Wind and light output scene generation method based on depth feature mining and adaptive clustering

Abstract

The invention discloses a wind and light output scene generation method based on depth feature mining and adaptive clustering, and the method comprises the steps: cleaning wind and light output data, carrying out the normalization processing of the data, and enabling the data to be mapped to a preset interval, so as to eliminate the dimension influence; constructing a deep convolutional feature extraction network to extract a corresponding feature map from the normalized wind and light output data; a K-Means + + algorithm is adopted to initialize a clustering center, an improved ISODATA clustering algorithm is executed based on a density threshold dynamic splitting mechanism, clustering parameters are optimized through Bayesian optimization, and a typical scene is generated. The accuracy of the wind and light output scene is remarkably improved.

Description

Technical Field

[0001] This application relates to the field of new energy power generation technology, and in particular to a method for generating wind and solar power output scenarios based on deep feature mining and adaptive clustering. Background Technology

[0002] Wind and solar energy are characterized by significant intermittency, randomness, and volatility. Their output is affected by various factors such as weather conditions and geographical location, making accurate prediction difficult. Accurately generating wind and solar power output scenarios can help power systems better cope with the uncertainties of wind and solar power generation, improve system stability and reliability, and is crucial for the planning, scheduling, and operation of power systems.

[0003] Existing methods for generating wind and solar power output scenarios suffer from several shortcomings. On the one hand, many methods rely on complex meteorological data and physical models, resulting in high computational costs and complex models that are difficult to adapt to the variable environments in real-world applications. On the other hand, some data-driven methods have deficiencies in feature extraction and scenario clustering. For example, they lack in-depth feature mining of wind and solar power output data, using only simple statistical features (such as mean and standard deviation), failing to fully capture complex patterns and potential regularities in the data. Furthermore, clustering algorithms are not adaptable enough to data distributions and are easily affected by initial parameter settings, leading to unstable clustering results and generating typical scenarios that do not accurately represent actual wind and solar power output. These shortcomings severely restrict the application and development of wind and solar power output scenario generation methods in practical engineering, necessitating more efficient, accurate, and robust solutions. Summary of the Invention

[0004] To address the issues of insufficient feature extraction, parameter dependence on experience, and fixed number of scenes in traditional scene generation methods, this application provides a method for generating wind and solar power output scenes based on deep feature mining and adaptive clustering.

[0005] This application discloses a method for generating wind and solar power output scenes based on deep feature mining and adaptive clustering, which includes: Step 1: Clean the wind and solar power output data and normalize it to map it to a preset range in order to eliminate the influence of dimensions; Step 2: Construct a deep convolutional feature extraction network to extract the corresponding feature maps from the normalized wind and solar power output data; Step 3: Initialize cluster centers using the K-Means++ algorithm, execute the improved ISODATA clustering algorithm based on the density threshold dynamic splitting mechanism, optimize clustering parameters through Bayesian optimization, and generate typical scenarios.

[0006] Further, step 2 includes: The constructed deep convolutional feature extraction network includes an input layer, a first convolutional layer, a first pooling layer, a second convolutional layer, a second pooling layer, a flattening layer, a fully connected layer, a batch normalization layer, and a fully connected layer connected in sequence. The formula for extracting feature maps from normalized wind and solar power output data using deep convolutional features is as follows:

[0007]

[0008] in, It is the output of the first convolutional layer. It is the unified scenery that contributes to the effort. It is the first convolutional layer. It's a bias. For the first Layer feature map, For the first Layer convolution kernel, For the first Layer bias, It is the ReLU activation function. This represents the convolution operation.

[0009] Furthermore, the input layer receives the normalized wind and solar power output time series. T represents the time step, and 2 represents the landscape feature dimension. For the first convolutional layer, the number of kernels is set to 32, the kernel size is 3, and the activation function is ReLU to maintain the temporal dimension. For the first pooling layer, the pooling window size is 2, and the stride is 2 to reduce the data dimension. For the second convolutional layer, the number of kernels is set to 64, the kernel size is 3, and the activation function is ReLU to maintain feature integrity. For the second pooling layer, the pooling window size is 2, and the stride is 2. There are two fully connected layers with 128 and 64 neurons respectively, outputting a deep feature vector. .

