Power grid design scheme generation method based on deep learning

Abstract

The invention discloses a power grid design scheme generation method based on deep learning, and belongs to the technical field of power grid planning, and the method comprises the steps: S1, obtaining a power grid description text and a power grid line text of a power grid design scheme; s2, respectively carrying out word embedding representation on the texts to obtain a word vector matrix; s3, extracting features of the word vector matrix by using two parallel convolutional networks introducing an attention mechanism to obtain text feature vectors; s4, performing feature fusion on the text feature vectors by using a bidirectional LSTM network to obtain comprehensive feature representation; s5, the comprehensive feature representations are learned through a collaborative filtering module, and prediction vector representations are obtained; and S6, fusing the prediction vector representations to obtain a generated power grid design scheme. According to the method, the power grid data including implicit feedback data and auxiliary features can be utilized to establish the deep learning model to learn the power grid features, so that accurate, efficient and personalized recommendation of the power grid design scheme is realized.

Description

Technical Field

[0001] The present invention belongs to the technical field of power grid planning, and specifically relates to a method for generating a power grid design scheme based on deep learning. Background Art

[0002] As the scale and complexity of power grids increase, traditional power grid planning and design methods can no longer meet the growing data processing needs. In order to improve the efficiency and quality of power grid planning and design, the design scheme recommendation method has begun to integrate deep learning technology. Deep learning can automatically learn complex patterns and relationships from massive data, providing more accurate predictions and analysis for power grid design. The design scheme recommendation method combines deep learning technology to accurately describe specific power grid design schemes by analyzing the lines used in the power grid scheme and the details of the power grid scheme, thereby providing effective support for the scheme selection of the power system. This method not only improves the efficiency of the design, but also ensures the quality of power grid planning and the stability of power grid operation.

[0003] In recent years, the development of deep neural network technology has brought new ideas to power grid design. Collaborative filtering (CF) algorithms, especially matrix factorization (MF) algorithms, have been widely used in the construction of recommendation systems due to their unique ability to utilize group wisdom and experience. Matrix factorization assumes that the relationship between users and items is connected through hidden factors. By mapping users and items into the same representation space until they can be directly compared, the similarity between the two is used to measure the quality of the match. In this case, the model learns low-dimensional vectors for users and items, and finally uses the dot product as the matching equation to calculate the score. DNN has a good performance in representation learning and is widely used. With this idea, we applied this method to power grid design. Through the powerful learning ability of deep learning, the relationship between the two is learned, so as to recommend suitable power grid design solutions to users, thereby improving the efficiency and quality of power grid planning and design. Summary of the invention

[0004] In response to the above-mentioned deficiencies in the prior art, the deep learning-based power grid design scheme generation method provided by the present invention solves the inefficient design situation in the traditional power grid design scheme recommendation process that relies on expert experience and manual analysis, and the problem that traditional data processing methods have limitations in extracting valuable information, thereby affecting the accuracy of power grid design scheme recommendations.

[0005] In order to achieve the above-mentioned invention object, the technical solution adopted by the present invention is: a method for generating a power grid design scheme based on deep learning, comprising the following steps:

[0006] S1. Obtaining a grid description text and a grid line text of a grid design plan;

[0007] S2, respectively perform word embedding representation on the power grid description text and the power grid line text to obtain the corresponding power grid description word vector matrix and power grid line word vector matrix;

[0008] S3, using two parallel convolutional networks that introduce an attention mechanism to perform feature extraction on the power grid description word vector matrix and the power grid line word vector matrix respectively, to obtain corresponding power grid description text feature vectors and power grid line text feature vectors;

[0009] S4, using a bidirectional LSTM network to perform feature fusion on the power grid description text feature vector and the power grid line text feature vector to obtain a comprehensive feature representation;

[0010] S5, learning the comprehensive feature representation respectively through the collaborative filtering module based on representation learning and the collaborative filtering module based on matching function learning to obtain the corresponding prediction vector representation;

[0011] S6. The prediction vector representations obtained based on representation learning and matching function learning are integrated to obtain a generated power grid design solution.

