Wind power generation power prediction method and system

Abstract

The invention discloses a wind power generation power prediction method and system, and belongs to the technical field of wind power generation processing, and the method comprises the steps: building a multivariate time series prediction data set based on the historical data of a to-be-predicted target, and training a multivariate time series prediction model based on the multivariate time series prediction data set to obtain a power prediction pre-training model; the power prediction pre-training model is adopted to predict the current parameter data of the to-be-predicted target to obtain the power generation power of the to-be-predicted target in the future set time, the method is excellent in performance in time series prediction tasks of multiple fields based on the multivariate time series prediction data set, and experimental results show that the method is high in prediction efficiency. According to the method provided by the invention, the long and short term dependency relationship in the multivariate time sequence can be effectively captured, and the accuracy and stability of wind power generation power prediction are improved by utilizing physical constraints.

Description

Technical Field

[0001] The present invention belongs to the technical field of wind power generation processing, and in particular relates to a wind power generation power prediction method and system. Background Art

[0002] Accurate prediction of wind power generation is conducive to grid dispatchers to formulate reasonable power generation plans and operation modes in advance, and coordinate the peak load regulation and frequency regulation of the power system, which is of great significance for the continuous and stable operation of the power system. There are many factors that affect the size of wind power generation. In addition to stable geographical factors such as topography and landforms, there are also meteorological factors with strong randomness, including wind speed, wind direction, temperature, atmospheric pressure and humidity, which leads to strong volatility and intermittency of wind power in the time dimension. Therefore, modeling of wind power generation requires not only in-depth consideration of the fluctuation regularity brought about by the long-term series of historical power generation, but also full exploration of the correlation between multiple related variables and future power generation.

[0003] Traditional physical and statistical methods are limited in both modeling difficulty and prediction accuracy, and it is difficult to mine the complex nonlinear relationship between wind power and related variables. Traditional methods often rely on simplified assumptions and cannot effectively capture the complex patterns in actual data, resulting in low prediction accuracy. Deep learning methods have significant advantages in fitting the complex nonlinear relationship between multiple influencing factors and power data. It can explore the fluctuation law of wind power in the time dimension, so that the prediction results can achieve higher accuracy. For example, the self-attention mechanism represented by the long short-term memory (LSTM) network and the Transformer (transformer model) is widely used in the field of sequence modeling, but the single LSTM has the disadvantages of insufficient feature extraction ability and easy overfitting of the model. Although the Transformer performs well in capturing dependencies, the quadratic complexity of its attention mechanism limits its application in long-distance time series prediction; therefore, the existing methods have low accuracy in wind power prediction and high computational complexity when dealing with long-distance time dependencies. Summary of the invention

[0004] The object of the present invention is to provide a method and system for predicting wind power generation, so as to overcome the problem of low accuracy of wind power generation prediction in the prior art.

[0005] To achieve the above purpose, the technical solution adopted by the present invention is as follows: A method for predicting wind power generation power comprises the following steps: A multivariate time series prediction data set is constructed based on the historical data of the target to be predicted, and a multivariate time series prediction model is trained based on the multivariate time series prediction data set to obtain a power prediction pre-training model; The power prediction pre-training model is used to predict the current parameter data of the target to be predicted to obtain the power generation power of the target to be predicted within a set time in the future.

[0006] Furthermore, the data in the multivariate time series prediction data set has time characteristics and physical characteristics, and the data in the multivariate time series prediction data set meets the requirements of uniform time intervals and constant number of features.

[0007] Furthermore, the time characteristics of the data in the multivariate time series prediction data set refer to that the data in the multivariate time series prediction data set includes the date and time stamp when the data is collected, and the date and time stamp format of all data collection is consistent.

[0008] Furthermore, the physical characteristics of the data in the multivariate time series prediction dataset refer to high-dimensional time series features obtained by integrating word embedding, time embedding and space embedding, and physical characteristics extracted from the high-dimensional time series features.

[0009] Furthermore, a multivariate time series prediction dataset is constructed based on the historical data of the target to be predicted, and the data in the multivariate time series prediction dataset obtained above is cleaned and standardized: The data in the multivariate time series prediction data set is cleaned, specifically including the following steps: the missing values ​​filled with NULL characters in the multivariate time series prediction data set are filled with the mean of the two values ​​before and after the missing interval; if both the two values ​​before and after are missing, the closest non-missing values ​​are searched level by level for mean calculation; The data in the cleaned multivariate time series prediction data set is standardized, specifically making the mean of the data in the multivariate time series prediction data set 0 and the variance 1.

