Wind power plant wind speed missing value complementation method based on mode meteorological data

Abstract

The invention provides a wind power plant wind speed missing value complementing method based on mode meteorological data, and the method comprises the following steps: forming a multivariable time sequence tensor based on an obtained wind power plant actually measured wind speed time sequence and corresponding mode meteorological multi-element data, and constructing sample data; training a time sequence interpolation model by using a weighted loss function based on the sample data; and inputting the actually measured wind speed time sequence with the missing position and the corresponding mode meteorological multi-element data into the time sequence interpolation model, performing prediction completion on the missing position, and performing post-processing operation to obtain a complete wind speed time sequence after completion. The method has the beneficial effects that by constructing an observation missing mask, designing a reasonable training strategy and introducing a deep learning time sequence interpolation model, high-credibility wind speed complementation can be realized in different missing scenes, so that the precision and reliability of wind power prediction, wind resource evaluation and wind power plant operation management are effectively improved.

Description

Technical Field

[0001] This invention belongs to the field of new energy data processing and machine learning technology, and in particular relates to a method for completing missing wind speed values ​​in wind farms based on model meteorological data. Background Technology

[0002] During wind farm operation, wind speed is a crucial parameter for wind power prediction, equipment control, and operation and maintenance. However, due to sensor malfunctions, communication interruptions, or abnormal data acquisition, wind speed observation data inevitably contains gaps, and these gaps are often irregular and can occur over extended periods. Such gaps not only affect the accuracy of wind power prediction but also pose potential risks to wind farm operation scheduling and equipment maintenance.

[0003] Existing methods for completing missing wind speed values ​​mainly include traditional methods such as linear interpolation, polynomial interpolation, mean imputation, and K-nearest neighbor (KNN) interpolation based on similar samples. While effective for short-term, regular missing values, these methods often fail when faced with long-term, continuous missing values ​​or simultaneous missing values ​​of multiple variables, resulting in significant discrepancies between the interpolated results and actual observations. Furthermore, they generally fail to fully utilize external meteorological data, making it difficult to reflect the true dynamic characteristics of the wind field.

[0004] Numerical Weather Prediction (NWP) and reanalysis data provide multi-element, multi-altitude meteorological information, offering advantages such as strong temporal continuity and wide spatial coverage. These model data can, to some extent, compensate for information gaps caused by observational deficiencies. However, systematic biases generally exist between model data and actual observations. Directly using model data to replace observational data often introduces error accumulation, making it difficult to meet high-precision wind speed completion and subsequent operational needs.

[0005] Therefore, a systematic approach is urgently needed to use model meteorological data as external prior information and to jointly model it with limited measured observation data. Summary of the Invention

[0006] In view of this, the present invention aims to propose a method for completing missing wind speed values ​​in wind farms based on model meteorological data, in order to solve the problems that existing technologies often fail in the completion process when faced with long-term continuous missing values ​​or simultaneous missing values ​​of multiple variables, the interpolation results have obvious deviations from the actual observations, and generally fail to make full use of external meteorological data, making it difficult to reflect the true dynamic characteristics of the wind farm.

[0007] To achieve the above objectives, the technical solution of the present invention is implemented as follows: The method for completing missing wind speed values ​​in wind farms based on model meteorological data includes the following steps: S1. Based on the obtained wind speed time series of wind farms and the corresponding model meteorological multi-element data, a multivariate time series tensor is formed, and sample data is constructed based on the multivariate time series tensor. S2. Based on the sample data, train the time series interpolation model using a weighted loss function; S3. Input the missing measured wind speed time series and its corresponding model meteorological multi-element data into the time series interpolation model, predict and fill in the missing positions, and obtain the complete wind speed time series after post-processing. In step S1, based on the acquired measured wind speed time series of the wind farm and its corresponding model meteorological multi-element data, a multivariate time series tensor is formed, including: Interpolation or resampling methods are used to align the time of multi-element meteorological data from the model. A missing mask matrix is ​​constructed based on the measured wind speed time series of wind farms. Normalize or standardize the measured wind speed time series and time-aligned model meteorological multi-element data of the wind farm; A time-encoding mechanism is constructed, and a multivariate time series tensor is formed based on the time-encoding, the missing mask matrix, the normalized or standardized wind speed time series of wind farms, and the multi-element meteorological data from models.

