Power system transient stability assessment method, device, electronic device and storage medium

Abstract

The present invention provides a method, device, electronic device, and storage medium for evaluating transient stability of a power system. The method includes: obtaining power system flow information and power system topology information; determining a power system flow characteristic diagram based on the power system flow information and power system topology information; inputting node characteristics and topology characteristics of the power system flow characteristic diagram into a transient stability evaluation model to obtain the transient stability and transient stability index of the power system after each expected fault in the expected fault set output by the transient stability evaluation model; the transient stability evaluation model is used to perform coupled analysis of the transient stability and transient stability index of the power system by learning the characteristics of the power system flow characteristic diagram. The method, device, electronic device, and storage medium provided by the present invention enable rapid evaluation and prediction of the transient stability and transient stability index of the power system after each expected fault in the expected fault set.

Description

Technical Field

[0001] The present invention relates to the field of power systems, and in particular to a method, device, electronic equipment and storage medium for evaluating transient stability of a power system. Background Art

[0002] When a power system is operating, driven by the potential of the power source, current or power flows from the power source through various system components into the load, and is distributed throughout the power grid. This is called a power flow. In power system operation analysis and calculations, a transient stability assessment of a given power system flow is performed based on a given set of anticipated faults to verify the operational safety of the flow. Due to the N-1 safety principle of power systems, the anticipated fault set is generally a typical N-1 fault. This process is known as the N-1 transient stability verification of the power flow.

[0003] The N-1 verification process involves multiple transient simulation calculations for a single power flow. However, since the N-1 expected fault set and the time required for a single transient simulation increase with the size of the system, the N-1 verification calculation for large systems is highly complex and time-consuming. In recent years, thanks to the development of machine learning algorithms and the generation of simulation big data, data-driven models have been increasingly applied to this problem. By making full use of existing simulation samples for learning, machine learning models are used to establish a nonlinear mapping from the system operating power flow to the N-1 verification results, thereby avoiding the transient simulation process and significantly reducing the time cost of the N-1 verification. Existing research on transient stability assessment using power flow characteristics mainly uses machine learning methods such as data mining theory, multiple support vector machines, and tree models. Summary of the Invention

[0004] The present invention provides a power system transient stability assessment method, device, electronic device and storage medium, which are used to solve the problems in the prior art that each expected fault in a set of expected faults cannot be predicted and only a single task can be completed.

[0005] The present invention provides a method for evaluating transient stability of a power system, comprising:

[0006] Obtain power system flow information and power system topology information;

[0007] Determine a power system power flow characteristic diagram based on the power system power flow information and the power system topology information; the power system power flow characteristic diagram is a power system power flow characteristic in a graphical form; the characteristics of the power system power flow characteristic diagram include node characteristics and topology characteristics;

[0008] The node characteristics and topological characteristics of the power system flow characteristic diagram are input into a transient stability assessment model to obtain the transient stability and transient stability index of the power system after each expected fault in the expected fault set output by the transient stability assessment model; the transient stability assessment model is used to perform coupled analysis on the transient stability and transient stability index of the power system by performing feature learning on the power system flow characteristic diagram.

[0009] According to a method for transient stability assessment of a power system provided by the present invention, the node characteristics and topological characteristics of the power system power flow characteristic diagram are input into a transient stability assessment model to obtain the transient stability and transient stability index of the power system after each expected fault in the expected fault set output by the transient stability assessment model occurs, including:

[0010] Obtaining a message vector of any edge of the power system power flow characteristic diagram and an updated feature of the edge according to the source node feature, the target node feature, and the feature of the edge;

[0011] determining, based on the message vectors of each edge on the power system power flow characteristic diagram and the characteristics of each edge, a message vector to be received by each node on the power system power flow characteristic diagram;

[0012] updating node characteristics of each node on the power system power flow characteristic diagram according to the message vector to be received by each node on the power system power flow characteristic diagram to obtain updated node characteristics of each node;

[0013] According to the updated characteristics of the edges and the updated node characteristics of each node, the transient stability and transient stability index of the power system after each expected fault in the expected fault set occurs are determined.