[0010] Further, step 3 includes: Step 31: Set clustering parameters; clustering parameters include the expected number of cluster centers. Minimum number of samples in each cluster Maximum distance standard deviation threshold within a cluster Minimum distance threshold between clusters and the number of iterations ; Step 32: Initialize using the K-MEANS++ algorithm Cluster centers: Randomly select the first cluster center, calculate the distance of each sample to the nearest selected cluster center and the probability of selecting the next cluster center, repeat this process until a cluster center is selected. Cluster centers until; Step 33: Cluster State Update: Calculate the distance between each sample and each cluster center using a distance formula. This formula dynamically weights the feature dimensions to accommodate the large fluctuations in wind power output and the intermittent output of photovoltaic power. It also introduces a local mean deviation product term to amplify the impact of samples deviating from the overall trend on the distance, preventing misclassification in extreme scenarios. The cluster to which a sample belongs is determined based on the distance, completing the cluster partitioning. Based on the samples contained in each partitioned cluster, the cluster center is recalculated to iteratively update the cluster center. Step 34: Cluster validity test: Check the number of samples within each cluster. If the number of samples in a cluster is less than... If the cluster is invalid, the cluster is cancelled and invalid small clusters are removed. The cluster density is calculated. If the cluster density is less than the preset density threshold, the "split operation" is performed, that is, step 35 is performed to adjust the cluster structure. Adjusting the cluster structure includes splitting the cluster and redistributing the samples. Step 35: Splitting Process: For and Cluster center First, target its cluster. Extract the fluctuation rate and peak-to-valley difference of wind and solar power output, and dynamically adapt the split amplitude in combination with corresponding global indicators; then... To perform PCA dimensionality reduction, along the principal component direction, a decay term is introduced for the distance between the current cluster center and its nearest selected cluster center, as well as a decay term for the average distance between each cluster center and its nearest selected cluster center. This prevents the distance between the new center after splitting the current cluster center and the nearest selected cluster center from being less than a preset distance, and finally, the split is performed. It is the cluster density of the j-th cluster. It is the j-th cluster center; Step 36: Merging Process: For For clusters that are closest to each other, merge that cluster into the cluster that is closest to it; for clusters that are far apart, merge that cluster into the cluster that is closest to it. Merge the cluster pairs with the highest similarity. Step 37: During the clustering process, when optimizing the clustering parameters through Bayesian optimization, the average correlation between the sample and the cluster center is used as the objective function. When calculating this correlation, the volatility similarity between the sample and the center is incorporated as a correction term based on the cosine similarity between the sample and the center. At the same time, an outlier penalty term is introduced to suppress the interference of extreme samples, thereby maximizing the optimization objective and finding the optimal density threshold when splitting. Step 38: If the maximum number of iterations is reached If the clustering results stabilize, the iteration stops; otherwise, steps 33 to 38 are repeated to continue iterative optimization. The clustering results stabilize when the change in cluster centers during consecutive iterations is less than the first preset value and the change in sample cluster affiliation is less than the second preset value. Step 39: Generate typical scenarios: After the iteration terminates, output the final clustering results to present typical scenarios of cluster analysis; the final clustering results include the cluster centers of each cluster, the distribution and number of samples within the cluster.

[0011] Further, in step 32, the distance from each sample to the nearest selected cluster center is calculated using the following formula:

[0012] in, For the first The distance from each sample to the nearest selected cluster center For the first A sample vector, For the first Cluster centers, For the selected set of cluster centers, The distance is Euclidean. The probability of selecting the next cluster center is calculated using the following formula:

[0013] in, The probability of selecting the next cluster center, The number of samples; In step 33, the distance between each sample and each cluster center is calculated using the following formula:

[0014] in, It is a sample To the Cluster centers The distance between them For the first A sample vector, For the first The weights of each sample, It is the number of feature dimensions. For the sample The Feature dimension Cluster center The Feature dimension For the sample The Local standard deviation of dimensional features The global standard deviation of the sample. The global mean of the sample is given. For the sample peak, , Samples Cluster Center In the Local mean of dimensional features This is an adjustment coefficient for extreme scenarios.

[0015] Furthermore, in step 35, splitting along the principal component direction is achieved using the following formula:

[0016]

[0017]

[0018]

[0019]

[0020] in, It is cluster density. , For PCA eigenvalues, It is the standard deviation within the cluster. It is the minimum distance between clusters. Cluster center The first in the cluster One sample, Cluster center The first in the cluster One sample, For PCA principal component direction, , For the first New centers after the split of a cluster center For the original undivided first Cluster centers, For scene adaptation coefficients, It is the j-th cluster Fluctuation rate of domestic wind and solar power output It is the time step. It is the first All samples within a cluster Average output of scenery at any given moment. It is the first Peak-valley difference within a cluster, It is the wind and light volatility of all samples globally. It is the peak-to-valley difference of all samples globally. It is the mean of the maximum output of all samples within the cluster. It is the mean of the minimum output of all samples within the cluster. It is a distance decay term to prevent the center from being too close to the neighboring center after splitting. The distance between cluster centers This represents the average distance between all cluster centers.

[0021] Further, in step 37, the formula for calculating the average correlation between a sample and its cluster center is:

[0022]

[0023] in, The average correlation between the sample and the cluster center. The input data matrix has the following dimensions: , For the sample size, The characteristic number; It is a set of cluster centers. ; This is the current number of clusters; It is the mean cosine similarity between the sample and the cluster center; It is the first The sample set of each cluster For the sample The cluster number to which it belongs; It is the first The number of samples in each cluster; It is cosine similarity. It is a dynamic adjustment coefficient. It is the sample-center volatility similarity. It is the time step. It is a global volatility benchmark used for normalization. , It is an outlier penalty term that suppresses interference from extreme samples within the cluster. It is the maximum relative fluctuation of the sample-center within the cluster. It is the average relative fluctuation of samples within a cluster relative to the center. It is the minimum value. Cluster center The wind power output value at time t. For the sample in The output value of the scenery at any moment.