[0008] Furthermore, in step S1, sample data is constructed based on the multivariate time series tensor, including: A sliding window is used to segment the multivariate time series tensor into sample data.

[0009] Furthermore, in step S2, based on the sample data, a time-series interpolation model is trained using a weighted loss function, including: A training target mask is constructed by randomly simulating short-term random missing data and long-term continuous missing data in the training samples. Construct a weighted loss function based on the training target mask; We use a weighted loss function to minimize the weighted reconstruction error.

[0010] Furthermore, the expression for the weighted loss function is as follows: ; In the formula, To predict wind speed, To measure the wind speed, Mean squared error (MSE) or mean absolute error (MAE) , To rebuild the weights, ∈{0,1} is the training target mask, and t is the time step.

[0011] Furthermore, in step S3, the post-processing operation includes: Smoothing; Physical constraint correction; Fusion verification with short-term available observation values.

[0012] Furthermore, the model's multi-element meteorological data includes at least one of the following elements: 2-meter temperature, 2-meter relative humidity, sea level pressure, 100-meter wind speed, 100-meter wind direction, 10-meter wind speed, 10-meter wind direction, and 10-meter gust.

[0013] Furthermore, the temporal interpolation model is set as a self-attention mechanism-based temporal interpolation model or other deep learning temporal interpolation models.

[0014] Compared with existing technologies, the wind speed missing value completion method for wind farms based on model meteorological data described in this invention has the following advantages: (1) Standardize and systematize multi-element meteorological data of multi-element and multi-altitude models and introduce them into the completion process. Utilize their temporal continuity and spatial coverage characteristics to provide reliable prior information for long missing segments, thereby significantly improving the completion accuracy.

[0015] (2) Enhance the model’s adaptability to diverse missing patterns (including long-term continuous missing patterns) by using missing simulation and mask weighted loss during the training phase.

[0016] (3) It has good scalability and supports multi-field joint training, online incremental updates and access to pattern data with different spatiotemporal resolutions.

[0017] (4) It can be directly and seamlessly embedded into the wind power forecasting business process, reducing the fluctuation of forecasting performance caused by missing data. Attached Figure Description

[0018] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a schematic diagram of the overall process described in an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the data organization and sample construction process described in an embodiment of the present invention; Figure 3 This is a schematic diagram of the complete wind speed filling sequence described in an embodiment of the present invention; Figure 4 This is a schematic diagram illustrating the effect of completing the missing wind speed segment according to an embodiment of the present invention. Detailed Implementation

[0019] It should be noted that, unless otherwise specified, the embodiments and features described in the present invention can be combined with each other.

[0020] In the description of this invention, it should be understood that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicating orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, are only for the convenience of describing the invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the invention. Furthermore, the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined with "first," "second," etc., may explicitly or implicitly include one or more of that feature. In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0021] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0022] The present invention will now be described in detail with reference to the accompanying drawings and embodiments.

[0023] The method for completing missing wind speed values ​​in wind farms based on model meteorological data includes the following steps: A1. Obtain the measured wind speed time series of the wind farm and the corresponding model meteorological multi-element data of the time series; A2. Perform time alignment and preprocessing on the model meteorological multi-element data to obtain a time-consistent multivariate sequence, and then normalize or standardize the multivariate sequence. A3. Construct an observation availability mask to identify the missing locations of measured wind speeds, and merge the measured wind speeds, multi-factor sequences, and the mask in chronological order to form the input tensor; A4. Input the input tensor into the temporal interpolation model. The temporal interpolation model is a self-attention-based temporal interpolation model or other deep learning temporal interpolation models. The trained model parameters are obtained by simulating missing observation data during the training phase and using a mask-based weighted loss function for optimization. A5. Based on the trained model, the missing locations of the measured wind speed are predicted and filled in, and the complete wind speed time series is obtained through physical constraints and post-processing operations.

