Lightweight multi-source data fusion photovoltaic power generation power prediction method and system

Abstract

The invention relates to the technical field of photovoltaic power generation power prediction, in particular to a lightweight multi-source data fusion photovoltaic power generation power prediction method and system. According to the method, the satellite cloud picture, the foundation cloud picture, the key meteorological factors and the historical photovoltaic power generation power data are combined, the data utilization efficiency and the prediction precision can be improved, an optimized feature extraction method is applied, the calculation speed is increased, the calculation burden is reduced, a lightweight architecture combining traditional time sequence modeling and an attention mechanism is used, and the prediction efficiency is improved. The method is suitable for deployment of low-resource scenes; according to the method, feature extraction and fusion of photovoltaic power generation multi-source data are realized, and accurate and lightweight power generation power prediction is realized, so that a manager of a small centralized photovoltaic power station in a rural area can perform real-time monitoring and accurate and efficient prediction on the photovoltaic power generation power on a mobile terminal; therefore, a corresponding energy management decision is made.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation prediction, and more specifically, to a lightweight multi-source data fusion photovoltaic power generation prediction method and system. Background Art

[0002] With the advancement of technology, policy support and cost reduction, the popularity of photovoltaic power generation in rural areas has increased year by year, bringing far-reaching impacts to the rural economy, energy supply and environmental protection. Some villages and regions choose to build centralized photovoltaic power stations on idle land. Especially in areas with sufficient sunshine, centralized photovoltaic power stations can generate electricity on a large scale and provide stable electricity. By connecting to the power grid, photovoltaic power stations can achieve self-generation and self-use and connect surplus electricity to the grid. Farmers' families can not only reduce electricity bills, but also obtain stable cash income by selling excess electricity.

[0003] For the prediction of photovoltaic power generation, the existing technology has the limitation of a single data source. Many prediction schemes rely only on satellite cloud images or historical power generation data, and fail to make full use of the complementarity between multi-source data, resulting in limited prediction accuracy. In addition, the existing technology has a heavy computational burden, especially the schemes based on satellite cloud images or complex neural networks, which often require high hardware resources and are not suitable for deployment in small rural power stations; or the method of independently using satellite cloud images or ground-based cloud images for cloud image extrapolation predicts the cloud images in the short term in the future, and indirectly realizes the prediction of photovoltaic power generation. However, the amount of image data is large, which is a great test for the calculation amount of the model and the memory of the device. In addition, the process of accurately predicting the image is complicated and requires high prediction models, which is not suitable for the needs of small centralized photovoltaic power stations. Secondly, the existing feature extraction technology for cloud images is not well adapted to complex weather conditions and nonlinear characteristics of cloud movement, and performs poorly in terms of calculation speed and memory usage. Summary of the invention

[0004] The purpose of the present invention is to overcome the shortcomings of the prior art in photovoltaic power generation prediction, which is complex in calculation and has high requirements on prediction models and equipment, and to provide a lightweight photovoltaic power generation prediction method and system with multi-source data fusion, which reduces the calculation burden of the model, improves the prediction speed and accuracy of the model, and is suitable for deployment in low-resource scenarios.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is: A lightweight photovoltaic power generation prediction method based on multi-source data fusion is provided, comprising the following steps: S1. Data collection: Obtain satellite cloud images, ground-based cloud images, meteorological data, and historical data of photovoltaic power generation of centralized photovoltaic power stations, build a data set, and perform data preprocessing; S2. Extract the features of multi-source data and form a multi-source data set: Use the dynamic cloud tracking method to extract the motion features of clouds in satellite cloud images, including the speed and direction of clouds; Use the multi-scale frequency domain optimization cloud segmentation method to automatically perform threshold segmentation on cloud images and extract cloud amount features in ground-based cloud images; Use the mutual information method to analyze the interdependence between photovoltaic power generation and meteorological factors, and extract meteorological factors with strong correlation as meteorological features; The collected motion features, transportation features, and meteorological features are constructed into a multi-source data set; S3. Construct a photovoltaic power generation prediction model based on multi-source data fusion: Construct a BiGRU-Attention network to fuse the features of multi-source data and predict photovoltaic power generation; S4. Training the photovoltaic power prediction model: divide the multi-source data set into a training set and a test set, use the training set to train the photovoltaic power prediction model fused with multi-source data, and use the test set to evaluate the photovoltaic power prediction model. When the accuracy of the photovoltaic power prediction model reaches the set threshold, the training is terminated; S5. Use the trained photovoltaic power prediction model to predict the photovoltaic power generation of the centralized photovoltaic power station.

[0006] The present invention provides a lightweight multi-source data fusion photovoltaic power prediction method, which combines satellite cloud images, ground-based cloud images, key meteorological factors, and historical photovoltaic power data, thereby improving data utilization efficiency and prediction accuracy, using an optimized feature extraction method to accelerate the calculation speed, reduce the calculation burden, and use a lightweight architecture that combines traditional time series modeling and an attention mechanism, which is suitable for deployment in low-resource scenarios. The present invention realizes feature extraction and fusion of multi-source data of photovoltaic power generation, and realizes accurate and lightweight power generation prediction, thereby enabling managers of small centralized photovoltaic power stations in rural areas to monitor photovoltaic power generation in real time and accurately and efficiently predict photovoltaic power generation on mobile terminals, so as to make corresponding energy management decisions.

