Intelligent wind power prediction method and system based on guidance of physical knowledge

Abstract

The invention discloses an intelligent wind power prediction method and system based on physical knowledge guidance, and the method comprises the steps: firstly collecting data of a wind power plant, carrying out the preprocessing, and dividing the preprocessed data into a training set, a test set and a verification set; secondly, constructing a wind power prediction model, fusing physical priori knowledge, and inputting data of the training set into the wind power prediction model for training; and finally, performing multi-step prediction by using the trained wind power prediction model through data in the test set and the verification set to obtain predicted power. The system comprises a data acquisition unit, a data preprocessing unit, a model construction unit, a model training unit and a model prediction unit. The method improves the prediction precision and generalization ability in a complex environment, can achieve the more accurate prediction of the wind power of a wind power plant under different meteorological conditions, and improves the prediction robustness.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power prediction in wind farms, and in particular to a method and system for intelligent wind power prediction based on physical knowledge guidance. Background Art

[0002] With the transformation of the global energy structure and the increasingly severe climate change problem, the development and utilization of wind energy as a clean and renewable energy has received widespread attention. As the main way to utilize wind energy, wind power plays an increasingly important role in energy production around the world. However, the output of wind power is affected by many factors such as wind speed, wind direction, and air density, and has great uncertainty and volatility. These characteristics bring certain challenges to the management of wind farms and the dispatching of power grids.

[0003] Traditional wind power prediction methods mainly include physical models and statistical models. Physical models predict wind speed and direction by simulating the physical processes of the atmosphere, and then predict wind power, but such models are usually complex to calculate and require a large amount of meteorological data and high computing power. Statistical models such as time series analysis and regression analysis, although they simplify the calculation process to a certain extent, often ignore the complex nonlinear relationship between wind power output and environmental conditions, which limits the prediction accuracy.

[0004] In recent years, with the development of artificial intelligence technology, wind power prediction methods based on deep learning have been widely studied. Such methods can capture the nonlinear relationship between wind power and related factors by learning patterns in historical data, thereby improving the accuracy of prediction. However, when processing wind power data, existing deep learning often ignores the spatial correlation between wind turbines within the wind farm and the physical constraints of wind power generation, which may lead to insufficient practicality and reliability of the prediction results.

[0005] Therefore, there is an urgent need to develop a new wind power forecasting method that can integrate the spatial relationships within the wind farm and the physical constraints of wind power generation to improve the accuracy and reliability of wind power forecasting. Summary of the invention

[0006] The present invention provides a wind power intelligent prediction method and system based on physical knowledge guidance, which can effectively simulate the interaction between wind turbines in a wind farm and their response to environmental factors such as wind speed and wind direction, thereby achieving more accurate and stable wind power prediction.

[0007] A wind power intelligent prediction method based on physical knowledge guidance, comprising:

[0008] S1. Collect wind farm data and perform preprocessing;

[0009] S2. Divide the data preprocessed in S1 into a training set, a test set and a validation set;

[0010] S3. Construct a wind power prediction model and integrate physical prior knowledge, and input the data of the training set processed by S2 into the wind power prediction model for training;

[0011] S4. Use the trained optimal wind power prediction model to perform multi-step prediction, and obtain the predicted power through the data in the test set and the validation set.

[0012] In this embodiment, the data preprocessing includes: data filtering, feature extraction and data standardization. Data filtering removes abnormal data, feature extraction selects key features, and data standardization eliminates dimensional differences.

[0013] In this embodiment, the data division is to divide the wind power data set into a training set, a validation set and a test set.

