Wind power prediction method and device, equipment and storage medium

Abstract

The invention discloses a wind power generation power prediction method and device, equipment and a storage medium, which are applied to the field of wind power generation, and the method comprises the steps: obtaining the historical power generation power data of a wind power plant and the historical meteorological data of a target region, and segmenting the historical meteorological data into a plurality of time sequence samples; training an RMT-LSTM space-time prediction deep learning network based on the meteorological data set constructed by the time sequence sample to obtain a trained meteorological numerical value space-time prediction model; constructing a spatial data conversion data set based on the historical power generation power data and the historical meteorological data to train a multi-channel spatial deep learning network, and obtaining a power generation power spatial data conversion model; and inputting to-be-measured meteorological data into the meteorological value space-time prediction model to obtain an output meteorological element prediction result, and inputting the meteorological element prediction result into the generated power space data conversion model to obtain an output generated power prediction result. The spatial feature extraction capability of the model is improved, and the prediction result is more accurate.

Description

Technical Field

[0001] The present invention relates to the field of wind power generation, and in particular to a wind power prediction method, device, equipment and computer-readable storage medium. Background Art

[0002] With the increasing global attention to sustainable development, the development and utilization of new energy, especially wind energy, has become a key way to cope with climate change and optimize the energy structure. Accurately predicting wind power generation can better optimize the dispatching and load balance of the power system, improve the operating efficiency and economic benefits of wind farms, and thus promote the development and application of renewable energy.

[0003] The artificial intelligence method is based on a data-driven approach to establish a machine learning or deep learning model for power forecasting. This method can effectively model the nonlinear relationship between data and has a high prediction accuracy. However, the current artificial intelligence methods usually only make ultra-short-term predictions of a few hours based on time series, and have poor prediction stability and long-term prediction capabilities. Summary of the invention

[0004] The purpose of the present invention is to provide a wind power prediction method, device, equipment and storage medium, which are applied to the field of wind power generation. The method divides the wind power prediction problem into two problems: meteorological numerical spatiotemporal prediction and power generation mapping, and solves them in turn. In the process of meteorological numerical spatiotemporal prediction, the RMT-LSTM structure that integrates the RMT model and the ST-LSTM model is adopted to improve the spatial feature extraction capability of the model and make the prediction result more accurate.

[0005] In order to solve the above technical problems, the present invention provides a wind power prediction method, comprising:

[0006] Acquire historical power generation data of the wind farm and historical meteorological data of the target area, and divide the historical meteorological data into multiple time series samples in chronological order;

[0007] The meteorological data set constructed based on the time series samples is used to train the RMT-LSTM spatiotemporal prediction deep learning network to obtain a trained meteorological numerical spatiotemporal prediction model;

[0008] Training a multi-channel spatial deep learning network based on a spatial data conversion data set constructed based on the historical power generation data and the historical meteorological data to obtain a power generation spatial data conversion model;

[0009] The meteorological data to be measured is input into the meteorological numerical spatiotemporal prediction model to obtain the output meteorological element prediction result, and the meteorological element prediction result is input into the power generation spatial data conversion model to obtain the output power generation prediction result.

[0010] Optionally, the obtaining of historical power generation data of the wind farm and historical meteorological data of the target area includes:

[0011] Acquiring initial historical power generation data of the wind farm and initial historical meteorological data of the target area;

[0012] Interpolating the missing data in the initial historical power generation data and the initial historical meteorological data to obtain the completed historical power generation data and the completed historical meteorological data;

[0013] The historical power generation data and the historical meteorological data are standardized to obtain the historical power generation data and the historical meteorological data.

[0014] Optionally, the method further includes:

[0015] Determine the Gaussian weight of each type of data in the historical meteorological data based on the Gaussian weight function;

[0016] The Gaussian weight and the historical meteorological data are stacked in the channel dimension.

