Power distribution network power prediction method, system and device based on multi-source heterogeneous data fusion and storage medium

Abstract

The invention discloses a power distribution network power prediction method, system and device based on multi-source heterogeneous data fusion, and a storage medium, and relates to the technical field of power distribution network data processing and prediction, and the method comprises the steps: constructing a data autocorrelation matrix based on the comprehensive operation and maintenance data of a power distribution network; performing eigenvalue decomposition on the data autocorrelation matrix, and constructing a principal component matrix; performing dimension reduction processing on zero-mean data obtained in the process of constructing the data autocorrelation matrix by using the principal component matrix to obtain operation and maintenance feature fusion associated data of the power distribution network; an echo state network model is established and trained, the operation and maintenance feature fusion associated data of the power distribution network is used as the input of the echo state network model, and the output power of the power distribution network is predicted; according to the method, the data dimension is reduced, the calculation complexity is reduced, and the output power of the power distribution network can be predicted more accurately; the operation efficiency and the management level of the power distribution network can be improved, and powerful support is provided for stable supply of a power system.

Description

Technical Field

[0001] This invention relates to the field of power distribution network data processing and prediction technology, and in particular to a power prediction method, system, device and storage medium for power distribution networks based on multi-source heterogeneous data fusion. Background Technology

[0002] As the nerve endings of the power grid system, the distribution network is crucial for ensuring the stable operation of the grid. However, its geographically dispersed and environmentally diverse nature makes maintenance difficult and costly, and its intelligent transformation and development need to be strengthened.

[0003] Currently, various distribution network operation and maintenance data databases exist, but these databases suffer from redundancy, sparsity, and strong correlations between different data types, hindering accurate prediction of distribution network output power. Existing multi-source heterogeneous data fusion methods fall into two categories: traditional and AI-based. Traditional methods include rule-based and statistical fusion methods. The former requires significant manual intervention and has poor adaptability, while the latter demands high data independence and is computationally complex. AI-based methods include fusion methods based on machine learning, deep learning, and graph neural networks. While these methods have advantages, they suffer from the need for large amounts of training data, complex and difficult-to-interpret models, and the need for skillful construction of graph structures. Summary of the Invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by this invention is: how to reduce the redundancy of distribution network operation and maintenance data, eliminate the adverse effects of complex correlations between data on output power prediction, and achieve efficient and accurate prediction of distribution network output power.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0007] In a first aspect, embodiments of the present invention provide a power prediction method for distribution networks based on multi-source heterogeneous data fusion, comprising:

[0008] Construct a data autocorrelation matrix based on integrated operation and maintenance data of the power distribution network;

[0009] Eigenvalue decomposition is performed on the autocorrelation matrix of the data to construct the principal component matrix;

[0010] The zero-mean data obtained during the construction of the data autocorrelation matrix is ​​reduced using the principal component matrix to obtain the fused correlation data of distribution network operation and maintenance characteristics.

[0011] An echo state network model was established and trained. The operation and maintenance characteristics of the distribution network were fused and correlated with data as input to the echo state network model to predict the output power of the distribution network.

[0012] As a preferred scheme for power prediction methods for distribution networks based on multi-source heterogeneous data fusion, wherein:

[0013] The construction of the data autocorrelation matrix based on the integrated operation and maintenance data of the distribution network includes:

[0014] The integrated operation and maintenance data of the power distribution network is represented in matrix form. The matrix contains multiple samples, each sample has multiple features, and the elements in the matrix are the specific values ​​of the corresponding features of each sample. At the same time, the matrix is ​​divided into multiple data channels by columns, and each channel contains multiple variables.

[0015] As a preferred scheme for power prediction methods for distribution networks based on multi-source heterogeneous data fusion, wherein:

[0016] The construction of the data autocorrelation matrix based on the integrated operation and maintenance data of the distribution network also includes:

[0017] Zero-mean processing is performed on the distribution network integrated operation and maintenance data represented in matrix form. Specifically, the original data is subtracted from the corresponding mean vector to obtain zero-mean data. The zero-mean data is then used to construct the data autocorrelation matrix.

