Method and system for identifying AC / DC power grid partition and weak nodes based on spectral clustering

Abstract

Method and system for identifying AC-DC power grid partition and weak nodes based on spectral clustering, including: calculating a similarity index according to the change of a set state variable between any two nodes in the power grid, and establishing a similarity index matrix; calculating the short-circuit ratio between any two nodes in the power grid to establish an AC-DC coupling strength matrix, taking into account the mutual influence of the AC-DC power grid, and the short-circuit ratio between two DC landing points in a node is the comprehensive short-circuit ratio index introducing AC-DC multi-infeed; fusing the similarity index matrix and the AC-DC coupling strength matrix to obtain an improved similarity matrix; performing dynamic partitioning based on the improved similarity matrix using spectral clustering; calculating the singular value entropy of all nodes in each partition, and taking the node with the largest singular value entropy in each partition as the weak node. The present invention takes into account the correlation of state parameters and the mutual coupling relationship between AC and DC in an AC-DC hybrid system, and can accurately perform partitioning and weak node identification.

Description

Technical Field

[0001] The present invention belongs to the technical field of power system operation, and more specifically, relates to a method and system for identifying AC-DC power grid partition and weak nodes based on spectral clustering. Background Art

[0002] DC power transmission has become one of the important ways for "transmitting power from the west to the east and interconnecting the national power grids" in China due to its advantages in long-distance, large-capacity, and cross-regional power transmission. The multi-infeed DC power transmission system can expand the system transmission capacity and increase the flexibility of operation modes, but it will also cause negative feedback interactions between AC-DC systems and between DC-DC systems. The increase in DC power transmission capacity will lead to the weakening of the strength of the receiving-end AC system, and the contradiction between "strong AC and weak DC" is prominent. Once the voltage of the receiving-end power grid AC system is abnormal or a fault occurs, it may cause commutation failure at the inverter station, and in severe cases, it may even lead to the interruption of multi-circuit DC power transmission, ultimately threatening the safe and stable operation of the entire system. Therefore, accurately and quickly partitioning the AC-DC hybrid power grid dynamically and identifying its weak nodes is of great significance for ensuring the safe and stable operation of large-scale AC-DC power grids.

[0003] CN111652469A discloses a method and system for identifying weak links in an AC-DC hybrid power grid, constructing a vulnerability index calculation model for identifying weak links in an AC-DC hybrid power grid; establishing an equivalent topological structure of the AC-DC hybrid power grid to be identified; according to the equivalent topological structure, calculating identification parameters, namely: statistically calculating the probability of transmission line failures in the power grid to be identified, calculating the ratio of the power flow transfer correlation degree of each transmission line, calculating the voltage ratio of each bus node, and determining the correlation degree between each transmission line and each bus node; inputting the identification parameters into the vulnerability index calculation model to calculate the vulnerability index of each transmission link, and the larger the value of the vulnerability index, the weaker the corresponding transmission link, so as to realize the identification of weak links. However, this invention only considers the correlation degree and voltage, does not consider the mutual influence of AC-DC power grids and the mutual coupling relationship between AC and DC in the AC-DC hybrid system, and does not consider partitioning to identify weak nodes in different regions. Summary of the Invention

[0004] To solve the deficiencies in the prior art, the present invention provides a method and system for identifying AC-DC power grid partition and weak nodes based on spectral clustering.

[0005] The present invention adopts the following technical solutions.

[0006] The first aspect of the present invention proposes a method for identifying AC-DC power grid partition and weak nodes based on spectral clustering, which is characterized by including:

[0007] Calculate the similarity between any two nodes according to the change of the set state variables between any two nodes in the power grid, and establish a similarity matrix;

[0008] Calculate the short-circuit ratio between any two nodes in the power grid, and establish an AC-DC coupling strength matrix, where the mutual influence of the AC-DC power grid is taken into account. For the short-circuit ratio between two DC landing points in a node, the comprehensive short-circuit ratio index considering AC-DC multi-infeed is introduced;

[0009] Fuse the similarity matrix and the AC-DC coupling strength matrix to obtain an improved similarity matrix;

[0010] Based on the improved similarity matrix, perform dynamic partitioning using spectral clustering that adaptively determines the number of clusters based on eigenvalues;

[0011] According to the dynamic partitioning results, calculate the singular value entropy of all nodes in each partition, and take the node with the largest singular value entropy in each partition as the weak node.

