Photovoltaic power generation power prediction method and system based on multi-source heterogeneous feature fusion

Abstract

The application discloses a photovoltaic power generation power prediction method and system based on multi-source heterogeneous feature fusion, and the method comprises the following steps: acquiring historical time series data and historical image data of a photovoltaic power plant; extracting features from the historical time series data to obtain a two-dimensional feature map corresponding to the historical time series data; performing image preprocessing on the historical image data; extracting features from the historical image data after image preprocessing to obtain a corresponding three-dimensional feature map; finally, converting the three-dimensional feature map into a two-dimensional feature map, splicing the two-dimensional feature map corresponding to the historical image data with the two-dimensional feature map corresponding to the historical time series data to obtain a two-dimensional feature map of heterogeneous feature fusion; and inputting the two-dimensional feature map of heterogeneous feature fusion into a trained Bayesian neural network to obtain a predicted value and a probability of photovoltaic power generation power. The application overcomes the limitations of traditional prediction models in feature selection and prediction results, thereby improving the accuracy and reliability of prediction.

Description

Technical Field

[0001] The present invention relates to photovoltaic power generation prediction technology, and in particular to a photovoltaic power generation power prediction method and system based on multi-source heterogeneous feature fusion. Background Art

[0002] Against the backdrop of today's global energy transition and the rapid development of renewable energy, photovoltaic power generation, as an important clean energy source, has garnered widespread attention. PV power forecasting is crucial for ensuring the normal operation and optimized dispatch of power grids, and its accuracy is crucial for grid security and economic operation. Traditional PV power forecasting technology primarily relies on deterministic single-point prediction methods, which provide a power output forecast at a specific moment through real-time monitoring and analysis of meteorological conditions. However, the inherent flaw of single-point predictions is that they struggle to accurately capture the randomness and uncertainty of PV power generation, and the results often fall short of practical application requirements. Because PV power generation is affected by a variety of meteorological factors, such as light intensity, temperature, wind speed, and cloud cover variations, this deterministic prediction method can easily lead to significant deviations between the predicted results and actual power generation capacity, creating challenges for grid dispatch and management.

[0003] In recent years, probabilistic forecasting methods for ultra-short-term photovoltaic power generation have gradually emerged. The core of these methods lies in their ability to describe the uncertainty of output power, providing decision makers with more information and support, and to a certain extent, facilitating the assessment of power generation distribution. However, most current methods for ultra-short-term probabilistic forecasting of photovoltaic power generation rely on specific meteorological data from a single source. For example, many studies use only ground-based meteorological observations or forecast results from specific meteorological models. This use of a single data source limits the diversity of feature extraction and fails to fully account for the complexity and variability of the photovoltaic power generation process, resulting in limited room for improvement in forecast accuracy. It also restricts the model's adaptability to diverse meteorological conditions and environmental changes, and limits the reliability of the forecast results, thus failing to fully reflect the complexity of photovoltaic power generation. Furthermore, some recent studies have attempted to use satellite cloud imagery alone for photovoltaic power generation forecasting. Although satellite cloud imagery can provide cloud information over a wide range of areas, its limited temporal and spatial resolution makes it difficult to accurately capture detailed and local features in the data, which in turn affects the effectiveness of photovoltaic power generation forecasts. Similarly, relying solely on ground cloud images for photovoltaic forecasting also faces shortcomings. Although ground cloud images captured by all-sky imagers can provide real-time local weather conditions and cloud dynamics, data may be missing in bad weather, limiting its effectiveness in photovoltaic power generation forecasting. Summary of the Invention

[0004] The technical problem to be solved by the present invention is as follows: In response to the above-mentioned problems of the prior art, a photovoltaic power generation power prediction method and system based on multi-source heterogeneous feature fusion is provided, which can effectively combine and extract potential patterns and features in multi-source heterogeneous meteorological data and historical data, while obtaining the probability distribution interval of photovoltaic ultra-short-term power generation, overcoming the limitations of traditional prediction models in feature selection and prediction results, thereby improving the accuracy and reliability of the prediction.