[0018] The beneficial effects of this preferred technical solution are as follows: zero-mean processing can eliminate the DC component in the data, making the mean of the data zero, which can highlight the fluctuation characteristics of the data, reduce the impact of mean differences between different characteristics, and thus make the constructed data autocorrelation matrix more reflective of the true correlation between data, thereby improving the accuracy of subsequent analysis.

[0019] As a preferred scheme for power prediction methods for distribution networks based on multi-source heterogeneous data fusion, wherein:

[0020] The step of performing eigenvalue decomposition on the data autocorrelation matrix to construct the principal component matrix includes:

[0021] Perform eigenvalue decomposition on the autocorrelation matrix of the data to obtain eigenvalues ​​and their corresponding eigenvectors. Sort all the obtained eigenvalues ​​in descending order from largest to smallest.

[0022] As a preferred scheme for power prediction methods for distribution networks based on multi-source heterogeneous data fusion, wherein:

[0023] The step of performing eigenvalue decomposition on the data autocorrelation matrix to construct the principal component matrix further includes:

[0024] Extract the first specified number of principal feature values ​​from the sorted feature values, select the feature vectors corresponding to these principal feature values, and combine the selected feature vectors to form the principal component matrix of the data. The principal component matrix contains a fusion weight vector.

[0025] The beneficial effects of this preferred technical solution are as follows: extracting the principal eigenvalues ​​and corresponding eigenvectors to construct the principal component matrix achieves dimensionality reduction of the data. The fusion weight vector in the principal component matrix can map the high-dimensional original data to a low-dimensional space, reducing the dimensionality of the data while retaining the main information, thus reducing computational complexity and improving the efficiency of subsequent model training and prediction.

[0026] As a preferred scheme for power prediction methods for distribution networks based on multi-source heterogeneous data fusion, wherein:

[0027] The process of establishing and training an echo state network model, and using the fused and correlated data of distribution network operation and maintenance characteristics as input to the echo state network model for distribution network output power prediction, includes:

[0028] The echo state network consists of an input layer, a storage pool, and an output layer. It uses the fusion and correlation data of distribution network operation and maintenance characteristics as input data and the distribution network output power data as target data.

[0029] As a preferred scheme for power prediction methods for distribution networks based on multi-source heterogeneous data fusion, wherein:

[0030] The step of establishing and training an echo state network model, and using the fused and correlated data of distribution network operation and maintenance characteristics as input to the echo state network model for distribution network output power prediction, also includes:

[0031] Define the loss function for the echo state network, and start calculating the loss function after the reservoir reaches a steady state;

[0032] Estimate the mapping vector from the reservoir to the output layer;

[0033] The trained echo state network is used to predict the output power of the distribution network.

[0034] The beneficial effects of this preferred technical solution are as follows: defining the loss function and calculating it from the point of equilibrium of the power reserve pool allows for a more accurate measurement of the model's prediction error, improving the model's training performance. Estimating the mapping vector from the power reserve pool to the output layer optimizes the model's parameters, enabling the model to better fit the data. Finally, using the trained echo state network for distribution network output power prediction yields more accurate prediction results, providing strong support for the operation and management of the distribution network.

[0035] Secondly, embodiments of the present invention provide a power prediction system for distribution networks based on multi-source heterogeneous data fusion, comprising:

[0036] The autocorrelation matrix construction module is used to construct a data autocorrelation matrix based on the comprehensive operation and maintenance data of the distribution network.

[0037] The principal component matrix construction module is used to perform eigenvalue decomposition on the data autocorrelation matrix and construct the principal component matrix.

[0038] The dimension reduction and fusion module is used to reduce the dimension of the zero-mean data obtained during the construction of the data autocorrelation matrix using the principal component matrix, so as to obtain the fused correlation data of the distribution network operation and maintenance characteristics.

[0039] The prediction module is used to build and train the echo state network model. It uses the fused and correlated data of distribution network operation and maintenance characteristics as input to the echo state network model to predict the output power of the distribution network.