[0012] Furthermore, in step S3, the convolutional network with the attention mechanism is introduced to the word vector matrix A of any power grid description / power grid line u. u The method for feature extraction and obtaining corresponding text features is as follows:

[0013] S31. Determine the word vector matrix A u Each word vector w k u The attention weight a k ;

[0014] S32, the attention weights of all word vectors are calculated according to the word vector matrix A u The word order is concatenated to obtain the word vector matrix A u The corresponding attention weight A(u) = (a1, a2, ..., a n ), k = 1, 2, 3, ..., n, k represents the index of the word vector element;

[0015] S33. Add the attention weight A(u) to the word vector matrix A u Perform corresponding multiplication to obtain the updated word vector matrix

[0016] S34, normalize the updated word vector matrix, extract its features through a set of convolutional layers, and then generate the corresponding feature map C i ;

[0017] S35, feature map C iPerform maximum pooling to obtain a simplified feature representation;

[0018] S36. Perform low-dimensional feature mapping on the simplified feature representation through a fully connected layer to obtain text features corresponding to the power grid description / power grid line.

[0019] Furthermore, in step S31, the attention weight a k It is expressed as:

[0020]

[0021] In the formula, g k represents the result of linear transformation of the kth element in the input sequence, ReLU(·) represents the ReLU activation function, A1 represents the weight parameter matrix, b1 represents the bias term when the first element in the input sequence is linearly transformed, and g j It represents the result of linear transformation of the jth element in the input sequence, where j represents the element index and n represents the sequence length;

[0022] In step S34, the method of performing feature extraction through the convolution layer is:

[0023] Let the convolution kernel W of each convolution layer ij After updating the word vector matrix Slide up, perform weighted summation and add bias terms, and then generate feature map C through activation function i , which is expressed as:

[0024]

[0025] In the formula, σ(·) represents the activation function, q i represents the bias term corresponding to the i-th feature map, Represents the updated word vector matrix The j-th element in , the subscript i represents the index of the feature map, and m represents the number of feature maps;

[0026] In step S36, the grid description / grid line text feature F is expressed as:

[0027] F=σ(W f *P f +z f )

[0028] In the formula, σ(·) represents the activation function, W f represents the weight, z f represents the bias term corresponding to the network neuron f, P f Represents the feature representation of the output of the pooling layer.

[0029] Furthermore, in step S4, the output y of the bidirectional LSTM network at the last time step T is T As the comprehensive fusion representation of the power grid description text feature vector and the power grid line text feature vector, output = y T .

[0030] Furthermore, in step S5, the collaborative filtering network based on the learning representation uses a multi-layer perceptron to learn the latent vector representation p of the power grid description for the comprehensive feature representation. j and the latent vector representation p of the power grid line u , and obtain the prediction vector representation corresponding to representation learning ⊙ represents the Hadamard product operation.

[0031] Furthermore, the collaborative filtering network based on learning representation uses a multi-layer perceptron to learn the corresponding latent vector representation of the comprehensive feature representation as follows:

[0032]

[0033] In the formula, ReLU(·) is the ReLU activation function, c0 represents the hidden state of the input sequence, c1 represents the output of the first hidden layer, c2 represents the output after processing by the next hidden layer based on c1, and c x-1 Represents in c x-2 The output after processing by the next hidden layer, c x Represents in c x-1 The output after the next hidden layer processing, W0, W1, ..., W x Represent the weight matrices of different intermediate layers, d1, d2, ..., d x Respectively represent the bias items corresponding to the first hidden layer, the second hidden layer to the xth hidden layer, y u Represents input data.

[0034] Furthermore, in step S5, the collaborative filtering network based on matching function learning first uses a linear embedding layer to learn the latent vector representation p of the power grid description. j and the latent vector representation p of the power grid line u , and then process them using a multi-layer perceptron network to obtain the prediction vector representation corresponding to the matching function learning.