[0012] Preferably, the calculating the similarity between any two nodes according to the change of the set state variables between any two nodes in the power grid and establishing a similarity matrix is specifically as follows:

[0013] Select one of the operating states of the AC-DC power grid as the state variable, and collect the states of the nodes i and the node j at a set time interval. The state variables of the two nodes within the set time period form two trajectories. Using two continuous non-decreasing functions defined on , stretch or compress the two trajectories locally on the time axis respectively, solve the maximum distance between each corresponding position of the two stretched or compressed trajectories, find two optimal continuous non-decreasing functions to minimize this maximum distance, and the minimized maximum distance is the similarity between these two nodes. Calculate the similarity between any two nodes and establish a similarity matrix.

[0014] Preferably, the comprehensive short-circuit ratio index for the nodes between two DC landing points is:

[0015]

[0016] In the formula: is the comprehensive short-circuit ratio index between the DC landing point p and the DC landing point q ; is the commutation bus voltage of the DC landing point p ; , are the DC powers of the DC landing points p , q respectively; The equivalent nodal impedance matrix as seen from each DC converter bus is the element in the p th row and the p th column; The equivalent nodal impedance matrix as seen from each DC converter bus is the element in the p th row and the q th column;

[0017] For short - circuit ratios between two nodes in other cases, it is the reciprocal of the absolute value of the per - unit impedance between the two nodes.

[0018] Preferably, fusing the similarity matrix and the AC - DC coupling strength matrix to obtain an improved similarity matrix is specifically as follows:

[0019] Taking node similarity and electrical distance as two factors, obtaining the importance weights of node similarity and electrical distance through the analytic hierarchy process, taking the importance weight of node similarity as the weight of the similarity matrix, taking the importance weight of electrical distance as the weight of the AC - DC coupling strength matrix, and obtaining the improved similarity matrix by weighting the similarity matrix and the AC - DC coupling strength matrix.

[0020] Preferably, based on the improved similarity matrix, using spectral clustering that adaptively determines the number of clusters based on eigenvalues for dynamic partitioning is specifically as follows:

[0021] According to the improved similarity matrix, calculating the adjacency matrix, performing a row - sum operation on the adjacency matrix, the degree of each node can be calculated, and using all degree values as diagonal elements to form a diagonal matrix, which is the degree matrix;

[0022] Subtracting the adjacency matrix from the degree matrix to obtain the Laplacian matrix, and normalizing the Laplacian matrix with the help of the degree matrix;

[0023] Performing eigenvalue decomposition on the normalized Laplacian matrix, sorting the decomposed eigenvalues, selecting the eigenvectors corresponding to the largest set number of eigenvalues, arranging these eigenvectors in columns to form an eigenvector matrix, and using each row in the eigenvector matrix as a clustering sample for K - means clustering.

[0024] Preferably, calculating the adjacency matrix according to the improved similarity matrix is specifically as follows:

[0025] Using the element in the i th row and the j th column of the improved similarity matrix to represent the i th node and the jThe square of the distance between nodes, set a scale parameter, which determines the attenuation rate of the similarity between nodes, and use the Gaussian kernel function to calculate the adjacency matrix according to the improved similarity matrix. The formula is:

[0026]

[0027] In the formula, is the element in the i row and j column of the adjacency matrix; is the element in the i row and j column of the improved similarity matrix; The set scale parameter.

[0028] Preferably, the number of clusters is adaptively determined based on eigenvalues, specifically:

[0029] Arrange the eigenvalues of the Laplacian matrix from largest to smallest, calculate the difference between each eigenvalue and its next eigenvalue as the eigenvalue gap, form an eigenvalue gap sequence, and sequentially find the first maximum value in the eigenvalue gap sequence. The label of this value in the eigenvalue gap sequence is the number of clusters.

[0030] Preferably, the calculation of the singular value entropy of all nodes in each partition is specifically:

[0031] For each node in each partition, perform AC-DC power flow calculations to obtain all power flow calculation equations for each node. Take the partial derivatives of each variable in each power flow calculation equation. These partial derivatives form a Jacobian matrix. After performing singular value decomposition on this matrix, normalize the singular values into a probability distribution and calculate the singular value entropy of the node, specifically:

[0032]

[0033] In the formula, is the singular value entropy, is the result of normalizing the l th singular value of the Jacobian matrix, is the order of the Jacobian matrix.