[0010] Further, a multivariate time series prediction model is trained based on the multivariate time series prediction data set to obtain a power prediction pre-training model, wherein the multivariate time series prediction model includes an embedding module layer, a preprocessing module layer, a feature enhancement module layer, and a prediction module layer; The embedding module layer is used to fuse word embedding, time embedding and space embedding of the input data to obtain high-dimensional time series features; The preprocessing module layer uses the multi-head attention mechanism to preprocess the high-dimensional time series features output by the embedding module layer and fuse the high-dimensional features of different subspaces; then the fused high-dimensional features are further processed through nonlinear activation functions, summation, and normalization; The feature enhancement module layer enhances the input sequence for further processing through a recursive mechanism; The prediction module layer is used to predict the fused features after enhancement processing to obtain the prediction results.

[0011] Furthermore, the feature enhancement module layer includes a state space module and a physical space module. The state space module is used to extract data state features of the high-dimensional features of the time series data after further processing, and the physical space module is used to extract physical constraints of the high-dimensional features of the time series data after further processing.

[0012] A second aspect of the present invention is a wind power generation power prediction system, comprising a pre-training module and a prediction module; A pre-training module, which constructs a multivariate time series prediction data set based on the historical data of the target to be predicted, and trains the multivariate time series prediction model based on the multivariate time series prediction data set to obtain a power prediction pre-training model; The prediction module predicts the current parameter data of the target to be predicted based on the power prediction pre-training model to obtain the power generation power of the target to be predicted within a set time in the future.

[0013] A third aspect of the present invention is a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned wind power generation prediction method when executing the computer program.

[0014] A fourth aspect of the present invention is a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned wind power generation prediction method are implemented.

[0015] Compared with the prior art, the present invention has the following beneficial technical effects: The present invention discloses a method for predicting wind power generation. A multivariate time series prediction data set is constructed based on historical data of a target to be predicted. A multivariate time series prediction model is trained based on the multivariate time series prediction data set to obtain a power prediction pre-training model. The power prediction pre-training model is used to predict current parameter data of the target to be predicted to obtain the power generation of the target to be predicted within a set future time. The present invention is based on the multivariate time series prediction data set and performs well in time series prediction tasks in multiple fields. Experimental results show that the method proposed by the present invention can effectively capture long-term and short-term dependencies in multivariate time series and use physical constraints to improve the accuracy and stability of wind power generation prediction.

[0016] Preferably, the present invention adopts the multivariate time series prediction model using the embedding module layer, preprocessing module layer, and feature enhancement module layer architecture, which can effectively reduce the cumulative error caused by the traditional recurrent neural network prediction method, reduce the deployment and use costs, and through the feature enhancement module layer, the predicted value at each moment does not depend on the prediction results at other moments, avoiding the cumulative error caused by recursion, and reducing the risk of gradient explosion or gradient disappearance caused by the recursive network. The input data is embedded in words, time embedded, and space embedded to obtain high-dimensional time series features, making the feature expression of the input vector richer and more stable, thereby improving the feature expression ability and improving the prediction accuracy.

[0017] Preferably, the present invention introduces physical constraint loss into the loss function to further ensure the physical consistency of the prediction results. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Schematic diagram of the wind power generation prediction method in an embodiment of the present invention. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings 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 should fall within the scope of protection of the present invention.

[0020] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0021] like Figure 1 As shown, the present invention provides a method for predicting wind power generation, which specifically includes the following steps: S1, constructing a multivariate time series prediction data set based on the historical data of the target to be predicted, and training a multivariate time series prediction model based on the multivariate time series prediction data set to obtain a power prediction pre-training model; S2, using the power prediction pre-training model to predict the current parameter data of the target to be predicted to obtain the power generation of the target to be predicted within a set time in the future.

[0022] The current parameter data of the target to be predicted includes the latitude and longitude, altitude, wind speed, wind direction, temperature, atmospheric pressure and humidity of the target to be predicted.