[0007] Preferably, step S3 includes: S31. Construct a BiGRU-Attention network to fuse multi-source data features and predict photovoltaic power generation. The BiGRU-Attention network includes an input layer, a bidirectional GRU layer, a feature attention mechanism layer, and a fully connected layer, and uses an error back propagation algorithm to optimize the network. S32. The input layer is used to receive cloud motion features from satellite cloud images, cloud amount features from ground-based cloud images, meteorological features from the meteorological department, and photovoltaic power generation history data, and merge each feature in a time series manner to form an input feature matrix:

[0008]

[0009] In the formula, is the cloud movement speed, is the direction of cloud movement, For cloud cover, is the preferred meteorological factor, is the photovoltaic power generation power; is the number of data, is the input feature matrix S33. The bidirectional GRU layer is used to capture the bidirectional context information of the time series and obtain the forward and backward hidden states. , and maps each time-step hidden state of the bidirectional GRU layer output to the feature dimension: , , , ; In the formula, is the forward hidden state, is the backward hidden state, is the weight matrix, is the bias matrix, is the output of the bidirectional GRU layer; S34. The feature attention mechanism layer is used to adjust the weights of multi-source data features and weight the features of multi-source data to obtain global features. :

[0010]

[0011] In the formula, in the formula, is the weight of multi-source data features, and N is the dimension of the feature vector; S35. Finally, the features are mapped to photovoltaic power through the fully connected layer:

[0012] In the formula, , is the weight matrix and bias of the fully connected layer, is the photovoltaic power output.

[0013] Preferably, the step S1 comprises: S11. Collect and organize multi-source data, including satellite remote sensing cloud images, ground-based cloud images, meteorological conditions, and photovoltaic power generation of centralized photovoltaic power stations over a continuous period of time; S12. Preprocess the data set, adjust the image data to a uniform size, remove noise from the image, and perform histogram equalization on the image; S13. Detect and process outliers and missing values ​​of meteorological factors and photovoltaic power generation, and normalize the data.

[0014] Preferably, the step S2 of extracting the motion characteristics of clouds in the satellite cloud image by using the dynamic cloud tracking method comprises the following steps: S211. Convert satellite cloud images to grayscale images and construct multi-frame cloud images, taking continuous satellite cloud image sequences as input:

[0015] In the formula, , is the gray value of the cloud image, is the pixel coordinate of the cloud image, Represents time; Represents the interval time of continuous satellite cloud image sequence; Divide the cloud image into small blocks, extract the gradient features in each small block, and calculate the grayscale gradient of each frame of the cloud image in space and time: , , , The grayscale gradient describes the rate of change of the cloud in the x and y directions, as well as the rate of change in the time dimension; Taylor decomposition of the grayscale function:

[0016] In the formula, , , Function right , , The partial derivative of is the remainder of the Taylor expansion; Will Ignore and let the velocity of the cloud in the x-axis direction , the speed in the y-axis direction , we get the equation:

[0017] S212. Based on the fact that the pixels in the satellite cloud image have the same displacement in the same time, the displacement equation corresponding to each pixel in the satellite cloud image is obtained:

[0018] S213. The conjugate gradient method is used to solve the above linear equations, and the cloud velocity vector is obtained. , the equation in step S212 is written as , in order to solve , construct the objective function ,Right now:

[0019] Calculate the step size:

[0020] In the formula, represents the number of iterations, represents the residual; Updated solution:

[0021] Update residuals:

[0022] Calculate the adjustment factor for the new direction:

[0023] like , stop the iteration, and then get the movement speed of the cloud , the displacement of the cloud, .

[0024] Preferably, in step S2, a multi-scale frequency domain optimized cloud segmentation method is used to perform automatic threshold segmentation on the cloud image to extract cloud amount features in the ground-based cloud image, specifically including: S221. Convert the ground-based cloud image from a color image to a grayscale image, count the number of pixels at each grayscale level in the grayscale image, and obtain the histogram of the ground-based cloud image. , the formula is as follows:

[0025] In the formula, is the pixel value of the grayscale image, is the Kronecker delta function, when hour , otherwise 0, , is the width and height of the ground-based cloud image, is a number from 0 to 255; S222. Normalize the grayscale histogram of the ground-based cloud image and divide the image into The grayscale distribution probability of each area is as follows: ; In the formula, Representing the region, Is the cloud map in the area The histogram of and The cloud maps are in the area The width and height of S223. For each region, calculate the inter-class variance of each region in the cloud map, and determine the optimal threshold by maximizing the inter-class variance. First, calculate the weight and mean of the cloud region and the non-cloud region: , , , , In the formula, represents the weight of the cloud region, represents the weight of the non-cloud area, represents the mean value of the cloud area, represents the mean value of non-cloud area; The between-class variance is: ; Find the threshold that maximizes the between-class variance , the regional threshold The global threshold is obtained by weighted averaging. , the formula is: ; S224. Use the best threshold Binarize the grayscale image of the cloud map and divide the image into cloud area and non-cloud area. The formula is as follows: , In the formula, The cloud image is binarized, 1 represents the cloud area, and 0 represents the non-cloud area; S225. Combine the binarization result of the cloud image with the frequency domain features of the image and obtain the frequency information through Fourier transform: , Gaussian filtering is used to enhance the cloud edge features and then superimposed on the binary image to optimize the results: , in is the inverse Fourier transform; According to the final optimized binary map Calculate the ratio of cloud area pixels to total pixels, and get the cloud amount characteristics : .