[0017] Optionally, the historical meteorological data include: historical satellite remote sensing data, historical numerical weather high-altitude data and historical numerical weather ground data.

[0018] Optionally, the spatial data conversion data set constructed based on the historical power generation data and the historical meteorological data trains a multi-channel spatial deep learning network to obtain a power generation spatial data conversion model, including:

[0019] The multi-channel spatial deep learning network is trained based on the spatial data conversion data set constructed based on the historical power generation data and the historical numerical weather ground data in the historical meteorological data to obtain the power generation spatial data conversion model.

[0020] Optionally, the RMT-LSTM spatiotemporal prediction deep learning network has 4 network layers.

[0021] Optionally, the multi-channel spatial deep learning network is a CNN model or a Swin-Transformer model.

[0022] In order to solve the above technical problems, the present invention provides a wind power prediction device, comprising:

[0023] The first module is used to obtain the historical power generation data of the wind farm and the historical meteorological data of the target area, and divide the historical meteorological data into multiple time series samples in chronological order;

[0024] The second module is used to train the RMT-LSTM spatiotemporal prediction deep learning network based on the meteorological data set constructed based on the time series samples to obtain a trained meteorological numerical spatiotemporal prediction model;

[0025] The third module is used to train a multi-channel spatial deep learning network based on the spatial data conversion data set constructed based on the historical power generation data and the historical meteorological data to obtain a power generation spatial data conversion model;

[0026] The fourth module is used to input the meteorological data to be measured into the meteorological numerical spatiotemporal prediction model to obtain the output meteorological element prediction results, and input the meteorological element prediction results into the power generation spatial data conversion model to obtain the output power generation prediction results.

[0027] In order to solve the above technical problems, the present invention provides an electronic device, comprising:

[0028] Memory, for storing computer programs;

[0029] A processor is used to implement the above-mentioned wind power prediction method when executing the computer program.

[0030] In order to solve the above technical problem, the present invention provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, the above-mentioned wind power prediction method is implemented.

[0031] It can be seen that the method of the present invention obtains the historical power generation data of the wind farm and the historical meteorological data of the target area, and divides the historical meteorological data into multiple time series samples in chronological order; trains the RMT-LSTM spatiotemporal prediction deep learning network based on the meteorological data set constructed based on the time series samples to obtain a trained meteorological numerical spatiotemporal prediction model; trains a multi-channel spatial deep learning network based on the spatial data conversion data set constructed based on the historical power generation data and the historical meteorological data to obtain a power generation spatial data conversion model; inputs the meteorological data to be tested into the meteorological numerical spatiotemporal prediction model to obtain the output meteorological element prediction result, and inputs the meteorological element prediction result into the power generation spatial data conversion model to obtain the output power generation prediction result.

[0032] The present invention proposes a wind power generation prediction method, which divides the wind power generation prediction problem into two problems: meteorological numerical spatiotemporal prediction and power generation mapping, and solves them in sequence. In the process of meteorological numerical spatiotemporal prediction, the RMT-LSTM structure fused with the RMT model and the ST-LSTM model is adopted to improve the spatial feature extraction capability of the model and make the prediction result more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0034] Figure 1 A flow chart of a wind power prediction method provided by an embodiment of the present invention;

[0035] Figure 2 An example of an RMT-LSTM spatiotemporal prediction deep learning network architecture provided by an embodiment of the present invention;

[0036] Figure 3 An example diagram of a general training process of a meteorological numerical spatiotemporal prediction model provided by an embodiment of the present invention;

[0037] Figure 4 An example diagram of a general training process of a power generation space data conversion model provided by an embodiment of the present invention;

[0038] Figure 5 An example diagram of a general process for wind power generation prediction provided by an embodiment of the present invention;

[0039] Figure 6 This is a structural block diagram of a wind power prediction device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0041] With the increasing global attention to sustainable development, the development and utilization of new energy, especially wind energy, has become a key way to cope with climate change and optimize the energy structure. Accurately predicting wind power generation can better optimize the dispatching and load balance of the power system, improve the operating efficiency and economic benefits of wind farms, and thus promote the development and application of renewable energy.

