Power system security device action scheme generation method, device, equipment and storage medium

Abstract

The application discloses a power system protection device action scheme generation method, device and equipment and a storage medium. The method comprises the following steps: based on the key attributes of various types of participating devices of a power system, a device attribute vector is constructed, and the device attribute vector is converted into a device representation vector through a device representation network; based on the device representation vector, a fault representation vector is constructed through aggregation, splicing and multilayer perception machine processing; according to the topological structure of the device network of the power system, a device topology graph is constructed, an isolated fault node is added, and the device representation vector and the fault representation vector are used as node attributes; the link relationship between the fault node and the device node is predicted through a multilayer message propagation network and a link prediction network, and the link relationship is converted into a protection device action scheme after a fault occurs. The application learns and mines the implicit correlation between the fault and the device from historical data, generates the protection device action scheme, and thus realizes the intelligentization and rapidization of the protection device action scheme of a large-scale power system.

Description

Technical Field

[0001] The present invention relates to the field of power systems, and in particular to a method, device, equipment and storage medium for generating an action plan for a large-scale power system anticipated fault safety device. Background Art

[0002] As the green and low-carbon transformation of the power industry accelerates and the proportion of installed renewable energy capacity continues to rise, safety and control strategies for large-scale power systems are facing new challenges. The introduction of large-scale renewable energy into the power system, coupled with the integration of an increasing number of flexible loads, has led to a dramatic increase in uncertainty affecting the power system, exponentially increasing the number of operational scenarios that need to be evaluated for online and offline scheduling plans. Furthermore, the set of anticipated faults in large-scale power networks is enormous. Detailed time-domain simulations make it difficult to quickly calculate safety and control device action plans for all anticipated faults, hindering timely assessment of system operational safety risks. Therefore, with the growing scale of renewable energy installed capacity and the gradual expansion of power generation, the challenge of intelligently and rapidly generating safety and control device action plans for large-scale power systems has become a pressing issue.

[0003] Current industrial approaches to generating action plans for safety and automatic devices rely on computationally intensive simulation systems. These methods are slow to solve in large-scale power systems and difficult to apply online in real time. Furthermore, as system scale expands and the number of potentially faulty components increases, the number of device states increases exponentially, leading to excessive computational time or even inability to solve. Furthermore, the increasing penetration of renewable energy sources complicates simulation modeling, further increasing computational overhead. While machine learning-based approaches have been explored in recent years, they remain limited by several key challenges. First, they fail to effectively leverage the power system's topology and exploit the complex dependencies inherent in devices. Second, they fail to consider how to unify the heterogeneous attribute information of different types of equipment in the power system, lacking a bird's-eye view of the relationships between operating generators, loads, and other related equipment, resulting in a lack of flexibility and scalability. Finally, most proposed methods have been tested only on small-scale power simulation models and have not been validated in modern industrial environments. Therefore, their reliability requires further verification.

[0004] Therefore, a method for generating action plans for anticipated fault safety devices in large-scale power systems is needed to realize the intelligent and rapid generation of action plans for safety devices in power systems. Summary of the Invention

[0005] The application aims to overcome the shortcomings of the existing generator scheme generation algorithm, and provides a power system self-restoration device action scheme generation method, device, equipment and storage medium to solve the problem of large time consumption in large-scale power system in the prior art.

[0006] Technical scheme: To achieve the above-mentioned purpose, the power system self-restoration device action scheme generation method provided by the application comprises the following steps:

[0007] Obtain the key attributes of each participating device in the power system, and combine them into a device attribute vector;

[0008] Input the device attribute vector into the device representation network, and obtain a device representation vector with the same length and unified semantics through convolution operation;

[0009] Aggregate all device representation vectors of the same category into a category representation vector representing the overall features of all devices in the category, splice the category representation vectors of all categories, and input them into a multilayer perception machine to obtain one or more fault representation vectors for representing the power system state information that needs to be focused on after the expected fault occurs;

[0010] According to the device association structure in the power system, a corresponding topology graph is constructed, and a number of isolated fault nodes equal to the number of fault representation vectors are added, and the device representation vector and the fault representation vector are used as node attributes to obtain the node attribute matrix X and the adjacency matrix A of the topology graph;