[0014] According to a method for evaluating transient stability of a power system provided by the present invention, determining a message vector to be received by each node on the power system power flow characteristic diagram based on the message vector of each edge on the power system power flow characteristic diagram and the characteristics of each edge, including:

[0015] The message vector of each edge on the power system flow characteristic diagram is scaled using the out-degree of the source node and the in-degree of the target node to obtain the message vector to be received by each node on the power system flow characteristic diagram.

[0016] According to a method for evaluating transient stability of a power system provided by the present invention, the transient stability index includes: the maximum power angle difference during the transient process in which the system maintains transient stability after an anticipated fault, and the transient instability time during which the system experiences transient instability after an anticipated fault.

[0017] According to a method for evaluating transient stability of a power system provided by the present invention, the power system flow information includes the voltage amplitude, voltage phase angle, generator active injection power, generator reactive injection power, active load and reactive load of each bus in the power system;

[0018] The determining of a power system power flow characteristic diagram according to the power system power flow information and the power system topology information includes:

[0019] Determining node characteristics of the power system power flow characteristic diagram according to the voltage amplitude, voltage phase angle, generator active injection power, generator reactive injection power, active load and reactive load of each bus in the power system;

[0020] The topological characteristics of the power system power flow characteristic diagram are determined according to the node admittance matrix and the node impedance matrix of the power system.

[0021] The present invention also provides a power system transient stability assessment device, comprising:

[0022] an acquisition unit, used for acquiring power system flow information and power system topology information;

[0023] a determining unit, configured to determine a power system power flow characteristic diagram based on the power system power flow information and the power system topology information; the power system power flow characteristic diagram is a power system power flow characteristic in a graphical form; the characteristics of the power system power flow characteristic diagram include: node characteristics and topology characteristics;

[0024] A transient stability assessment unit is used to input the node characteristics and topological characteristics of the power system flow characteristic diagram into a transient stability assessment model to obtain the transient stability and transient stability index of the power system after each expected fault in the expected fault set output by the transient stability assessment model occurs; the transient stability assessment model is used to perform coupled analysis on the transient stability and transient stability index of the power system by performing feature learning on the power system flow characteristic diagram.

[0025] According to a power system transient stability assessment device provided by the present invention, the transient stability assessment unit includes:

[0026] a message generating subunit, configured to obtain a message vector of any edge of the power system power flow characteristic diagram and an updated feature of the edge according to the source node feature, the target node feature, and the feature of the edge;

[0027] a message collecting subunit, configured to determine a message vector to be received by each node on the power system power flow characteristic diagram according to the message vector of each edge on the power system power flow characteristic diagram and the characteristics of each edge;

[0028] a node feature updating subunit, configured to update the node features of each node on the power system power flow feature diagram according to the message vector to be received by each node on the power system power flow feature diagram, and obtain updated node features of each node;

[0029] The evaluation subunit is used to determine the transient stability and transient stability index of the power system after each expected fault in the expected fault set occurs based on the updated characteristics of the edge and the updated node characteristics of each node.

[0030] According to a power system transient stability assessment device provided by the present invention, the message collection subunit uses the out-degree of the source node and the in-degree of the target node of each edge on the power system flow characteristic diagram to scale the message vector of each edge to obtain the message vector to be received by each node on the power system flow characteristic diagram.

[0031] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of any of the above-described methods for evaluating transient stability of a power system are implemented.

[0032] The present invention also provides a non-transient computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the above-mentioned methods for transient stability assessment of a power system.

[0033] The power system transient stability assessment method, device, electronic device and storage medium provided by the present invention determine the graphical power system flow characteristics by comprehensively analyzing the power system flow information and the power system topology information. The power system flow characteristic diagram can simultaneously describe the energy distribution in the power system and the internal transient stability characteristics of the power system, so that the transient stability assessment model can quickly evaluate and predict the transient stability and transient stability indicators of the power system after each expected fault in the expected fault set occurs, thereby enhancing the utilization of the power system flow information. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the present invention or the prior art, a brief introduction is given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0035] Figure 1 A flow chart of the power system transient stability assessment method provided by the present invention;

[0036] Figure 2 A schematic flow chart of a method for determining a power system power flow characteristic diagram provided by the present invention;

[0037] Figure 3 A schematic diagram of the structure of the topological matrix of the power system flow characteristic diagram provided by the present invention;

[0038] Figure 4 A schematic diagram of the evaluation process of the transient stability evaluation model provided by the present invention;