[0042] There are currently three mainstream wind power forecasting methods, namely statistical methods, physical model methods, and artificial intelligence methods. The statistical method uses statistical models to analyze the statistical characteristics of historical data to forecast power. This method is simple to implement but has weak nonlinear modeling capabilities and is difficult to handle the relationship between complex meteorological factors and wind power. The physical model method predicts future wind power by simulating the distribution of the atmosphere and wind fields. This method can better simulate the physical mechanism of the actual wind power generation process and has high accuracy, but requires strong computing resources and has poor real-time prediction performance. The artificial intelligence method is based on a data-driven approach to establish a machine learning or deep learning model for power forecasting. This method can effectively model the nonlinear relationship between data and has a high prediction accuracy, but the current artificial intelligence methods usually only make ultra-short-term forecasts of several hours based on time series, and have poor prediction stability and long-term prediction capabilities.

[0043] The above three methods are difficult to simultaneously meet the needs of accurate, stable and long-term prediction of wind power generation under the current background of new energy development. Therefore, how to achieve these requirements in the wind power generation prediction task is a problem that needs to be further solved.

[0044] In order to meet the demand for accurate, stable and long-term prediction of wind power generation, the present invention proposes a wind power generation prediction method based on meteorological numerical spatiotemporal forecast, which divides the wind power generation prediction problem into two problems: meteorological numerical spatiotemporal forecast and power generation mapping, and solves them in turn.

[0045] The following combination Figure 1 , Figure 1 A flow chart of a wind power prediction method provided by an embodiment of the present invention, the method may include:

[0046] S101: Obtain historical power generation data of a wind farm and historical meteorological data of a target area, and divide the historical meteorological data into a plurality of time series samples in chronological order.

[0047] This embodiment can obtain the historical power generation data of the selected wind farm and the historical meteorological data of the target area where it is located. This embodiment does not limit the specific type of meteorological data, and generally can include multi-source meteorological data such as satellite remote sensing data, numerical weather high-altitude data and numerical weather ground data. Numerical weather high-altitude data may include: high-altitude wind speed, high-altitude wind direction, high-altitude air temperature, high-altitude humidity, etc.; numerical weather ground data may include: ground wind speed, ground wind direction, ground air temperature, ground humidity, ground air pressure, etc. This embodiment can align the collected data in spatial and temporal dimensions.

[0048] In this embodiment, after the initial historical meteorological data and historical power generation data are collected, the data can be preprocessed to obtain samples that meet the model training specifications.

[0049] This embodiment does not limit the specific method of preprocessing. Generally, the initial historical power generation data of the wind farm and the initial historical meteorological data of the target area can be obtained; the missing data in the initial historical power generation data and the initial historical meteorological data can be interpolated to obtain the completed historical power generation data and the completed historical meteorological data; the completed historical power generation data and the initial completed historical meteorological data can be standardized to obtain the historical power generation data and the historical meteorological data.

[0050] This embodiment does not limit the specific method of interpolating the missing data, and generally, methods such as bilinear interpolation or Newton interpolation can be selected.

[0051] This embodiment does not limit the specific method of performing the standardization process. Generally, methods such as normalization and Z-SCORE standardization can be selected. Z-SCORE is also called a standard score, which is a process of dividing the difference between a number and the mean by the standard deviation.

[0052] Furthermore, the prediction weight of the central location, i.e., the location of the wind farm, can be amplified by using the Gaussian weight function calculation, so that the meteorological prediction model focuses on predicting the changes in meteorological data at the location of the wind farm and the surrounding area. Specifically, this embodiment can determine the Gaussian weights of various types of data in the historical power generation data and the historical meteorological data based on the Gaussian weight function; and stack the Gaussian weights with the historical power generation data and the historical meteorological data in the channel dimension.