[0005] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0006] A photovoltaic power generation power prediction method based on multi-source heterogeneous feature fusion includes the following steps:

[0007] Obtain historical time series data and historical image data of photovoltaic power plants;

[0008] Extracting features from the historical time series data to obtain a two-dimensional feature map corresponding to the historical time series data;

[0009] performing image preprocessing on the historical image data;

[0010] Perform feature extraction on the historical image data after image preprocessing to obtain the corresponding three-dimensional feature map, convert the three-dimensional feature map of the historical image data into the corresponding two-dimensional feature map, and splice the two-dimensional feature map corresponding to the historical image data with the two-dimensional feature map corresponding to the historical time series data to obtain a two-dimensional feature map of heterogeneous feature fusion;

[0011] The two-dimensional feature map of heterogeneous feature fusion is input into the trained Bayesian neural network to obtain the predicted value and probability of photovoltaic power generation.

[0012] Furthermore, the historical time series data and historical image data specifically refer to all historical time series data and historical image data in a preset time period before the prediction moment. Before obtaining the historical time series data and historical image data of the photovoltaic power plant, it also includes: obtaining time series data and image data in real time according to the specified sampling interval.

[0013] Furthermore, the historical time series data includes historical measured power generation data and historical measured weather data. When extracting features from the historical time series data, the following steps are specifically performed:

[0014] Combine the historical measured power generation data and the historical measured weather data into a data matrix, where the number of rows in the data matrix is ​​the number of samples in the preset time period before the prediction moment, and the number of columns in the data matrix is ​​the number of features in the historical measured power generation data and the historical measured weather data;

[0015] The trained TS2Vec representation model is used to perform feature representation on the data matrix to obtain a data matrix with upgraded feature dimensions as a two-dimensional feature map corresponding to the historical time series data.

[0016] Furthermore, the historical image data includes historical satellite cloud images and historical ground cloud images. When performing image preprocessing on the historical image data, the images of the historical satellite cloud images and historical ground cloud images are specifically grayscaled and then the image sizes are adjusted to a uniform size.

[0017] Furthermore, when performing feature extraction on the historical image data after image preprocessing, specifically performing feature extraction on the historical satellite cloud images and historical ground cloud images after image preprocessing, specifically including:

[0018] The preprocessed current image data is used as the initial feature map, and the initial feature Figure 1 The global average pooling and global maximum pooling are performed in sequence, and then the channel attention map is calculated through the shared multi-layer perceptron. The channel attention map is used to multiply the initial feature map in another way to obtain the intermediate feature map;

[0019] The intermediate features Figure 1 The global average pooling and global maximum pooling are performed in the first and second paths respectively, and then the results of the global average pooling and the global maximum pooling are concatenated and passed through the convolution layer to obtain the spatial attention map. The spatial attention map is used to multiply the intermediate feature map in the other path to obtain the final feature map.

[0020] Furthermore, when splicing the two-dimensional feature map of historical image data with the two-dimensional feature map corresponding to the historical time series data, specifically, the two-dimensional feature map corresponding to the historical image data and the two-dimensional feature map corresponding to the historical time series data are both added with a channel dimension of size 1 as the third dimension, and data splicing is performed on the third dimension to obtain a three-dimensional feature map of heterogeneous feature fusion, and then the three-dimensional feature map of heterogeneous feature fusion is converted into the corresponding two-dimensional feature map.

[0021] Furthermore, when the two-dimensional feature map of the heterogeneous feature fusion is input into the trained Bayesian neural network, specifically, the vector after the two-dimensional feature map of the heterogeneous feature fusion is flattened is input into the trained Bayesian neural network.

[0022] The present invention also proposes a photovoltaic power generation prediction system based on multi-source heterogeneous feature fusion, including a memory, a processor and a computer program stored in the memory, and the processor executes the computer program to implement any step of the photovoltaic power generation prediction method based on multi-source heterogeneous feature fusion.

[0023] The present invention also proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the photovoltaic power generation power prediction methods based on multi-source heterogeneous feature fusion.

[0024] The present invention also proposes a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of any one of the photovoltaic power generation power prediction methods based on multi-source heterogeneous feature fusion.

[0025] Compared with the prior art, the advantages of the present invention are:

[0026] The present invention combines multi-source heterogeneous time series data and image data, such as historical measured weather data, historical measured power generation, historical satellite cloud images, and historical ground cloud images. After extracting features from the time series data and image data respectively, the feature maps of the time series data and image data are spliced ​​to achieve feature extraction and fusion of different types of data. The Bayesian neural network (BNN) model is used to perform probabilistic prediction of distributed photovoltaic power generation power, and the BNN model's excellent uncertainty modeling capabilities are used to provide reliable confidence intervals for power prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 Flowchart of a method according to an embodiment of the present invention.