[0039] Figure 5 A schematic diagram of the structure of the message generation layer provided by the present invention;

[0040] Figure 6 A schematic diagram of the structure of the node feature update layer provided by the present invention;

[0041] Figure 7 A schematic diagram of the structure of the power system transient stability assessment device provided by the present invention;

[0042] Figure 8 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0043] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0044] The machine learning methods such as data mining theory, multiple support vector machines, and tree models used in the prior art are single-input and single-output modeling methods. Given a single power flow, they cannot predict every expected fault in the expected fault set. In addition, the existing transient stability assessment model based on power flow characteristics lacks the use of power system topology information and can only complete a single task. To address this problem, the present invention provides a method for transient stability assessment of a power system. Figures 1-6 The present invention describes a method for evaluating transient stability of a power system.

[0045] Figure 1 The flow chart of the method for evaluating transient stability of a power system provided by the present invention is as follows: Figure 1 As shown, the method includes:

[0046] Step 110: Acquire power system flow information and power system topology information.

[0047] Specifically, the power system flow information includes the voltage amplitude, voltage phase angle, generator active injection power, generator reactive injection power, active load and reactive load of each bus in the power system.

[0048] Step 120 , determining a power system power flow characteristic diagram based on the power system power flow information and the power system topology information; the power system power flow characteristic diagram is a graph of power system power flow characteristics; the characteristics of the power system power flow characteristic diagram include node characteristics and topology characteristics.

[0049] Specifically, the power system has typical graph structure characteristics, and the flow characteristics can be described in the form of a graph. The power system flow characteristics are expressed as G(V,H V ,E,H E ), where V represents a set of nodes on a finite non-empty graph, The nodes in the diagram correspond to the buses of the power system one by one; V represents the node feature matrix, Among them, f v is the node feature dimension; E represents the edge set, Among them, e k = <v i ,v j > represents the slave node v i Points to node v j Directed edges, k∈[N e ],i,j∈[N v ]; H E represents the edge feature matrix, Among them, f e is the edge feature dimension.

[0050] Step 130: Input the node characteristics and topological characteristics of the power system flow characteristic diagram into the transient stability assessment model to obtain the transient stability and transient stability index of the power system after each expected fault in the expected fault set output by the transient stability assessment model; the transient stability assessment model is used to perform coupled analysis on the transient stability and transient stability index of the power system by performing feature learning on the power system flow characteristic diagram.

[0051] Specifically, for the transient stability assessment problem of power systems, it is necessary to first define the construction method of the expected fault set. For example, a three-phase short-circuit grounding fault on a busbar lasts for 0.1s and then disappears; v There are N busbars in the power system. v The expected faults are located at each node on the graph, so each node on the graph is a labeled node. Its label y contains two parts y = (y S ,yI ,y T ), where y s is a binary quantity, indicating the transient stability of the system after the expected fault; I is a real number, indicating the maximum power angle difference of the transient process of the system after the expected fault; T is a real number, indicating the time when the system will experience transient instability after the expected fault. The transient stability assessment problem based on power flow characteristics can be modeled as a node label prediction problem on the graph. The label y is obtained using the following formula (1):

[0052]

[0053] The modeling method for node label prediction aligns with the physical properties of power system transient stability analysis. Since the transient stability of a system can be considered to be affected by two types of factors—the system's internal properties and states, and external disturbance information—the power system's flow characteristics describe the current energy distribution in the system. After feature propagation on the graph, different eigenvectors are generated at different nodes due to the influence of location factors. These eigenvectors describe the system's internal transient stability characteristics and, combined with disturbance information, further generate transient stability label predictions for the current location. This method allows for rapid prediction of transient stability indicators for all anticipated faults, while also taking into account the topological characteristics of the power system and enhancing the utilization of flow information.

[0054] The method provided by the present invention determines the graphical power system flow characteristics by comprehensively analyzing the power system flow information and the power system topology information. The power system flow characteristic diagram can simultaneously describe the energy distribution in the power system and the internal transient stability characteristics of the power system, so that the transient stability assessment model can quickly evaluate and predict the transient stability and transient stability indicators of the power system after each expected fault in the expected fault set occurs, thereby enhancing the utilization of the power system flow information.