[0053] In this embodiment, the wind power prediction can be divided into two parts: meteorological prediction and power prediction. In the meteorological prediction part, future meteorological data are predicted based on historical meteorological data, and in the power prediction part, future wind power is predicted based on the predicted future meteorological data.

[0054] In this embodiment, the historical meteorological data can be divided into multiple time series samples in chronological order to construct a data set for meteorological forecasting.

[0055] This embodiment does not limit the specific way of dividing to obtain time series samples. Generally, each time series sample may include an input sequence and an output sequence. This embodiment does not limit the length of the input sequence and the output sequence. Generally, the length of the input sequence and the output sequence is selected to be 8. This embodiment also does not limit the time interval of the data in the sequence. Generally, it can be 3 hours, that is, in this embodiment, the time length of the input sequence and the output sequence can both be 24 hours.

[0056] S102: Train the RMT-LSTM spatiotemporal prediction deep learning network based on the meteorological data set constructed based on time series samples to obtain a trained meteorological numerical spatiotemporal prediction model.

[0057] This embodiment can train the RMT-LSTM spatiotemporal prediction deep learning network based on the meteorological data set constructed based on time series samples to obtain a trained meteorological numerical spatiotemporal prediction model.

[0058] This embodiment does not limit the ratio of the training set to the test set. Generally, the ratio of the training set to the test set can be 8:2.

[0059] The full name of the RMT model is Retentive Networks Meet Vision Transformers. This model is a spatial feature extraction deep learning model that introduces Manhattan self-attention and attention decomposition calculation mechanism. Manhattan self-attention can capture the spatial features of different positions by adjusting the weights, and can fully extract the spatial feature information of long-distance dependencies and short-distance dependencies in the data.

[0060] The ST-LSTM structure is a deep learning structure in the spatiotemporal prediction model PredRNN-V2. This structure mainly captures the spatiotemporal information in the data by introducing temporal memory states and spatial memory states, and adds decoupling loss to enhance the model's ability to capture long-term dependencies. The extraction of spatial feature information is achieved using traditional convolutional neural networks, which are usually used to capture short-distance dependent spatial features and cannot fully capture long-distance dependent spatial features.

[0061] This embodiment can combine the RMT model and the ST-LSTM structure. Specifically, the RMT model can replace the convolutional neural network in the spatial feature information extraction module of the ST-LSTM structure to improve the spatial feature extraction capability of the model and obtain the RMT-LSTM spatiotemporal prediction deep learning network.

[0062] This embodiment does not limit the specific architecture of the RMT-LSTM spatiotemporal prediction deep learning network. Figure 2 As shown, the number of network layers of the model can be set to 4 layers. When the input of the model is the historical meteorological data before time t (including time t), the model can output the predicted meteorological data after time t.

[0063] In this embodiment, the training set in the meteorological data set can be input into the RMT-LSTM spatiotemporal prediction deep learning network for training to obtain a trained meteorological numerical spatiotemporal prediction model to be tested;

[0064] The test set in the meteorological data set is input into the meteorological numerical spatiotemporal prediction model to be tested, and the test results are obtained and the meteorological numerical spatiotemporal prediction model to be tested is judged whether the training is completed according to the set threshold; if the test passes, the meteorological numerical spatiotemporal prediction model is obtained; if not, it is retrained. The meteorological numerical spatiotemporal prediction model obtained after the training is completed is the first submodel of the wind power generation prediction model.

[0065] In this embodiment, this embodiment does not limit the way of setting the threshold value, and it can generally be set so that the average prediction relative errors of various meteorological data are less than 10%.

[0066] S103: Training a multi-channel spatial deep learning network based on a spatial data conversion data set constructed based on historical power generation data and historical meteorological data to obtain a power generation spatial data conversion model.