[0034] The second aspect of the present invention proposes a spectral clustering-based AC-DC power grid partitioning and weak node identification system using the method described in the first aspect of the present invention, including a similarity matrix construction model, an AC-DC coupling strength matrix construction module, a fusion module, a dynamic partitioning module, and a weak node identification module, characterized in that:

[0035] Similarity matrix construction model: Calculate the similarity between any two nodes according to the change of the set state variables between any two nodes in the power grid, and establish a similarity matrix;

[0036] AC-DC coupling strength matrix construction module: Calculate the short-circuit ratio between any two nodes in the power grid, and establish an AC-DC coupling strength matrix, taking into account the mutual influence between the AC and DC power grids. For the short-circuit ratio between two DC landing points in a node, introduce the comprehensive short-circuit ratio index of multi-infeed AC-DC.

[0037] Fusion module: Fuse the similarity matrix and the AC-DC coupling strength matrix to obtain an improved similarity matrix.

[0038] Dynamic partitioning module: Based on the improved similarity matrix, perform dynamic partitioning using spectral clustering that adaptively determines the number of clusters based on eigenvalues.

[0039] Weak node identification module: According to the dynamic partitioning result, calculate the singular value entropy of all nodes in each partition, and take the node with the largest singular value entropy in each partition as the weak node.

[0040] The third aspect of the present invention proposes a computer device, including a memory and a processor. The memory stores a computer program. It is characterized in that when the processor executes the computer program, the steps of the AC-DC power grid partitioning and weak node identification method based on spectral clustering described in the first aspect of the present invention are implemented.

[0041] The fourth aspect of the present invention proposes a computer-readable storage medium, on which a computer program is stored. It is characterized in that when the computer program is executed by a processor, the steps of the AC-DC power grid partitioning and weak node identification method based on spectral clustering described in the first aspect of the present invention are implemented.

[0042] The beneficial effects of the present invention are as follows. Compared with the prior art, the present invention first calculates the similarity between any two nodes in the system for the trajectory of the operation state change of the AC-DC system, describes the correlation between each node, forms a similarity matrix, and reflects the similarity of nodes within a certain time scale. Then, taking into account the mutual influence between the AC and DC power grids, the coupling degree between the nodes of the AC-DC hybrid system is reflected based on the short-circuit ratio, and the multi-infeed AC-DC short-circuit ratio index is introduced at the DC landing point to form an AC-DC coupling strength matrix, which is more accurate than the short-circuit ratio obtained by the theoretical model. It not only considers the correlation of state parameters but also the mutual coupling relationship between AC and DC in the AC-DC hybrid system. The weights are selected based on the analytic hierarchy process, and the similarity matrix and the AC-DC coupling strength matrix are weighted to form an improved similarity matrix, and spectral clustering is used for dynamic partitioning to adapt to the dynamic changes of complex environments. Finally, the singular value entropy of the nodes in the region is calculated, and the node with the largest singular value entropy is used as the weak node in the region to obtain the identification result of the weak nodes in the AC-DC hybrid system, which can capture complex non-linear relationships and improve the accuracy and sensitivity of region recognition by combining partitioning, avoiding the influence of node data with low correlation. Description of the Drawings

[0043] Figure 1 It is a flowchart of a method for identifying AC-DC power grid partitions and weak nodes based on spectral clustering. Specific implementation manner

[0044] To make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. The embodiments described in this application are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the spirit of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the protection scope of the present invention.

[0045] As Figure 1 shown, Embodiment 1 of the present invention provides a method for identifying AC-DC power grid partitions and weak nodes based on spectral clustering, which is characterized by including:

[0046] Calculate the similarity between any two nodes according to the change of the set state variables between any two nodes in the power grid, and establish a similarity matrix;

[0047] Calculate the short-circuit ratio between any two nodes in the power grid, and establish an AC-DC coupling strength matrix. Considering the mutual influence between the AC and DC power grids, the short-circuit ratio between two DC landing points in a node is the comprehensive short-circuit ratio index introducing AC-DC multi-infeed;

[0048] Fuse the similarity matrix and the AC-DC coupling strength matrix to obtain an improved similarity matrix;

[0049] Based on the improved similarity matrix, perform dynamic partitioning using spectral clustering with the number of clusters adaptively determined based on eigenvalues;

[0050] According to the dynamic partitioning result, calculate the singular value entropy of all nodes in each partition, and take the node with the largest singular value entropy in each partition as the weak node.