[0035] Furthermore, the corresponding prediction vector representation is learned based on the matching function The process is expressed as:

[0036]

[0037] Where P and Q represent the weight matrices of the linear embedding layer, which are used to transform l u and l j The original features are mapped to the vector representation in the latent space, l u The characteristics of the lines representing the power grid scheme, l j The features representing the detailed information of the power grid scheme, v0 represents the potential vector representation p j and the latent vector representation p u The concatenated vector, v1 represents the output vector after the first hidden layer, v Y Represents the final output vector of the multilayer perceptron, v Y-1 Represents the output vector of the second-to-last layer of the multilayer perceptron, W y1 , W Y They represent the weight matrices of the first hidden layer and the last hidden layer in the multilayer perceptron, k1 represents the bias term corresponding to the first layer in the multilayer perceptron, and k Y represents the bias term corresponding to the y-th layer in the multilayer perceptron, and ReLU(·) represents the ReLU activation function.

[0038] Furthermore, in step S6, the prediction vector representation is fused to be represented as:

[0039]

[0040] In the formula, represents the generated power grid design scheme, σ(·) represents the activation function, W out Represents the weight matrix of the output layer.

[0041] The beneficial effects of the present invention are:

[0042] (1) This paper proposes an innovative deep learning recommendation network GridDeepCF by learning relevant knowledge in the field of power grid planning and design, and combining the characteristics and shortcomings of traditional power grid design solution recommendation methods, to effectively assist power engineers in identifying and selecting the optimal power grid design solution. In GridDeepCF, the traditional recommendation system is improved by introducing two key network modules, which improve the quality and relevance of the recommended solutions through in-depth feature extraction and fusion of power grid data and enhanced attention to the key elements of power grid solutions.

[0043] (2) Through a large number of experiments on multiple real power grid datasets, the present invention verifies the effectiveness of the proposed recommendation network GridDeepCF. Compared with other advanced methods, the proposed method has achieved remarkable achievements in the accuracy, efficiency and personalization of power grid design scheme recommendation. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a flow chart of the method for generating a power grid design solution based on deep learning in the present invention. DETAILED DESCRIPTION

[0045] The specific implementation modes of the present invention are described below to facilitate those skilled in the art to understand the present invention. However, it should be clear that the present invention is not limited to the scope of the specific implementation modes. For those of ordinary skill in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the attached claims, these changes are obvious, and all inventions and creations utilizing the concept of the present invention are protected.

[0046] The embodiment of the present invention provides a method for generating a power grid design scheme based on deep learning, such as Figure 1 As shown, the following steps are included:

[0047] S1. Obtaining a grid description text and a grid line text of a grid design plan;

[0048] S2, respectively perform word embedding representation on the power grid description text and the power grid line text to obtain the corresponding power grid description word vector matrix and power grid line word vector matrix;

[0049] S3, using two parallel convolutional networks that introduce an attention mechanism to perform feature extraction on the power grid description word vector matrix and the power grid line word vector matrix respectively, to obtain corresponding power grid description text feature vectors and power grid line text feature vectors;

[0050] S4, using a bidirectional LSTM network to perform feature fusion on the power grid description text feature vector and the power grid line text feature vector to obtain a comprehensive feature representation;

[0051] S5, learning the comprehensive feature representation respectively through the collaborative filtering module based on representation learning and the collaborative filtering module based on matching function learning to obtain the corresponding prediction vector representation;

[0052] S6. The prediction vector representations obtained based on representation learning and matching function learning are integrated to obtain a generated power grid design solution.

[0053] In an embodiment of the present invention, the convolutional network, bidirectional LSTM network and collaborative filtering module introduced with the attention mechanism in the above method are combined to form a network framework GridDeepCF for generating a power grid design scheme. The input of the network framework is a detailed description of the lines used in the power grid scheme and the power grid scheme. The generated power grid design scheme is obtained through the processing output of the above network framework.