[0067] In this embodiment, a multi-channel spatial deep learning network can be trained based on a spatial data conversion data set constructed based on historical power generation data and historical meteorological data to obtain a power generation spatial data conversion model.

[0068] This embodiment can construct the historical power generation data and historical meteorological data collected at the same time into a sample of a spatial data conversion data set, the input data in the sample is the historical meteorological data, and the output data in the sample is the historical power generation data.

[0069] This embodiment does not limit the ratio of the training set to the test set in the spatial data conversion data set, which can generally be 8:2.

[0070] Since wind power generation is most affected by ground weather, this embodiment can train a multi-channel spatial deep learning network based on a spatial data conversion data set constructed based on historical power generation data and historical numerical weather ground data in historical meteorological data to obtain a power generation spatial data conversion model.

[0071] In this embodiment, the training set in the spatial data conversion data set can be input into a multi-channel spatial deep learning network for training to obtain a trained power generation spatial data conversion model; wherein, the multi-channel spatial deep learning network can select models such as CNN (Convolutional Neural Networks) or Swin-Transformer. Swin-Transformer is a new visual Transformer model that can be used as a general backbone of computer vision.

[0072] In this embodiment, the test set in the spatial data conversion data set can be input into the power generation spatial data conversion model to be tested, and the test result can be obtained and the power generation spatial data conversion model to be tested can be judged whether the training is completed according to the set threshold value; if the test passes, the power generation spatial data conversion model is obtained; if not, retraining is performed. The power generation spatial data conversion model obtained after the training is completed is the second sub-model of the wind power generation prediction model.

[0073] In this embodiment, this embodiment does not limit the way of setting the threshold value, and it can generally be set so that the average prediction relative errors of various meteorological data are less than 10%.

[0074] S104: inputting the meteorological data to be measured into the meteorological numerical spatiotemporal prediction model to obtain output meteorological element prediction results, and inputting the meteorological element prediction results into the power generation spatial data conversion model to obtain output power generation prediction results.

[0075] In this embodiment, the meteorological data to be measured can be input into the meteorological numerical spatiotemporal prediction model to obtain the output meteorological element prediction results, and the meteorological element prediction results can be input into the power generation spatial data conversion model to obtain the output power generation prediction results.

[0076] That is, the wind power generation model in this embodiment may include two sub-models, namely a meteorological numerical spatiotemporal prediction model and a power generation spatial data conversion model.

[0077] In this embodiment, the meteorological data to be measured in the area where the wind farm is located can be input into the wind power prediction model. The data will first pass through the first sub-model of the wind power prediction model, namely the meteorological numerical spatiotemporal prediction model, to obtain the prediction results of various meteorological elements in the future in the area where the wind farm is located.

[0078] Furthermore, the ground meteorological data in the prediction results of various meteorological elements can be input into the second sub-model of the wind power prediction model, namely the power generation space data conversion model, to obtain the prediction results of future wind power generation.

[0079] Based on the above embodiments, the method of the present invention divides the wind power prediction problem into two problems: meteorological numerical spatiotemporal prediction and power generation mapping, and solves them in turn. In the process of meteorological numerical spatiotemporal prediction, the RMT-LSTM structure that integrates the RMT model and the ST-LSTM model is adopted to enhance the spatial feature extraction capability of the model and make the prediction results more accurate.

[0080] The general training process of the meteorological numerical spatiotemporal prediction model in this embodiment can be as follows: Figure 3As shown, this embodiment can obtain raw meteorological data from satellite remote sensing data, numerical weather high-altitude data and numerical weather ground data, and preprocess the raw meteorological data to obtain preprocessed meteorological data. The preprocessing process includes Gaussian weight calculation, building a meteorological data set based on the preprocessed meteorological data, training an RMT-LSTM spatiotemporal prediction deep learning model based on the meteorological data set, and using the trained RMT-LSTM spatiotemporal prediction deep learning model as a meteorological numerical spatiotemporal prediction model.