[0028] Figure 2 This is a schematic diagram of the TS2Vec representation of historical measured data and the preprocessing of historical satellite cloud images and historical ground cloud images in an embodiment of the present invention.

[0029] Figure 3 Schematic diagram of a multi-source heterogeneous feature fusion module according to an embodiment of the present invention.

[0030] Figure 4 Schematic diagram of the structure of the Bayesian neural network model. DETAILED DESCRIPTION

[0031] The present invention will be further described below in conjunction with the accompanying drawings and specific preferred embodiments, but the scope of protection of the present invention is not limited thereby.

[0032] Example 1

[0033] This embodiment proposes a photovoltaic power generation prediction method based on multi-source heterogeneous feature fusion, which comprehensively utilizes various heterogeneous data such as historical measured weather data, historical measured power generation, historical satellite cloud images, and historical ground cloud images, and constructs a multi-source heterogeneous feature fusion module to fully tap the complementary advantages of different types of data, improve the accuracy and robustness of the prediction model, and overcome the shortcomings of relying on a single meteorological data source. Figure 1As shown, the method of this embodiment includes the following steps:

[0034] S1) acquiring historical time series data and historical image data of the photovoltaic power plant. In this embodiment, the historical time series data and historical image data specifically refer to all historical time series data and historical image data of a preset time period before the prediction moment, wherein the historical time series data includes historical measured weather data and historical measured power generation, and the historical image data includes historical satellite cloud images and historical ground cloud images;

[0035] S2) extracting features from the historical time series data to obtain a two-dimensional feature graph corresponding to the historical time series data. In this embodiment, when extracting features from the historical time series data, a TS2Vec characterization model is used to characterize the data matrix containing the historical measured weather data and the historical measured power generation;

[0036] S3) performing image preprocessing on the historical image data, specifically performing image preprocessing on the historical satellite cloud images and the historical ground cloud images, and uniformly processing them into single-channel images of a preset size;

[0037] S4) performing feature extraction on the historical image data after image preprocessing to obtain a corresponding three-dimensional feature map, converting the three-dimensional feature map of the historical image data into a corresponding two-dimensional feature map, and splicing the two-dimensional feature map corresponding to the historical image data with the two-dimensional feature map corresponding to the historical time series data to obtain a two-dimensional feature map of heterogeneous feature fusion. In this embodiment, this step is achieved by inputting the feature characterization results of the data matrix containing the historical measured weather data and the historical measured power generation data together with the historical satellite cloud map and the historical ground cloud map after image preprocessing into a multi-source heterogeneous feature fusion module to form a data matrix;

[0038] S5) The two-dimensional feature map of the heterogeneous feature fusion is input into a trained Bayesian neural network (BNN). In this embodiment, the BNN module is used to process the data matrix output by the multi-source heterogeneous feature fusion module and output the photovoltaic power generation power and its probability interval distribution within the ultra-short-term prediction time period to obtain the predicted value and probability of the photovoltaic power generation power.

[0039] Through the above steps, the probabilistic prediction model established in this embodiment can replace the traditional deterministic prediction method, calculate and output the probability distribution of photovoltaic power generation, quantitatively describe the uncertainty of power prediction, establish a probabilistic prediction interval, provide richer decision-making basis for power dispatch, and effectively reduce the impact of photovoltaic power generation fluctuations on the power system.

[0040] Each step is described in detail below.

[0041] Since the historical time series data and historical image data in this embodiment specifically refer to all historical time series data and historical image data in a preset time period before the predicted moment, before step S1, the process further includes: acquiring time series data and image data in real time according to a specified sampling interval. In this embodiment, the sampling interval is preferably 15 minutes, and the preset time period is preferably 6 hours before the predicted moment.