[0014] In this embodiment, the wind power prediction model includes:

[0015] S3.1 builds a cross-space-time convolutional neural network, which adopts an encoder-decoder architecture, and its core is sampling convolution and cross-learning mechanism; the cross-space-time convolutional neural network is constructed by arranging multiple multi-resolution feature extraction modules into a binary tree structure; the essence of the multi-resolution feature extraction module is to extract multi-level time features from the time series through the mechanism of downsampling-convolution-interaction, and integrate interactive learning to make up for the information loss in the downsampling process, so as to achieve more efficient time series modeling and prediction; the interactive learning is to exchange information between the downsampled subsequences, and convert the input sequence and Use two different 1D convolution modules respectively and Projected into the hidden state and passed through function to transform and pass the element-wise product ( )and and Interact; the multi-resolution feature extraction module retains the input features respectively The elements with odd numbers and the elements with even numbers in the sequence are sampled into two odd and even sequences. and , and integrate cross-learning, the formula is as follows:

[0016]

[0017] In the formula, is an even sequence, is an odd subsequence, and is the scaling feature, and is the updated feature of the output, The Hadamard product is the element-wise product, is an exponential function transformation, , , and They are different 1D convolution modules. Representation training adaptively learns whether to use addition or subtraction operations to optimize performance.

[0018] S3.2 Physical prior knowledge: Two physical prior knowledge are extracted based on the physical characteristics of wind power and the relationship between wind power and wind speed;

[0019] The first physical prior knowledge is integrated into a clipping module, which is used to limit the output of the wind power prediction model to a reasonable range during training and testing. According to the laws of physics, in practical applications, the value of wind power should be greater than zero, so the model output should be positive to eliminate physically unreasonable predictions. The formula is as follows:

[0020]

[0021] In the formula, is the output of the cross-spatiotemporal convolutional neural network, is the predicted value;

[0022] The second physical prior knowledge is integrated into the penalty loss module. Theoretically, the wind power generation in a certain period should fall within a certain range. According to the wind power conversion relationship between wind power and wind speed, the upper and lower limit constraint functions are introduced, and the penalty loss module is constructed by the upper and lower limit functions. The formula is as follows:

[0023]

[0024]

[0025] In the formula, is the wind speed, is the cut-in wind speed, is the rated wind speed, is the cut-out wind speed, is the model output, It is a penalty loss. is the total number of samples, and other constant parameters , , , , It can be obtained by fitting using software fitting tools.

[0026] S3.3 Model training: The loss function of the wind power prediction model is derived from the cross-spatiotemporal convolutional neural network. Loss term and integration of physical prior knowledge The penalty loss term is composed of the following formula:

[0027]

[0028]

[0029]

[0030] In the formula, is the loss function of the cross-spatial convolutional neural network wind power prediction model, It is a penalty loss. is the total number of samples, is the loss function of the wind power prediction model integrating physical prior knowledge, is the true value, and are the predicted values ​​and model outputs, respectively.

[0031] The multi-step prediction is to use recursive multi-step prediction to perform power prediction. The recursive multi-step prediction first performs multi-step prediction initialization, splices the first step prediction result with the original data along the time dimension, and obtains the initial input for the next step prediction; then multi-step recursive prediction is performed, and then multi-step recursive prediction is performed. When the number of prediction steps reaches a set value, the prediction is stopped; the input of the multi-step recursive prediction is a sequence with a time window length of T1, and the output is the prediction value of the future T2 steps.

[0032] A wind power intelligent prediction system based on physical knowledge guidance, comprising:

[0033] Data acquisition unit: The data acquisition module uses sensors to collect wind farm data;

[0034] Data preprocessing unit: The data preprocessing module is used to preprocess the wind farm data to obtain high-quality model input data;

[0035] Model building unit: the model building module is used to build a wind power prediction model while incorporating physical prior knowledge;

[0036] Model training unit: the model training module is used to construct a loss function of the wind power prediction model, and train the wind power prediction model through the wind farm data and the loss function to obtain a trained prediction model;

[0037] Model prediction unit: The model prediction module is used to input the measured wind farm data into the trained wind power prediction model to obtain the future multi-step wind power prediction for use in wind power prediction.