[0054] In step S3 of the embodiment of the present invention, in order to enhance the importance of text features, an attention mechanism is introduced into the convolutional network CNN, which can assign different weights to each word in the input text, thereby highlighting the words that have the greatest impact on the text description.

[0055] In step S3 of this embodiment, the convolutional network with the attention mechanism is introduced to the word vector matrix A of any power grid description / power grid line u. u The method for feature extraction and obtaining corresponding text features is as follows:

[0056] S31. Determine the word vector matrix A u Each word vector in The attention weight a k ;

[0057] S32, the attention weights of all word vectors are calculated according to the word vector matrix A u The word order is concatenated to obtain the word vector matrix A u The corresponding attention weight A(u) = (a1, a2, ..., a n ), k = 1, 2, 3, ..., n, k represents the index of the word vector element;

[0058] S33. Add the attention weight A(u) to the word vector matrix A u Perform corresponding multiplication to obtain the updated word vector matrix

[0059] S34, normalize the updated word vector matrix, extract its features through a set of convolutional layers, and then generate the corresponding feature map C i ;

[0060] S35, feature map C i Perform maximum pooling to obtain a simplified feature representation;

[0061] S36. Perform low-dimensional feature mapping on the simplified feature representation through a fully connected layer to obtain text features corresponding to the power grid description / power grid line.

[0062] In the above step S31 of this embodiment, the attention weight a k It is expressed as;

[0063]

[0064] In the formula, g k represents the result of linear transformation of the kth element in the input sequence, ReLU(·) represents the ReLU activation function, A1 represents the weight parameter matrix, b1 represents the bias term when the first element in the input sequence is linearly transformed, and g jIt represents the result of linear transformation of the jth element in the input sequence, where j represents the element index and n represents the sequence length;

[0065] In step S34, the method of performing feature extraction through the convolution layer is:

[0066] In the above step S34 of this embodiment, the method of performing feature extraction through the convolution layer is:

[0067] Let the convolution kernel W of each convolution layer ij After updating the word vector matrix Slide up, perform weighted summation and add bias terms, and then generate feature map C through activation function i , which is expressed as:

[0068]

[0069] In the formula, σ(·) represents the activation function, q i represents the bias term corresponding to the i-th feature map, Represents the updated word vector matrix The j-th element in , the subscript i represents the index of the feature map, and m represents the number of feature maps;

[0070] In step S34 of this embodiment, the above-mentioned weighted summed word vector matrix is ​​standardized. Taking the power grid line as an example, the usage of each line is placed in the range of [0,1] through standardization. This can speed up the network and improve the generalization ability of the model.

[0071] In step S35 of this embodiment, in order to reduce the spatial dimension of the feature, a pooling layer is introduced to select the maximum value max(C i ) to simplify the feature representation.

[0072] In step S36 of this embodiment, the power grid description / power grid line text feature F is expressed as:

[0073] F=σ(W f *P f +z f )

[0074] In the formula, σ(·) represents the activation function, W f represents the weight, z f represents the bias term corresponding to the network neuron f, P f Represents the feature representation of the output of the pooling layer.

[0075] In this embodiment, the above steps are used to obtain the power grid description / power grid line text feature F, and then obtain the corresponding feature vector including the power grid description text feature vector output j and power grid line text feature vector output u , and use it as the input of the subsequent bidirectional LSTM network.

[0076] In this embodiment, text features play an important role in the process of realizing power grid design solution generation. By mapping professional terms into dense vector representations, the network structure can capture the deep semantic information in the text data.