[0026] Preferably, in step S2, the mutual information method is used to analyze the interdependence between photovoltaic power generation and meteorological factors, and meteorological factors with strong correlation are extracted as meteorological features, which specifically include: S231. Obtain the temperature T, humidity H, wind speed W and radiation intensity S of the photovoltaic power station from the meteorological observation station As the main influencing factor; S232. Normalize each meteorological factor and photovoltaic power generation to eliminate dimensional differences; S233. Estimation of the joint probability density of meteorological factors and photovoltaic power generation using histogram method , estimate the marginal probability density of meteorological factors and photovoltaic power generation , ; S234. Calculate the mutual information between meteorological factors and photovoltaic power generation based on joint distribution and marginal distribution:

[0027] S235. Select meteorological factors whose mutual information values ​​are greater than a set threshold as meteorological features.

[0028] Preferably, the step S4 comprises: S41. Dividing the multi-source data set extracted in step S2 into a training set and a test set; S42. Use the test set to evaluate the trained photovoltaic power prediction model based on multi-source data fusion, and the evaluation indicator is the root mean square error RMSE to determine the prediction accuracy of the model; S43. When the prediction accuracy of the model is lower than the set threshold, the model is optimized according to the evaluation results, and the photovoltaic power generation prediction model based on multi-source data fusion is continued to be trained until the prediction accuracy reaches the set threshold.

[0029] The present invention also provides a lightweight multi-source data fusion photovoltaic power generation prediction system, comprising: Data acquisition module: used to obtain satellite cloud images, ground-based cloud images, meteorological data and photovoltaic power generation history data of centralized photovoltaic power stations, build data sets and perform data preprocessing; Multi-source data feature extraction module: used to extract the motion features of clouds in satellite cloud images using dynamic cloud tracking method, including cloud speed and direction; use multi-scale frequency domain optimization cloud segmentation method to automatically perform threshold segmentation on cloud images and extract cloud amount features in ground-based cloud images; use mutual information method to analyze the interdependence between photovoltaic power generation and meteorological factors, and extract meteorological factors with strong correlation as meteorological features; the collected motion features, transportation volume features, and meteorological features are constructed into a multi-source data set; Model building module: used to build a photovoltaic power prediction model that integrates multi-source data. By building a BiGRU-Attention network, the features of multi-source data are integrated to predict photovoltaic power. Model training module: used to train the photovoltaic power prediction model. The multi-source data set is divided into a training set and a test set. The photovoltaic power prediction model fused with multi-source data is trained with the training set, and the photovoltaic power prediction model is evaluated with the test set. When the accuracy of the photovoltaic power prediction model reaches the set threshold, the training is terminated. Prediction module: used to use the trained photovoltaic power prediction model to predict the photovoltaic power generation of centralized photovoltaic power stations.

[0030] Preferably, in the model building module, the BiGRU-Attention network includes: Input layer unit: used to receive cloud motion features from satellite cloud images, cloud amount features from ground-based cloud images, meteorological features from meteorological departments, and photovoltaic power generation history data, and merge each feature in a time series manner to form an input feature matrix:

[0031]

[0032] In the formula, is the cloud movement speed, is the direction of cloud movement, For cloud cover, is the preferred meteorological factor, is the photovoltaic power generation power; is the number of data, is the input feature matrix; Bidirectional GRU layer unit: used to capture the bidirectional context information of the time series and obtain the forward and backward hidden states , and maps each time-step hidden state of the bidirectional GRU layer output to the feature dimension: , , , ; In the formula, is the forward hidden state, is the backward hidden state, is the weight matrix, is the bias matrix, is the output of the bidirectional GRU layer; Feature attention mechanism layer unit: used to adjust the weights of multi-source data features and weight the features of multi-source data to obtain global features :

[0033]

[0034] In the formula, is the weight of multi-source data features, and N is the dimension of the feature vector; Fully connected layer: used to map features into photovoltaic power generation:

[0035] In the formula, , is the weight matrix and bias of the fully connected layer; is the photovoltaic power output.

[0036] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above-described methods when executing the computer program.

[0037] Compared with the prior art, the present invention has the following beneficial effects: The present invention discloses a lightweight multi-source data fusion photovoltaic power prediction method and system, which combines satellite cloud images, ground-based cloud images, key meteorological factors, and historical photovoltaic power data, thereby improving data utilization efficiency and prediction accuracy, using optimized feature extraction methods to accelerate calculation speed, reduce calculation burden, and use a lightweight architecture that combines traditional time series modeling and attention mechanism, which is suitable for deployment in low-resource scenarios. The present invention realizes feature extraction and fusion of multi-source data of photovoltaic power generation, and realizes accurate and lightweight power generation prediction, thereby enabling managers of small centralized photovoltaic power stations in rural areas to monitor photovoltaic power generation in real time and accurately and efficiently predict photovoltaic power generation on mobile terminals, so as to make corresponding energy management decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a schematic diagram of a method flow chart of Embodiment 1 of the present invention; Figure 2 It is a schematic diagram of the principle of the present invention; Figure 3 This is a diagram showing the prediction effect of the volt power generation in the fourth embodiment of the present invention; Figure 4 This is a schematic diagram of the system structure in Embodiment 5 of the present invention. DETAILED DESCRIPTION

[0039] The present invention is further described below in conjunction with specific implementation methods. The accompanying drawings are only used for exemplary descriptions and are only schematic diagrams, not actual drawings, and cannot be understood as limiting this patent; in order to better illustrate the embodiments of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product; for those skilled in the art, it is understandable that some well-known structures and their descriptions in the accompanying drawings may be omitted.

