind turbine head under the background field for the current day specifically includes: configuring the configuration parameters of the weather research and forecasting model and sending background field data and physical boundary conditions to the weather research and forecasting model to obtain a simulation model; Running the simulation model and inputting the first historical observed wind speed data set into the simulation model, so that the simulation model obtains the first prediction data based on the 3DVAR and / or 4DVAR algorithm; The determining, based on the background field data and the second historical observed wind speed data set, second forecast data for the wind turbine head under the background field after the current day specifically includes: configuring the configuration parameters of the weather research and forecasting model and sending background field data and physical boundary conditions to the weather research and forecasting model to obtain a simulation model; The simulation model is run and the second historical observation wind speed data set is input into the simulation model to obtain the second prediction data.
2. A wind speed prediction method according to claim 1, characterized in that: The first forecast data and the second historical observed wind speed data set are input into a convolutional neural network to obtain third forecast data after the current day, specifically including: Performing data preprocessing on the first prediction data and the second historical observation wind speed data set to obtain training data; The training data is input into the convolutional neural network to obtain the third prediction data.
3. A wind speed prediction method according to claim 2, characterized in that: The step of preprocessing the first prediction data and the second historical observation wind speed data set to obtain training data specifically includes: The first prediction data and the second historical observation wind speed data set are subjected to data alignment processing, and the first prediction data and the second historical observation wind speed data set are subjected to data format adjustment processing to obtain training data.
4. A wind speed prediction method according to claim 1, characterized in that: The step of adjusting the parameters of the convolutional neural network according to the second prediction data and the third prediction data to obtain a trained convolutional neural network specifically includes: determining a training error based on the second prediction data and the third prediction data; When the training error is greater than the preset error, the parameters of the convolutional neural network are adjusted and the convolutional neural network is retrained until the training error is less than or equal to the preset error, thereby obtaining the trained convolutional neural network.
5. A wind speed prediction method according to claim 1, characterized in that: The determining of the training error according to the second prediction data and the third prediction data specifically includes: Subtracting the second predicted data from the third predicted data to obtain a first difference; The first difference is used as the training error.
6. A wind speed prediction system, characterized in that: include: A first processing unit is configured to obtain a first historical observation wind speed data set and a second historical observation wind speed data set for a wind turbine head; The first historical observation wind speed data set is a set of historical observation wind speed data of the wind turbine head before the current day; the second historical observation wind speed data set is a set of wind speed data of the wind turbine head before the current day and wind speed data of the current day; a second processing unit, configured to determine first forecast data for a current day for a head of a wind turbine under the background field based on the background field data and the first set of historical observed wind speed data, and to determine second forecast data for a head of a wind turbine under the background field after the current day based on the background field data and the second set of historical observed wind speed data; The determining, based on the background field data and the first historical observed wind speed data set, first forecast data of the wind turbine head under the background field for the current day specifically includes: configuring the configuration parameters of the weather research and forecasting model and sending background field data and physical boundary conditions to the weather research and forecasting model to obtain a simulation model; Running the simulation model and inputting the first historical observed wind speed data set into the simulation model, so that the simulation model obtains the first prediction data based on the 3DVAR and / or 4DVAR algorithm; The determining, based on the background field data and the second historical observed wind speed data set, second forecast data for the wind turbine head under the background field after the current day specifically includes: configuring the configuration parameters of the weather research and forecasting model and sending background field data and physical boundary conditions to the weather research and forecasting model to obtain a simulation model; Running the simulation model and inputting the second historical observation wind speed data set into the simulation model to obtain the second prediction data; a third processing unit, configured to input the first forecast data and the second historical observed wind speed data set into a convolutional neural network to obtain third forecast data after the current day; a fourth processing unit, configured to adjust parameters of the convolutional neural network according to the second prediction data and the third prediction data to obtain a trained convolutional neural network; The fifth processing unit is used to input the wind speed observed at the wind turbine head before the forecast day into the trained convolutional neural network to obtain the target wind speed for the forecast day.
7. A wind speed prediction device, characterized in that include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the wind speed prediction method according to any one of claims 1 to 5.
8. A computer-readable storage medium storing instructions executable by a processor, characterized in that: The processor-executable instructions are used to execute a wind speed prediction method according to any one of claims 1 to 5 when executed by the processor.
Citation Information
Patent Citations
Complex terrain wind energy resource assessment method based on digital-analog driven incremental deep learning
CN116777072A