[0011] Using the node attribute matrix X and the adjacency matrix A of the topology graph, a node embedding vector is obtained through a multi-layer message propagation network;

[0012] Based on the node embedding vector, the device nodes belonging to the self-restoration device and the fault nodes are spliced two by two to obtain a synthetic embedding vector, which is input into a node pair link prediction network to obtain a link relationship prediction result between nodes;

[0013] According to the link relationship prediction result between nodes, the device nodes belonging to the self-restoration device and having a link relationship with a certain fault node are collected as a node set, and the devices included in the set are the devices required to be operated after the corresponding fault occurs, and the above operation is performed on each fault node to obtain a target operation device set for each fault, which is the self-restoration device action scheme required after the occurrence of these faults.

[0014] The device representation network, multi-layer perceptron, multi-layer message propagation network, and node-to-link prediction network constitute an end-to-end model of the system. The model is trained using a target equation using a pre-collected data set. The purpose of training is to minimize the loss calculated by the target equation. Each sample in the data set includes the key attributes of each device involved in the power system, the device association structure of the power system, and the safety and automatic device action plan corresponding to each fault.

[0015] The objective equation used in model training is expressed as:

[0016]

[0017] Where l represents the loss function, N f is the number of possible fault types in the power system, N c is the number of equipment in the power system that belongs to the safety device. is the predicted probability that there is a link relationship between the fault node i and the device j belonging to the safety device, y i,j Indicates whether fault type i in the data set requires operation of device j belonging to the safety device. If operation is required, it is 1, otherwise it is 0.

[0018] The calculation method of the multi-layer message propagation network is:

[0019]

[0020] Where σ(·) represents the activation function, || represents the concatenation operation, represents the aggregation function, N(i) represents the set of neighbor nodes of node i, represents the embedding vector of node i after k rounds of message propagation, W (k) represents the learnable parameters in the kth round of message passing.

[0021] The device representation network consists of convolutional layers and fully connected layers. The convolutional layer composed of multiple 1×1 convolution kernels is used to process the attribute vector into vectors of the same length.

[0022] The node attribute matrix X is a shape of (N e +N f )×D two-dimensional matrix, where N e is the number of devices in the power system, N f is the number of possible fault types in the power system, and D is the length of the device representation vector.

[0023] The adjacency matrix A is a (N e +N f )×(N e +N f), each row represents the relationship between a device or faulty node and other devices or faulty nodes. The values ​​of the matrix elements are 0 or 1. When there is a link relationship between the i-th node and the j-th node, the adjacency matrix A in A ij is equal to 1, otherwise it is equal to 0.

[0024] The present invention provides a device for generating an action plan for a power system safety device, comprising:

[0025] The device attribute vector construction module obtains the key attributes of each device involved in the power system and combines them into an attribute vector;

[0026] The device representation vector construction module inputs the device attribute vector into the device representation network and obtains the device representation vector of the same length and unified semantics through convolution operation;

[0027] The fault representation vector construction module aggregates all device representation vectors of the same category into a category representation vector, which represents the overall characteristics of all devices in that category. The category representation vectors of all categories are then concatenated and input into a multi-layer perceptron to generate one or more fault representation vectors, which represent the power system status information that requires attention after a predicted fault occurs.

[0028] The device topology construction module constructs a corresponding topology based on the device association structure in the power system and adds isolated fault nodes equal to the number of fault representation vectors. The device representation vectors and fault representation vectors are used as node attributes to obtain the node attribute matrix X and adjacency matrix A of the topology.

[0029] The node embedding vector construction module uses the node attribute matrix X and the adjacency matrix A of the topological graph to obtain the node embedding vector through a multi-layer message propagation network;

[0030] The link prediction module, based on the node embedding vector, concatenates the device nodes belonging to the safety and automation device and the fault nodes in pairs to obtain a synthetic embedding vector, which is input into the node pair link prediction network to obtain the link relationship prediction result between the nodes;

[0031] The automatic safety device action plan generation module collects the device nodes belonging to the automatic safety device that have a link relationship with a certain fault node into a node set based on the link relationship prediction results between nodes. The devices included in the set are the devices that need to be operated after the corresponding fault occurs. The above operations are performed on each fault node to obtain the target operation device set for each fault, which is the automatic safety device action plan required after these faults occur.