[0040] The same or similar numbers in the drawings of the embodiments of the present invention correspond to the same or similar parts; in the description of the present invention, it should be understood that if the terms "upper", "lower", "left", "right" and the like indicate directions or positional relationships based on the directions or positional relationships shown in the drawings, it is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction. Therefore, the terms describing the positional relationship in the drawings are only used for illustrative purposes and cannot be understood as limitations on this patent. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to specific circumstances.

[0041] Embodiment 1 This embodiment is the first embodiment of a lightweight multi-source data fusion photovoltaic power prediction method. Figure 1 As shown, the method comprises the following steps: S1. Data collection: Obtain satellite cloud images, ground-based cloud images, meteorological data, and historical data of photovoltaic power generation of centralized photovoltaic power stations, build a data set, and perform data preprocessing; S2. Extract the features of multi-source data and form a multi-source data set: Use the dynamic cloud tracking method to extract the motion features of clouds in satellite cloud images, including the speed and direction of clouds; Use the multi-scale frequency domain optimization cloud segmentation method to automatically perform threshold segmentation on cloud images and extract cloud amount features in ground-based cloud images; Use the mutual information method to analyze the interdependence between photovoltaic power generation and meteorological factors, and extract meteorological factors with strong correlation as meteorological features; The collected motion features, transportation features, and meteorological features are constructed into a multi-source data set; S3. Construct a photovoltaic power generation prediction model based on multi-source data fusion: Construct a BiGRU-Attention network to fuse the features of multi-source data and predict photovoltaic power generation; S4. Training the photovoltaic power prediction model: divide the multi-source data set into a training set and a test set, use the training set to train the photovoltaic power prediction model fused with multi-source data, and use the test set to evaluate the photovoltaic power prediction model. When the accuracy of the photovoltaic power prediction model reaches the set threshold, the training is terminated; S5. Use the trained photovoltaic power prediction model to predict the photovoltaic power generation of the centralized photovoltaic power station.

[0042] This embodiment provides a lightweight multi-source data fusion photovoltaic power prediction method, firstly, obtain the satellite cloud map, ground cloud map, meteorological data and photovoltaic power history data of the photovoltaic base, construct a data set and perform data preprocessing; use the dynamic cloud tracking method to extract the motion characteristics of the cloud in the satellite cloud map, use the multi-scale frequency domain optimization cloud segmentation method to perform threshold segmentation on the ground cloud map, extract the cloud amount information in the ground cloud map, use the mutual information method to analyze the interdependence between photovoltaic power generation and meteorological factors, and extract meteorological factors with strong correlation; then send various features to the BiGRU-Attention network for model training; finally, deploy the trained model to the Solar Eye system, and use the prediction model to predict the photovoltaic power generation. The present invention realizes the feature extraction and fusion of multi-source data of photovoltaic power generation, and realizes accurate and lightweight power generation prediction, so that managers of small centralized photovoltaic power stations in rural areas can monitor photovoltaic power generation in real time and accurately and efficiently predict it on mobile terminals, so as to make corresponding energy management decisions.

[0043] Embodiment 2 This embodiment is the second embodiment of a lightweight multi-source data fusion photovoltaic power prediction method. This embodiment is similar to the first embodiment, except that in this embodiment, method steps are provided for constructing a data set, performing data preprocessing, and extracting features of multi-source data.

[0044] In this embodiment, data collection and processing specifically include the following steps: S11. Collect and organize multi-source data, including satellite remote sensing cloud images, ground-based cloud images, meteorological conditions, and photovoltaic power generation of centralized photovoltaic power stations over a continuous period of time; S12. Preprocess the data set, adjust the image data to a uniform size, remove noise from the image, and perform histogram equalization on the image; S13. Detect and process outliers and missing values ​​of meteorological factors and photovoltaic power generation, and normalize the data.

[0045] In this embodiment, the dynamic cloud tracking method is used to extract the motion characteristics of clouds in the satellite cloud image, including the following steps: S211. Convert satellite cloud images to grayscale images and construct multi-frame cloud images, taking continuous satellite cloud image sequences as input:

[0046] In the formula, , is the gray value of the cloud image, is the pixel coordinate of the cloud image, Represents time; Represents the interval time of continuous satellite cloud image sequence; Divide the cloud image into small blocks, extract the gradient features in each small block, and calculate the grayscale gradient of each frame of the cloud image in space and time: , , , The grayscale gradient describes the rate of change of the cloud in the x and y directions, as well as the rate of change in the time dimension; Taylor decomposition of the grayscale function:

[0047] In the formula, , , Function right , , The partial derivative of is the remainder of the Taylor expansion; Will Ignore and let the velocity of the cloud in the x-axis direction , the speed in the y-axis direction , we get the equation:

[0048] S212. Based on the fact that the pixels in the satellite cloud image have the same displacement in the same time, the displacement equation corresponding to each pixel in the satellite cloud image is obtained:

[0049] S213. The conjugate gradient method is used to solve the above linear equations, and the cloud velocity vector is obtained. , the equation in step S212 is written as , in order to solve , construct the objective function ,Right now:

[0050] Calculate the step size:

[0051] In the formula, represents the number of iterations, Residual Updated solution:

[0052] Update residuals:

[0053] Calculate the adjustment factor for the new direction:

[0054] like , stop the iteration, and then get the movement speed of the cloud , the displacement of the cloud, .