[0042] In step S2 of this embodiment, the TS2Vec characterization model is used to perform feature characterization on the data matrix containing the historical measured weather data and the historical measured power generation. This embodiment combines the feature characterization of the historical measured weather data and the historical measured power generation to provide more comprehensive information support for photovoltaic power probability prediction. Feature characterization can extract potential patterns and features in time series data, thereby improving the performance of the prediction model. Furthermore, the historical time series data includes historical measured power generation data and historical measured weather data. When feature extraction is performed on the historical time series data, as shown in FIG. Figure 2 As shown, specifically including:

[0043] S21) combining the historical measured power generation data and the historical measured weather data into a data matrix, wherein the number of rows of the data matrix is ​​the number of sampling times in a preset time period before the prediction moment, and the number of columns of the data matrix is ​​the number of features in the historical measured power generation data and the historical measured weather data;

[0044] In this embodiment, the sampling interval is preferably 15 minutes, and the preset time period is preferably 6 hours before the forecast time. The historical measured weather data includes historical measured irradiance, historical measured temperature, historical measured humidity, historical measured wind speed, and historical measured wind direction data. Therefore, the data matrix obtained by combining the historical measured power generation data with the historical measured weather data is a 24×6 data matrix. The number of rows (24) indicates that 24 samples were taken within 6 hours, and the number of columns (6) indicates that each sampling records data of 5 characteristic sources in the historical measured weather data and 1 characteristic source of the historical measured power generation data, a total of 6 characteristic sources.

[0045] S22) Use the trained TS2Vec representation model to perform feature representation on the data matrix to obtain a data matrix after the feature dimension is upgraded as a two-dimensional feature map corresponding to the historical time series data.

[0046] In this example, the 24×6 data is represented by the TS2Vec representation module, increasing its feature dimension to 224, resulting in a 24×224 two-dimensional feature map. TS2Vec (Time Series to Vector) is a model for learning time series representations. Its goal is to convert time series data into a fixed-length vector representation to facilitate various subsequent tasks. Convolutional Neural Networks (CNNs) or Recurrent Neural Networks (RNNs) are typically used to extract time series features.

[0047] In this embodiment, the TS2Vec representation model includes an input layer, a hidden layer, and an output layer. The input layer accepts a 24×6 input matrix. The hidden layer uses a multi-layer convolutional network to process the input data, gradually extracts complex features in the time series, and generates a feature representation for each time step. The output layer maps the output of the hidden layer to the target feature dimension, that is, 224 dimensions. The output layer dimension is 24×224, that is, a 224-dimensional feature vector is generated for each time step.

[0048] The TS2Vec characterization model in this embodiment can perform self-supervised learning by constructing positive and negative sample pairs, where the positive sample pair refers to adjacent time steps in the same time series, and the negative sample pair refers to the time steps in different time series. At the same time, the TS2Vec characterization model uses a loss function such as InfoNCE to ensure that the features of adjacent time steps in the same time series are more similar. Adam or similar optimization algorithms are used for model training. Monitor the training and validation losses during training and adjust the model hyperparameters when necessary. The trained model can convert a 24×6 input matrix into a 24×224 two-dimensional feature map. After the input of each time step passes through the model, a 224-dimensional feature vector is output.

[0049] In step S3 of this embodiment, when performing image preprocessing on the historical image data, specifically, an image preprocessing module is used to perform grayscale processing on the images of the historical satellite cloud images and the historical ground cloud images, and then the image sizes are adjusted to a uniform size.

[0050] like Figure 2 As shown, in this embodiment, the sampling interval is preferably 15 minutes, and the preset time period is preferably 6 hours before the prediction time. Therefore, the historical satellite cloud image and the historical ground cloud image are 24 three-channel color pictures with a size of H×W and a sampling interval of 15 minutes within the past 6 hours of the current time. The image preprocessing module first performs image grayscale processing to transform the original color three-channel image into a single-channel image, and then transforms the image size into 24×224×224.

[0051] like Figure 3As shown, in step S4 of this embodiment, when feature extraction is performed on the historical image data after image preprocessing, a parallel neural network is specifically designed to perform feature extraction on the historical satellite cloud images and historical ground cloud images after image preprocessing. In this embodiment, the parallel neural network includes a CBAM (Convolutional Block Attention Module) convolutional attention module composed of a channel attention module and a spatial attention module, wherein the channel attention module performs global average pooling and global maximum pooling on the input, compresses the features of each channel into a real number, and then obtains a channel attention map through a shared multi-layer perceptron and a sigmoid function, and multiplies the channel attention map and the input of the channel attention module to obtain the output of the channel attention module. The output of the channel attention module will serve as the input of the spatial attention module, and then global average pooling and global maximum pooling will be performed. The results of the two pooling will be spliced ​​and passed through a convolution layer and sigmoid function to generate a spatial attention map. The spatial attention map and the output of the channel attention module will be multiplied to obtain the output of the CBAM convolutional attention module. The size of the feature map after the CBAM convolutional attention module is consistent with the size of the input historical satellite cloud image and historical ground cloud image after image preprocessing. Therefore, when extracting features from the historical satellite cloud image and historical ground cloud image after image preprocessing, the following steps are specifically included:

[0052] S41) using the preprocessed current image data as an initial feature map. In this embodiment, the initial feature map has a size of 24×224×224;

[0053] S42) Initial feature Figure 1 The global average pooling and global maximum pooling are performed in sequence, and then the channel attention map is calculated through a shared multi-layer perceptron;

[0054] In this embodiment, for the initial feature map, global average pooling and maximum pooling are performed on each channel in the spatial dimension, and the expression is as follows:

[0055] V avg =GAP(F),V max =GMP(F)

[0056] Among them, Vavg represents the result of global average pooling, and Vmax represents the result of maximum pooling. Both are input into the shared multi-layer perceptron (MLP), and a channel attention weight scalar M is generated through nonlinear activation (such as ReLU) and Sigmoid function. c , the expression is as follows:

[0057] M c =σ(MLP(V avg ))+MLP(Vmax )

[0058] S43) Use the channel attention map to multiply the initial feature map in another direction to obtain the intermediate feature map, which is expressed as follows:

[0059] F ′ =M c ·F

[0060] Among them, F represents the initial feature map, F ′ Represents the intermediate feature map, size is 24×224×224;

[0061] S44) The intermediate features Figure 1 The global average pooling and global maximum pooling are performed on the two paths respectively, and then the results of global average pooling and global maximum pooling are spliced ​​and passed through the convolution layer to obtain the spatial attention map;

[0062] In this embodiment, average pooling and maximum pooling are performed on the channel dimension to obtain two feature maps of size 24×224×224, which are the processing results of the complete image itself for a single-channel image. These two feature maps are spliced ​​on the channel dimension, and then a 7×7 convolution kernel is used to convolve the spliced ​​feature map to generate a spatial attention map M. s , the expression is as follows:

[0063] M s =σ(f 7×7 [A avg ; A max ])

[0064] Among them, [A avg ; A max ] is the concatenation of the average pooling result and the maximum pooling result, A avg is the average pooling result, A max is the maximum pooling result;

[0065] S45) Use the spatial attention map to multiply the intermediate feature map in another direction to obtain the final feature map, which is expressed as follows:

[0066] F″=M s ⊙F′

[0067] Among them, ⊙ represents element-by-element multiplication, F″ represents the final feature map, and the size is still 24×224×224.

[0068] like Figure 3As shown, in step S4 of this embodiment, when converting the three-dimensional feature map of the historical image data into the corresponding two-dimensional feature map, specifically, the feature map after passing through the CBAM convolutional attention module is transformed into a three-dimensional feature map of size 24×224×224 by using a Linear linear fully connected layer through a linear connection transformation module, and then the feature map is transformed into a two-dimensional feature map of size 24×224 by removing the channel dimension of size 1.

[0069] Correspondingly, in step S4 of this embodiment, when splicing the two-dimensional feature map of the historical image data with the two-dimensional feature map corresponding to the historical time series data, specifically, the two-dimensional feature map (size of 24×224) corresponding to the historical satellite cloud map and the historical ground cloud map in the historical image data after the linear connection transformation module and the two-dimensional feature map (size of 24×224) corresponding to the historical time series data represented by the TS2Vec characterization model are both added with a channel dimension of size 1 as the third dimension, and data are spliced ​​on the third dimension to obtain a three-dimensional feature map of heterogeneous feature fusion (size of 24×224×3), and then the three-dimensional feature map of heterogeneous feature fusion is converted into the corresponding two-dimensional feature map, specifically, the linear connection transformation module uses the Linear linear fully connected layer to transform the three-dimensional feature map of size 24×224×3 into 24×224×1, and then the feature map is transformed into a two-dimensional feature map of size 24×224 by removing the channel dimension of size 1.

[0070] In step S5 of this embodiment, the BNN module is used to process the data matrix of size 24×224 output by the multi-source heterogeneous feature fusion module and output the photovoltaic power generation power and its probability interval distribution within the ultra-short-term prediction period. When the two-dimensional feature map of the heterogeneous feature fusion is input into the trained Bayesian neural network, the vector after the two-dimensional feature map of the heterogeneous feature fusion is flattened is input into the trained Bayesian neural network.