[0024] Furthermore, after step 3, the method further includes: Using cluster centers as typical scenario benchmarks, a set of wind and solar power output scenarios that can be quantitatively evaluated is generated after inverse normalization.

[0025] Furthermore, the process of generating a set of quantifiable and evaluable wind and solar power output scenarios by inverse normalization, using cluster centers as typical scenario benchmarks, includes: A scene generator is constructed, which consists of an input module, a scene probability calculation module, a feature decoding module, and an output module; the input module includes a clustering model, a data preprocessor, and a feature extractor. The data preprocessor is used to normalize and denormalize the raw wind and solar power output data to eliminate the influence of dimensions and restore the data; the feature extractor is used to extract the deep feature vector of the wind and solar power output time series through the deep convolutional feature extraction network (CNN); the clustering model is used to execute the improved ISODATA clustering algorithm and output the cluster centers and sample labels. The scene probability calculation module counts the number of samples in each cluster and calculates the scene probability based on the cluster center and sample label; The cluster centers output by the clustering model are input into the feature decoding module. Through layer-by-layer operations of the feature decoding module, a three-dimensional temporal feature sequence is generated, which is the scene data after inverse normalization. A decoding path network structure symmetrical to the encoding path is extracted from the feature extractor, namely the feature decoding module. The feature decoding module includes an input layer, a first fully connected layer, a second fully connected layer, an output layer, and a reshaping layer connected in sequence. The dimension of the input layer is consistent with the dimension of the depth feature vector output by the feature extractor, and it is used to receive the cluster centers output by the clustering model. The first fully connected layer is symmetrical to the penultimate fully connected layer of the feature extractor. The second fully connected layer is symmetrical to the last fully connected layer of the feature extractor. The output layer is used to generate an intermediate representation of the temporal features. The reshaping layer is symmetrical to the flattening layer structure of the feature extractor and reshapes the one-dimensional feature vector of the output layer into a three-dimensional temporal feature sequence with the dimension of sample number × time step × feature dimension. The output module outputs a set of wind and solar power output scenarios based on the scenario probability output by the scenario probability calculation module and the three-dimensional time-series feature sequence output by the feature decoding module. The set of wind and solar power output scenarios includes a set of wind power output scenarios, a set of photovoltaic power output scenarios, and a scenario probability distribution.

[0026] Furthermore, the scenario probability is calculated using the following formula:

[0027] in, For the first Number of samples in each cluster The total number of clusters.

[0028] Due to the adoption of the above technical solution, this application has the following advantages: 1. This application utilizes a convolutional autoencoder to extract deep features from a wind and solar power output sequence over a period of time (e.g., 24 hours); employs an improved ISODATA algorithm for adaptive clustering, and automatically determines the optimal clustering parameters through Bayesian optimization; finally, it generates and visualizes typical power output scenes. This application solves the problems of insufficient feature extraction, parameter dependence on experience, and fixed number of scenes in traditional scene generation methods, thereby improving the accuracy and representativeness of wind and solar power output scenes.

[0029] 2. The method proposed in this application has three major advantages: By constructing a CNN model for deep feature extraction, it can more comprehensively and accurately describe the characteristics of wind and solar power output, improving the accuracy of scene generation; The improved ISODATA clustering algorithm improves the adaptability and stability of the clustering algorithm to different data distributions by optimizing the initial center selection, introducing a density-based splitting strategy, and adaptive parameter adjustment, and the generated typical scenes can more accurately represent the actual wind and solar power output, while reducing the dependence on manual parameter settings; The generated wind and solar power output scene set not only includes typical power output scenes, but also calculates the probability of each scene based on the clustering results, realizing the coordinated output of typical power output scenes and probability information, which helps the power system better cope with the uncertainty of wind and solar power generation. Attached Figure Description

[0030] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments recorded in the embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0031] Figure 1 This is a flowchart of a method for generating wind and solar power output scenes based on deep feature mining and adaptive clustering; Figure 2 A schematic diagram of the constructed deep convolutional feature extraction network (CNN); Figure 3 Flowchart of the improved ISODATA clustering algorithm; Figure 4 Flowchart for the scene generator; Figures 5(a) to 5(f) All are wind power output curves for samples within the cluster; Figures 6(a) to 6(f) All are photovoltaic power output curves of samples within the cluster; Figures 7(a) to 7(f) All are clustering curves of photovoltaic power output; Figures 8(a) to 8(f)All are clustered curves of wind power output. Detailed Implementation

[0032] The present application will be further described in conjunction with the accompanying drawings and embodiments. The described embodiments are only some, not all, of the embodiments of the present application. All other embodiments obtained by those skilled in the art should fall within the protection scope of the embodiments of the present application.