[0051] Preferably, the step of calculating the similarity between any two nodes according to the change of the set state variables between any two nodes in the power grid and establishing a similarity matrix is specifically:

[0052] Select one of the operating states of the AC-DC power grid as the state variable, and collect the state variables of node i and node j at a set time interval. The state variables of the two nodes within the set time period form two trajectories, and use the two trajectories defined on Continuous non-decreasing functions are used to locally stretch or compress the two trajectories on the time axis, and the maximum distance between each corresponding position of the two trajectories after stretching or compression is solved. Two optimal continuous non-decreasing functions are found to minimize this maximum distance. The minimized maximum distance is the similarity between these two nodes. The similarity between any two nodes is calculated to establish a similarity matrix.

[0053] It should be noted that the operating states include, but are not limited to, the voltages, frequencies, power flows, etc. of each node in the power grid.

[0054] Calculate the similarity between any two nodes , and the formula is:

[0055]

[0056] In the formula: and are the trajectories composed of the state variables of node i and node j ; and are both continuous non-decreasing functions; represents the distance between the two trajectories at the th moment after stretching or compression, represents the maximum distance among all , represents finding the minimum value of the maximum distance for all possible and .

[0057] Similarity matrix is:

[0058]

[0059] In the formula, n is the total number of nodes.

[0060] Preferably, for the comprehensive short-circuit ratio index between two nodes with DC landing points, it is:

[0061]

[0062] In the formula: is the comprehensive short-circuit ratio index between DC landing point p and DC landing point q ; is the commutation bus voltage of DC landing point p ; , are the DC powers of DC landing points p , q respectively; Is the equivalent nodal impedance matrix seen from each DC converter bus The p th row and p th column element; The equivalent nodal impedance matrix seen from each DC converter bus The p th row and q th column element;

[0063] For the short-circuit ratio between two nodes in other cases, it is the reciprocal of the absolute value of the per-unit impedance between the two nodes. The formula is:

[0064]

[0065] In the formula: Is when The short-circuit ratio between node i and node j ; Is the short-circuit capacity of node i ; Is the rated voltage of node i ; Is the rated power; Is the equivalent impedance between node i and node j ; Is the per-unit impedance between node i and node j .

[0066] The AC-DC coupling strength matrix composed of

[0067]

[0068] Preferably, the similarity matrix and the AC-DC coupling strength matrix are fused to obtain an improved similarity matrix. Specifically:

[0069] Regarding the node similarity and the electrical distance as two factors, the importance weights of the node similarity and the electrical distance are obtained through the analytic hierarchy process. The importance weight of the node similarity is used as the weight of the similarity matrix, and the importance weight of the electrical distance is used as the weight of the AC-DC coupling strength matrix. The similarity matrix and the AC-DC coupling strength matrix are weighted to obtain an improved similarity matrix. The formula is:

[0070]

[0071] In the formula, and Are the importance weights of the node similarity and the electrical distance respectively, Is the improved similarity matrix.

[0072] Preferably, based on the improved similarity matrix, spectral clustering that adaptively determines the number of clusters based on eigenvalues is used for dynamic partitioning. Specifically:

[0073] According to the improved similarity matrix, calculate the adjacency matrix, perform a row-sum operation on the adjacency matrix, and the degree of each node can be calculated. Use all the degree values as the diagonal elements to form a diagonal matrix, and this diagonal matrix is the degree matrix; the degree matrix D The formula is:

[0074]

[0075] In the formula, is the element in the i th row and the j th column of the adjacency matrix; is the degree of the i th node.

[0076] Subtract the adjacency matrix from the degree matrix to obtain the Laplacian matrix. The formula is:

[0077]

[0078] In the formula: is the Laplacian matrix, A is the adjacency matrix, is the element in the i th row and the j th column of the adjacency matrix.