[0077] In a specific example of this embodiment, the professional terms embedded in the matrix, such as "steel core aluminum stranded wire", "110kV", "transmission line", "transformer", "GB standard", "high temperature", "industrial load" and "mountainous area", not only represent the physical properties and engineering requirements of the power grid design, but also reflect the operating characteristics of the power grid under different environmental conditions. These text features are used as input features, so that the neural network can learn the similarities and differences between different design schemes in terms of material selection, voltage level, line type, equipment configuration, compliance standards, environmental challenges, service load types and geographical locations. When faced with a new power grid design project, such as a project located in a mountainous area, the model has learned to identify text features related to "mountainous area" through training. These text features carry environmental factors and design considerations unique to mountainous areas, so that the model can accurately recommend power grid design schemes that are adapted to the complex terrain and climatic conditions of mountainous areas, ensuring that the design schemes are both economical, efficient, safe and reliable. In this way, the network structure converts the word vector matrix of professional terms into a knowledge representation with a deep understanding of the design scheme, thereby greatly improving the accuracy and practicality of the recommendation.

[0078] In a specific example of this embodiment, the designed convolutional network includes two convolutional layers, two pooling layers, and a fully connected layer. Convolutional layer 1 uses 32 3x3 convolution kernels, a step size of 1, a border padding of 1, an activation function of ReLU, weights initialized with He, and bias items initialized with 0; followed by pooling layer 1, using a 2x2 maximum pooling window with a step size of 2 to reduce the spatial dimension of the feature map. Convolutional layer 2 further extracts features, using 64 3x3 convolution kernels, a step size of 1, a border padding of 1, and a ReLU activation function. The initialization of weights and bias items is the same as that of convolutional layer 1; the following pooling layer 2 also uses a 2x2 maximum pooling window with a step size of 2. Fully connected layer 1 maps the output of pooling layer 2 to a low-dimensional space, has 128 neurons, and an activation function of ReLU. The weights and bias items are initialized with He initialization and 0 initialization, respectively.

[0079] In step S4 of the embodiment of the present invention, the output y of the bidirectional LSTM network at the last time step T is converted into T As the comprehensive fusion representation of the power grid description text feature vector and the power grid line text feature vector, output = y T .

[0080] In this embodiment, a bidirectional LSTM network structure is used to simultaneously capture the forward and backward information of text features. At each time step, the forward LSTM layer processes the information from the beginning of the text to the current point, while the reverse LSTM layer processes the information from the end of the text to the current point. The outputs of these two layers of LSTM are merged at each time step, thereby forming a comprehensive feature vector at each moment, which incorporates the forward-looking and retrospective context of the text. Subsequently, these merged feature vectors are sent to the fully connected layer, where deeper processing and abstraction are performed to extract richer and more abstract feature representations. When all time steps are processed, the output of the bidirectional LSTM at the last time step is taken as the final fusion representation of the two text features. This representation fully reflects the global semantic information of the two text features and provides strong feature support for subsequent tasks.

[0081] In step S5 of the embodiment of the present invention, the collaborative filtering network based on the learning representation uses a multi-layer perceptron to learn the latent vector representation p of the power grid description for the comprehensive feature representation. j and the latent vector representation p of the power grid line u , get the prediction vector representation v based on representation learning Y rl =p u ⊙p j , ⊙ represents the Hadamard product operation.

[0082] In this embodiment, the process of using a multi-layer perceptron to learn the corresponding latent vector representation of the comprehensive feature representation based on the collaborative filtering network of the learning representation is expressed as follows:

[0083]

[0084] In the formula, ReLU(·) is the ReLU activation function, c0 represents the hidden state of the input sequence, c1 represents the output of the first hidden layer, c2 represents the output after processing by the next hidden layer based on c1, and c x-1 Represents in c x-2 The output after processing by the next hidden layer, c x Represents in c x-1 The output after the next hidden layer processing, W0, W1, ..., W x Represent the weight matrices of different intermediate layers, d1, d2, ..., dx Respectively represent the bias items corresponding to the first hidden layer, the second hidden layer to the xth hidden layer, y u Represents input data.