[0040] Thirdly, embodiments of the present invention provide an electronic device, including:

[0041] Memory and processor;

[0042] The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions. When the one or more programs are executed by the one or more processors, the one or more processors implement the power prediction method for power distribution networks based on multi-source heterogeneous data fusion as described in any embodiment of the present invention.

[0043] Fourthly, embodiments of the present invention provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the power prediction method for power distribution networks based on multi-source heterogeneous data fusion.

[0044] The beneficial effects of this invention are as follows: This invention addresses the problem of power output prediction in distribution networks, proposing a principal component analysis method to achieve feature fusion of distribution network operation and maintenance data. This reduces data dimensionality while achieving a complete representation of the characteristics of the operation and maintenance data. Simultaneously, an echo state network is introduced into the power output prediction process, enabling rapid network convergence. Experimental simulation results show that, compared with existing algorithms, the algorithm proposed in this invention can predict the power output of distribution networks more accurately, which is beneficial to the safe and efficient operation and maintenance of distribution networks. Attached Figure Description

[0045] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is an overall flowchart of the power prediction method for distribution networks based on multi-source heterogeneous data fusion described in this invention;

[0047] Figure 2This is an ESN network structure diagram of the power prediction method for distribution networks based on multi-source heterogeneous data fusion described in this invention;

[0048] Figure 3 This is a simulation example of the power prediction diagram of the distribution network output power in the power prediction method of the distribution network based on multi-source heterogeneous data fusion described in this invention. Detailed Implementation

[0049] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0050] Example 1, referring to Figure 1 This is the first embodiment of the present invention, which provides a power prediction method for distribution networks based on multi-source heterogeneous data fusion, including:

[0051] S1: Construct a data autocorrelation matrix based on integrated operation and maintenance data of the power distribution network;

[0052] S2: Perform eigenvalue decomposition on the autocorrelation matrix of the data to construct the principal component matrix;

[0053] S3: Use the principal component matrix to reduce the dimensionality of the zero-mean data obtained in the process of constructing the data autocorrelation matrix to obtain the fused correlation data of distribution network operation and maintenance characteristics;

[0054] S4: Establish and train an echo state network model, and use the fused and correlated data of distribution network operation and maintenance characteristics as input to the echo state network model to predict the output power of the distribution network.

[0055] It should be noted that, through steps S1-S4, this embodiment performs a series of scientific processing steps on the integrated operation and maintenance data of the distribution network, including constructing a data autocorrelation matrix, performing eigenvalue decomposition to construct a principal component matrix, reducing dimensionality to obtain operation and maintenance feature fusion and correlation data, and then using an echo state network model for training and prediction. This effectively integrates multi-source heterogeneous data and uncovers potential correlations between data. This method not only reduces data dimensionality and computational complexity but also fully utilizes the ability of the echo state network to capture dynamic information, enabling more accurate prediction of the distribution network's output power. This is of great significance for the scientific planning, rational scheduling, and reliable operation of the distribution network, helping to improve the operational efficiency and management level of the distribution network and providing strong support for the stable supply of the power system.

[0056] Example 2, refer to Figures 1-2As one embodiment of the present invention, based on the previous embodiment, a power prediction method for distribution networks based on multi-source heterogeneous data fusion is provided, including:

[0057] In this embodiment, the step S1 above, which involves constructing a data autocorrelation matrix based on the integrated operation and maintenance data of the distribution network, includes:

[0058] Let the integrated operation and maintenance data X of the distribution network be represented as:

[0059]

[0060] Where, x NK This represents the specific value of the Kth feature of the Nth sample;

[0061] x k =(x 1k ,x 2k ,…,x Nk ) T k = 1, 2, ..., K, where K is the number of data channels and N is the number of variables in each channel.