[0032] The present invention provides a computer device comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, and when the programs are executed by the processors, the steps of the method for generating an action plan for an electric power system safety device are implemented as described above.

[0033] The present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the method for generating an action plan for a power system safety device as described above are implemented.

[0034] Beneficial effects:

[0035] (1) This paper proposes, for the first time, a method for converting the problem of generating action plans for safety and automation devices in power systems into a link prediction problem in a graph neural network. It also designs an end-to-end generation method for safety and automation device action plans based on a graph neural network. The device association structure of a power system has a significant impact on the operation and analysis of the power system. This model converts the device association structure of the power system into a topological graph, fully exploring and capturing the complex implicit dependencies between different devices. This solves the problem that previous learning-based algorithms ignored the link relationships between nodes.

[0036] (2) In the process of constructing the device representation vector, the convolution kernel with shared weights is used to semantically unify the device attribute vectors of different types and lengths, and the originally heterogeneous node information reflecting the current status, operating conditions and performance parameters of various types of equipment is converted into device representation vectors with the same length and expression. This solves the difficulties in data information understanding and data alignment caused by the heterogeneity of power system equipment data, and unifies the prediction methods of equipment belonging to safety devices such as operating generator equipment, load equipment, and parallel capacitor / reactor equipment, thereby improving the flexibility of the model.

[0037] (3) The present invention connects a series of processes such as device representation vector construction, fault representation vector construction, and node embedding vector construction in series, and directly predicts the link relationship between two nodes end to end, reducing the data, computing power, and time overhead of the entire network training process, improving the efficiency of mining the valuable information contained in massive historical power system status data, and making the generation of safety and self-driving device action plans faster and more accurate. After sufficient training, this method can be deployed on existing consumer-grade central processing units and graphics cards to have a millisecond-level safety and self-driving device action plan generation speed, and efficiently generate safety control measures for large-scale power systems, solving the problem of high computational overhead of traditional methods in large-scale power systems under the background of increasing installed capacity of high-energy and new energy. The method of the present invention was tested in real, specific scenarios in the industry, such as the data of the Northwest China Power System. The accuracy of the algorithm prediction met the use requirements, and achieved good results in the algorithm risk analysis and evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a flow chart of a method for generating an action plan for a large-scale power system with high renewable energy penetration rate according to the present invention;

[0039] Figure 2 is a flow chart of the apparatus of the present invention representing the vector generation phase;

[0040] Figure 3 is a flow chart of the fault representation vector generation phase of the present invention;

[0041] Figure 4 It is a diagram of the message propagation calculation method of a single node in the multi-layer propagation network of the present invention. DETAILED DESCRIPTION

[0042] The present invention will be further described below with reference to the accompanying drawings.

[0043] The present invention proposes a method for generating an action plan for a large-scale power system anticipatory fault safety device. Figure 1 As shown in the figure, this method generates an action plan for the safety and automatic device based on the key attributes of the power system's participating devices and the power system's topology through a series of computational processes. Regarding data flow, this method first constructs the key attributes of the power system's participating devices into device attribute vectors. Second, through a device representation network, these device attribute vectors are converted into device representation vectors of the same length and semantically unified. The device representation vectors are then aggregated and concatenated according to device category and input into a multi-layer perceptron to obtain a fault representation vector. A device topology graph is then constructed based on the device representation vectors, fault representation vectors, and the power system's topology. Finally, a multi-layer message propagation network and link prediction network are used to predict the link relationship between the fault node and the device nodes belonging to the safety and automatic device, generating an action plan for the safety and automatic device.