[0085] In step S5 of the embodiment of the present invention, the collaborative filtering network based on matching function learning first uses a linear embedding layer to learn the latent vector representation p of the power grid description. j and the latent vector representation p of the power grid line u , and then process them using a multi-layer perceptron network to obtain the prediction vector representation corresponding to the matching function learning.

[0086] In this embodiment, the corresponding prediction vector representation is learned based on the matching function The process is expressed as:

[0087]

[0088] Where P and Q represent the weight matrices of the linear embedding layer, which are used to transform l u and l j The original features are mapped to the vector representation in the latent space, l u The characteristics of the lines representing the power grid scheme, l j The features representing the detailed information of the power grid scheme, v0 represents the potential vector representation p j and the latent vector representation p u The concatenated vector, v1 represents the output vector after the first hidden layer, v Y Represents the final output vector of the multilayer perceptron, v Y-1 Represents the output vector of the second-to-last layer of the multilayer perceptron, W y1 , W Y They represent the weight matrices of the first hidden layer and the last hidden layer in the multilayer perceptron, k1 represents the bias term corresponding to the first layer in the multilayer perceptron, and k Y represents the bias term corresponding to the y-th layer in the multilayer perceptron, and ReLU(·) represents the ReLU activation function.

[0089] In step S6 of the embodiment of the present invention, the prediction vector representations obtained from the two parts are finally fused to obtain the output of the final entire model; based on this, the prediction vector representation is fused as follows:

[0090]

[0091] In the formula, represents the generated power grid design scheme, σ(·) represents the activation function, W out Represents the weight matrix of the output layer.

[0092] The present invention uses specific embodiments to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

[0093] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. A method for generating a power grid design scheme based on deep learning, characterized in that: The following steps are involved: S1. Obtaining a grid description text and a grid line text of a grid design plan; S2, respectively perform word embedding representation on the power grid description text and the power grid line text to obtain the corresponding power grid description word vector matrix and power grid line word vector matrix; S3, using two parallel convolutional networks that introduce an attention mechanism to perform feature extraction on the power grid description word vector matrix and the power grid line word vector matrix respectively, to obtain corresponding power grid description text feature vectors and power grid line text feature vectors; S4, using a bidirectional LSTM network to perform feature fusion on the power grid description text feature vector and the power grid line text feature vector to obtain a comprehensive feature representation; S5, learning the comprehensive feature representation respectively through the collaborative filtering module based on representation learning and the collaborative filtering module based on matching function learning to obtain the corresponding prediction vector representation; S6. The prediction vector representations obtained based on representation learning and matching function learning are integrated to obtain a generated power grid design solution.

2. The method for generating a power grid design scheme based on deep learning according to claim 1, characterized in that: In step S3, the convolutional network with the attention mechanism is introduced to the word vector matrix A of any power grid description / power grid line u. u The method for feature extraction and obtaining corresponding text features is as follows: S31. Determine the word vector matrix A u Each word vector in The attention weight a k ; S32, the attention weights of all word vectors are calculated according to the word vector matrix A u The word order is concatenated to obtain the word vector matrix A u The corresponding attention weight A(u) = (a1, a2, ..., a n ), k = 1, 2, 3, ..., n, k represents the index of the word vector element; S33. Add the attention weight A(u) to the word vector matrix A u Perform corresponding multiplication to obtain the updated word vector matrix S34, normalize the updated word vector matrix, extract its features through a set of convolutional layers, and then generate the corresponding feature map C i ; S35, feature map C i Perform maximum pooling to obtain a simplified feature representation; S36. Perform low-dimensional feature mapping on the simplified feature representation through a fully connected layer to obtain text features corresponding to the power grid description / power grid line.