[0079] And normalize the Laplacian matrix with the help of the degree matrix. The normalization formula is:

[0080]

[0081] In the formula: is the normalized Laplacian matrix.

[0082] Perform eigenvalue decomposition on the normalized Laplacian matrix, sort the decomposed eigenvalues, select the eigenvectors corresponding to the largest set number of eigenvalues, and arrange these eigenvectors in columns to form an eigenvector matrix. The eigenvector matrix is expressed as:

[0083]

[0084] In the formula: is the eigenvector matrix; is the eigenvector corresponding to the largest set number of eigenvalues; c is the set number;

[0085] Each row in the feature vector matrix is used as a clustering sample for K-means clustering.

[0086] Preferably, calculating the adjacency matrix according to the improved similarity matrix is specifically as follows:

[0087] Use the element in the i th row and j th column of the improved similarity matrix to represent the square of the distance between the i th node and the j th node. Set a scale parameter, which determines the attenuation rate of the similarity between nodes. Use the Gaussian kernel function to calculate the adjacency matrix according to the improved similarity matrix. The formula is:

[0088]

[0089] In the formula, is the element in the i th row and j th column of the adjacency matrix; is the element in the i th row and j th column of the improved similarity matrix; is the set scale parameter.

[0090] Preferably, adaptively determining the number of clusters based on eigenvalues is specifically as follows:

[0091] Arrange the eigenvalues of the Laplacian matrix from largest to smallest, calculate the difference between each eigenvalue and its next eigenvalue and use it as the eigenvalue gap to form an eigenvalue gap sequence. The formula of this sequence is:

[0092]

[0093] In the formula, is the o th eigenvalue gap after sorting all the eigenvalues corresponding to the nodes, , are respectively the o th and the o +1 th eigenvalues after sorting all the eigenvalues corresponding to the nodes.

[0094] Find the first maximum value in the eigenvalue gap sequence in turn. The label of this value in the eigenvalue gap sequence is the number of clusters. The formula for the number of clusters is:

[0095]

[0096] In the formula, is all the eigenvalue gaps before the o th eigenvalue gap after sorting all the eigenvalues corresponding to the nodes; The 1st eigenvalue gap after sorting the eigenvalue corresponding to all nodes; o+ 1 eigenvalue gap; To achieve the minimum o value when;

[0097] Preferably, calculating the singular value entropy of all nodes in each partition specifically includes:

[0098] For each node in each partition, perform AC-DC power flow calculations to obtain all power flow calculation equations for each node. Take partial derivatives of each variable in each power flow calculation equation. These partial derivatives form a Jacobian matrix. After performing singular value decomposition on this matrix, normalize the singular values into a probability distribution and calculate the singular value entropy of the node, specifically as follows:

[0099]

[0100] In the formula, is the singular value entropy, is the result of normalizing the l th singular value of the Jacobian matrix, is the order of the Jacobian matrix.

[0101] It should be noted that the sensitivity i of the active power of node is defined as:

[0102]

[0103] In the formula, is the active power of node i .

[0104] The larger the value of , the greater the change caused by the change of the active power of the node. At this time, the change of the node load will cause significant fluctuations in the node voltage amplitude and phase angle. Thus, it can reflect the change of the singular value entropy when the active power of the node changes, indicating that it is effective to identify weak nodes by calculating the singular value entropy.

[0105] Embodiment 2 of the present invention proposes an AC-DC power grid partitioning and weak node identification system using the method described in Embodiment 1 of the present invention, including a similarity matrix construction model, an AC-DC coupling strength matrix construction module, a fusion module, a dynamic partitioning module, and a weak node identification module, characterized in that:

[0106] Similarity matrix construction model: Calculate the similarity between any two nodes according to the change of the set state variables between any two nodes in the power grid, and establish a similarity matrix;

[0107] AC-DC coupling strength matrix construction module: Calculate the short-circuit ratio between any two nodes in the power grid, and establish an AC-DC coupling strength matrix, taking into account the mutual influence between the AC and DC power grids. For the short-circuit ratio between two DC landing points in a node, the comprehensive short-circuit ratio index considering multi-infeed of AC and DC is introduced;

[0108] Fusion module: Fusion the similarity matrix and the AC-DC coupling strength matrix to obtain an improved similarity matrix;

[0109] Dynamic partitioning module: Based on the improved similarity matrix, perform dynamic partitioning using spectral clustering that adaptively determines the number of clusters based on eigenvalues;

[0110] Weak node identification module: According to the dynamic partitioning result, calculate the singular value entropy of all nodes in each partition, and take the node with the largest singular value entropy in each partition as the weak node.