[0023] The data in the multivariate time series prediction data set has time characteristics and physical characteristics; the data in the multivariate time series prediction data set meets the requirements of uniform time intervals and constant number of features.

[0024] The data must meet the requirement of uniform time intervals. Specifically, the historical data of the target to be predicted is time series data, that is, it is sorted in chronological order, and the time difference between adjacent data is constant. If data is lost in the time series data, a timestamp is added at the time node, and NULL characters are used to fill in the position where the data is missing.

[0025] For data that meets the requirement of a constant number of features, specifically: the data in the multivariate time series prediction data set has the same feature type and number of features at each moment. If the value of the data at some moment is missing, a timestamp is added at the time node, and NULL characters are used to fill in the position where the data is missing.

[0026] The time characteristics of the data in the multivariate time series prediction data set refer to that the data in the multivariate time series prediction data set not only records the data itself, but also records the date and time stamp when the data is collected, and the date and time stamp format of all data collection is consistent.

[0027] The physical characteristics of the data in the multivariate time series prediction dataset refer to the high-dimensional time series features obtained by integrating word embedding, time embedding and space embedding, and the physical characteristics extracted from the high-dimensional time series features; the extracted physical characteristics specifically include time change rate, flow velocity and divergence. In order to improve the accuracy of wind power prediction, the data in the multivariate time series prediction dataset contains physical quantity information related to physical constraints, including latitude and longitude, altitude, wind speed, wind direction, temperature, atmospheric pressure and humidity.

[0028] Clean and standardize the data in the multivariate time series forecasting dataset obtained in the above steps: The data in the multivariate time series prediction data set are cleaned, specifically including the following steps: the missing values ​​filled with NULL characters in the multivariate time series prediction data set are filled with the mean of the two values ​​before and after the missing interval; if both the two values ​​before and after are missing, the closest non-missing values ​​are searched level by level for mean calculation.

[0029] The data in the cleaned multivariate time series forecasting dataset is standardized, which specifically includes the following steps: The following formula is used for standardization so that the mean of the data in the multivariate time series prediction data set is 0 and the variance is 1:

[0030] In the formula, represents the i-th data point in the multivariate time series forecasting dataset, represents the mean of the sequence, represents the calculated series standard deviation, Represents the data in the Multivariate Time Series Forecasting dataset.

[0031] Based on the multivariate time series prediction data set, a multivariate time series prediction model is trained to obtain a power prediction pre-trained model, wherein the multivariate time series prediction model includes an embedding module layer, a preprocessing module layer, a feature enhancement module layer, and a prediction module layer; The embedding module layer is used to fuse word embedding, time embedding and space embedding of the input data to obtain high-dimensional time series features; the data input to the embedding module layer is standardized data.

[0032] The embedding module layer is the basic part of the multivariate time series prediction model. Its function is to convert the input time series data and related context information into high-dimensional time series features so that the complex patterns and features in the data can be effectively processed and captured later. In this application, the embedding module layer is used to perform word embedding, time embedding and space embedding fusion. The calculation formula is as follows.

[0033]

[0034]

[0035]

[0036]

[0037] In the formula, represents the input time series data, Represents temporal context information, Represents spatial information. and Represent one-dimensional convolution and linear transformation respectively, , , and They represent the calculated total data embedding, word embedding, time embedding, and space embedding respectively.

[0038] The preprocessing module layer uses the multi-head attention mechanism to preprocess the high-dimensional time series features output by the embedding module layer and fuse the high-dimensional features of different subspaces; then the fused high-dimensional features are further processed through nonlinear activation functions, summation, and normalization.

[0039] The multi-head self-attention mechanism can capture the correlation between different positions in the input high-dimensional time series features through parallel calculation of multiple attention heads, thereby enhancing the feature extraction ability of the model.

[0040] (11) (12) (13) (14) (15) In the formula, , and Respectively query, key, and value vectors for each attention head; , and are the learnable weight matrices for query, key, and value, respectively; For the The output of an attention head is Represents the projection matrix of the multi-head attention output; is the scaling factor, is the dimension of the key vector, which is used to prevent the gradient from disappearing due to excessive dot product values; Represents the output of the multi-head attention mechanism.