[0081] The general training process of the power generation space data conversion model in this embodiment can be as follows: Figure 4 As shown, this embodiment can obtain the ground meteorological data of the original power generation data set from the numerical weather ground data of the power generation data set, preprocess the ground meteorological data of the original power generation data set to obtain preprocessed power conversion data, and construct a spatial data conversion data set based on the preprocessed power conversion data to train a CNN multi-channel spatial deep learning network, and use the trained CNN model as the power generation power spatial data conversion model.

[0082] The general process of predicting wind power generation in this embodiment can be as follows: Figure 5 As shown, in this embodiment, the meteorological data to be measured can be obtained from the satellite remote sensing data, numerical weather high-altitude data and numerical weather ground data collected in real time, and the meteorological data to be measured is first input into the meteorological numerical spatiotemporal prediction model to obtain prediction results of various meteorological elements. In this embodiment, the ground meteorological data prediction results can be selected to predict the wind power generation, and the ground meteorological data prediction results are input into the power generation space data conversion model to obtain the output wind power generation prediction results.

[0083] The following combination Figure 6 , Figure 6 A structural block diagram of a wind power prediction device provided by an embodiment of the present invention, the device may include:

[0084] The first module 100 is used to obtain historical power generation data of the wind farm and historical meteorological data of the target area, and divide the historical meteorological data into multiple time series samples in chronological order;

[0085] The second module 200 is used to train the RMT-LSTM spatiotemporal prediction deep learning network based on the meteorological data set constructed based on the time series samples to obtain a trained meteorological numerical spatiotemporal prediction model;

[0086] The third module 300 is used to train a multi-channel spatial deep learning network based on the spatial data conversion data set constructed based on the historical power generation data and the historical meteorological data to obtain a power generation spatial data conversion model;

[0087] The fourth module 400 is used to input the meteorological data to be measured into the meteorological numerical spatiotemporal prediction model to obtain the output meteorological element prediction results, and input the meteorological element prediction results into the power generation spatial data conversion model to obtain the output power generation prediction results.

[0088] Based on the above embodiments, the method of the present invention divides the wind power prediction problem into two problems: meteorological numerical spatiotemporal prediction and power generation mapping, and solves them in turn. In the process of meteorological numerical spatiotemporal prediction, the RMT-LSTM structure that integrates the RMT model and the ST-LSTM model is adopted to enhance the spatial feature extraction capability of the model and make the prediction results more accurate.

[0089] Based on the above embodiment, the first module 100 may include:

[0090] The first unit is used to obtain the initial historical power generation data of the wind farm and the initial historical meteorological data of the target area;

[0091] The second unit is used to perform interpolation processing on the missing data in the initial historical power generation data and the initial historical meteorological data to obtain the completed historical power generation data and the completed historical meteorological data;

[0092] The third unit is used to perform standardization processing on the supplemented historical power generation data and the supplemented historical meteorological data to obtain the historical power generation data and the historical meteorological data.

[0093] Based on the above embodiments, the first module 100 may further include:

[0094] A fourth unit is used to determine the Gaussian weight of each type of data in the historical meteorological data based on the Gaussian weight function;

[0095] The fifth unit is used to stack the Gaussian weight and the historical meteorological data in the channel dimension.

[0096] Based on the above embodiments, the historical meteorological data includes: historical satellite remote sensing data, historical numerical weather high-altitude data and historical numerical weather ground data.

[0097] Based on the above embodiments, the third module 300 includes:

[0098] The sixth unit is used to train the multi-channel spatial deep learning network based on the spatial data conversion data set constructed based on the historical power generation data and the historical numerical weather ground data in the historical meteorological data to obtain the power generation spatial data conversion model.

[0099] Based on the above embodiments, the RMT-LSTM spatiotemporal prediction deep learning network has 4 network layers.

[0100] Based on the above embodiments, the multi-channel spatial deep learning network is a CNN model or a Swin-Transformer model.