[0111] Embodiment 3 of the present invention proposes a computer device, including a memory and a processor. The memory stores a computer program, and it is characterized in that when the processor executes the computer program, the steps of the method for partitioning the AC-DC power grid and identifying weak nodes based on spectral clustering according to Embodiment 1 of the present invention are realized.

[0112] Embodiment 4 of the present invention proposes a computer-readable storage medium, on which a computer program is stored, and it is characterized in that when the computer program is executed by a processor, the steps of the method for partitioning the AC-DC power grid and identifying weak nodes based on spectral clustering according to Embodiment 1 of the present invention are realized.

[0113] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: still can modify the specific implementation manners of the present invention or make equivalent replacements, and any modification or equivalent replacement without departing from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A method for identifying AC-DC power grid partitions and weak nodes based on spectral clustering, characterized in that Including: Select one of the operating states of the AC-DC power grid as the state variable, calculate the similarity between any two nodes in the power grid according to the change of the set state variable between any two nodes, and establish a similarity matrix; Calculate the short-circuit ratio between any two nodes in the power grid, and establish an AC-DC coupling strength matrix, where the mutual influence between the AC and DC power grids is taken into account. For the short-circuit ratio between two DC landing points in a node, the comprehensive short-circuit ratio index considering multi-infeed of AC and DC is introduced; Fuse the similarity matrix and the AC-DC coupling strength matrix to obtain an improved similarity matrix; Convert the improved similarity matrix into a Laplacian matrix, and use spectral clustering based on eigenvalue self-adaptively determining the number of clusters for dynamic partitioning; The eigenvalue is the eigenvalue of the Laplacian matrix; According to the dynamic partitioning result, calculate the singular value entropy of all nodes in each partition, and the node with the largest singular value entropy in each partition is the weak node.

2. The method for partitioning an AC-DC power grid and identifying weak nodes based on spectral clustering according to claim 1, wherein: The calculating the similarity between any two nodes in the power grid according to the change of the set state variable between any two nodes and establishing a similarity matrix is specifically as follows: Select one of the operating states of the AC / DC power grid as the state variable, and collect the state variables of the nodes at a set time interval i and the nodes j The state variables of the two nodes within the set time period are used to form two trajectories. By using two continuous non-decreasing functions defined on stretch or compress the two trajectories locally on the time axis respectively, solve the maximum distance between each corresponding position of the two trajectories after stretching or compressing, find two optimal continuous non-decreasing functions to minimize this maximum distance, and the minimized maximum distance is the similarity between these two nodes. Calculate the similarity between any two nodes and establish a similarity matrix 3. The method for partitioning an AC-DC power grid and identifying weak nodes based on spectral clustering according to claim 1, wherein: The comprehensive short-circuit ratio index for two nodes with DC landing points is: Where: is the DC landing point p and the comprehensive short-circuit ratio index between the DC landing point q ; is the commutation bus voltage of the DC landing point p ; , are respectively the DC powers of the DC landing points p , q ; is the element at the -th row and p -th column of the equivalent nodal impedance matrix p viewed from each DC commutation bus; is the element at the -th row and p -th column of the equivalent nodal impedance matrix q viewed from each DC commutation bus; For the short-circuit ratio between two nodes in other cases, it is the reciprocal of the absolute value of the per-unit impedance value between the two nodes.

4. The method for partitioning an AC-DC power grid and identifying weak nodes based on spectral clustering according to claim 1, wherein: The fusing the similarity matrix and the AC-DC coupling strength matrix to obtain an improved similarity matrix is specifically as follows: Regarding the node similarity and the electrical distance as two factors, obtain the importance weights of the node similarity and the electrical distance through the analytic hierarchy process, use the importance weight of the node similarity as the weight of the similarity matrix, use the importance weight of the electrical distance as the weight of the AC-DC coupling strength matrix, and perform weighted processing on the similarity matrix and the AC-DC coupling strength matrix to obtain an improved similarity matrix.