[0041] After the multi-head attention mechanism outputs, in order to further enhance the nonlinear representation and stability of the features, this application introduces nonlinear activation functions, summation, and normalization to enhance the output of the multi-head attention mechanism. The purpose is to enhance the effect of feature extraction, improve the expression ability of the model and the training stability. After the enhanced processing, the output is obtained. .

[0042]

[0043] In the formula Representation layer normalization processing; Represents activation of the output of the multi-head attention mechanism.

[0044] The feature enhancement module layer is the core component in the multivariate time series prediction model. The feature enhancement module layer enhances the input sequence for further processing through a recursive mechanism, capturing the temporal features in the input sequence while maintaining the consistency of the physical properties of the high-dimensional features.

[0045] Specifically, the feature enhancement module layer processes the high-dimensional features obtained by preprocessing the multi-head attention mechanism through a recursive mechanism to enhance the expressive power of feature representation; it can effectively capture local features, physical constraints and temporal dependencies in the input data, thereby improving the prediction performance of the model.

[0046] The feature enhancement module layer includes a state space module and a physical space module. The state space module is used to extract the data state features of the high-dimensional features of the time series data after further processing. The physical space module is used to extract the physical constraints of the high-dimensional features of the time series data after further processing. The physical constraints include the channel velocity field and the time divergence field. The specific calculation steps are as follows: The state space module is used to extract the data state features of high-dimensional features of time series data. The specific process is as follows:

[0047]

[0048]

[0049] In the formula is the predicted output of the state-space module, which is the output of the convolution and nonlinear activation. Input to the state space module to capture timing dependencies. , is the batch size, is the time dimension, is the number of high-dimensional feature channels. , and are the parameter matrices of the state-space module, , They are Moment and The hidden state of the moment, It is a time series.

[0050] Next, the linear transformation result output by the state space module is With the original input Through residual connection multiplication, a new feature representation is formed, and then linear transformation is performed again to match the dimension of the original input to obtain the data state features extracted by the state space module for the time series data. :

[0051] The physical space module is used to extract the physical constraints of high-dimensional features of time series data using the following formula:

[0052] In the physical space module, the enhanced features are first transposed so that the subsequent one-dimensional convolution operation can calculate the channel velocity on the feature channel axis; where, express The transpose of represents the channel speed, represents the transposed coefficient, Represents the time difference between two time points in a time series.

[0053] After obtaining the channel velocity, use the same method to calculate the channel acceleration :

[0054] Where: express The channel speed at the moment, express The channel speed at the moment.

[0055] For the untransposed input features, the partial derivatives are calculated and added on multiple feature channels at the same time, which is the divergence of the features on the multi-channel axis at that moment, reflecting the expansion and compression of the time series features on the time series. Represented as a feature in The dispersion of time reflects its Expansion and compression at d channels at a time:

[0056] The convolved channel velocity and acceleration representations are input into the channel velocity field of the physical space module to extract the velocity field information in the high-dimensional feature channel. :

[0057]

[0058] In the formula, They represent the velocity matrices in the physical space model respectively; express The hidden state of the velocity field at time , express The hidden state of the velocity field at time , Represents the velocity field adjustment coefficient in the physical space module; Similarly, the time divergence after convolution is input into the time divergence field of the physical space module to extract the divergence field information of high-dimensional features at multiple times. :

[0059]

[0060] In the formula, They represent the scatter matrix in the physical space model, express Hidden state of the momentary divergence field; express The hidden state of the momentary divergence field, Represents the divergence field adjustment coefficient in the physical space module.

[0061] The time divergence field output is transposed, dot-producted with the channel velocity field, and then linearly transformed to obtain the physical constraints of the physical space module. :

[0062] Finally, the state space and physical space obtained by the time series data through the state space module and the physical space module are integrated, so that the time series data and its physical characteristics can be kept consistent while also integrating the data state characteristics and physical constraints to support subsequent loss calculations. The final integrated fusion feature for:

[0063] The prediction module layer linearly transforms the fused features output by the feature enhancement module layer, and inputs them into the prediction layer for prediction under the constraints of the physical loss function to generate the final prediction result:

[0064] In the formula, is the final predicted power generation; It is the high-dimensional feature matrix of the prediction module layer; is the weight matrix; is the bias term.