[0055] Based on the above embodiment, the transient stability index includes: the maximum power angle difference during the transient process in which the system maintains transient stability after a predicted fault, and the transient instability time after the system experiences transient instability after a predicted fault. Due to the strong correlation between power angle stability and transient stability index, both describe the transient stability characteristics of the system. Three analysis results corresponding to each predicted fault are defined:

[0056] a) Transient stability: If transient instability occurs after the anticipated fault, the transient instability classification result is output; otherwise, the transient stability classification result is output. This analysis result is a categorical variable.

[0057] b) Maximum transient power angle difference: If the system is expected to maintain transient stability after a fault, the maximum power angle difference between any two generators in the system during the transient process is calculated. This analysis result is a regression variable related to the system's transient stability margin: the smaller the maximum transient power angle difference, the further the system is from the transient stability boundary.

[0058] c) Transient instability time: If the system experiences transient instability after a predicted fault, the length of time from the occurrence of the predicted fault to the onset of transient instability. This analysis result is a regression variable related to the system's transient stability margin: a smaller value indicates that the system is further from the transient stability boundary.

[0059] The regression of the system's transient indicators is divided into two categories: the maximum power angle difference in the transient process and the transient instability time. The former fully describes the system information in the stable scenario, but is insufficient to describe the system information in the unstable scenario; the latter fully describes the system information in the unstable scenario; the two complement each other.

[0060] Based on the above embodiment, the power system flow information includes the voltage amplitude, voltage phase angle, generator active injection power, generator reactive injection power, active load and reactive load of each bus in the power system; wherein, Figure 2 The flow chart of the method for determining the power system flow characteristic diagram provided by the present invention is as follows: Figure 2 As shown, step 120 specifically includes:

[0061] Step 121 : determining node characteristics of a power system power flow characteristic diagram according to voltage amplitude, voltage phase angle, generator active injection power, generator reactive injection power, active load, and reactive load of each bus in the power system.

[0062] Specifically, the busbars in the power system are modeled as nodes on the graph, and the power system flow information in the form of nodes can be expressed as the node characteristic matrix H V , node feature matrix H V According to formula (2), a row in the matrix represents the node feature of the corresponding node:

[0063]

[0064] Among them, V i represents the voltage amplitude of bus i, θ i Indicates the voltage phase angle of bus i, PG i , QG i PL i and QL i They represent the active power injected by the generator at bus i, the reactive power injected by the generator, the active load and the reactive load respectively. If a generator is connected to bus i, then Tj irepresents the inertia time constant of the generator; otherwise, Tj i =0.

[0065] Step 122: determining the topological characteristics of the power system power flow characteristic diagram based on the node admittance matrix and the node impedance matrix of the power system.

[0066] Specifically, based on the energy transmission patterns within the power system and addressing the N-1 transient stability verification problem, we construct a topology matrix A for the power system's power flow characteristic diagram by combining the power system's node admittance matrix and node impedance matrix. The construction of topology A is described in detail below.

[0067] First, we need to Perform LU decomposition. Since the matrix Y is a complex matrix, the equations are transformed according to the correspondence between the real and imaginary parts. The transformation process refers to formula (3):

[0068]

[0069] The coefficient matrix of the transformed equation is recorded as And use formula (4) to perform LU decomposition:

[0070]

[0071] in, and It is a block sparse matrix, and the node number optimization can be improved and Sparsity; and The non-zero block size is also 2×2. and Taking the inverse, we get and Easy to know is a lower triangular matrix, are upper triangular matrices, and they are also block sparse matrices. Taking the inverse, we get

[0072] Pick The part below the diagonal line, The portion above the diagonal, and The diagonal part of composes the matrix A. Figure 3 A schematic diagram of the topological matrix of the power system flow characteristic diagram provided by the present invention is shown in FIG. Figure 3 As shown, the matrix A describes the topological structure and edge features of the power system characteristic propagation graph: Matrix A is a block sparse matrix. If the 2×2 submatrix A ijis a non-zero submatrix, which means that there is an edge i→j in the power system characteristic propagation graph, and the characteristic of this edge is A ij The 4-dimensional vector obtained after one-dimensionalization; otherwise, the edge i→j does not exist. Matrix A is divided into three parts, representing three types of edges: those falling in the lower triangle are edge type 1, those falling in the upper triangle are edge type 2, and those falling in the diagonal are edge type 3. Therefore, the power system flow characteristic diagram is a heterogeneous graph containing three types of edges and one type of node.