[0033] This application addresses the shortcomings of traditional clustering methods in capturing the temporal characteristics of wind and solar power output and their sensitivity to cluster numbers by integrating the deep feature extraction capabilities of one-dimensional convolutional autoencoders with an improved ISODATA dynamic clustering algorithm. The method is then applied to extract typical wind and solar power output scenarios in the Xiluodu area, constructing a database of typical wind and solar combined power output scenarios to improve the operational economy and renewable energy absorption capacity of multi-energy complementary systems under complex climatic conditions.

[0034] This application uses a typical landscape scene from a certain region as an analysis case. (See [link / reference]) Figure 1 This application provides an embodiment of a method for generating wind and solar power output scenes based on deep feature mining and adaptive clustering, which includes the following steps: Step 1: Clean the wind and solar power output data and normalize it to map it to a preset range in order to eliminate the influence of dimensions.

[0035] Step 2: Construct a deep convolutional feature extraction network to extract the corresponding feature maps from the normalized wind and solar power output data.

[0036] Step 2 includes: See also Figure 2 The constructed deep convolutional feature extraction network includes an input layer, a first convolutional layer, a first pooling layer, a second convolutional layer, a second pooling layer, a flattening layer, a fully connected layer, a batch normalization layer, and a fully connected layer connected in sequence. The formula for extracting feature maps from normalized wind and solar power output data using deep convolutional features is as follows:

[0037]

[0038] in, It is the output of the first convolutional layer. It is the unified scenery that contributes to the effort. It is the first convolutional layer. It's a bias. For the first Layer feature map, For the first Layer convolution kernel, For the first Layer bias, It is the ReLU activation function. This represents the convolution operation.

[0039] The input layer receives the normalized wind and solar power output time series. T represents the time step, and 2 represents the landscape feature dimension. For the first convolutional layer, the number of kernels is set to 32, the kernel size is 3, and the activation function is ReLU to maintain the temporal dimension. For the first pooling layer, the pooling window size is 2, and the stride is 2 to reduce the data dimension. For the second convolutional layer, the number of kernels is set to 64, the kernel size is 3, and the activation function is ReLU to maintain feature integrity. For the second pooling layer, the pooling window size is 2, and the stride is 2. There are two fully connected layers with 128 and 64 neurons respectively, outputting a deep feature vector. .

[0040] Step 3: Initialize cluster centers using the K-Means++ algorithm, execute the improved ISODATA clustering algorithm based on the density threshold dynamic splitting mechanism, optimize clustering parameters through Bayesian optimization, and generate typical scenarios.

[0041] See also Figure 3 Step 3 includes: Step 31: Set clustering parameters; clustering parameters include the expected number of cluster centers. Minimum number of samples in each cluster Maximum distance standard deviation threshold within a cluster Minimum distance threshold between clusters and the number of iterations ; Step 32: Initialize using the K-MEANS++ algorithm Cluster centers: Randomly select the first cluster center, calculate the distance of each sample to the nearest selected cluster center and the probability of selecting the next cluster center, repeat this process until a cluster center is selected. Cluster centers until; Step 33: Cluster State Update: Calculate the distance between each sample and each cluster center using a distance formula. This formula dynamically weights the feature dimensions to accommodate the large fluctuations in wind power output and the intermittent output of photovoltaic power. It also introduces a local mean deviation product term to amplify the impact of samples deviating from the overall trend on the distance, preventing misclassification in extreme scenarios. The cluster to which a sample belongs is determined based on the distance, completing the cluster partitioning. Based on the samples contained in each partitioned cluster, the cluster center is recalculated to iteratively update the cluster center. Step 34: Cluster validity test: Check the number of samples within each cluster. If the number of samples in a cluster is less than... If the cluster is invalid, the cluster is cancelled and invalid small clusters are removed. The cluster density is calculated. If the cluster density is less than the preset density threshold, the "split operation" is performed, that is, step 35 is performed to adjust the cluster structure. Adjusting the cluster structure includes splitting the cluster and redistributing the samples. Step 35: Splitting Process: For and Cluster center First, target its cluster. Extract the fluctuation rate and peak-to-valley difference of wind and solar power output, and dynamically adapt the split amplitude in combination with corresponding global indicators; then... To perform PCA dimensionality reduction, along the principal component direction, a decay term is introduced for the distance between the current cluster center and its nearest selected cluster center, as well as a decay term for the average distance between each cluster center and its nearest selected cluster center. This prevents the distance between the new center after splitting the current cluster center and the nearest selected cluster center from being less than a preset distance, and finally, the split is performed. It is the cluster density of the j-th cluster. It is the j-th cluster center; Step 36: Merging Process: For For clusters that are closest to each other, merge that cluster into the cluster that is closest to it; for clusters that are far apart, merge that cluster into the cluster that is closest to it. Merge the cluster pairs with the highest similarity. Step 37: During the clustering process, when optimizing the clustering parameters through Bayesian optimization, the average correlation between the sample and the cluster center is used as the objective function. When calculating this correlation, the volatility similarity between the sample and the center is incorporated as a correction term based on the cosine similarity between the sample and the center. At the same time, an outlier penalty term is introduced to suppress the interference of extreme samples, thereby maximizing the optimization objective and finding the optimal density threshold when splitting. Step 38: If the maximum number of iterations is reached If the clustering results stabilize, the iteration stops; otherwise, steps 33 to 38 are repeated to continue iterative optimization. The clustering results stabilize when the change in cluster centers during consecutive iterations is less than the first preset value and the change in sample cluster affiliation is less than the second preset value. Step 39: Generate typical scenarios: After the iteration terminates, output the final clustering results to present typical scenarios of cluster analysis; the final clustering results include the cluster centers of each cluster, the distribution and number of samples within the cluster.