[0065] A loss function is set in the prediction module layer, and a physical constraint loss term is introduced into the loss function to measure the deviation between the model prediction results and the physical laws. The formula is:

[0066] In the formula, represents the loss function, represents the hyperparameter that adjusts the weight between the prediction error loss and the physical constraint loss, is the total number of samples in the dataset.

[0067] During the specific training process, the multivariate time series prediction dataset is divided into training set, test set and validation set in a ratio of 7:2:1; the loss is tested on the test set after each round of training. When the loss increases for three consecutive rounds, the training is stopped, and the weight file with the smallest loss on the test set is stored.

[0068] The power prediction pre-training model obtained after training is used to predict the test set, and the test set used for prediction and the training set used for training are independent and identically distributed. The present invention shows the characteristics of accuracy and speed in real tasks.

[0069] In the experimental verification, the present application evaluates the prediction results of various models on the prediction data for the next 15 minutes. The experimental results show that the method of the present application performs well in the task of wind power generation prediction. The specific results are shown in Table 1. In the table, They represent the mean absolute error, root mean square error and coefficient of determination between the predicted value and the actual value respectively.

[0070] Table 1 Comparison of prediction results of the method of the present invention and the prior art in the next 15 minutes

[0071] Table 2 Prediction results of the method of the present invention and the prior art for the next 30 minutes

[0072] Table 3 Prediction results of the method of the present invention and the prior art at the next hour

[0073] Table 4 Prediction results of the method of the present invention and the prior art at the next 2 hours

[0074] Table 5 Prediction results of the method of the present invention and the prior art in the next 4 hours

[0075] In the study of wind power prediction, we used a variety of deep learning models for comparison, including LSTM (Long Short-Term Memory Network), GRU (Gated Recurrent Unit), BiGRU (Bidirectional Gated Recurrent Unit), Transformer (Transformer Model) and Mamba (Selective Structured State Space Model). LSTM and GRU models can effectively capture long-term and short-term dependencies in time series data through their unique gate mechanism, while BiGRU further enhances the ability to extract bidirectional features of data. The Transformer model uses a self-attention mechanism and performs well in processing long time series, especially in capturing global dependencies. The Mamba model is an existing improved model method that further optimizes the structure of the deep learning model and improves its performance in wind power prediction.

[0076] By comparing the experimental data in Tables 1 to 5, we can clearly see the excellent performance of the method of the present invention in wind power prediction. Compared with other models, the method of the present invention shows higher accuracy in predictions of multiple time windows (such as the next 15 minutes, 30 minutes, 1 hour, 2 hours and 4 hours). ) and the root mean square error ( ), the error values ​​of the method of the present invention are lower than those of other models in all time periods, especially in the long time window (such as 2 hours and 4 hours), the prediction error is the smallest. At the same time, the coefficient of determination ( ) is close to or exceeds 0.9 in each time period, which is significantly higher than other models. This shows that the method of the present invention can not only capture the long-term and short-term dependence characteristics of wind power generation, but also better adapt to the complex changes of data, so it has higher prediction accuracy and stability in practical applications.

[0077] In one embodiment of the present invention, a wind power generation power prediction system includes a pre-training module and a prediction module; A pre-training module, which constructs a multivariate time series prediction data set based on the historical data of the target to be predicted, and trains the multivariate time series prediction model based on the multivariate time series prediction data set to obtain a power prediction pre-training model; The prediction module predicts the current parameter data of the target to be predicted based on the power prediction pre-training model to obtain the power generation power of the target to be predicted within a set time in the future.

[0078] In another embodiment of the present invention, the present invention further provides a storage medium, specifically a computer-readable storage medium (Memory), which is a memory device in a terminal device for storing programs and data. It is understandable that the computer-readable storage medium here can include both the built-in storage medium in the terminal device and the extended storage medium supported by the terminal device. The computer-readable storage medium provides a storage space, which stores the operating system of the terminal. In addition, one or more instructions suitable for being loaded and executed by the processor are also stored in the storage space, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed memory or a non-volatile memory, such as at least one disk storage.