[0073] The method provided by the present invention can construct a complete power system flow characteristic diagram through a construction method based on node features and a construction method based on topological features. Since the direction of feature propagation on the graph is the same as the direction of the edge, and the last column and the last row of matrix A do not contain non-zero submatrices, that is, the node has a bidirectional connection with all other nodes on the graph, when feature propagation is performed on the topology described by matrix A, the connection between any two nodes on the graph is realized through the "transit function" of the node, avoiding both the locality problem of feature propagation caused by the use of the node admittance matrix and the problem of excessive computational complexity caused by the use of the node impedance matrix. On the other hand, due to the transformation relationship between matrices and the directed nature of feature propagation on the graph, stacking shallow graph convolutional networks achieves a computational effect similar to the "forward and back substitution" in power system network calculations.

[0074] Based on any one of the above embodiments, the transient stability assessment model includes: a message generation layer, a message collection layer, and a node feature update layer; wherein, the message generation layer is used to obtain the message vector of any edge of the power system flow characteristic diagram and the updated features of the edge according to the source node features, target node features and features of the edge of the edge; the message collection layer is used to determine the message vector to be received by each node on the power system flow characteristic diagram according to the message vectors of each edge and the features of each edge on the power system flow characteristic diagram; the node feature update layer is used to update the node features of each node on the power system flow characteristic diagram according to the message vector to be received by each node on the power system flow characteristic diagram. Wherein, Figure 4 This is a schematic diagram of the evaluation process of the transient stability evaluation model provided by the present invention, as shown in FIG. Figure 4 As shown, step 130 specifically includes:

[0075] Step 131 : Obtain a message vector of an edge and updated edge features according to the source node features, target node features, and edge features of any edge in the power system power flow characteristic diagram.

[0076] Specifically, the message generation layer is used to obtain a message vector for any edge in the power system flow characteristic diagram and the updated characteristics of the edge based on the source node characteristics, target node characteristics, and characteristics of the edge. For each edge in the power system flow characteristic diagram, the message generation layer generates corresponding message content. Figure 5 The structural diagram of the message generation layer provided by the present invention is as follows: Figure 5 As shown in Figure 2, a message generation layer M(·) is constructed based on a multi-layer neural network, where the message module (Message Tower) and the edge module (Edge Tower) are multi-layer fully connected neural networks. To sum a vector, is the Hadamard product. The module input includes the source node features Target node characteristics and the characteristics of the edge from the source node to the target node The module output is a message vector and edge features Specific steps may include:

[0077] 1) Calculate and concatenate vectors Among them, cos d Represents the cosine similarity calculation function. This vector is input into the message module of the message generation layer to obtain the initial message vector.

[0078] 2) Input to the edge module of the message generation layer to generate new edge features

[0079] 3) Calculation The Hadamard product of the initial message vector and the message vector is obtained

[0080] Among them, since there are three types of edges in the graph, type 1 and type 2 use the same message module, denoted as M1; the message module used by type 3 is denoted as M2; type 1, type 2 and type 3 each use different edge modules, denoted as E1, E2 and E3.

[0081] Step 132 : determining a message vector to be received by each node on the power system power flow characteristic diagram according to the message vector of each edge on the power system power flow characteristic diagram and the characteristics of each edge.

[0082] The message collection layer is used to determine the message vector to be received by each node on the power system flow characteristic diagram based on the message vector of each edge and the characteristics of each edge on the power system flow characteristic diagram. The message collection layer collects all messages to be received by each node for all nodes on the diagram.

[0083] Optionally, the message collection layer uses the out-degree of the source node and the in-degree of the target node of each edge on the power system flow characteristic diagram to scale the message vector of each edge to obtain the message vector to be received by each node on the power system flow characteristic diagram. For example, the message vector to be received by node v can be calculated using formula (5):

[0084]

[0085] Among them, N(v) is the set of neighbor nodes of node v, is the out-degree of node u, is the in-degree of node v. Scaling the message vector using the in-degree can avoid the inconsistent feature variances between nodes on the graph due to the difference in in-degree and out-degree.

[0086] Step 133 : updating the node characteristics of each node on the power system power flow characteristic diagram according to the message vector to be received by each node on the power system power flow characteristic diagram, and obtaining the updated node characteristics of each node.