[0042] Step 4: Using cluster centers as typical scenario benchmarks, generate a set of wind and solar power output scenarios that can be quantitatively evaluated after inverse normalization.

[0043] Optionally, in step 32, the distance from each sample to the nearest selected cluster center is calculated using the following formula:

[0044] in, For the first The distance from each sample to the nearest selected cluster center For the first A sample vector, For the first Cluster centers, For the selected set of cluster centers, The distance is Euclidean. The probability of selecting the next cluster center is calculated using the following formula:

[0045] in, The probability of selecting the next cluster center, This represents the number of samples.

[0046] Optionally, in step 33, the distance between each sample and each cluster center is calculated using the following formula:

[0047] in, It is a sample To the Cluster centers The distance between them For the first A sample vector, For the first The weights of each sample, It is the number of feature dimensions. For the sample The Feature dimension Cluster center The Feature dimension For the sample The Local standard deviation of dimensional features The global standard deviation of the sample. The global mean of the sample is given. For the sample peak, , Samples Cluster Center In the Local mean of dimensional features This is an adjustment coefficient for extreme scenarios.

[0048] Optionally, in step 35, splitting along the principal component direction is achieved using the following formula:

[0049]

[0050]

[0051]

[0052]

[0053]

[0054] in, It is cluster density. , For PCA eigenvalues, It is the standard deviation within the cluster. It is the minimum distance between clusters. Cluster center The first in the cluster One sample, Cluster center The first in the cluster One sample, For PCA principal component direction, , For the first New centers after the split of a cluster center For the original undivided first Cluster centers, For scene adaptation coefficients, It is the j-th cluster Fluctuation rate of domestic wind and solar power output It is the time step. It is the first All samples within a cluster Average output of scenery at any given moment. It is the first Peak-valley difference within a cluster, It is the wind and light volatility of all samples globally. It is the peak-to-valley difference of all samples globally. It is the mean of the maximum output of all samples within the cluster. It is the mean of the minimum output of all samples within the cluster. It is a distance decay term to prevent the center from being too close to the neighboring center after splitting. The distance between cluster centers This represents the average distance between all cluster centers.

[0055] Optionally, in step 37, the formula for calculating the average correlation between a sample and its cluster center is:

[0056]

[0057] in, The average correlation between the sample and the cluster center. The input data matrix has the following dimensions: , For the sample size, The characteristic number; It is a set of cluster centers. ; This is the current number of clusters; It is the mean cosine similarity between the sample and the cluster center; It is the first The sample set of each cluster For the sample The cluster number to which it belongs; It is the first The number of samples in each cluster; It is cosine similarity. It is a dynamic adjustment coefficient. It is the sample-center volatility similarity. It is the time step. It is a global volatility benchmark used for normalization. , It is an outlier penalty term that suppresses interference from extreme samples within the cluster. It is the maximum relative fluctuation of the sample-center within the cluster. It is the average relative fluctuation of samples within a cluster relative to the center. For example, take the minimum value (e.g., take) ), Cluster center The wind power output value at time t. For the sample in The output value of the scenery at any moment.

[0058] After step 3, the following is also included: Using cluster centers as typical scenario benchmarks, a set of wind and solar power output scenarios that can be quantitatively evaluated is generated after inverse normalization.