[0062] Zero-mean normalization of data X yields zero-mean normalized data Z, represented as:

[0063] Z = X - μ

[0064] Where Z = [z1, z2, ..., z K ],z k =x k -μ, where μ is the mean vector, is represented as:

[0065]

[0066] Construct the data autocorrelation matrix, represented as follows:

[0067] R X =E{XX H}

[0068] In this embodiment, step S2 above, which involves eigenvalue decomposition of the data autocorrelation matrix to construct the principal component matrix, includes:

[0069] For the data autocorrelation matrix R X Perform eigenvalue decomposition to obtain eigenvalues ​​λ. n n = 1, 2, ..., N and their corresponding eigenvectors ω n For each eigenvalue, n = 1, 2, ..., N, sort all eigenvalues ​​in descending order and extract the eigenvectors corresponding to the top D principal eigenvalues ​​to form the principal component matrix of the data X, which is represented as:

[0070]

[0071] Where, ω d =(ω 1d ,ω 2d ,…,ω Nd ) T d = 1, 2, ..., D is the fusion weight vector.

[0072] In this embodiment, step S3 above uses the principal component matrix to perform dimensionality reduction processing on the zero-mean data obtained during the construction of the data autocorrelation matrix, resulting in the following fused correlation data of distribution network operation and maintenance features:

[0073] Using the principal component matrix W D Dimensionality reduction is performed on the zero-mean data Z to obtain the fused and correlated data of distribution network operation and maintenance characteristics, represented as follows:

[0074]

[0075] It should be noted that through this operation, the dimension of the zero-mean data Z is reduced from N to D, thus achieving data fusion.

[0076] In another possible implementation, the dimensionality-reduced data can be used to reconstruct the integrated operation and maintenance data of the power distribution network;

[0077] Specifically, using the dimensionality-reduced data, the original data is reconstructed as follows:

[0078]

[0079] It should be noted that by reconstructing the data, we can check whether the dimensionality reduction retains the key information of the original data. If the reconstruction error is small, it indicates that the principal component matrix can effectively represent the original data, indirectly verifying the rationality of the features after dimensionality reduction. This ensures that the fused features (such as voltage, current, and environmental quantities) do not lose key information affecting power prediction. Some models (such as traditional regression) may require input from the original dimensions; the reconstructed data can serve as a backup input. During the method validation phase, the prediction performance of the dimensionality-reduced data and the reconstructed data can be compared to demonstrate the necessity of dimensionality reduction.

[0080] In this embodiment, the process of establishing and training the echo state network model in step S4, and using the fused and correlated data of distribution network operation and maintenance characteristics as input to the echo state network model for distribution network output power prediction, includes:

[0081] It should be noted that most multivariate regression analysis problems are currently implemented using recurrent neural networks (RNNs), but RNNs have a slow convergence speed and are prone to getting trapped in local optima. Therefore, this method proposes to use echo state networks (ESNs) to predict the output power of distribution networks.

[0082] like Figure 2 The diagram shows the ESN network structure, which includes an input layer, a storage pool, and an output layer. The diagram also shows the fusion and correlation of distribution network operation and maintenance characteristics data. As input data, power output data of the distribution network As the target data, the mapping matrix from the input layer to the reserve pool is: The mapping vector from the reservoir to the output layer is M represents the number of neurons in the reserve pool, and the update equation within the reserve pool is:

[0083]

[0084] The activation function f is typically the tanh function, and the internal connection matrix of the reservoir is... Sparse matrices are typically initialized randomly.

[0085] The update result within the reserve pool is related to the previous time step's update result and the input. The output layer output is represented as follows:

[0086]

[0087] The loss function of the ESN network is expressed as:

[0088]

[0089] Where η is the regularization coefficient.

[0090] It should be noted that, since ESN only applies to w RO Training is performed, so the loss function is calculated only from the (h+1)th step, and the reservoir reaches a stable state after the first h calculations.

[0091] The estimated mapping vector from the reservoir to the output layer is expressed as:

[0092]

[0093] Where R = [r(1), r(2), ..., r(N)] t )] represents the time-stacked form of r(t).

[0094] Based on the trained ESN, the output power of the distribution network can be predicted.