[0087] The node feature update layer is used to update the node features of each node on the power system flow feature diagram according to the message vector to be received by each node on the power system flow feature diagram, and generate new node features. Figure 6 This is a schematic diagram of the structure of the node feature update layer provided by the present invention, and the node feature update function U(·) is as follows Figure 6 In the neural network shown, since only one type of node exists on the power system flow characteristic graph, all nodes share the same application module (ApplyTower). The message generation process is an edge-wise operation, while the message collection and node feature update process are node-wise operations. It should be noted that the node feature update layer not only updates the node features on the graph, but also the edge features on the graph. This allows the transient stability assessment model to have stronger feature expression capabilities.

[0088] Step 134 : determining the transient stability and transient stability index of the power system after each anticipated fault in the anticipated fault set occurs based on the updated edge characteristics and the updated node characteristics of each node.

[0089] The method provided by the present invention can simultaneously describe the energy distribution in the power system and the internal transient stability characteristics of the power system by comprehensively analyzing the graphical power system flow characteristics determined by the power system flow information and the power system topology information. When the transient stability evaluation model is used to perform feature learning on the power system flow characteristic diagram, the transient stability and transient stability index of the power system after each expected fault in the expected fault set can be quickly evaluated and predicted, thereby enhancing the utilization of the power system flow information.

[0090] The power system transient stability assessment device provided by the present invention is described below. The power system transient stability assessment device described below and the power system transient stability assessment method described above can refer to each other.

[0091] Based on any of the above embodiments, Figure 7 This is a schematic diagram of the structure of the power system transient stability assessment device provided by the present invention, as shown in FIG. Figure 7 As shown, the device includes an acquisition unit 710, a determination unit 720 and a transient stability assessment unit 730; wherein,

[0092] An acquisition unit 710 is configured to acquire power system flow information and power system topology information;

[0093] A determining unit 720 is configured to determine a power system power flow characteristic diagram based on the power system power flow information and the power system topology information; the power system power flow characteristic diagram is a graph of power system power flow characteristics; and the characteristics of the power system power flow characteristic diagram include node characteristics and topology characteristics.

[0094] The transient stability assessment unit 730 is used to input the node characteristics and topological characteristics of the power system flow characteristic diagram into the transient stability assessment model to obtain the transient stability and transient stability index of the power system after each expected fault in the expected fault set output by the transient stability assessment model occurs; the transient stability assessment model is used to perform coupled analysis on the transient stability and transient stability index of the power system by performing feature learning on the power system flow characteristic diagram.

[0095] The device provided by the present invention determines the graphical power system flow characteristics by comprehensively analyzing the power system flow information and the power system topology information. The power system flow characteristic diagram can simultaneously describe the energy distribution in the power system and the internal transient stability characteristics of the power system, so that the transient stability assessment model can quickly evaluate and predict the transient stability and transient stability indicators of the power system after each expected fault in the expected fault set occurs, thereby enhancing the utilization of the power system flow information.

[0096] Based on any of the above embodiments, the transient stability assessment unit 730 includes:

[0097] a message generating subunit, configured to obtain a message vector of any edge of the power system power flow characteristic diagram and an updated feature of the edge according to the source node feature, the target node feature, and the feature of the edge;

[0098] a message collecting subunit, configured to determine a message vector to be received by each node on the power system power flow characteristic diagram according to the message vector of each edge on the power system power flow characteristic diagram and the characteristics of each edge;

[0099] a node feature updating subunit, configured to update the node features of each node on the power system power flow feature diagram according to the message vector to be received by each node on the power system power flow feature diagram, and obtain updated node features of each node;

[0100] The evaluation subunit is used to determine the transient stability and transient stability index of the power system after each expected fault in the expected fault set occurs based on the updated characteristics of the edge and the updated node characteristics of each node.

[0101] Based on any of the above embodiments, the message collection subunit uses the out-degree of the source node and the in-degree of the target node of each edge on the power system flow characteristic diagram to scale the message vector of each edge to obtain the message vector to be received by each node on the power system flow characteristic diagram.

[0102] Based on any of the above embodiments, the transient stability index includes: a maximum power angle difference during a transient process in which the system maintains transient stability after an anticipated fault, and a transient instability time during which the system experiences transient instability after an anticipated fault.