[0055] In this embodiment, a multi-scale frequency domain optimized cloud segmentation method is used to perform automatic threshold segmentation on the cloud image to extract cloud amount features in the ground-based cloud image, specifically including: S221. Convert the ground-based cloud image from a color image to a grayscale image, count the number of pixels at each grayscale level in the grayscale image, and obtain the histogram of the ground-based cloud image. , the formula is as follows:

[0056] In the formula, is the pixel value of the grayscale image, is the Kronecker delta function, when hour , otherwise 0, , is the width and height of the ground-based cloud image, is a number from 0 to 255; S222. Normalize the grayscale histogram of the ground-based cloud image and divide the image into The grayscale distribution probability of each area is as follows: ; In the formula, Representing the region, Is the cloud map in the area The histogram of and The cloud maps are in the area The width and height of S223. For each region, calculate the inter-class variance of each region in the cloud map, and determine the optimal threshold by maximizing the inter-class variance. First, calculate the weight and mean of the cloud region and the non-cloud region: , , , , In the formula, represents the weight of the cloud region, represents the weight of the non-cloud area, represents the mean value of the cloud area, represents the mean value of non-cloud area; The between-class variance is: ; Find the threshold that maximizes the between-class variance , the regional threshold The global threshold is obtained by weighted averaging. , the formula is: ; S224. Use the best threshold Binarize the grayscale image of the cloud map and divide the image into cloud area and non-cloud area. The formula is as follows: , In the formula, The cloud image is binarized, 1 represents the cloud area, and 0 represents the non-cloud area; S225. Combine the binarization result of the cloud image with the frequency domain features of the image and obtain the frequency information through Fourier transform: , Gaussian filtering is used to enhance the cloud edge features and then superimposed on the binary image to optimize the results: , in is the inverse Fourier transform; According to the final optimized binary map Calculate the ratio of cloud area pixels to total pixels, and get the cloud amount characteristics : .

[0057] In this embodiment, the mutual information method is used to analyze the interdependence between photovoltaic power generation and meteorological factors, and meteorological factors with strong correlation are extracted as meteorological features, specifically including: S231. Obtain the temperature T, humidity H, wind speed W and radiation intensity S of the photovoltaic power station from the meteorological observation station As the main influencing factor; S232. Normalize each meteorological factor and photovoltaic power generation to eliminate dimensional differences; S233. Estimation of the joint probability density of meteorological factors and photovoltaic power generation using histogram method , estimate the marginal probability density of meteorological factors and photovoltaic power generation , ; S234. Calculate the mutual information between meteorological factors and photovoltaic power generation based on joint distribution and marginal distribution:

[0058] S235. Select meteorological factors whose mutual information values ​​are greater than a set threshold as meteorological features.

[0059] Ground-based cloud images can provide high-resolution local cloud information, while satellite cloud images provide large-scale cloud coverage and movement trends. Therefore, the cloud motion characteristics of satellite cloud images and cloud characteristics of ground-based cloud images are extracted separately, and then important meteorological characteristics are obtained. This fusion of multi-source data can improve the accuracy and reliability of predictions. The optimized feature extraction method is used to extract the features of multi-source data, and the extracted features are directly input into the lightweight prediction network after fusion, which greatly reduces the computational burden of the model and improves the prediction speed of the model.

[0060] Embodiment 3 This embodiment is the second embodiment of a lightweight multi-source data fusion photovoltaic power prediction method. This embodiment is similar to the first embodiment, except that this embodiment provides steps for constructing and training a multi-source data fusion photovoltaic power prediction model.

[0061] In this embodiment, constructing a photovoltaic power generation prediction model based on multi-source data fusion specifically includes the following steps: S31. Construct a BiGRU-Attention network to fuse multi-source data features and predict photovoltaic power generation. The BiGRU-Attention network includes an input layer, a bidirectional GRU layer, a feature attention mechanism layer, and a fully connected layer, and uses an error back propagation algorithm to optimize the network. S32. The input layer is used to receive cloud motion features from satellite cloud images, cloud amount features from ground-based cloud images, meteorological features from the meteorological department, and photovoltaic power generation history data, and merge each feature in a time series manner to form an input feature matrix:

[0062]

[0063] In the formula, is the cloud movement speed, is the direction of cloud movement, For cloud cover, is the preferred meteorological factor, is the photovoltaic power generation power; is the number of data, is the input feature matrix; S33. The bidirectional GRU layer is used to capture the bidirectional context information of the time series and obtain the forward and backward hidden states. , and maps each time-step hidden state of the bidirectional GRU layer output to the feature dimension: , , , ; In the formula, is the forward hidden state, is the backward hidden state, is the weight matrix, is the bias matrix, is the output of the bidirectional GRU layer; S34. The feature attention mechanism layer is used to adjust the weights of multi-source data features and weight the features of multi-source data to obtain global features. :

[0064]

[0065] In the formula, is the weight of multi-source data features, and N is the dimension of the feature vector; S35. Finally, the features are mapped to photovoltaic power through the fully connected layer:

[0066] In the formula, , is the weight matrix and bias of the fully connected layer.

[0067] In this embodiment, the training of the model includes the following steps: S41. The multi-source data set extracted in Example 2 is divided into a training set and a test set; S42. Use the test set to evaluate the trained photovoltaic power prediction model based on multi-source data fusion, and the evaluation indicator is the root mean square error RMSE to determine the prediction accuracy of the model; S43. When the prediction accuracy of the model is lower than the set threshold, the model is optimized according to the evaluation results, and the photovoltaic power generation prediction model based on multi-source data fusion is continued to be trained until the prediction accuracy reaches the set threshold.

[0068] In this embodiment, a lightweight prediction network is designed to optimize the feature extraction of multi-source data, fuse the multi-source data that affect photovoltaic power generation, and directly input the extracted features into the lightweight prediction network after fusion, which greatly reduces the computational burden of the model and improves the prediction speed of the model.