[0024] The model's meteorological multi-element includes at least one of the following elements: 2-meter temperature, 2-meter relative humidity, sea level pressure, 100-meter wind speed, 100-meter wind direction, 10-meter wind speed, 10-meter wind direction, and 10-meter gust.

[0025] Model meteorological multi-element data are time-aligned using interpolation or resampling methods to compensate for differences in temporal resolution and data integrity.

[0026] During the training phase, training target masks are constructed by randomly simulating short-term random missing data and long-term continuous missing data in the training samples to enhance the model's generalization ability under different missing data conditions.

[0027] During training, a loss function based on missing location weights is used.

[0028] The completed wind speed time series can be applied to downstream operations such as wind power forecasting, wind resource assessment, or wind farm operation and maintenance. It can also be post-processed, including but not limited to smoothing, physical constraint correction, and fusion verification with short-term available observation values, to improve forecast accuracy and application reliability.

[0029] The specific implementation method is as follows: B1. Data Acquisition and Preprocessing B11. Obtain the measured wind speed time series V of the wind farm, and the corresponding model meteorological multi-element data M for that time period, as shown in the following expressions: ; ; In the formula, This is a time series of measured wind speeds at a wind farm. For model meteorological multi-element data, The measured wind speed at the wind farm at time step t. For model meteorological elements at time step t Data, This represents the total time step. =8 indicates the total number of meteorological elements in the model, including: 2-meter temperature, 2-meter relative humidity, sea level pressure, 100-meter wind speed, 100-meter wind direction, 10-meter gust, 10-meter wind speed, and 10-meter wind direction. If other meteorological layer data or reanalysis data are available, the element dimensions can be flexibly expanded.

[0030] B12. Considering that the sampling interval of model meteorological multi-element data is usually different from that of observation data, and there may be occasional missing data, interpolation or resampling methods are used to align the model meteorological multi-element data in time to obtain the completed time series, as shown in the following expression: ; In the formula, For time-aligned meteorological elements at time step t Data, For model meteorological elements at time step t Data, For time steps, For model meteorological elements, The total time step, This represents the total number of meteorological elements in the model.

[0031] B13. Construct a missing mask matrix for observed wind speeds. The missing mask matrix is ​​obtained directly from the integrity of the original data: when the observed wind speed at time step t exists and passes quality control (non-empty, non-anomaly), When the wind speed at that moment is missing or determined to be an invalid value, let To indicate the absence of a target object, and based on this, in order to achieve self-supervised reconstruction learning during the training phase, a training target mask is constructed. The training target mask does not come from the actual missing values, but rather from... At the effective observation locations, a subset of time steps are selected as "pseudo-missing" locations according to a preset masking strategy (such as random sampling, continuous time-time masking, or proportional masking), and the corresponding... This indicates that the given location is the training target (and needs to be reconstructed), and the remaining locations are set as follows: .

[0032] B14. To improve model convergence and training stability, the observed wind speed and model meteorological elements are standardized, such as using Z-score standardization, as shown in the following expression: ; In the formula, The measured wind speed at the wind farm at time step t is the standardized value. For the standardized model meteorological elements at time step t Data, and Let these represent the mean and standard deviation of the observed wind speed on the training dataset, respectively. and and are the mean and standard deviation of the k-th meteorological element on the training set, respectively.

[0033] To improve the convergence of model training.

[0034] B15. Considering that wind speed observations may be affected by sensor errors or environmental interference, outlier detection and denoising steps are introduced. Thresholding methods, seasonal quantile tests, and Median Absolute Deviation (MAD) methods can be used to mark outliers, and wavelet denoising or moving median filtering can be combined to suppress short-term noise, improving the stability and accuracy of the input data.

[0035] B16. To improve the model's ability to perceive time periodicity and temporal location information, a time encoding PE is added, with the following expression: ; In the formula, This indicates that time step t is the th position in the position encoding vector. Sine positional encoding values ​​in each dimension This indicates that time step t is the th position in the position encoding vector. Cosine positional encoding values ​​in each dimension; =0, 1, ..., d / 2-1 are the coding dimension indices, d is the total coding dimension, and 10000 is the scaling cardinality (empirical value). This coding can be concatenated with observed wind speed and model meteorological multi-element data features as model input.