[0044] Based on the logic of data flow, this method can be broken down into three stages: device representation vector generation, fault representation generation, and graph neural link prediction. The device representation vector generation stage converts the key attributes of power system equipment into device attribute vectors, which are then input into the device representation network to obtain the device representation vector. The fault representation vector generation stage aggregates and concatenates the device representation vectors and inputs them into a multi-layer perceptron to obtain the fault representation vector. The graph neural link prediction stage uses the power system equipment association structure to construct a device topology graph, with node attributes being device representation vectors and fault representation vectors. The safety and automatic device action plan is then generated based on the outputs of the multi-layer message propagation network and link prediction network. All three stages contain learnable parameters, which are initialized using random data. Appropriate parameters are learned during the training step. After training, the parameters are fixed, and the learned parameters are used to predict the safety and automatic device action plan in subsequent use.

[0045] Specifically, the process of the device representation vector generation phase of the method is as follows Figure 2 As shown, the following steps are included:

[0046] (11) Device attribute vector construction steps.

[0047] The goal of this step is to obtain a naive vector description of the devices in the power system. These vectors contain information about the devices' operating status within the power system and are closely related to the operation of the entire system. Large-scale power systems incorporating renewable energy sources contain a wide range of devices, including but not limited to generators, loads, buses, AC lines, transformers, DC systems, series compensators, and shunt capacitors / reactors. Each device has distinct attribute values. Despite the diverse range of device attributes, only a subset, referred to as key attributes, are closely related to power system operation. The device attribute vector constructed in this step consists solely of these key attributes, as redundant attributes can interfere with the performance of deep learning models. To this end, the corresponding key attributes must be selected from the various devices and combined into a device attribute vector. This combination is accomplished by arranging the key attributes of each device into a vector in a fixed order. Key attributes vary between different device categories. For example, key attributes for generators include but are not limited to active power, reactive power, and voltage, while key attributes for series compensators include but are not limited to head-end active power, head-end reactive power, end-end active power, and end-end reactive power.

[0048] (12) Device representation vector construction step.

[0049] The purpose of this step is to convert the naive device attribute vectors with different lengths and different semantic representations into comprehensive device representation vectors with the same length and unified semantics. The device attribute vector simply arranges the key attributes and does not have comprehensive expression capabilities. At the same time, due to the variety of device categories, the number of their key attributes and the physical quantities they represent are also inconsistent, resulting in uneven lengths of the device attribute vectors and different semantics of the vector numerical representations at the same position. In this step, a device representation network is used to convert the device attribute vectors into device representation vectors. The device representation network consists of a convolutional layer composed of multiple 1×1 convolution kernels and multiple fully connected layers. In one embodiment of the present method, the convolutional layer of the device representation network contains 128 1×1 convolution kernels, and the fully connected layer has 3 layers. The input and output dimensions of each fully connected layer are 128, and a rectified linear unit is connected to the tail end as an activation function. The calculation formula of the convolutional layer is Where x is the input vector, y is the output vector, W and b are learnable parameters, and C r is the number of convolution kernels, C l is the length of the input vector, and ★ is the cross-correlation operator. The calculation formula of the fully connected layer is y=σ(xW T +b), where x is the input vector, y is the output vector, W and b are learnable parameters, and σ(·) is the activation function.

[0050] The process of the fault representation vector generation phase of the method is as follows Figure 3 As shown, the following steps are included:

[0051] (21) Device representation vector aggregation step.

[0052] The purpose of this step is to obtain the aggregate representation vector of each category of devices. Although the device representation vectors are semantically unified, the device representation vectors of the same category of devices will be more closely related because their original physical quantities have the same meaning. In order to utilize the category relationship of the device representation vectors, fuse and extract their associated information, and reduce the dimension of the vectors, this step performs an aggregation operation on the device representation vectors. The specific aggregation operation can include but is not limited to additive aggregation. Average Aggregation Maximum aggregation max n x i , where n is the number of vectors, x i is the i-th vector, and the length of the vector before and after the aggregation operation remains the same. In one embodiment of the method, the aggregation operation uses additive aggregation.

[0053] (22) The device represents the vector concatenation operation.

[0054] The purpose of this step is to convert the aggregated representation vectors of multiple device categories into a single vector. The specific method of the splicing operation is to connect the multiple vectors in order, head to tail. This way, even if the vectors to be spliced ​​come from different device categories, the single vector will not lose information.