[0103] Based on any of the above embodiments, the power system flow information includes the voltage amplitude, voltage phase angle, generator active injection power, generator reactive injection power, active load, and reactive load of each bus in the power system; the determining unit 720 includes:

[0104] a node feature determination subunit, configured to determine the node features of the power system power flow characteristic diagram according to the voltage amplitude, voltage phase angle, generator active injection power, generator reactive injection power, active load, and reactive load of each bus in the power system;

[0105] The topology feature determination subunit is used to determine the topology features of the power system power flow characteristic diagram according to the node admittance matrix and the node impedance matrix of the power system.

[0106] Figure 8 An example of a physical structure diagram of an electronic device is shown below. Figure 8As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830, and a communication bus 840, wherein the processor 810, the communication interface 820, and the memory 830 communicate with each other via the communication bus 840. The processor 810 may call logic instructions in the memory 830 to execute a power system transient stability assessment method, the method comprising: obtaining power system flow information and power system topology information; determining a power system flow characteristic diagram based on the power system flow information and the power system topology information; the power system flow characteristic diagram is a graph of power system flow characteristics; the characteristics of the power system flow characteristic diagram include node characteristics and topology characteristics; inputting the node characteristics and topology characteristics of the power system flow characteristic diagram into a transient stability assessment model to obtain the transient stability and transient stability index of the power system after each expected fault in the expected fault set output by the transient stability assessment model; the transient stability assessment model is used to perform coupled analysis on the transient stability and transient stability index of the power system by learning the characteristics of the power system flow characteristic diagram.

[0107] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0108] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transient computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the power system transient stability assessment method provided by the above methods, the method including: obtaining power system flow information and power system topology information; determining a power system flow characteristic diagram based on the power system flow information and the power system topology information; the power system flow characteristic diagram is a graphical form of power system flow characteristics; the characteristics of the power system flow characteristic diagram include node characteristics and topology characteristics; the node characteristics and topology characteristics of the power system flow characteristic diagram are input into a transient stability assessment model to obtain the transient stability and transient stability index of the power system after each expected fault in the expected fault set output by the transient stability assessment model; the transient stability assessment model is used to perform coupling analysis on the transient stability and transient stability index of the power system by performing feature learning on the power system flow characteristic diagram.

[0109] On the other hand, the present invention also provides a non-transient computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the power system transient stability assessment method provided in the above-mentioned embodiments, the method comprising: obtaining power system flow information and power system topology information; determining a power system flow characteristic diagram based on the power system flow information and the power system topology information; the power system flow characteristic diagram is a graph of power system flow characteristics; the characteristics of the power system flow characteristic diagram include node characteristics and topology characteristics; the node characteristics and topology characteristics of the power system flow characteristic diagram are input into a transient stability assessment model to obtain the transient stability and transient stability index of the power system after each expected fault in the expected fault set output by the transient stability assessment model; the transient stability assessment model is used to perform coupling analysis on the transient stability and transient stability index of the power system by performing feature learning on the power system flow characteristic diagram.

[0110] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0111] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.

[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A method for evaluating transient stability of a power system, characterized in that: include: Obtain power system flow information and power system topology information; According to the power system flow information and the power system topology information, a power system flow characteristic diagram is determined; the power system flow characteristic diagram is a graph of the power system flow characteristics; the power system flow characteristics are expressed as G(V,H V ,E,H E ) represents, V represents the set of nodes on a finite non-empty graph, H V represents the node feature matrix, E represents the edge set, H E represents an edge feature matrix; the features of the power system flow characteristic diagram include node features and topological features; The node characteristics and topological characteristics of the power system flow characteristic diagram are input into the transient stability assessment model to obtain the transient stability and transient stability index of the power system after each expected fault in the expected fault set output by the transient stability assessment model; the transient stability assessment model is used to perform coupling analysis on the transient stability and transient stability index of the power system by performing feature learning on the power system flow characteristic diagram; the transient stability assessment model includes a message generation layer, a message collection layer and a node feature update layer.