[0036] B2. Sample Construction and Enhancement B21. Combine the normalized observed wind speed, model meteorological elements, missing mask, and time code to form a multivariate time series tensor, as shown in the following expression: ; In the formula, Let be a multivariable temporal tensor at time step t. This is the position encoding at time step t.

[0037] B22. Construct training samples using the sliding window method, with each window having a length of [length missing]. time step ; In the formula, For the i-th training sample window, Training sample window The sequence starting tensor in the sequence, Training sample window The tensor at the end of the sequence in the sequence, For window length, This is the sliding step size, which can be adjusted according to the number of samples. This is the starting position index of the sliding window.

[0038] B23. During training, a simulated missing mask is generated based on the empirical distribution. (i.e., the training target mask), including short-term random missing data and long-term continuous missing data, is expressed as follows: ; In the formula, This represents the minimum interval for wind farm data. This represents the maximum length of missing segments supported by the device and can be modified according to actual business needs. For each sample, the training objective is to reconstruct the masked portion while retaining some true observation locations to supervise model generalization.

[0039] B24. For long missing samples, oversampling can be used, or the long missing position can be weighted in the loss function to avoid the model training being biased towards short missing cases.

[0040] B3. Interpolation Implementation B31, will , , Input a temporal interpolation model and train it. The model can be a self-attention type temporal interpolation model or other existing deep learning temporal interpolation models.

[0041] B32. In the attention or input flow, an attention masking mechanism should be used to prevent the model from acquiring the masked true value (i.e., the value set to be true). The location is masked in attention logits.

[0042] B33. The model output is the predicted sequence within the window.

[0043] B34. The model training objective is to minimize the weighted reconstruction error, expressed as follows: ; In the formula, To predict wind speed, To measure the wind speed, Mean squared error (MSE) or mean absolute error (MAE) ∈{0,1} is the training target mask. , To reconstruct the weights, t is the time step.

[0044] Simultaneously, smoothing regularization and parameter regularization can be added to control output smoothness and prevent overfitting. Gradient clipping, learning rate decay, or optimizers (such as Adam) can also be used during training to stabilize the training.

[0045] B4. Reasoning Completion and Post-processing B41. In the inference phase, multiple overlapping predictions output by the sliding window are combined into a sequence using window weighting (triangular window or linear weight), as shown in the following expression: ; In the formula, For the first Time step in each window Predicted wind speed at that time The predicted wind speed is obtained by weighting multiple overlapping predictions. For the set of all windows covering time step t, For fusion weights (the first) Each window at time step The weighting coefficients, often using triangular windows or linear weights (to give higher prediction weights at the center of the window and lower weights at the edges), are ultimately synthesized into a complete wind speed sequence, as shown in the following expression: ; In the formula, This is the interpolated complete wind speed sequence.

[0046] B42. By using methods such as non-negative truncation, consistency correction with multi-height wind speed (power law or logarithmic wind profile), and extreme value truncation, ensure that the completion results conform to the physical laws of wind speed.

[0047] B5. Downstream Applications and Extended Scenarios B51. Input the completed wind speed sequence into the downstream model, including wind power prediction, wind resource assessment or wind farm operation and maintenance, to improve prediction accuracy and decision quality.

[0048] B52 can be expanded to multi-wind farm joint training, multi-regional model meteorological multi-element data input, multi-step prediction or iterative autoregressive prediction scenarios.

[0049] B53. It can support online incremental training or real-time updates of multi-element meteorological data input for the model, enabling the model to adapt to long-term operation of wind farms and seasonal meteorological changes.