[0038] Beneficial effects of the present invention:

[0039] It can be seen from the above technical solutions that the present invention provides a method and system for intelligent prediction of wind power based on physical knowledge guidance. This method combines physical prior knowledge in the field of wind power and deep learning to construct a wind power prediction model that can simultaneously consider the physical characteristics of wind farms and historical data characteristics. The wind power prediction model ensures the accuracy of model prediction by introducing physical prior knowledge in the field of wind power. In addition, the wind power prediction model uses the downsampling-convolution-interaction mechanism to effectively extract and fuse the mutual influence and spatiotemporal characteristics between multiple wind turbines, greatly improving the prediction accuracy and generalization ability of the model in complex environments. Based on the work done in this study, it is possible to achieve more accurate predictions of wind power in wind farms under different meteorological conditions, while improving the robustness of the prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 A flow chart of a wind power intelligent prediction method based on physical knowledge guidance provided by an embodiment of the present invention;

[0041] Figure 2 A model logic diagram of a wind power intelligent prediction method based on physical knowledge guidance provided by an embodiment of the present invention;

[0042] Figure 3 A schematic diagram of the prediction effect of a wind power intelligent prediction method based on physical knowledge guidance provided by an embodiment of the present invention;

[0043] Figure 4 A schematic diagram of the structure of a wind power intelligent prediction system based on physical knowledge guidance provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0044] 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.

[0045] The embodiment of the present invention discloses a wind power intelligent prediction method and system based on physical knowledge guidance, aiming to achieve more accurate prediction of wind power of a wind farm under different meteorological conditions.

[0046] Please refer to Figure 1 , this application proposes a wind power intelligent prediction method based on physical knowledge guidance, including:

[0047] Step 101: Collect wind farm data and perform preprocessing;

[0048] Specifically, in this embodiment, the data preprocessing in step 101 includes:

[0049] Data filtering: According to the normal operating parameters of the wind turbine, data with abnormal wind speed are eliminated to ensure that the model training is carried out on valid data;

[0050] Feature extraction: wind speed, wind direction and historical power are selected as input features of the wind power prediction model;

[0051] Data standardization: In order to eliminate the dimensional differences between different features, the data was standardized. The formula is as follows:

[0052]

[0053] In the formula, X is the original data, μ is the mean, σ is the standard deviation, is the standardized data.

[0054] Step 102: Divide the data preprocessed in step 101 into a training set, a test set and a validation set;

[0055] Specifically, in this embodiment, the data is divided into a training set (70%), a test set (20%) and a validation set (10%), and a training set (70%). The training set contains a large amount of historical data. The model adjusts its own parameters by learning the patterns and relationships in these data to achieve the best prediction performance. The validation set is used to evaluate and adjust the performance of the model during the training process, which helps to optimize the structure and training strategy of the model and ensure that the model has good generalization ability on unseen data. The test set is used to evaluate the final performance of the model after the model training is completed. The test set is data that the model has not been exposed to during the training process. By evaluating on the test set, the actual prediction ability of the model can be objectively measured. The data is input into the wind power prediction model for training using the sliding window method.

[0056] Step 103: construct a wind power prediction model and integrate physical prior knowledge, and input the data processed in step 102 into the wind power prediction model for training;

[0057] Step 104: Use the trained optimal wind power prediction model to perform multi-step prediction to obtain predicted power.

[0058] Please refer to Figure 2 In this embodiment, the wind power prediction model used in the present application in step 103 includes:

[0059] A cross-space-time convolutional neural network is constructed. The cross-space-time convolutional neural network adopts an encoder-decoder architecture, and its core is sampling convolution and cross-learning mechanism. The cross-space-time convolutional neural network is constructed by arranging multiple multi-resolution feature extraction modules into a binary tree structure. The essence of the multi-resolution feature extraction module is to extract multi-level time features from the time series through the downsampling-convolution-interaction mechanism, and integrate interactive learning to make up for the information loss in the downsampling process, so as to achieve more efficient time series modeling and prediction. The interactive learning is to exchange information between the downsampled subsequences. and Use two different 1D convolution modules respectively and Projected into the hidden state and passed through function to transform and pass the element-wise product ( )and and Interact; the multi-resolution feature extraction module retains the input features respectively The elements with odd numbers and the elements with even numbers in the sequence are sampled into two odd and even sequences. and , and integrate cross-learning, the formula is as follows:

[0060]

[0061] In the formula, is an even sequence, is an odd subsequence, and is the scaling feature, and is the updated feature of the output, The Hadamard product is the element-wise product, is an exponential function transformation, , , and They are different 1D convolution modules. Representation training adaptively learns whether to use addition or subtraction operations to optimize performance.