[0069] In this embodiment, various features are sent to the BiGRU-Attention network for model training; the trained model is used to predict the photovoltaic power generation of the centralized photovoltaic power station; and finally, the prediction model is deployed to the Solar Eye system. The Solar Eye system not only has the function of dynamically updating data, but also can automatically obtain multi-source data through networking and automatically delete old data to optimize storage space. It also has an intelligent optimization function, which can automatically use the acquired new data to train and update the model to maintain the best prediction effect. This embodiment realizes the feature extraction and fusion of multi-source data of photovoltaic power generation, and realizes accurate and lightweight power generation prediction, so that managers of small centralized photovoltaic power stations in rural areas can monitor photovoltaic power generation in real time and accurately and efficiently predict it on mobile terminals, so as to make corresponding energy management decisions, which is very effective for small centralized photovoltaic power stations in rural areas.

[0070] Embodiment 4 This example verifies the effectiveness of the lightweight multi-source data fusion photovoltaic power prediction method proposed in the present invention. First, in step S1, the photovoltaic power generation data, satellite cloud images, ground-based cloud images and meteorological data of centralized photovoltaic power generation in a rural area of ​​Guangdong Province in the time period of 2023 / 6 / 1 / 0:00~2023 / 12 / 31 / 23:00 are obtained, and the data is preprocessed and then feature extracted, and then input into the BiGRU-Attention network for prediction. The lightweight multi-source data fusion photovoltaic power prediction method proposed in the present invention is used to obtain the following Figure 3 The predicted effect diagram of photovoltaic power generation is shown in Figure 3 In the figure, the dotted line represents the actual value of photovoltaic power generation, and the solid line represents the predicted value of photovoltaic power generation. Figure 3 It can be seen that the error between the true value and the predicted value is very small, indicating that the method proposed in the present invention can effectively improve the accuracy of centralized photovoltaic power generation power prediction.

[0071] Embodiment 5 This embodiment is the first embodiment of a lightweight multi-source data fusion photovoltaic power generation prediction system. The system not only has the function of dynamically updating data, but also can automatically obtain multi-source data through networking and automatically delete old data to optimize storage space. It also has an intelligent optimization function, which can automatically use the acquired new data to train and update the model to maintain the best prediction effect. The system includes: Data acquisition module: used to automatically and synchronously collect satellite cloud images above the photovoltaic base from the satellite data service system at the same time interval, collect ground-based cloud images from the panoramic sky imager of the photovoltaic base, and obtain meteorological information around the photovoltaic base from the meteorological department; Multi-source data feature extraction module: used to extract the motion features of clouds in satellite cloud images using dynamic cloud tracking method, including cloud speed and direction; use multi-scale frequency domain optimization cloud segmentation method to automatically perform threshold segmentation on cloud images and extract cloud amount features in ground-based cloud images; use mutual information method to analyze the interdependence between photovoltaic power generation and meteorological factors, and extract meteorological factors with strong correlation as meteorological features; the collected motion features, transportation volume features, and meteorological features are constructed into a multi-source data set; Model building module: used to build a photovoltaic power prediction model that integrates multi-source data. By building a BiGRU-Attention network, the features of multi-source data are integrated to predict photovoltaic power. Model training module: used to train the photovoltaic power prediction model. The multi-source data set is divided into a training set and a test set. The photovoltaic power prediction model fused with multi-source data is trained with the training set, and the photovoltaic power prediction model is evaluated with the test set. When the accuracy of the photovoltaic power prediction model reaches the set threshold, the training is terminated. Prediction module: used to use the trained photovoltaic power prediction model to predict the photovoltaic power generation of centralized photovoltaic power stations.

[0072] In this embodiment, the BiGRU-Attention network includes: Input layer unit: used to receive cloud motion features from satellite cloud images, cloud amount features from ground-based cloud images, meteorological features from meteorological departments, and photovoltaic power generation history data, and merge each feature in a time series manner to form an input feature matrix:

[0073]

[0074] In the formula, is the cloud movement speed, is the direction of cloud movement, For cloud cover, is the preferred meteorological factor, is the photovoltaic power generation power; is the number of data, is the input feature matrix; Bidirectional GRU layer unit: used to capture the bidirectional context information of the time series and obtain the forward and backward hidden states , and maps each time-step hidden state of the bidirectional GRU layer output to the feature dimension: , , , ; In the formula, is the forward hidden state, is the backward hidden state, is the weight matrix, is the bias matrix, is the output of the bidirectional GRU layer; Feature attention mechanism layer unit: used to adjust the weights of multi-source data features and weight the features of multi-source data to obtain global features :

[0075]

[0076] In the formula, is the weight of multi-source data features, and N is the dimension of the feature vector; Fully connected layer: used to map features into photovoltaic power generation:

[0077] In the formula, , is the weight matrix and bias of the fully connected layer, is the photovoltaic power output.

[0078] Embodiment 6 This embodiment is a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described in any of the above embodiments when executing the computer program.