[0095] Example 3: The above is an illustrative scheme of the power prediction method for distribution networks based on multi-source heterogeneous data fusion in this embodiment. It should be noted that the technical solution of the power prediction system for distribution networks based on multi-source heterogeneous data fusion and the technical solution of the power prediction method for distribution networks based on multi-source heterogeneous data fusion described above belong to the same concept. Details not described in detail in the technical solution of the power prediction system for distribution networks based on multi-source heterogeneous data fusion in this embodiment can be found in the description of the technical solution of the power prediction method for distribution networks based on multi-source heterogeneous data fusion described above.

[0096] This embodiment also provides a power prediction system for distribution networks based on multi-source heterogeneous data fusion, including:

[0097] The autocorrelation matrix construction module is used to construct a data autocorrelation matrix based on the comprehensive operation and maintenance data of the distribution network.

[0098] The principal component matrix construction module is used to perform eigenvalue decomposition on the data autocorrelation matrix and construct the principal component matrix.

[0099] The dimension reduction and fusion module is used to reduce the dimension of the zero-mean data obtained during the construction of the data autocorrelation matrix using the principal component matrix, so as to obtain the fused correlation data of the distribution network operation and maintenance characteristics.

[0100] The prediction module is used to build and train the echo state network model. It uses the fused and correlated data of distribution network operation and maintenance characteristics as input to the echo state network model to predict the output power of the distribution network.

[0101] This embodiment also provides an electronic device applicable to power prediction methods for distribution networks based on multi-source heterogeneous data fusion, including:

[0102] The system includes a memory and a processor. The memory stores computer-executable instructions, and the processor executes these instructions to implement the power prediction method for power distribution networks based on multi-source heterogeneous data fusion as proposed in the above embodiments.

[0103] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the power prediction method for distribution networks based on multi-source heterogeneous data fusion as proposed in the above embodiments.

[0104] The storage medium proposed in this embodiment belongs to the same inventive concept as the power prediction method for distribution networks based on multi-source heterogeneous data fusion proposed in the above embodiments. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0105] Example 4, refer to Figure 3Table 1 illustrates one embodiment of the present invention, providing a power prediction method for distribution networks based on multi-source heterogeneous data fusion. To verify the beneficial effects of the present invention, a simulation experiment is conducted for scientific demonstration.

[0106] This embodiment uses the distribution network operation and maintenance management data of a certain city over the past ten years as a basis to construct a training dataset for the distribution network output power prediction model. This dataset contains multi-dimensional data such as distribution network operation data, operation and management data, and environmental meteorological data. All types of data have been preprocessed and meet the requirements for model training.

[0107] To improve the algorithm's efficiency, feature fusion was performed on the existing training dataset. A total of 68 data features that affect the output power of the distribution network were selected, and the cumulative contribution rate of the feature values ​​was defined as the feature fusion evaluation index, namely:

[0108]

[0109] Where, λ k Let p be the k-th eigenvalue, K be the total number of eigenvalues, and p be the cumulative number of eigenvalues.

[0110] Sixty-eight data features affecting the output power of the distribution network were fused, and the fused data was used to train a model. The model convergence time and the cumulative contribution rate of the feature values ​​are shown in Table 1.

[0111] Table 1 Comparison of Feature Fusion Changes

[0112]

[0113] As shown in Table 1, fusing data features can accelerate model convergence. Furthermore, when the cumulative contribution rate of feature values ​​reaches 75%, the model convergence time and the number of accumulated feature values ​​no longer change significantly. Therefore, selecting 38 fused features can comprehensively reflect the overall information of the original data. Based on the dataset associated with the extracted 38 fused features, the ESN network is used to predict the output power of the distribution network. The prediction curve is shown in Table 1. Figure 3 As shown. From Figure 3 As can be seen, the power output curve of the distribution network predicted by this method basically coincides with the actual power output curve of the distribution network throughout the day, indicating that this method can achieve accurate prediction of the power output of the distribution network.