[0062] In this embodiment, the function of the cross-space-time convolutional neural network is to divide a sequence into an odd sequence and an even sequence after interaction. From the sampling frequency point of view, it is similar to performing two regular downsampling operations; the cross-space-time convolutional neural network uses a tree structure to nest the multi-resolution feature extraction module. There are 2L-1 multi-resolution feature extraction modules in the Lth layer. After sampling in the Lth layer, a total of 2L subsequences will be obtained; the length of these sequences will only be 1 / 2 of the original sequence. L ,After the connection and alignment splicing operations, the total sequence length is equal to the original sequence length.

[0063] A significant advantage of the cross-spatiotemporal convolutional neural network described in this embodiment is that each multi-resolution feature extraction module has a local and global view of the entire time series, which facilitates the extraction of useful temporal features; after all downsampling-convolution-interaction operations, the extracted features are rearranged into a new sequence representation and added to the original time series for prediction using a fully connected network as a decoder.

[0064] Physical prior knowledge: Based on the physical characteristics of wind power and the relationship between wind power and wind speed, two physical prior knowledge are extracted:

[0065] The first physical prior knowledge is integrated into a clipping module, which is used to limit the output of the wind power prediction model to a reasonable range during training and testing. According to the laws of physics, in practical applications, the value of wind power should be greater than zero, so the model output should be positive to eliminate physically unreasonable predictions. The formula is as follows:

[0066]

[0067] In the formula, is the output of the cross-spatiotemporal convolutional neural network, is the predicted value.

[0068] The second physical prior knowledge is integrated into the penalty loss module. Theoretically, the wind power generation in a certain period should fall within a certain range. According to the wind power conversion relationship between wind power and wind speed, the upper and lower limit constraint functions are introduced, and the penalty loss module is constructed by the upper and lower limit functions. The formula is as follows:

[0069]

[0070]

[0071] In the formula, is the wind speed, is the cut-in wind speed, is the rated wind speed, is the cut-out wind speed, is the model output, It is a penalty loss. is the total number of samples, and other constant parameters can be fitted by the software fitting tool.

[0072] Model training: The loss function of the wind power prediction model is derived from the cross-spatiotemporal convolutional neural network. Loss term and integration of physical prior knowledge The penalty loss term is composed of the following formula:

[0073]

[0074]

[0075]

[0076] In the formula, is the loss function of the cross-spatial convolutional neural network wind power prediction model, It is a penalty loss. is the total number of samples, is the loss function of the wind power prediction model integrating physical prior knowledge, is the true value, and are the predicted values ​​and model outputs, respectively.

[0077] The wind power prediction model of this embodiment uses the training set data to train the model, and adjusts the model parameters through the optimization algorithm (Adam optimizer) to minimize the loss function on the training set. After the training is completed, the performance of the model is evaluated using the validation set. The hyperparameters of the model are adjusted according to the performance on the validation set to prevent overfitting. After the model training and verification are completed, the final performance of the model is evaluated using the test set. The results of the test set are used to measure the predictive ability of the model in practical applications. The input of the model is data of 16 time steps, and the output is the state data of the 17th step. The number of hidden layers of the wind power prediction model is 5, the size of the convolution kernel is 3, the learning rate is 0.01, and the batch size is 32.

[0078] The wind power prediction model of this embodiment uses an early stop mechanism to prevent the model from overfitting and achieve the best performance on the validation set. The core idea of ​​the early stop mechanism is to stop training early if the performance of the model on the validation set does not improve significantly after a certain number of training rounds. The patience value of the early stop mechanism is set to 10. The prediction effect diagram is shown in the figure. Figure 3 shown.