2. The method for evaluating transient stability of a power system according to claim 1, wherein: The step of inputting the node characteristics and topological characteristics of the power system flow characteristic diagram into the transient stability assessment model to obtain the transient stability and transient stability index of the power system after each expected fault in the expected fault set output by the transient stability assessment model occurs includes: Obtaining a message vector of any edge of the power system power flow characteristic diagram and an updated feature of the edge according to the source node feature, the target node feature, and the feature of the edge; determining, based on the message vectors of each edge on the power system power flow characteristic diagram and the characteristics of each edge, a message vector to be received by each node on the power system power flow characteristic diagram; updating node characteristics of each node on the power system power flow characteristic diagram according to the message vector to be received by each node on the power system power flow characteristic diagram to obtain updated node characteristics of each node; According to the updated characteristics of the edges and the updated node characteristics of each node, the transient stability and transient stability index of the power system after each expected fault in the expected fault set occurs are determined.

3. The method for evaluating transient stability of a power system according to claim 2, wherein: The determining, based on the message vectors of the edges on the power system flow characteristic diagram and the characteristics of the edges, the message vectors to be received by the nodes on the power system flow characteristic diagram includes: The message vector of each edge on the power system flow characteristic diagram is scaled using the out-degree of the source node and the in-degree of the target node to obtain the message vector to be received by each node on the power system flow characteristic diagram.

4. The method for evaluating transient stability of a power system according to claim 1, wherein: The transient stability index includes: the maximum power angle difference during the transient process in which the system maintains transient stability after the anticipated fault, and the transient instability time during which the system experiences transient instability after the anticipated fault.

5. The method for evaluating transient stability of a power system according to claim 1, wherein: The power system flow information includes the voltage amplitude, voltage phase angle, generator active injection power, generator reactive injection power, active load and reactive load of each bus in the power system; The determining of a power system power flow characteristic diagram according to the power system power flow information and the power system topology information includes: Determining node characteristics of the power system power flow characteristic diagram according to the voltage amplitude, voltage phase angle, generator active injection power, generator reactive injection power, active load and reactive load of each bus in the power system; The topological characteristics of the power system power flow characteristic diagram are determined according to the node admittance matrix and the node impedance matrix of the power system.

6. A power system transient stability assessment device, characterized in that: include: an acquisition unit, used for acquiring power system flow information and power system topology information; The determining unit is used to determine a power system power flow characteristic diagram according to the power system power flow information and the power system topology information; the power system power flow characteristic diagram is a power system power flow characteristic in a graphical form; the power system power flow characteristic is represented by G(V,H V ,E,H E ) represents, V represents the set of nodes on a finite non-empty graph, H V represents the node feature matrix, E represents the edge set, H E represents an edge feature matrix; the features of the power system flow characteristic diagram include node features and topological features; A transient stability assessment unit is used to input the node characteristics and topological characteristics of the power system flow characteristic diagram into a transient stability assessment model to obtain the transient stability and transient stability index of the power system after each expected fault in the expected fault set output by the transient stability assessment model occurs; the transient stability assessment model is used to perform coupled analysis on the transient stability and transient stability index of the power system by performing feature learning on the power system flow characteristic diagram; the transient stability assessment model includes a message generation layer, a message collection layer and a node feature update layer.

7. The power system transient stability assessment device according to claim 6, characterized in that: The transient stability assessment unit includes: a message generating subunit, configured to obtain a message vector of any edge of the power system power flow characteristic diagram and an updated feature of the edge according to the source node feature, the target node feature, and the feature of the edge; a message collecting subunit, configured to determine a message vector to be received by each node on the power system power flow characteristic diagram according to the message vector of each edge on the power system power flow characteristic diagram and the characteristics of each edge; a node feature updating subunit, configured to update the node features of each node on the power system power flow feature diagram according to the message vector to be received by each node on the power system power flow feature diagram, and obtain updated node features of each node; The evaluation subunit is used to determine the transient stability and transient stability index of the power system after each expected fault in the expected fault set occurs based on the updated characteristics of the edge and the updated node characteristics of each node.

8. The power system transient stability assessment device according to claim 7, characterized in that: The message collection subunit uses the out-degree of the source node and the in-degree of the target node of each edge on the power system flow characteristic diagram to scale the message vector of each edge to obtain the message vector to be received by each node on the power system flow characteristic diagram.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the steps of the power system transient stability assessment method according to any one of claims 1 to 5 are implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the power system transient stability assessment method according to any one of claims 1 to 5 are implemented.

Images