[0114] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A power prediction method for distribution networks based on multi-source heterogeneous data fusion, characterized in that, include: Construct a data autocorrelation matrix based on integrated operation and maintenance data of the power distribution network; Eigenvalue decomposition is performed on the autocorrelation matrix of the data to construct the principal component matrix; The zero-mean data obtained during the construction of the data autocorrelation matrix is ​​reduced using the principal component matrix to obtain the fused correlation data of distribution network operation and maintenance characteristics. An echo state network model was established and trained. The operation and maintenance characteristics of the distribution network were fused and correlated with data as input to the echo state network model to predict the output power of the distribution network.

2. The power prediction method for distribution networks based on multi-source heterogeneous data fusion as described in claim 1, characterized in that, The construction of the data autocorrelation matrix based on the integrated operation and maintenance data of the distribution network includes: The integrated operation and maintenance data of the power distribution network is represented in matrix form. The matrix contains multiple samples, each sample has multiple features, and the elements in the matrix are the specific values ​​of the corresponding features of each sample. At the same time, the matrix is ​​divided into multiple data channels by columns, and each channel contains multiple variables.

3. The power prediction method for distribution networks based on multi-source heterogeneous data fusion as described in claim 2, characterized in that, The construction of the data autocorrelation matrix based on the integrated operation and maintenance data of the distribution network also includes: Zero-mean processing is performed on the distribution network integrated operation and maintenance data represented in matrix form. Specifically, the original data is subtracted from the corresponding mean vector to obtain zero-mean data. The zero-mean data is then used to construct the data autocorrelation matrix.

4. The power prediction method for distribution networks based on multi-source heterogeneous data fusion as described in claim 3, characterized in that, The step of performing eigenvalue decomposition on the data autocorrelation matrix to construct the principal component matrix includes: Perform eigenvalue decomposition on the autocorrelation matrix of the data to obtain eigenvalues ​​and their corresponding eigenvectors. Sort all the obtained eigenvalues ​​in descending order from largest to smallest.

5. The power prediction method for distribution networks based on multi-source heterogeneous data fusion as described in claim 4, characterized in that, The step of performing eigenvalue decomposition on the data autocorrelation matrix to construct the principal component matrix further includes: Extract the first specified number of principal feature values ​​from the sorted feature values, select the feature vectors corresponding to these principal feature values, and combine the selected feature vectors to form the principal component matrix of the data. The principal component matrix contains a fusion weight vector.

6. The power prediction method for distribution networks based on multi-source heterogeneous data fusion as described in claim 5, characterized in that, The process of establishing and training an echo state network model, and using the fused and correlated data of distribution network operation and maintenance characteristics as input to the echo state network model for distribution network output power prediction, includes: The echo state network consists of an input layer, a storage pool, and an output layer. It uses the fusion and correlation data of distribution network operation and maintenance characteristics as input data and the distribution network output power data as target data.

7. The power prediction method for distribution networks based on multi-source heterogeneous data fusion as described in claim 6, characterized in that, The step of establishing and training an echo state network model, and using the fused and correlated data of distribution network operation and maintenance characteristics as input to the echo state network model for distribution network output power prediction, also includes: Define the loss function for the echo state network, and start calculating the loss function after the reservoir reaches a steady state; Estimate the mapping vector from the reservoir to the output layer; The trained echo state network is used to predict the output power of the distribution network.

8. A power prediction system for a distribution network based on multi-source heterogeneous data fusion, using the method described in any one of claims 1 to 7, characterized in that, include: The autocorrelation matrix construction module is used to construct a data autocorrelation matrix based on the comprehensive operation and maintenance data of the distribution network. The principal component matrix construction module is used to perform eigenvalue decomposition on the data autocorrelation matrix and construct the principal component matrix. The dimension reduction and fusion module is used to reduce the dimension of the zero-mean data obtained during the construction of the data autocorrelation matrix using the principal component matrix, so as to obtain the fused correlation data of the distribution network operation and maintenance characteristics. The prediction module is used to build and train the echo state network model. It uses the fused and correlated data of distribution network operation and maintenance characteristics as input to the echo state network model to predict the output power of the distribution network.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the method according to any one of claims 1 to 7.

Images