[0079] In this embodiment, the original wind power prediction model MAE and R 2 The MAE and R of the wind power prediction model after integrating physical prior knowledge are 178.604 and 0.957 respectively.2 They are 157.541 and 0.9611 respectively. Compared with the original model, MAE is reduced by about 11.8%, R 2 It has increased by about 0.43%, which is a significant improvement over the original wind power prediction model; the results show that the wind power prediction model that integrates physical prior knowledge can more deeply reveal the inherent change law of the wind power series and improve the overall prediction accuracy.

[0080] In this embodiment, the model prediction of the present application in step 104 includes:

[0081] The multi-step prediction is to use recursive multi-step prediction to perform power prediction. The recursive multi-step prediction first performs multi-step prediction initialization, splices the first step prediction result with the original data along the time dimension, and obtains the initial input for the next step prediction; then multi-step recursive prediction is performed, and when the number of prediction steps reaches the set value, the prediction is stopped; the input of the multi-step recursive prediction is a sequence with a time window length of T1, and the output is the prediction value of the future T2 steps. The number of recursions of the multi-step recursive prediction is pred_step-1 times, pred_step=16.

[0082] Please refer to Figure 4 In an embodiment of the present invention, a wind power intelligent prediction system based on physical knowledge guidance is provided, including:

[0083] Data acquisition unit 401: the data acquisition module uses sensors to collect wind farm data;

[0084] Data preprocessing unit 402: the data preprocessing module is used to perform data preprocessing on the wind farm data, so as to obtain high-quality model input data;

[0085] Model building unit 403: The model building module is used to build a wind power prediction model and incorporate physical prior knowledge;

[0086] Model training unit 404: the model training module is used to construct a loss function of the wind power prediction model, and train the wind power prediction model through the wind farm data and the loss function to obtain a trained prediction model;

[0087] Model prediction unit 405: The model prediction module is used to input the measured wind farm data into the trained wind power prediction model to obtain a future multi-step wind power prediction for use in wind power prediction.

[0088] The present invention constructs an intelligent wind power prediction method guided by physical knowledge, effectively integrating the local information of wind turbines in wind farms with global environmental factors, thereby achieving a high degree of accuracy and efficiency in wind power prediction. Specifically, the wind power prediction model that integrates physical prior knowledge can tap into the physical characteristics of each wind turbine or wind farm site itself, such as local influencing factors such as wind speed, wind direction, and air density, while analyzing and processing the interaction between wind turbines and their response to the surrounding environment; the model can not only more comprehensively reflect the complex associations and mutual influences between sites in the region, but also fully consider the influence of global environmental factors while retaining the local characteristics of each wind turbine, thereby significantly improving the accuracy of wind power prediction.

[0089] In the field of the present invention, professionals should understand that the various components and algorithm steps shown in the embodiments disclosed in the present invention can be implemented by electronic hardware, computer software or a combination thereof. In order to clearly demonstrate the interchangeability of hardware and software, these components and steps have been described universally based on functions. The implementation of these functions, whether through hardware or software, depends on specific technical application environments and design limitations. Technicians can choose different implementation means to achieve these functions according to each specific application environment, and such selection should not be regarded as departing from the scope of the present invention.

Claims

1. A wind power intelligent prediction method based on physical knowledge, characterized in that: The following steps are involved: S1. Collect wind farm data and perform preprocessing; S2. Divide the preprocessed data into training set, test set and validation set; S3. Construct a wind power prediction model, integrate physical prior knowledge, and input the data of the training set into the wind power prediction model for training; S4. Use the trained wind power prediction model to perform multi-step predictions using the data in the test set and validation set to obtain the predicted power.

2. The method for intelligent wind power prediction based on physical knowledge guidance according to claim 1 is characterized in that: The specific implementation process of the wind power prediction model is as follows: S3.1 builds a cross-spatiotemporal convolutional neural network, extracts data features of the training set and calculates the loss; S3.2 extracts two physical prior knowledge based on the physical characteristics of wind power and the relationship between wind power and wind speed; S3.3 Construct the loss function of the wind power prediction model and perform training.