[0055] (23) Fault representation vector generation step.

[0056] The purpose of this step is to convert the concatenated vectors into several fault representation vectors, whose length matches that of the device representation vectors. The fault representation vectors represent the power system state information that requires attention after a predicted fault occurs. Therefore, they can be calculated from the power grid state information. Since the power system state is determined by the device state, the aggregation and concatenation of all device representation vectors contain all the information required for calculation, allowing the fault representation vector to be calculated. It is important to note that the device representation vectors, after being aggregated and concatenated and then input into the multilayer perceptron for "calculation," can be converted into fault representation vectors; they do not simply aggregate and concatenate to form fault representation vectors. The number of fault representation vectors is the same as the number of faults in the predicted power system fault set to be focused on. For example, if the predicted fault set consists of 20 DC bipolar blocking faults on the power lines, 20 fault representation vectors are generated in this step, each corresponding to one of these faults. The multilayer perceptron is a basic structure in deep learning. It has a simple structure and provides nonlinear mapping and learnable parameters. It maps a set of input vectors to a set of output vectors, and each node in it is a neuron with a nonlinear activation function. It is suitable here to nonlinearly map the "power system status" represented by the device representation vector to "the power system status information that needs to be paid attention to after this type of fault occurs." The way to adjust the number of fault representation vectors generated is to adjust the output channel size of the multilayer perceptron. The number of output channels is the number of fault representation vectors generated. In one embodiment of the present method, the multilayer perceptron has 3 layers, and the dimensions of each layer are 512, 256 and 128 respectively, and the rectified linear unit is used as the activation function of the multilayer perceptron.

[0057] The process of the graph neural link prediction phase of the method specifically includes the following steps:

[0058] (31) Steps for constructing device topology map.

[0059] The purpose of this step is to create a topological graph structure and organize the device representation vectors and fault representation vectors in the format of graph data. The link relationship of the device nodes in the graph data is mapped to the corresponding topological graph according to the device association structure in the power system, and then a number of isolated fault nodes equal to the number of fault representation vectors are added to the topological graph. The device association structure refers to the association relationship between different devices, and the device topology structure, device type relationship, device subnet link structure, etc. in the power system can be used, or a customized device complete graph structure, device group link structure, etc. can be used. In one embodiment of the present method, the device association structure uses the type relationship of the device, that is, according to the type of the device, devices of the same type are linked to each other, in order to improve the efficiency of information exchange within the type. In this way, a topological graph consisting of device nodes and fault nodes is obtained.

[0060] The specific mathematical form of the topological graph is composed of the node attribute matrix X and the adjacency matrix A. The node attribute matrix X is a shape of (N e +N f )×D two-dimensional matrix, where N e is the number of devices in the power system, N f Is the number of possible fault types in the power system. Each column of the matrix is ​​the corresponding device representation vector or fault representation vector. Therefore, D is the length of the device representation vector or fault representation vector. According to the above steps, the length of the device representation vector and the fault representation vector are equal. The adjacency matrix A is a (N e +N f )×(N e +N f ), each row represents the relationship between a device or fault node and other devices or fault nodes. The current topology diagram only has links between devices and device nodes, indicating the topological association of the corresponding devices in the power system. The values ​​of the matrix elements are 0 or 1. The construction method is that when there is a link relationship between the i-th node and the j-th node, let A in the adjacency matrix A be ij is equal to 1, otherwise it is equal to 0.

[0061] (32) Node embedding vector construction step.

[0062] The purpose of this step is to fully explore the complex implicit associations between nodes based on the device topology graph constructed in the previous step, thereby creating a more expressive node embedding vector. This step uses a multi-layer message propagation network to utilize the structural characteristics of the device topology graph. Its input is the node attribute matrix X and the adjacency matrix A. The multi-layer message propagation network requires multiple message propagation processes, and each message propagation requires the participation of all nodes. The message propagation process of a single node is as follows: Figure 4As shown in the figure, node 0 needs to do a k-th layer message propagation, and its neighbor nodes include node 1, node 2, node 3, and node 4. First, get the k-1 layer message propagation results of the neighbor nodes Then use the aggregation function to aggregate them. In one embodiment of this method, the addition aggregation function is used. Then the aggregation result is combined with the k-1 layer message propagation result of node 0. Perform the splicing operation and finally input it into the fully connected layer to obtain the k-layer message propagation result of node 0 The fully connected layer contains learnable parameters. The starting point of the node iteration is the message propagation result of the 0th layer. It is the attribute vector of the node, that is, the column vector corresponding to the node in the node attribute matrix X.