[0059] Optionally, the step of generating a set of wind and solar power output scenarios that can be quantitatively evaluated after denormalization, using cluster centers as typical scenario benchmarks, includes: See also Figure 4A scene generator is constructed, which consists of an input module, a scene probability calculation module, a feature decoding module, and an output module; the input module includes a clustering model, a data preprocessor, and a feature extractor. The data preprocessor is used to normalize and denormalize the raw wind and solar power output data to eliminate the influence of dimensions and restore the data; the feature extractor is used to extract the deep feature vector of the wind and solar power output time series through the deep convolutional feature extraction network (CNN); the clustering model is used to execute the improved ISODATA clustering algorithm and output the cluster centers and sample labels. The scene probability calculation module counts the number of samples in each cluster and calculates the scene probability based on the cluster center and sample label; The cluster centers output by the clustering model are input into the feature decoding module. Through layer-by-layer operations of the feature decoding module, a three-dimensional temporal feature sequence is generated, which is the scene data after inverse normalization. A decoding path network structure symmetrical to the encoding path is extracted from the feature extractor, namely the feature decoding module. The feature decoding module includes an input layer, a first fully connected layer, a second fully connected layer, an output layer, and a reshaping layer connected in sequence. The dimension of the input layer is consistent with the dimension of the depth feature vector output by the feature extractor, and it is used to receive the cluster centers output by the clustering model. The first fully connected layer is symmetrical to the penultimate fully connected layer of the feature extractor. The second fully connected layer is symmetrical to the last fully connected layer of the feature extractor. The output layer is used to generate an intermediate representation of the temporal features. The reshaping layer is symmetrical to the flattening layer structure of the feature extractor and reshapes the one-dimensional feature vector of the output layer into a three-dimensional temporal feature sequence with the dimension of sample number × time step × feature dimension. The output module outputs a set of wind and solar power output scenarios based on the scenario probability output by the scenario probability calculation module and the three-dimensional time-series feature sequence output by the feature decoding module. The set of wind and solar power output scenarios includes a set of wind power output scenarios, a set of photovoltaic power output scenarios, and a scenario probability distribution.

[0060] Optionally, the scenario probability can be calculated using the following formula:

[0061] in, For the first Number of samples in each cluster The total number of clusters.

[0062] The improved ISODATA algorithm was used to adaptively cluster the wind and solar power output sequences, and finally generated 6 typical photovoltaic power output scenarios, the probability distribution of which is shown in Table 1.

[0063] Table 1 Probability distribution of typical scenarios

[0064] Figures 5(a) to 5(f) Wind power output curves of samples within a uniform cluster. Figures 6(a) to 6(f) All are photovoltaic output curves of samples within the cluster. Figures 7(a) to 7(f) All are clustering curves of photovoltaic power output. Figures 8(a) to 8(f) All figures are clustering curves for wind power output. From the perspective of sample size and probability distribution, scenarios 6 (48.9%) and 5 (29.7%) dominate, accounting for a total of 78.6%, indicating that these two scenarios have the highest frequency of occurrence in historical data and can represent the main mode of combined wind and solar power output. Scenario 3 (0.6%) has a significantly lower sample size than other scenarios, corresponding to extreme wind power output conditions. During the clustering process, the algorithm effectively identified data clusters with different output characteristics by dynamically adjusting the density threshold (optimal value 0.5591) and the number of clusters (finally stabilizing at 6), combined with weighted distance calculation and density splitting strategies. The final cluster sample distribution is [124, 124, 11, 125, 533, 879], covering the complete range from low to high output.

[0065] From the clustering quality assessment results, the silhouette coefficient was 0.3408 and the CH index was 1573. The clustering results showed good performance in terms of intra-cluster compactness and inter-cluster separation, and could clearly distinguish different photovoltaic power output modes. Compared with the results of the original ISODATA algorithm, the silhouette coefficient (SC) improved from 0.3074 to 0.3408, a relative improvement of +10.9%, indicating a significant optimization of intra-cluster compactness and inter-cluster separation; the Calinski-Harabasz index (CH) improved from 1481.44 to 1573, a relative improvement of +6.2%, reflecting a better ratio of inter-cluster dispersion to intra-cluster variance.

[0066] Analyzing the characteristics of typical scenarios, the photovoltaic output range of scenarios 1 and 2 is relatively low (0.1-819.6 MW and 0.2-664.4 MW), corresponding to cloudy or insufficient sunlight weather conditions; the photovoltaic output of scenario 3 is near the historical maximum (1.0-3519.3 MW), and the corresponding wind power output is also near the historical maximum, which is judged as an extreme weather event; scenarios 5 and 6 represent typical wind-solar combined modes under medium and high output conditions, respectively.

[0067] In summary, the improved ISODATA algorithm, by combining Bayesian optimization and dynamic clustering strategies, effectively extracts typical scenarios of wind and solar power output. The generated scenarios not only cover the main distribution characteristics of historical data, but also reflect the frequency of occurrence of different scenarios through probability weighting, which helps the power system better cope with the uncertainties of wind and solar power generation.

[0068] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application and not to limit them. Although this application has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of this application. Any modifications or equivalent substitutions that do not depart from the spirit and scope of this application should be covered within the protection scope of the claims of this application.

Claims

1. A method for generating wind and solar power output scenes based on deep feature mining and adaptive clustering, characterized in that, include: Step 1: Clean the wind and solar power output data and normalize it to map it to a preset range in order to eliminate the influence of dimensions; Step 2: Construct a deep convolutional feature extraction network to extract the corresponding feature maps from the normalized wind and solar power output data; Step 3: Initialize cluster centers using the K-Means++ algorithm, execute the improved ISODATA clustering algorithm based on the density threshold dynamic splitting mechanism, optimize clustering parameters through Bayesian optimization, and generate typical scenarios.