[0079] In the specific contents of the above-mentioned specific implementation methods, the various technical features can be combined in any non-contradictory manner. In order to make the description concise, not all possible combinations of the above-mentioned technical features are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0080] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A lightweight photovoltaic power generation prediction method based on multi-source data fusion, characterized in that: The following steps are involved: S1. Data collection: Obtain satellite cloud images, ground-based cloud images, meteorological data, and historical data of photovoltaic power generation of centralized photovoltaic power stations, build a data set, and perform data preprocessing; S2. Extract the features of multi-source data and form a multi-source data set: Use the dynamic cloud tracking method to extract the motion features of clouds in satellite cloud images, including the speed and direction of clouds; Use the multi-scale frequency domain optimization cloud segmentation method to perform automatic threshold segmentation on cloud images and extract the cloud amount features in ground-based cloud images; The mutual information method is used to analyze the interdependence between photovoltaic power generation and meteorological factors, and the meteorological factors with strong correlation are extracted as meteorological characteristics; the collected movement characteristics, transportation volume characteristics, and meteorological characteristics are constructed into a multi-source data set; S3. Construct a photovoltaic power generation prediction model based on multi-source data fusion: Construct a BiGRU-Attention network to fuse the features of multi-source data and predict photovoltaic power generation; S4. Training the photovoltaic power prediction model: divide the multi-source data set into a training set and a test set, use the training set to train the photovoltaic power prediction model fused with multi-source data, and use the test set to evaluate the photovoltaic power prediction model. When the accuracy of the photovoltaic power prediction model reaches the set threshold, the training is terminated; S5. Use the trained photovoltaic power prediction model to predict the photovoltaic power generation of the centralized photovoltaic power station.

2. The lightweight multi-source data fusion photovoltaic power prediction method according to claim 1 is characterized in that: The step S3 comprises: S31. Construct a BiGRU-Attention network to fuse multi-source data features and predict photovoltaic power generation. The BiGRU-Attention network includes an input layer, a bidirectional GRU layer, a feature attention mechanism layer, and a fully connected layer, and uses an error back propagation algorithm to optimize the network. S32. The input layer is used to receive cloud motion features from satellite cloud images, cloud amount features from ground-based cloud images, meteorological features from the meteorological department, and photovoltaic power generation history data, and merge each feature in a time series manner to form an input feature matrix: In the formula, is the cloud movement speed, is the direction of cloud movement, For cloud cover, is the preferred meteorological factor, is the photovoltaic power generation power; is the number of data, is the input feature matrix; S33. The bidirectional GRU layer is used to capture the bidirectional context information of the time series and obtain the forward and backward hidden states. , and maps each time-step hidden state of the bidirectional GRU layer output to the feature dimension: ， ， ， ； In the formula, is the forward hidden state, is the backward hidden state, is the weight matrix, is the bias matrix, is the output of the bidirectional GRU layer; S34. The feature attention mechanism layer is used to adjust the weights of multi-source data features and weight the features of multi-source data to obtain global features. : In the formula, is the weight of multi-source data features, and N is the dimension of the feature vector; S35. Finally, the features are mapped to photovoltaic power through the fully connected layer: In the formula, , is the weight matrix and bias of the fully connected layer, is the photovoltaic power output.

3. The lightweight multi-source data fusion photovoltaic power prediction method according to claim 1 is characterized in that: The step S1 comprises: S11. Collect and organize multi-source data, including satellite remote sensing cloud images, ground-based cloud images, meteorological conditions, and photovoltaic power generation of centralized photovoltaic power stations over a continuous period of time; S12. Preprocess the data set, adjust the image data to a uniform size, remove noise from the image, and perform histogram equalization on the image; S13. Detect and process outliers and missing values ​​of meteorological factors and photovoltaic power generation, and normalize the data.

4. The lightweight multi-source data fusion photovoltaic power prediction method according to claim 1 is characterized in that: The step S2 of extracting the motion characteristics of clouds in the satellite cloud image by using the dynamic cloud tracking method includes the following steps: S211. Convert satellite cloud images to grayscale images and construct multi-frame cloud images, taking continuous satellite cloud image sequences as input: In the formula, , is the gray value of the cloud image, is the pixel coordinate of the cloud image, Represents time, Represents the interval time of continuous satellite cloud image sequence; Divide the cloud image into small blocks, extract the gradient features in each small block, and calculate the grayscale gradient of each frame of the cloud image in space and time: ， ， ， The grayscale gradient describes the rate of change of the cloud in the x and y directions, as well as the rate of change in the time dimension; Taylor decomposition of the grayscale function: In the formula, , , Function right , , The partial derivative of is the remainder of the Taylor expansion; Will Ignore and let the velocity of the cloud in the x-axis direction , the speed in the y-axis direction , we get the equation: S212. Based on the fact that the pixels in the satellite cloud image have the same displacement in the same time, the displacement equation corresponding to each pixel in the satellite cloud image is obtained: S213. The conjugate gradient method is used to solve the above linear equations, and the cloud velocity vector is obtained. , the equation in step S212 is written as , in order to solve , construct the objective function ,Right now: Calculate the step size: In the formula, represents the number of iterations, represents the residual; Updated solution: Update residuals: Calculate the adjustment factor for the new direction: like , stop the iteration, and then get the movement speed of the cloud , the displacement of the cloud, .