[0050] Example 1: like Figure 1 As shown, the overall process of the wind speed missing value completion method for wind farms based on model meteorological data is as follows: This study uses partial data from a 15-minute interval measured wind speed dataset of a coastal wind farm from January 2023 to June 2025. The external model meteorological multi-element data is sourced from the Global Forecast System (GFS) provided by Open-Meteo, which offers wide spatial coverage and strong temporal continuity, providing reliable external references for missing observational data. The model meteorological elements selected in this embodiment include the following eight types: (a) Temperature at 2 meters (T2m); (b) 2m relative humidity RH; (c) Sea level pressure Psl; (d) Wind speed at 100 meters: WS100m; (e) 100m wind direction WD100m; (f) 10-meter gust GF10m; (g) Wind speed at 10 meters WS10m; (h) 10m wind direction WD10m; These elements can characterize, to some extent, various physical processes that affect wind speed changes, such as thermal circulation driven by temperature gradients, large-scale wind fields caused by pressure field distribution, and near-surface turbulence and surface friction effects.

[0051] C1. Data Sample Construction C11, such as Figure 2 As shown, the data organization and sample construction process strictly aligns the model meteorological multi-element data with the observed wind speed data according to timestamps, ensuring a one-to-one correspondence between the two at each time point. If the time resolution (e.g., 1 hour) of the model meteorological multi-element data is inconsistent with the observation resolution (15 minutes), cubic spline interpolation is used for resampling to obtain a sequence with consistent time intervals Δt=15 minutes, thereby eliminating the error caused by the inconsistent time resolution.

[0052] C12. Constructing a missing mask matrix The expression is as follows: ; This matrix is ​​used not only to distinguish between available and missing locations when inputting the model, but also as a supervision signal during training to ensure that the model only makes reconstruction predictions at missing locations, thus avoiding information leakage.

[0053] C13. Use Z-score normalization to normalize the observed wind speed and model meteorological multi-element data. The expression is as follows: ; In the formula, The mean, The standard deviation is the standard deviation. The purpose of standardization is to eliminate the dimensional differences between different physical quantities, ensuring that the model can learn features at a uniform scale during training.

[0054] C14, Add time location coding Then, the input variables are combined in chronological order into a multivariate temporal tensor. The expression is as follows: ; ; C15. The long sequence is divided into training samples using a sliding window method. Each window is set to a length of N = 4096 time steps (approximately 42 days), and the step size S is 2048. These values ​​can be adjusted based on the number of samples. The window sample format is as follows: ; In the formula, For the i-th training sample window, For training samples The sequence starting tensor in the sequence, For training samples The tensor at the end of the sequence in the sequence, For window length, This is the starting position index of the sliding window.

[0055] This construction method ensures that the model can capture long-term dependencies while avoiding excessive memory consumption caused by excessively long sequences.

[0056] C16. During training, additional simulated missing masks are generated. (i.e., training target mask), with a missing length of 1-1344 (corresponding to 15 minutes to 14 days) time steps. This strategy effectively improves the model's generalization ability under different missing modes, especially for scenarios such as long-term communication interruptions and equipment shutdowns common in wind farms.

[0057] C2. Model Training and Testing C21. It adopts a time-series interpolation model based on self-attention mechanism. Its core advantage is that it can dynamically capture the correlation between multiple factors and the long-range dependence across time steps through attention weights, thereby avoiding the gradient decay problem of traditional RNN / LSTM models under long sequences.

[0058] C22. During training, the initial learning rate is set to 0.001, and cosine annealing is used to bring the learning rate to 1×10⁻⁶. The optimizer is AdamW, and the training run consists of 500 epochs. The early stopping threshold is set to 20 epochs. The weight parameter is 5 (reconstruction term weight), the regularization parameter is 1e⁻⁵, and the smoothing term coefficient γ = 1e⁻³. This configuration ensures stable model convergence while effectively avoiding overfitting and improving the recovery accuracy for long missing data scenarios.

[0059] C3. Wind farm missing value completion based on model meteorological multi-element data C31. Input the missing observed wind speed sequences and model meteorological multi-element data into the trained model to obtain the prediction results. To ensure physical plausibility, the completed values ​​need to undergo non-negative truncation, extreme value correction, and wind profile consistency correction to obtain the final predicted wind speed. ; C32, such as Figure 3 As shown, based on the mask matrix The complete wind speed filling sequence can be obtained by replacing the missing positions with the predicted values. The expression is as follows: ; like Figure 4 The image shows the completion effect of missing wind speed segments. The horizontal axis represents the date and time, and the vertical axis represents the wind speed value (m / s). The blue line segment (Oriainal) represents the original missing wind speed data, and the yellow dashed line (Imputed-connected) represents the imputed data. During the missing value completion process, the original broken wind speed sequence can be effectively restored, transforming it into a complete and continuous time series.