3. The method for generating a power grid design scheme based on deep learning according to claim 2, characterized in that: In step S31, the attention weight a k It is expressed as: In the formula, g k represents the result of linear transformation of the kth element in the input sequence, ReLU(·) represents the ReLU activation function, A1 represents the weight parameter matrix, b1 represents the bias term when the first element in the input sequence is linearly transformed, and g j It represents the result of linear transformation of the jth element in the input sequence, where j represents the element index and n represents the sequence length; In step S34, the method of performing feature extraction through the convolution layer is: Let the convolution kernel W of each convolution layer ij After updating the word vector matrix Slide up, perform weighted summation and add bias terms, and then generate feature map C through activation function i , which is expressed as: In the formula, σ(·) represents the activation function, q i represents the bias term corresponding to the i-th feature map, Represents the updated word vector matrix The j-th element in , the subscript i represents the index of the feature map, and m represents the number of feature maps; In step S36, the grid description / grid line text feature F is expressed as: F=σ(W f *P f +z f ) In the formula, σ(·) represents the activation function, W f represents the weight, z f represents the bias term corresponding to the network neuron f, P f Represents the feature representation of the output of the pooling layer.

4. The method for generating a power grid design scheme based on deep learning according to claim 1, characterized in that: In step S4, the output y of the bidirectional LSTM network at the last time step T is T As the comprehensive fusion representation of the power grid description text feature vector and the power grid line text feature vector, output = y T .

5. The method for generating a power grid design scheme based on deep learning according to claim 1, characterized in that: In step S5, the collaborative filtering network based on the learning representation uses a multi-layer perceptron to learn the potential vector representation p of the power grid description for the comprehensive feature representation. j and the latent vector representation p of the power grid line u , and obtain the prediction vector representation corresponding to representation learning ⊙ represents the Hadamard product operation.

6. The method for generating a power grid design scheme based on deep learning according to claim 5, characterized in that: The collaborative filtering network based on learning representation uses a multi-layer perceptron to learn the corresponding latent vector representation of comprehensive feature representation as follows: In the formula, ReLU(·) is the ReLU activation function, c0 represents the hidden state of the input sequence, c1 represents the output of the first hidden layer, c2 represents the output after processing by the next hidden layer based on c1, and c x-1 Represents in c x-2 The output after processing by the next hidden layer, c x Represents in c x-1 The output after the next hidden layer processing, W0, W1, ..., W x Represent the weight matrices of different intermediate layers, d1, d2, ..., d x Respectively represent the bias items corresponding to the first hidden layer, the second hidden layer to the xth hidden layer, y u Represents input data.

7. The method for generating a power grid design scheme based on deep learning according to claim 5, characterized in that: In step S5, the collaborative filtering network based on matching function learning first uses a linear embedding layer to learn the potential vector representation p of the power grid description. j and the latent vector representation p of the power grid line u , and then process them using a multi-layer perceptron network to obtain the prediction vector representation corresponding to the matching function learning.

8. The method for generating a power grid design scheme based on deep learning according to claim 7, characterized in that: Learning the corresponding prediction vector representation based on the matching function The process is expressed as: Where P and Q represent the weight matrices of the linear embedding layer, which are used to transform l u and l j The original features are mapped to the vector representation in the latent space, l u The characteristics of the lines representing the power grid scheme, l j The features representing the detailed information of the power grid scheme, v0 represents the potential vector representation p j and the latent vector representation p u The concatenated vector, v1 represents the output vector after the first hidden layer, v Y Represents the final output vector of the multilayer perceptron, v Y-1 Represents the output vector of the second-to-last layer of the multilayer perceptron, W y1 , W Y They represent the weight matrices of the first hidden layer and the last hidden layer in the multilayer perceptron, k1 represents the bias term corresponding to the first layer in the multilayer perceptron, and k Y represents the bias term corresponding to the y-th layer in the multilayer perceptron, and ReLU(·) represents the ReLU activation function.

9. The method for generating a power grid design scheme based on deep learning according to claim 7, characterized in that: In step S6, the prediction vector representation is fused as follows: In the formula, represents the generated power grid design scheme, σ(·) represents the activation function, W out Represents the weight matrix of the output layer.

Images