[0063] The calculation formula of the multi-layer message propagation network is: Where σ(·) represents the activation function, || represents the concatenation operation, represents the aggregation function, N(i) represents the set of neighbor nodes of node i, represents the embedding vector of node i after k rounds of message propagation, W (k) represents the learnable parameters in the kth round of message passing, which will be adjusted during the model training step.

[0064] (33) Link prediction step.

[0065] The purpose of this step is to predict the link relationship between the device node and the faulty node. When constructing the topology graph, the faulty node is added to the graph as an isolated node. Therefore, in the initial state, the faulty node has no link relationship with all devices. Therefore, the link prediction network is used here to predict the link relationship between the faulty node and the device node belonging to the safety and self-service device. The link prediction network consists of a fully connected layer and an exponential normalization layer with a temperature hyperparameter. The input is obtained by concatenating the node embedding vectors of a pair of nodes. Here, a pair of nodes refers to the faulty node and the device node belonging to the safety and self-service device. The fully connected layer contains learnable parameters and outputs a vector of length 2, which is provided to the exponential normalization layer with a temperature hyperparameter. The exponential normalization layer with a temperature hyperparameter is calculated as follows: where z i is each element of the input vector, T is the temperature hyperparameter, and p i Is the probability that there is a link relationship between the node pairs. If the probability is greater than 0.5, then it is predicted that there is a link relationship between the node pairs, otherwise it is predicted that there is no link relationship.

[0066] (34) Steps for generating an automatic device action plan.

[0067] The purpose of this step is to generate an action plan for the automated safety device based on the link relationship between the faulty node and the device nodes belonging to the automated safety device. For any faulty node, the device nodes belonging to the automated safety device that are linked to it are collected into a node set. After the fault occurs, the device that needs to be operated is the device set corresponding to this node set.

[0068] The three stages of the present invention all contain learnable parameters and need to be trained before they can be used. After the training is completed, the corresponding learnable parameters are fixed, and the subsequent self-device action plan can be used to generate tasks. This method proposes an end-to-end model, which means that the device representation network, multi-layer perceptron, multi-layer message propagation network, and node-to-link prediction network involved in the three stages are trained simultaneously and do not need to be trained separately, which is beneficial to the robustness of the model and the economy of training. In the initial state, the learnable parameters of the three stages are initialized with random numbers and trained using the gradient descent method. A round of training process includes two stages: forward propagation and back propagation, where the loss function used in the forward propagation is where N f is the number of possible fault types in the power system, N c is the number of equipment in the power system that belongs to the safety device. is the predicted probability that there is a link relationship between the fault node i and the device node j belonging to the safety device, y i,j Indicates whether fault type i in the dataset requires action on device j belonging to the safety device. If action is required, the value is 1; otherwise, the value is 0. Backward propagation uses the gradients obtained during the forward propagation calculation to adjust the learnable parameters. In one embodiment of the present invention, the number of training rounds is 1000, the learning rate is 0.0001, and the Adam optimizer is used.

[0069] The model training step uses a pre-collected data set and the target equation for end-to-end training. The purpose of the training is to minimize the loss of the target equation calculation. Each sample in the data set includes the key attributes of each device involved in the power system, the device association structure of the power system, and the safety and automatic device action plan corresponding to each fault. This step only needs to be performed once. When the safety and automatic device action plan for the target fault needs to be generated in the future, only steps (11) to (34) need to be performed. The safety and automatic device action plan obtained in step (34) is the safety and automatic device action plan finally generated by this method.