[0060] The completed wind speed sequence can be directly used as input for wind power prediction models, wind resource assessment platforms, or wind farm operation and maintenance systems, thereby significantly improving the accuracy, stability, and reliability of downstream operations.

[0061] Advantages and benefits of this invention: (1) Standardize and systematize multi-element meteorological data of multi-element and multi-altitude models and introduce them into the completion process. Utilize their temporal continuity and spatial coverage characteristics to provide reliable prior information for long missing segments, thereby significantly improving the completion accuracy.

[0062] (2) Enhance the model’s adaptability to diverse missing patterns (including long-term continuous missing patterns) by using missing simulation and mask weighted loss during the training phase.

[0063] (3) It has good scalability and supports multi-field joint training, online incremental updates and access to pattern data with different spatiotemporal resolutions.

[0064] (4) It can be directly and seamlessly embedded into the wind power forecasting business process, reducing the fluctuation of forecasting performance caused by missing data.

[0065] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for completing missing wind speed values ​​in wind farms based on model meteorological data, characterized in that: Includes the following steps: S1. Based on the obtained wind speed time series of wind farms and the corresponding model meteorological multi-element data, a multivariate time series tensor is formed, and sample data is constructed based on the multivariate time series tensor. S2. Based on the sample data, train the time series interpolation model using a weighted loss function; S3. Input the missing measured wind speed time series and its corresponding model meteorological multi-element data into the time series interpolation model, predict and fill in the missing positions, and obtain the complete wind speed time series after post-processing. In step S1, based on the acquired measured wind speed time series of the wind farm and its corresponding model meteorological multi-element data, a multivariate time series tensor is formed, including: Interpolation or resampling methods are used to align the time of multi-element meteorological data from the model. Construct a missing mask matrix based on the measured wind speed time series of wind farms; Normalize or standardize the measured wind speed time series and time-aligned model meteorological multi-element data of the wind farm; A time-encoding mechanism is constructed, and a multivariate time series tensor is formed based on the time-encoding, the missing mask matrix, the normalized or standardized wind speed time series of wind farms, and the multi-element meteorological data from models.

2. The method for completing missing wind speed values ​​in wind farms based on model meteorological data according to claim 1, characterized in that: In step S1, sample data is constructed based on multivariate time series tensors, including: A sliding window is used to segment the multivariate time series tensor into sample data.

3. The method for completing missing wind speed values ​​in wind farms based on model meteorological data according to claim 1, characterized in that: In step S2, based on the sample data, a time-series interpolation model is trained using a weighted loss function, including: A training target mask is constructed by randomly simulating short-term random missing data and long-term continuous missing data in the training samples. Construct a weighted loss function based on the training target mask; We use a weighted loss function to minimize the weighted reconstruction error.

4. The method for completing missing wind speed values ​​in wind farms based on model meteorological data according to claim 3, characterized in that: The expression for the weighted loss function is as follows: ； In the formula, To predict wind speed, To measure the wind speed, Mean square error or mean absolute error , To rebuild the weights, ∈{0,1} is the training target mask, and t is the time step.

5. The method for completing missing wind speed values ​​in wind farms based on model meteorological data according to claim 1, characterized in that: In step S3, the post-processing operations include: Smoothing; Physical constraint correction; Fusion verification with short-term available observation values.

6. The method for completing missing wind speed values ​​in wind farms based on model meteorological data according to claim 1, characterized in that: The model's multi-element meteorological data includes at least one of the following elements: 2-meter temperature, 2-meter relative humidity, sea level pressure, 100-meter wind speed, 100-meter wind direction, 10-meter wind speed, 10-meter wind direction, and 10-meter gust.

7. The method for completing missing wind speed values ​​in wind farms based on model meteorological data according to claim 1, characterized in that: The temporal interpolation model is set as a self-attention mechanism-based temporal interpolation model or other deep learning temporal interpolation models.

Images