5. The lightweight multi-source data fusion photovoltaic power prediction method according to claim 1 is characterized in that: In step S2, a multi-scale frequency domain optimized cloud segmentation method is used to perform automatic threshold segmentation on the cloud image to extract cloud amount features in the ground-based cloud image, specifically including: S221. Convert the ground-based cloud image from a color image to a grayscale image, count the number of pixels at each grayscale level in the grayscale image, and obtain the histogram of the ground-based cloud image. , the formula is as follows: In the formula, is the pixel value of the grayscale image, is the Kronecker delta function, when hour , otherwise 0, , is the width and height of the ground-based cloud image, is a number from 0 to 255; S222. Normalize the grayscale histogram of the ground-based cloud image and divide the image into The grayscale distribution probability of each area is as follows: ； In the formula, Representing the region, Is the cloud map in the area The histogram of and The cloud maps are in the area The width and height of S223. For each region, calculate the inter-class variance of each region in the cloud map, and determine the optimal threshold by maximizing the inter-class variance. First, calculate the weight and mean of the cloud region and the non-cloud region: ， ， ， ， In the formula, represents the weight of the cloud region, represents the weight of the non-cloud area, represents the mean value of the cloud area, represents the mean value of non-cloud area; The between-class variance is: ; Find the threshold that maximizes the between-class variance , the regional threshold The global threshold is obtained by weighted averaging. , the formula is: ； S224. Use the best threshold Binarize the grayscale image of the cloud map and divide the image into cloud area and non-cloud area. The formula is as follows: ， In the formula, The cloud image is binarized, 1 represents the cloud area, and 0 represents the non-cloud area; S225. Combine the binarization result of the cloud image with the frequency domain features of the image and obtain the frequency information through Fourier transform: ， Gaussian filtering is used to enhance the cloud edge features and then superimposed on the binary image to optimize the results: ， in is the inverse Fourier transform; According to the final optimized binary map Calculate the ratio of cloud area pixels to total pixels, and get the cloud amount characteristics : 。 6. The lightweight multi-source data fusion photovoltaic power prediction method according to claim 1 is characterized in that: In step S2, the mutual information method is used to analyze the interdependence between photovoltaic power generation and meteorological factors, and meteorological factors with strong correlation are extracted as meteorological features, including: S231. Obtain the temperature T, humidity H, wind speed W and radiation intensity S of the photovoltaic power station from the meteorological observation station As the main influencing factor; S232. Normalize each meteorological factor and photovoltaic power generation to eliminate dimensional differences; S233. Estimation of the joint probability density of meteorological factors and photovoltaic power generation using histogram method , estimate the marginal probability density of meteorological factors and photovoltaic power generation , ; S234. Calculate the mutual information between meteorological factors and photovoltaic power generation based on joint distribution and marginal distribution: S235. Select meteorological factors whose mutual information values ​​are greater than a set threshold as meteorological features.

7. The lightweight multi-source data fusion photovoltaic power prediction method according to claim 1 is characterized in that: The step S4 comprises: S41. Dividing the multi-source data set extracted in step S2 into a training set and a test set; S42. Use the test set to evaluate the trained photovoltaic power prediction model based on multi-source data fusion, and the evaluation indicator is the root mean square error RMSE to determine the prediction accuracy of the model; S43. When the prediction accuracy of the model is lower than the set threshold, the model is optimized according to the evaluation results, and the photovoltaic power generation prediction model based on multi-source data fusion is continued to be trained until the prediction accuracy reaches the set threshold.

8. A lightweight multi-source data fusion photovoltaic power generation prediction system, characterized in that: include: Data acquisition module: used to obtain satellite cloud images, ground-based cloud images, meteorological data and photovoltaic power generation historical data of centralized photovoltaic power stations, build data sets and perform data preprocessing; Multi-source data feature extraction module: used to extract the motion characteristics of clouds in satellite cloud images using dynamic cloud tracking method, including cloud speed and direction; use multi-scale frequency domain optimization cloud segmentation method to perform automatic threshold segmentation on cloud images and extract cloud amount characteristics in ground-based cloud images; The mutual information method is used to analyze the interdependence between photovoltaic power generation and meteorological factors, and the meteorological factors with strong correlation are extracted as meteorological characteristics; the collected movement characteristics, transportation volume characteristics, and meteorological characteristics are constructed into a multi-source data set; Model building module: used to build a photovoltaic power prediction model that integrates multi-source data. By building a BiGRU-Attention network, the features of multi-source data are integrated to predict photovoltaic power. Model training module: used to train the photovoltaic power prediction model. The multi-source data set is divided into a training set and a test set. The photovoltaic power prediction model fused with multi-source data is trained with the training set, and the photovoltaic power prediction model is evaluated with the test set. When the accuracy of the photovoltaic power prediction model reaches the set threshold, the training is terminated. Prediction module: used to use the trained photovoltaic power prediction model to predict the photovoltaic power generation of centralized photovoltaic power stations.

9. The lightweight multi-source data fusion photovoltaic power generation prediction system according to claim 8 is characterized in that: In the model building module, the BiGRU-Attention network includes: Input layer unit: used to receive cloud motion features from satellite cloud images, cloud amount features from ground-based cloud images, meteorological features from meteorological departments, and photovoltaic power generation history data, and merge each feature in a time series manner to form an input feature matrix: In the formula, is the cloud movement speed, is the direction of cloud movement, For cloud cover, is the preferred meteorological factor, is the photovoltaic power generation power; is the number of data, is the input feature matrix; Bidirectional GRU layer unit: used to capture the bidirectional context information of the time series and obtain the forward and backward hidden states , and maps each time-step hidden state of the bidirectional GRU layer output to the feature dimension: ， ， ， ； In the formula, is the forward hidden state, is the backward hidden state, is the weight matrix, is the bias matrix, is the output of the bidirectional GRU layer; Feature attention mechanism layer unit: used to adjust the weights of multi-source data features and weight the features of multi-source data to obtain global features : In the formula, is the weight of multi-source data features, and N is the dimension of the feature vector; Fully connected layer: used to map features into photovoltaic power generation: In the formula, , is the weight matrix and bias of the fully connected layer, is the photovoltaic power output.

10. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the steps of the method described in any one of claims 1 to 8 when executing the computer program.

Images