[0070] The present invention also provides a device for generating an action plan for a power system safety device, comprising:

[0071] The device attribute vector construction module obtains the key attributes of each device involved in the power system and combines them into an attribute vector;

[0072] The device representation vector construction module inputs the device attribute vector into the device representation network and obtains the device representation vector of the same length and unified semantics through convolution operation;

[0073] The fault representation vector construction module aggregates all device representation vectors of the same category into a category representation vector, which represents the overall characteristics of all devices in that category. The category representation vectors of all categories are then concatenated and input into a multi-layer perceptron to obtain one or more fault representation vectors.

[0074] The device topology construction module constructs a corresponding topology based on the device association structure in the power system and adds isolated fault nodes equal to the number of fault representation vectors. The device representation vectors and fault representation vectors are used as node attributes to obtain the node attribute matrix X and adjacency matrix A of the topology.

[0075] The node embedding vector construction module uses the node attribute matrix X and the adjacency matrix A of the topological graph to obtain the node embedding vector through a multi-layer message propagation network;

[0076] The link prediction module, based on the node embedding vector, concatenates the device nodes belonging to the safety and automation device and the fault nodes in pairs to obtain a synthetic embedding vector, which is input into the node pair link prediction network to obtain the link relationship prediction result between the nodes;

[0077] The automatic safety device action plan generation module collects the device nodes belonging to the automatic safety device that have a link relationship with a certain fault node into a node set based on the link relationship prediction results between nodes. The devices included in the set are the devices that need to be operated after the corresponding fault occurs. The above operations are performed on each fault node to obtain the target operation device set for each fault, which is the automatic safety device action plan required after these faults occur.

[0078] It should be understood that the power system safety device action plan generation device in the embodiment of the present invention can implement all the technical solutions in the above method embodiment, and the functions of its various functional modules can be specifically implemented according to the method in the above method embodiment. Its specific implementation process can refer to the relevant description in the above embodiment, and will not be repeated here.

[0079] The present invention also provides a computer device comprising: one or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and when the programs are executed by the processors, the steps of the method for generating an action plan for an electric power system safety device are implemented as described above.

[0080] The present invention also provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the method for generating an action plan for an electric power system safety device as described above are implemented.

[0081] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus (systems), computer devices, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0082] The present invention is described with reference to flowcharts of methods according to embodiments of the present invention. It should be understood that each process in the flowcharts and combinations of processes in the flowcharts can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts. Figure 1 A device that specifies functions in a process or multiple processes.

[0083] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A function specified in a process or multiple processes.

[0084] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 The steps of a specified function in a process or multiple processes.

[0085] The preferred embodiments of the present invention are described in detail above. However, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, various equivalent transformations can be made to the technical solutions of the present invention, and these equivalent transformations all fall within the scope of protection of the present invention.

Claims

1. A method for generating an action plan for a power system safety device, characterized in that: The method comprises the following steps: Obtain the key attributes of each participating device in the power system and combine them into a device attribute vector; Input the device attribute vector into the device representation network and obtain the device representation vector with the same length and unified semantics through convolution operation; Aggregate all device representation vectors of the same category into a category representation vector, which represents the overall characteristics of all devices in that category. Then, concatenate the category representation vectors of all categories and input them into a multi-layer perceptron to obtain one or more fault representation vectors, which are used to represent the power system status information that requires attention after a predicted fault occurs. Based on the equipment association structure in the power system, a corresponding topology graph is constructed. A number of isolated fault nodes equal to the number of fault representation vectors is added. The equipment representation vectors and fault representation vectors are used as node attributes to obtain the node attribute matrix X and adjacency matrix A of the topology graph. Using the node attribute matrix X and adjacency matrix A of the topology graph, we can obtain the node embedding vector through a multi-layer message propagation network. Based on the node embedding vector, the device nodes belonging to the safety and automation device and the fault nodes are spliced ​​in pairs to obtain a synthetic embedding vector, which is input into the node pair link prediction network to obtain the link relationship prediction result between the nodes; Based on the predicted results of the link relationship between nodes, the device nodes belonging to the safety and automation devices that have a link relationship with a certain faulty node are collected into a node set. The devices included in the set are the devices that need to be operated after the corresponding fault occurs. The above operations are performed on each faulty node to obtain the target operation device set for each fault. This is the action plan for the safety and automation devices required after these faults occur. The device representation network, multi-layer perceptron, multi-layer message propagation network, and node-to-link prediction network constitute the system's end-to-end model. The model is trained using a pre-collected dataset and the target equation. The goal of the training is to minimize the loss of the target equation calculation. Each sample in the dataset includes the key attributes of each device involved in the power system, the device association structure of the power system, and the safety and automatic device action plan corresponding to each fault. The objective equation used in model training is expressed as: Where l represents the loss function, N f is the number of possible fault types in the power system, N c is the number of equipment in the power system that belongs to the safety device. is the predicted probability that there is a link relationship between the fault node i and the device j belonging to the safety device, y i,j Indicates whether fault type i in the data set requires operation of device j belonging to the safety device. If operation is required, it is 1, otherwise it is 0.