[0079] One or more instructions stored in a computer-readable storage medium can be loaded and executed by a processor to implement the corresponding steps of the power grid broadband oscillation monitoring method in the above-mentioned embodiment; one or more instructions in the computer-readable storage medium are loaded by the processor and the following steps are executed: acquiring a power grid signal and performing spectrum analysis to obtain an initial spectrum analysis result; based on the initial spectrum analysis result, acquiring all non-power frequency band oscillation monitoring signals in the power grid signal; selecting each oscillation detection signal to be corrected from all non-power frequency band oscillation monitoring signals, wherein the oscillation detection signal to be corrected is an oscillation monitoring signal whose amplitude is greater than the average amplitude of all non-power frequency band oscillation monitoring signals; based on each oscillation monitoring signal to be corrected and the oscillation monitoring signal within a preset frequency range thereof, correcting the initial spectrum analysis result of each oscillation monitoring signal to be corrected, obtaining a corrected spectrum analysis result of each oscillation monitoring signal to be corrected, and monitoring the broadband oscillation of the power grid according to the corrected spectrum analysis result.

[0080] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, optical storage, etc.) containing computer-usable program codes.

Claims

1. A method for predicting wind power generation, characterized in that: The following steps are involved: A multivariate time series prediction data set is constructed based on the historical data of the target to be predicted, and a multivariate time series prediction model is trained based on the multivariate time series prediction data set to obtain a power prediction pre-training model; Construct a multivariate time series prediction dataset based on the historical data of the target to be predicted, and clean and standardize the data in the obtained multivariate time series prediction dataset: The data in the multivariate time series prediction data set is cleaned, specifically including the following steps: the missing values ​​filled with NULL characters in the multivariate time series prediction data set are filled with the mean of the two values ​​before and after the missing interval; if both the two values ​​before and after are missing, the closest non-missing values ​​are searched level by level for mean calculation; Standardize the data in the cleaned multivariate time series prediction data set, specifically making the mean of the data in the multivariate time series prediction data set 0 and the variance 1; Use the power prediction pre-training model to predict the current parameter data of the target to be predicted to obtain the power generation of the target to be predicted within a set time in the future; Based on the multivariate time series prediction data set, a multivariate time series prediction model is trained to obtain a power prediction pre-trained model, wherein the multivariate time series prediction model includes an embedding module layer, a preprocessing module layer, a feature enhancement module layer, and a prediction module layer; The embedding module layer is used to fuse word embedding, time embedding and space embedding of the input data to obtain high-dimensional time series features; The preprocessing module layer uses the multi-head attention mechanism to preprocess the high-dimensional time series features output by the embedding module layer and fuse the high-dimensional features of different subspaces; then the fused high-dimensional features are further processed through nonlinear activation functions, summation, and normalization; The feature enhancement module layer enhances the input sequence for further processing through a recursive mechanism; The prediction module layer is used to predict the fused features after enhancement processing to obtain the prediction results.

2. A method for predicting wind power generation according to claim 1, characterized in that: The data in the multivariate time series prediction data set has time characteristics and physical characteristics, and the data in the multivariate time series prediction data set meets the requirements of uniform time intervals and constant number of features.

3. A method for predicting wind power generation according to claim 2, characterized in that: The time characteristics of the data in the multivariate time series prediction data set refer to that the data in the multivariate time series prediction data set includes the date and time stamp when the data is collected, and the date and time stamp format of all data collection is consistent.

4. A method for predicting wind power generation according to claim 2, characterized in that: The physical characteristics of the data in the multivariate time series prediction dataset refer to high-dimensional time series features obtained by integrating word embedding, time embedding and space embedding, and physical characteristics extracted from the high-dimensional time series features.

5. A method for predicting wind power generation according to claim 1, characterized in that: The feature enhancement module layer includes a state space module and a physical space module. The state space module is used to extract data state features of high-dimensional features of time series data after further processing, and the physical space module is used to extract physical constraints of high-dimensional features of time series data after further processing.

6. A wind power generation power prediction system, characterized in that: Includes pre-training module and prediction module; A pre-training module constructs a multivariate time series prediction data set based on the historical data of the target to be predicted, and trains the multivariate time series prediction model based on the multivariate time series prediction data set to obtain a power prediction pre-training model; The prediction module predicts the current parameter data of the target to be predicted based on the power prediction pre-training model to obtain the power generation power of the target to be predicted within a set time in the future.

7. A computer device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the wind power generation prediction method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the wind power generation prediction method according to any one of claims 1 to 5 are implemented.

Images