[0071] In this embodiment, the data matrix of size 24×224 from the multi-source heterogeneous feature fusion module is flattened to obtain a one-dimensional vector of length 5376. The structure of the Bayesian neural network is as follows: Figure 4 As shown in the figure, the input layer obtains a vector of length 5376 and directly passes it as the input of the hidden layer. The length of the vector output by the output layer is the number of photovoltaic power samples in the next hour, that is, the length of 4 sampling intervals.

[0072] The number of neurons in the hidden layer of the Bayesian neural network of this embodiment is set to 256. The hidden layer transmits a vector of length 5376 from the input layer, and after forward propagation calculation, it outputs a vector of length 256. The expression is as follows:

[0073]

[0074] Where f() is the activation function of the hidden layer (such as ReLU), x i is the input feature, b j is the bias, W ij is the weight, i represents the input unit, and j represents the hidden layer unit.

[0075] The output layer of the Bayesian neural network in this embodiment obtains a vector of length 256 transmitted from the hidden layer. The number of neurons in the output layer is set to 4, corresponding to 4 sampling intervals in the next hour. The output vector of length 4 represents the predicted value of photovoltaic power generation, which is expressed as follows:

[0076]

[0077] Among them, g() is the activation function of the output layer, which can be a linear function, b k is the bias, W jk is the weight, j represents the hidden layer unit, and k represents the output unit.

[0078] Each weight between the neurons in the hidden layer and the output layer of the Bayesian neural network of this embodiment is considered to obey a Gaussian distribution with a mean of μ and a variance of σ. However, if different Gaussian distributions are obeyed, multiple prediction results can be obtained by sampling multiple times from each Gaussian distribution to obtain different weight values ​​when making probability predictions, thereby obtaining prediction probability intervals at different confidence levels. Specifically, the following steps are included:

[0079] S51) obtaining input features and corresponding true labels as training data, then using variational inference or Monte Carlo method to update μ and σ parameters of each weight, and finally outputting optimized weight distribution parameters;

[0080] S52) obtaining input features as test data, sampling multiple times from the Gaussian distribution of each weight, and performing forward propagation on the weight set obtained from each sampling to obtain multiple prediction results and form a predicted value distribution;

[0081] S53) Based on the multiple prediction results, the prediction mean and standard deviation are calculated, and the confidence interval of the prediction value at different confidence levels is calculated based on this, and the expression is as follows:

[0082]

[0083] in, represents the mean of the predicted values, z α / 2 represents the critical value of the standard normal distribution, corresponding to the confidence level 1-α, σ y Represents the standard deviation of the predicted value.

[0084] Example 2

[0085] This embodiment proposes a photovoltaic power generation prediction system based on multi-source heterogeneous feature fusion, including a memory, a processor and a computer program stored in the memory. The processor executes the computer program to implement the steps of the photovoltaic power generation power prediction method based on multi-source heterogeneous feature fusion in Example 1.

[0086] This embodiment also proposes a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the photovoltaic power generation power prediction method based on multi-source heterogeneous feature fusion in embodiment one are implemented.

[0087] This embodiment also proposes a computer program product, including a computer program, which, when executed by a processor, implements the steps of the photovoltaic power generation power prediction method based on multi-source heterogeneous feature fusion in embodiment one.

[0088] In summary, the present invention discloses a photovoltaic power generation power prediction method and system based on multi-source heterogeneous feature fusion. It combines multi-source heterogeneous time series data and image data such as historical measured weather data, historical measured power generation, historical satellite cloud images, and historical ground cloud images to construct a multi-source heterogeneous feature fusion module to realize feature extraction and fusion of different types of data. It adopts a Bayesian neural network (BNN) model to perform probability prediction of ultra-short-term power of distributed photovoltaic power generation. Relying on the good uncertainty modeling ability of the BNN model, it provides a reliable confidence interval for power prediction. While effectively combining and extracting potential patterns and features in multi-source heterogeneous meteorological data and historical data, it obtains the probability distribution interval of photovoltaic ultra-short-term power generation, overcomes the limitations of traditional prediction models in feature selection and prediction results, and thus improves the accuracy and reliability of the prediction.