[0101] Based on the above embodiments, the present invention further provides an electronic device, which may include a memory and a processor, wherein the memory stores a computer program, and when the processor calls the computer program in the memory, the steps provided in the above embodiments may be implemented. Of course, the device may also include various necessary network interfaces, power supplies, and other components.

[0102] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by an execution terminal or a processor, the method provided in the embodiment of the present invention can be implemented; the storage medium may include: 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, and other media that can store program codes.

[0103] In this article, relational terms such as first and second, etc. are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

Claims

1. A wind power prediction method, characterized in that: include: Acquire historical power generation data of the wind farm and historical meteorological data of the target area, and divide the historical meteorological data into multiple time series samples in chronological order; The meteorological data set constructed based on the time series samples is used to train the RMT-LSTM spatiotemporal prediction deep learning network to obtain a trained meteorological numerical spatiotemporal prediction model; Training a multi-channel spatial deep learning network based on a spatial data conversion data set constructed based on the historical power generation data and the historical meteorological data to obtain a power generation spatial data conversion model; The meteorological data to be measured is input into the meteorological numerical spatiotemporal prediction model to obtain the output meteorological element prediction result, and the meteorological element prediction result is input into the power generation spatial data conversion model to obtain the output power generation prediction result.

2. The wind power prediction method according to claim 1, characterized in that: The obtaining of historical power generation data of the wind farm and historical meteorological data of the target area includes: Acquiring initial historical power generation data of the wind farm and initial historical meteorological data of the target area; Interpolating the missing data in the initial historical power generation data and the initial historical meteorological data to obtain the completed historical power generation data and the completed historical meteorological data; The historical power generation data and the historical meteorological data are standardized to obtain the historical power generation data and the historical meteorological data.

3. The wind power prediction method according to claim 2, characterized in that: Also includes: Determine the Gaussian weight of each type of data in the historical meteorological data based on the Gaussian weight function; The Gaussian weight and the historical meteorological data are stacked in the channel dimension.

4. The wind power prediction method according to claim 1, characterized in that: The historical meteorological data include: historical satellite remote sensing data, historical numerical weather high-altitude data and historical numerical weather ground data.

5. The wind power prediction method according to claim 1, characterized in that: The spatial data conversion data set constructed based on the historical power generation data and the historical meteorological data trains a multi-channel spatial deep learning network to obtain a power generation spatial data conversion model, including: The multi-channel spatial deep learning network is trained based on the spatial data conversion data set constructed based on the historical power generation data and the historical numerical weather ground data in the historical meteorological data to obtain the power generation spatial data conversion model.

6. The wind power prediction method according to claim 1, characterized in that: The RMT-LSTM spatiotemporal prediction deep learning network has 4 network layers.

7. The wind power prediction method according to claim 1, characterized in that: The multi-channel spatial deep learning network is a CNN model or a Swin-Transformer model.

8. A wind power prediction device, characterized in that: include: The first module is used to obtain the historical power generation data of the wind farm and the historical meteorological data of the target area, and divide the historical meteorological data into multiple time series samples in chronological order; The second module is used to train the RMT-LSTM spatiotemporal prediction deep learning network based on the meteorological data set constructed based on the time series samples to obtain a trained meteorological numerical spatiotemporal prediction model; The third module is used to train a multi-channel spatial deep learning network based on the spatial data conversion data set constructed based on the historical power generation data and the historical meteorological data to obtain a power generation spatial data conversion model; The fourth module is used to input the meteorological data to be measured into the meteorological numerical spatiotemporal prediction model to obtain the output meteorological element prediction results, and input the meteorological element prediction results into the power generation spatial data conversion model to obtain the output power generation prediction results.

9. An electronic device, characterized in that: include: Memory, for storing computer programs; A processor, configured to implement the wind power prediction method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the wind power prediction method according to any one of claims 1 to 7 is implemented.

Images