2. The method according to claim 1, characterized in that, Step 2 includes: The constructed deep convolutional feature extraction network includes an input layer, a first convolutional layer, a first pooling layer, a second convolutional layer, a second pooling layer, a flattening layer, a fully connected layer, a batch normalization layer, and a fully connected layer connected in sequence. The formula for extracting feature maps from normalized wind and solar power output data using deep convolutional features is as follows: in, It is the output of the first convolutional layer. It is the unified scenery that contributes to the effort. It is the first convolutional layer. It's a bias. For the first Layer feature map, For the first Layer convolution kernel, For the first Layer bias, It is the ReLU activation function. This represents the convolution operation.

3. The method according to claim 2, characterized in that, The input layer receives the normalized wind and solar power output time series. T represents the time step, and 2 represents the landscape feature dimension; For the first convolutional layer, the number of kernels is set to 32, the kernel size is 3, and the activation function is ReLU to preserve temporal dimension. For the first pooling layer, the pooling window size is 2, and the stride is 2 to reduce data dimensionality. For the second convolutional layer, the number of kernels is set to 64, the kernel size is 3, and the activation function is ReLU to preserve feature integrity. For the second pooling layer, the pooling window size is 2, and the stride is 2. There are two fully connected layers with 128 and 64 neurons respectively, outputting a deep feature vector. .

4. The method according to claim 1, characterized in that, Step 3 includes: Step 31: Set clustering parameters; clustering parameters include the expected number of cluster centers. Minimum number of samples in each cluster Maximum distance standard deviation threshold within a cluster Minimum distance threshold between clusters and the number of iterations ; Step 32: Initialize using the K-MEANS++ algorithm Cluster centers: Randomly select the first cluster center, calculate the distance of each sample to the nearest selected cluster center and the probability of selecting the next cluster center, repeat this process until a cluster center is selected. Cluster centers until; Step 33: Cluster State Update: Calculate the distance between each sample and each cluster center using the distance formula. The distance formula dynamically weights the feature dimensions to suit the characteristics of large fluctuations in wind power output and intermittent photovoltaic output. It also introduces a local mean deviation product term to amplify the impact of samples that deviate from the overall trend on the distance. Determine the cluster to which the sample belongs based on the distance, thus completing the cluster division. Based on the samples contained in each cluster after division, recalculate the cluster center to achieve iterative update of the cluster center. Step 34: Cluster validity test: Check the number of samples within each cluster. If the number of samples in a cluster is less than... If the cluster is invalid, the cluster is cancelled and invalid small clusters are removed. The cluster density is calculated. If the cluster density is less than the preset density threshold, the "split operation" is performed, that is, step 35 is performed to adjust the cluster structure. Adjusting the cluster structure includes splitting the cluster and redistributing samples. Step 35: Splitting Process: For and Cluster center First, target its cluster. Extract the fluctuation rate and peak-to-valley difference of wind and solar power output, and dynamically adapt the split amplitude in combination with corresponding global indicators; then... To perform PCA dimensionality reduction, along the principal component direction, a decay term is introduced for the distance between the current cluster center and its nearest selected cluster center, as well as a decay term for the average distance between each cluster center and its nearest selected cluster center. This prevents the distance between the new center after splitting the current cluster center and the nearest selected cluster center from being less than a preset distance, and finally, the split is performed. It is the cluster density of the j-th cluster. It is the j-th cluster center; Step 36: Merging Process: For For clusters that are closest to each other, merge that cluster into the cluster that is closest to it; for clusters that are far apart, merge that cluster into the cluster that is closest to it. Merge the cluster pairs with the highest similarity. Step 37: During the clustering process, when optimizing the clustering parameters through Bayesian optimization, the average correlation between the sample and the cluster center is used as the objective function. When calculating this correlation, the volatility similarity between the sample and the center is incorporated as a correction term based on the cosine similarity between the sample and the center. At the same time, an outlier penalty term is introduced to suppress the interference of extreme samples, thereby maximizing the optimization objective and finding the optimal density threshold when splitting. Step 38: If the maximum number of iterations is reached If the clustering results stabilize, the iteration stops; otherwise, steps 33 to 38 are repeated to continue iterative optimization. The clustering results stabilize when the change in cluster centers during consecutive iterations is less than the first preset value and the change in sample cluster affiliation is less than the second preset value. Step 39: Generate typical scenarios: After the iteration terminates, output the final clustering results to present typical scenarios of cluster analysis; the final clustering results include the cluster centers of each cluster, the distribution and number of samples within the cluster.