2. The method according to claim 1, characterized in that The calculation method of the multi-layer message propagation network is: Where σ(·) represents the activation function, ‖ represents the concatenation operation, represents the aggregation function, N(i) represents the set of neighbor nodes of node i, represents the embedding vector of node i after k rounds of message propagation, W (k) represents the learnable parameters in the kth round of message passing.

3. The method according to claim 1, characterized in that The device representation network consists of a convolutional layer and a fully connected layer. The convolutional layer composed of multiple 1×1 convolution kernels is used to process the attribute vector into vectors of the same length.

4. The method according to claim 1, wherein The node attribute matrix X is a shape of (N e +N f )×D two-dimensional matrix, where N e is the number of devices in the power system, N f is the number of possible fault types in the power system, and D is the length of the device representation vector.

5. The method according to claim 1, wherein The adjacency matrix A is a (N e +N f )×(N e +N f ), each row represents the relationship between a device or faulty node and other devices or faulty nodes. The values ​​of the matrix elements are 0 or 1. When there is a link relationship between the i-th node and the j-th node, the adjacency matrix A in A ij is equal to 1, otherwise equal to 0, where N e is the number of devices in the power system, N f It is the number of possible fault types that may occur in the power system.

6. A device for generating an action plan for a power system safety device, characterized in that: The method for generating an action plan for a force system safety device according to any one of claims 1 to 5 comprises: The device attribute vector construction module obtains the key attributes of each device involved in the power system and combines them into an attribute vector; The device representation vector construction module inputs the device attribute vector into the device representation network and obtains the device representation vector of the same length and unified semantics through convolution operation; The fault representation vector construction module aggregates all device representation vectors of the same category into a category representation vector, which represents the overall characteristics of all devices in that category. The category representation vectors of all categories are then concatenated and input into a multi-layer perceptron to generate one or more fault representation vectors, which represent the power system status information that requires attention after a predicted fault occurs. The device topology construction module constructs a corresponding topology based on the device association structure in the power system and adds isolated fault nodes equal to the number of fault representation vectors. The device representation vectors and fault representation vectors are used as node attributes to obtain the node attribute matrix X and adjacency matrix A of the topology. The node embedding vector construction module uses the node attribute matrix X and the adjacency matrix A of the topological graph to obtain the node embedding vector through a multi-layer message propagation network; The link prediction module, based on the node embedding vector, concatenates the device nodes belonging to the safety and automation device and the fault nodes in pairs to obtain a synthetic embedding vector, which is input into the node pair link prediction network to obtain the link relationship prediction result between the nodes; The automatic safety device action plan generation module collects the device nodes belonging to the automatic safety device that have a link relationship with a certain fault node into a node set based on the link relationship prediction results between nodes. The devices included in the set are the devices that need to be operated after the corresponding fault occurs. The above operations are performed on each fault node to obtain the target operation device set for each fault, which is the automatic safety device action plan required after these faults occur.

7. A computer device, characterized in that: include: one or more processors; Memory; And one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by the one or more processors, and when the programs are executed by the processors, the steps of the method for generating an action plan for an electric power system safety device as described in any one of claims 1 to 5 are implemented.

8. A 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 method for generating an action plan for a power system safety device according to any one of claims 1 to 5 are implemented.

Images