5. The method for partitioning an AC-DC power grid and identifying weak nodes based on spectral clustering according to claim 4, wherein: Based on the improved similarity matrix, using spectral clustering based on eigenvalue self-adaptively determining the number of clusters for dynamic partitioning is specifically as follows: According to the improved similarity matrix, calculate the adjacency matrix, perform row-sum operation on the adjacency matrix, and the degree of each node can be calculated. Use all degree values as diagonal elements to form a diagonal matrix, and this diagonal matrix is the degree matrix; Subtract the adjacency matrix from the degree matrix to obtain the Laplacian matrix, and normalize the Laplacian matrix with the help of the degree matrix; Perform eigenvalue decomposition on the normalized Laplacian matrix, sort the decomposed eigenvalues, select the eigenvectors corresponding to the largest set number of eigenvalues, arrange these eigenvectors column by column to form an eigenvector matrix, and use each row in the eigenvector matrix as a clustering sample for K-means clustering.

6. A method for identifying AC-DC power grid partitions and weak nodes based on spectral clustering according to claim 5, characterized in that: Calculating the adjacency matrix according to the improved similarity matrix, specifically: The element in the i -th row and j -th column of the improved similarity matrix represents the square of the distance between the i -th node and the j -th node. Set a scale parameter, which determines the attenuation rate of the similarity between nodes. Use the Gaussian kernel function to calculate the adjacency matrix according to the improved similarity matrix. The formula is: In the formula, is the element in the i -th row and j -th column of the adjacency matrix; is the element in the i -th row and j -th column of the improved similarity matrix; is the set scale parameter.

7. A method for identifying AC-DC power grid partitions and weak nodes based on spectral clustering according to claim 6, characterized in that: Determining the number of clusters adaptively based on eigenvalues, specifically: Arrange the eigenvalues of the Laplacian matrix from largest to smallest, calculate the difference between each eigenvalue and its next eigenvalue as the eigenvalue gap, form an eigenvalue gap sequence, and sequentially find the first maximum value in the eigenvalue gap sequence. The label of this value in the eigenvalue gap sequence is the number of clusters.

8. A method for identifying AC-DC power grid partitions and weak nodes based on spectral clustering according to claim 1, characterized in that: Calculating the singular value entropy of all nodes in each partition, specifically: For each node in each partition, perform AC-DC power flow calculations to obtain all power flow calculation equations for each node, take partial derivatives of each variable in each power flow calculation equation, and these partial derivatives form a Jacobian matrix. After performing singular value decomposition on this matrix, normalize the singular values to a probability distribution and calculate the singular value entropy of the node, specifically: In the formula, is the singular value entropy, is the result of normalizing the l -th singular value of the Jacobian matrix, is the order of the Jacobian matrix.

9. A system for identifying AC-DC power grid partitions and weak nodes based on spectral clustering using the method according to any one of claims 1-8, including a similarity matrix construction model, an AC-DC coupling strength matrix construction module, a fusion module, a dynamic partitioning module, and a weak node identification module, characterized in that: Similarity matrix construction model: Calculate the similarity between any two nodes according to the change of the set state variables between any two nodes in the power grid, and establish a similarity matrix; AC-DC coupling strength matrix construction module: Calculate the short-circuit ratio between any two nodes in the power grid and establish an AC-DC coupling strength matrix, where the mutual influence of the AC-DC power grid is taken into account, and the short-circuit ratio between two DC landing points in a node is the comprehensive short-circuit ratio index introducing AC-DC multi-infeed; Fusion module: Fuse the similarity matrix and the AC-DC coupling strength matrix to obtain an improved similarity matrix; Dynamic partitioning module: Based on the improved similarity matrix, perform dynamic partitioning using spectral clustering that adaptively determines the number of clusters based on eigenvalues; Weak node identification module: According to the dynamic partitioning result, calculate the singular value entropy of all nodes in each partition, and take the node with the largest singular value entropy in each partition as the weak node.

10. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for identifying AC-DC power grid partitions and weak nodes based on spectral clustering according to any one of claims 1 to 8.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method for AC / DC power grid partitioning and weak node identification based on spectral clustering according to any one of claims 1 to 8.

Images