3. The method for intelligent wind power prediction based on physical knowledge guidance according to claim 2 is characterized in that: The cross-spatiotemporal convolutional neural network is an encoder-decoder architecture, including sampling convolution and cross-learning mechanisms; The cross-spatiotemporal convolutional neural network is constructed by arranging multiple multi-resolution feature extraction modules into a binary tree structure; the essence of the multi-resolution feature extraction module is to extract multi-level time features from the time series through the mechanism of downsampling-convolution-interaction, and integrate interactive learning to compensate for the information loss in the downsampling process; The interactive learning is to exchange information between the downsampled subsequences. and Use two different 1D convolution modules respectively and Projected into the hidden state and passed through The function transforms and multiplies the elements and and Interact; the multi-resolution feature extraction module retains the input features respectively The elements with odd numbers and the elements with even numbers in the sequence are sampled into two odd and even sequences. and , and integrate cross-learning, the formula is as follows: ； In the formula, is an even sequence, is an odd subsequence, and is the scaling feature, and is the updated feature of the output, is an exponential function transformation, , , and They are different 1D convolution modules. Indicates whether training adaptive learning uses addition or subtraction operations to optimize performance.

4. The method for intelligent wind power prediction based on physical knowledge guidance according to claim 3 is characterized in that: The two physical prior knowledge are as follows: The first physical prior knowledge is integrated into the clipping module. According to the laws of physics, in practical applications, the value of wind power should be greater than zero, so the output should be positive to eliminate physically unreasonable predictions. The formula is as follows: ； In the formula, is the output of the cross-spatiotemporal convolutional neural network, is the predicted value; The second physical prior knowledge is integrated into a penalty loss module. According to the wind power conversion relationship between wind power and wind speed, the upper and lower limit constraint functions are introduced. The penalty loss module is constructed by the upper and lower limit functions. The formula is as follows: ； ； In the formula, is the wind speed, is the cut-in wind speed, is the rated wind speed, is the cut-out wind speed, is the model output, It is a penalty loss. is the total number of samples, and other constant parameters , , , , It is obtained by fitting using the software fitting tool.

5. The method for intelligent wind power prediction based on physical knowledge guidance according to claim 4 is characterized in that: The loss function of the wind power prediction model is derived from the cross-spatiotemporal convolutional neural network. Loss term and integration of physical prior knowledge The penalty loss term is composed of the following formula: ； ； ； In the formula, is the loss function of the cross-spatial convolutional neural network wind power prediction model, It is a penalty loss. is the total number of samples, is the loss function of the wind power prediction model integrating physical prior knowledge, is the true value.

6. The method for intelligent wind power prediction based on physical knowledge guidance according to claim 5 is characterized in that: The multi-step prediction is to use recursive multi-step prediction to perform power prediction. The recursive multi-step prediction first performs multi-step prediction initialization, splices the first step prediction result with the original data along the time dimension, and obtains the initial input for the next step prediction; then multi-step recursive prediction is performed, and then multi-step recursive prediction is performed. When the number of prediction steps reaches a set value, the prediction is stopped; the input of the multi-step recursive prediction is a sequence with a time window length of T1, and the output is the prediction value of the future T2 steps.

7. A wind power intelligent prediction system guided by physical knowledge, used to implement the wind power intelligent prediction method according to any one of claims 1 to 6, characterized in that: Includes the following modules: Data acquisition unit: uses sensors to collect wind farm data; Data preprocessing unit: used for preprocessing wind farm data; Model building unit: used to build a wind power prediction model while incorporating physical prior knowledge; Model training unit: used for constructing the loss function of the wind power prediction model, training the wind power prediction model through the wind farm data and the loss function, and obtaining a trained prediction model; Model prediction unit: used to input the measured wind farm data into the trained wind power prediction model, obtain the future multi-step wind power prediction, and perform wind power prediction.

Images