[0089] The above description is merely a preferred embodiment of the present invention. The scope of protection of the present invention is not limited to the above embodiment. All technical solutions based on the concept of the present invention are within the scope of protection of the present invention. It should be noted that for those skilled in the art, various improvements and modifications that do not depart from the principles of the present invention should also be considered within the scope of protection of the present invention.

Claims

1. A photovoltaic power generation prediction method based on multi-source heterogeneous feature fusion, characterized in that: The following steps are involved: Obtain historical time series data and historical image data of photovoltaic power plants; Extracting features from the historical time series data to obtain a two-dimensional feature map corresponding to the historical time series data; performing image preprocessing on the historical image data; Perform feature extraction on the historical image data after image preprocessing to obtain the corresponding three-dimensional feature map, convert the three-dimensional feature map of the historical image data into the corresponding two-dimensional feature map, and splice the two-dimensional feature map corresponding to the historical image data with the two-dimensional feature map corresponding to the historical time series data to obtain a two-dimensional feature map of heterogeneous feature fusion; The two-dimensional feature map of heterogeneous feature fusion is input into the trained Bayesian neural network to obtain the predicted value and probability of photovoltaic power generation; The historical time series data includes historical measured power generation data and historical measured weather data. Feature extraction of the historical time series data specifically includes: Combine the historical measured power generation data and the historical measured weather data into a data matrix, where the number of rows in the data matrix is ​​the number of samples in the preset time period before the prediction moment, and the number of columns in the data matrix is ​​the number of features in the historical measured power generation data and the historical measured weather data; Use the trained TS2Vec representation model to perform feature representation on the data matrix to obtain a data matrix with upgraded feature dimensions as a two-dimensional feature map corresponding to the historical time series data; The historical image data includes historical satellite cloud images and historical ground cloud images. When performing image preprocessing on the historical image data, specifically grayscale processing is performed on the images of the historical satellite cloud images and historical ground cloud images, and then the image sizes are adjusted to a uniform size; When performing feature extraction on the historical image data after image preprocessing, specifically, feature extraction is performed on the historical satellite cloud images and historical ground cloud images after image preprocessing, specifically including: The preprocessed current image data is used as the initial feature map, and the initial feature map is subjected to global average pooling and global maximum pooling in sequence. Then, the channel attention map is calculated through a shared multi-layer perceptron, and the channel attention map is used to multiply the initial feature map in another direction to obtain the intermediate feature map. The intermediate feature map is subjected to global average pooling and global maximum pooling respectively. The results of global average pooling and global maximum pooling are then concatenated and passed through a convolutional layer to obtain a spatial attention map. The spatial attention map is then multiplied with the intermediate feature map to obtain the final feature map. When splicing the two-dimensional feature map of historical image data with the two-dimensional feature map corresponding to the historical time series data, specifically, the two-dimensional feature map corresponding to the historical image data and the two-dimensional feature map corresponding to the historical time series data are both added with a channel dimension of size 1 as the third dimension, and data are spliced ​​on the third dimension to obtain a three-dimensional feature map of heterogeneous feature fusion, and then the three-dimensional feature map of heterogeneous feature fusion is converted into the corresponding two-dimensional feature map.

2. The photovoltaic power generation prediction method based on multi-source heterogeneous feature fusion according to claim 1 is characterized in that: The historical time series data and historical image data specifically refer to all historical time series data and historical image data in a preset time period before the prediction moment. Before obtaining the historical time series data and historical image data of the photovoltaic power plant, it also includes: obtaining time series data and image data in real time according to the specified sampling interval.

3. The photovoltaic power generation prediction method based on multi-source heterogeneous feature fusion according to claim 1 is characterized in that: When the two-dimensional feature map of heterogeneous feature fusion is input into the trained Bayesian neural network, specifically, the vector after the two-dimensional feature map of heterogeneous feature fusion is flattened is input into the trained Bayesian neural network.

4. A photovoltaic power generation prediction system based on multi-source heterogeneous feature fusion, comprising a memory, a processor, and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the photovoltaic power generation power prediction method based on multi-source heterogeneous feature fusion as described in any one of claims 1 to 3.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the photovoltaic power generation power prediction method based on multi-source heterogeneous feature fusion as described in any one of claims 1 to 3 are implemented.

6. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the photovoltaic power generation power prediction method based on multi-source heterogeneous feature fusion as described in any one of claims 1 to 3 are implemented.

Images