5. The method according to claim 4, characterized in that, In step 32, the distance from each sample to the nearest selected cluster center is calculated using the following formula: in, For the first The distance from each sample to the nearest selected cluster center For the first A sample vector, For the first Cluster centers, For the selected set of cluster centers, The distance is Euclidean. The probability of selecting the next cluster center is calculated using the following formula: in, The probability of selecting the next cluster center, The number of samples; In step 33, the distance between each sample and each cluster center is calculated using the following formula: in, It is a sample To the Cluster centers The distance between them For the first A sample vector, For the first The weights of each sample, It is the number of feature dimensions. For the sample The Feature dimension Cluster center The Feature dimension For the sample The Local standard deviation of dimensional features The global standard deviation of the sample. The global mean of the sample is given. For the sample peak, , Samples Cluster Center In the Local mean of dimensional features This is an adjustment coefficient for extreme scenarios.

6. The method according to claim 4, characterized in that, In step 35, splitting along the principal component direction is achieved using the following formula: in, It is cluster density. , For PCA eigenvalues, It is the standard deviation within the cluster. It is the minimum distance between clusters. Cluster center The first in the cluster One sample, Cluster center The first in the cluster One sample, For PCA principal component direction, , For the first New centers after the split of a cluster center For the original undivided first Cluster centers, For scene adaptation coefficients, It is the j-th cluster Fluctuation rate of domestic wind and solar power output It is the time step. It is the first All samples within a cluster Average output of scenery at any given moment. It is the first Peak-valley difference within a cluster, It is the wind and light volatility of all samples globally. It is the peak-to-valley difference of all samples globally. It is the mean of the maximum output of all samples within the cluster. It is the mean of the minimum output of all samples within the cluster. It is a distance attenuation term. The distance between cluster centers This represents the average distance between all cluster centers.

7. The method according to claim 4, characterized in that, In step 37, the formula for calculating the average correlation between a sample and its cluster center is: in, The average correlation between the sample and the cluster center. The input data matrix has the following dimensions: , For the sample size, The characteristic number; It is a set of cluster centers. ; This is the current number of clusters; It is the mean cosine similarity between the sample and the cluster center; It is the first The sample set of each cluster For the sample The cluster number to which it belongs; It is the first The number of samples in each cluster; It is cosine similarity. It is a dynamic adjustment coefficient. It is the sample-center volatility similarity. It is the time step. It is a global volatility benchmark used for normalization. , It is an outlier penalty term that suppresses interference from extreme samples within the cluster. It is the maximum relative fluctuation of the sample-center within the cluster. It is the average relative fluctuation of samples within a cluster relative to the center. It is the minimum value. Cluster center The wind power output value at time t. For the sample in The output value of the scenery at any moment.

8. The method according to claim 1, characterized in that, After step 3, the following is also included: Using cluster centers as typical scenario benchmarks, a set of wind and solar power output scenarios that can be quantitatively evaluated is generated after inverse normalization.

9. The method according to claim 8, characterized in that, The set of wind and solar power output scenarios that can be quantitatively evaluated after inverse normalization, using cluster centers as typical scenario benchmarks, includes: A scene generator is constructed, which consists of an input module, a scene probability calculation module, a feature decoding module, and an output module; the input module includes a clustering model, a data preprocessor, and a feature extractor. The data preprocessor is used to normalize and denormalize the raw wind and solar power output data to eliminate the influence of dimensions and restore the data; the feature extractor is used to extract the deep feature vector of the wind and solar power output time series through the deep convolutional feature extraction network (CNN); the clustering model is used to execute the improved ISODATA clustering algorithm and output the cluster centers and sample labels. The scene probability calculation module counts the number of samples in each cluster and calculates the scene probability based on the cluster center and sample label; The cluster centers output by the clustering model are input into the feature decoding module. Through layer-by-layer operations of the feature decoding module, a three-dimensional temporal feature sequence is generated, which is the scene data after inverse normalization. A decoding path network structure symmetrical to the encoding path is extracted from the feature extractor, namely the feature decoding module. The feature decoding module includes an input layer, a first fully connected layer, a second fully connected layer, an output layer, and a reshaping layer connected in sequence. The dimension of the input layer is consistent with the dimension of the depth feature vector output by the feature extractor, and it is used to receive the cluster centers output by the clustering model. The first fully connected layer is symmetrical to the penultimate fully connected layer of the feature extractor. The second fully connected layer is symmetrical to the last fully connected layer of the feature extractor. The output layer is used to generate an intermediate representation of the temporal features. The reshaping layer is symmetrical to the flattening layer structure of the feature extractor and reshapes the one-dimensional feature vector of the output layer into a three-dimensional temporal feature sequence with the dimension of sample number × time step × feature dimension. The output module outputs a set of wind and solar power output scenarios based on the scenario probability output by the scenario probability calculation module and the three-dimensional time-series feature sequence output by the feature decoding module. The set of wind and solar power output scenarios includes a set of wind power output scenarios, a set of photovoltaic power output scenarios, and a scenario probability distribution.

10. The method according to claim 9, characterized in that, The scenario probability is calculated using the following formula: in, For the first Number of samples in each cluster The total number of clusters.

Images