Power distribution network dynamic topology online identification method and related device
By constructing a power distribution network diagram structure model using graph neural networks and attention mechanisms, the problem of low computational efficiency in traditional methods is solved, enabling fast and accurate dynamic topology identification and adapting to complex operating environments.
Patent Information
- Application Number
- CN202511061040.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-30
- Publication Date
- 2025-11-07
AI Technical Summary
Traditional distribution network topology identification methods are difficult to adapt to complex and ever-changing operating environments, have low computational efficiency, and cannot meet the needs of rapid online monitoring of modern distribution networks.
By employing the information propagation mechanism and attention mechanism in graph neural networks, a graph structure model of the power distribution network is constructed. The node features are aggregated through the graph information propagation mechanism and weighted summation is performed based on the attention mechanism. The summation is then input into a classifier to identify the dynamic topology.
It enables rapid and accurate identification of dynamic topology in distribution networks, improves sensitivity to changes in the status of key nodes, and can promptly identify topology changes during faults or equipment switching, thereby improving computational efficiency and accuracy.
Smart Images
Figure CN120910455A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The application belongs to the field of power system operation monitoring, and relates to a power distribution network dynamic topology online identification method and related devices. BACKGROUND
[0002] With the growth of power demand and the wide access of distributed energy, the structure and operation state of the power distribution network become increasingly complex. Accurate and real-time grasp of the dynamic topology of the power distribution network is crucial for ensuring the safe and stable operation of the power system, optimizing power dispatching and improving power supply reliability. Traditional power distribution network topology identification methods are difficult to adapt to complex and variable operating environments, have low calculation efficiency, are not sensitive to key node information capture, and cannot meet the needs of modern power distribution network fast online monitoring. SUMMARY
[0003] The purpose of the present application is to overcome the shortcomings of the prior art and provide a power distribution network dynamic topology online identification method and related devices that can quickly and online identify the dynamic topology of the power distribution network.
[0004] To achieve the above purpose, the application discloses a power distribution network dynamic topology online identification method, comprising:
[0005] constructing a graph structure model of the power distribution network according to the structure of the power distribution network, wherein the nodes in the graph structure model represent the devices in the power distribution network, and the edges in the graph structure model represent the connection relationship between the devices;
[0006] aggregating the features of the nodes in the graph structure model with the features of their adjacent nodes;
[0007] based on the attention mechanism, performing weighted summation on the features of all nodes in the graph structure model to obtain weighted feature information;
[0008] inputting the weighted feature information into a classifier to obtain the dynamic topology structure of the power distribution network at the current time.
[0009] Further improvement of the power distribution network dynamic topology online identification method of the application is that:
[0010] Further, the process of aggregating the features of the nodes in the graph structure model with the features of their adjacent nodes is:
[0011] using the information propagation mechanism in the graph neural network to aggregate the features of the nodes in the graph structure model with the features of their adjacent nodes.
[0012] Further, after aggregating the features of the nodes in the graph structure model with the features of their adjacent nodes, the features of the nodes are represented as:
[0013]
[0014] Wherein, N(v) is the neighbor node set of node v, deg(v) and deg(u) are the degrees of node v and node u respectively, W l is the weight matrix of the lth layer, and sigma is a nonlinear activation function.
[0015] Further, the weighted feature information is:
[0016] h i =∑ j∈N(i) α ij Wh j
[0017] Wherein, W is a weight matrix, alpha ij is an attention coefficient, and the attention coefficient alpha ij is used to measure the attention degree of node i to the feature of node j, wherein the weight in the weight matrix is determined based on an attention mechanism.
[0018] The application discloses a power distribution network dynamic topology online identification system, comprising:
[0019] A construction module is configured to construct a graph structure model of the power distribution network according to the structure of the power distribution network, wherein a node in the graph structure model represents a device in the power distribution network, and an edge in the graph structure model represents a connection relationship between devices.
[0020] An aggregation module is configured to aggregate the features of a node in the graph structure model with the features of adjacent nodes.
[0021] A weighted summation module is configured to perform weighted summation on the features of all nodes in the graph structure model based on an attention mechanism to obtain weighted feature information.
[0022] A classification module is configured to input the weighted feature information into a classifier to obtain a dynamic topology structure of the power distribution network at a current time.
[0023] The power distribution network dynamic topology online identification system further improves in that:
[0024] Further, the process of aggregating the features of a node in the graph structure model with the features of adjacent nodes is:
[0025] The features of the node in the graph structure model are aggregated with the features of adjacent nodes by using an information propagation mechanism in a graph neural network.
[0026] Further, after the features of the node in the graph structure model are aggregated with the features of adjacent nodes, the features of the node are represented as:
[0027]
[0028] wherein N(v) is the neighbor node set of node v, deg(v) and deg(u) are the degrees of node v and node u respectively, W l is the weight matrix of the lth layer, and sigma is a nonlinear activation function.
[0029] Further, the weighted feature information is:
[0030] h i =∑ j∈N(i) alpha ij Wh j
[0031] wherein W is a weight matrix, alpha ij is an attention coefficient, and the attention coefficient alpha ij is used to measure the attention degree of node i to the feature of node j, and the weight in the weight matrix is determined based on an attention mechanism.
[0032] The application discloses a computer device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the power distribution network dynamic topology online identification method when executing the computer program.
[0033] The application discloses a computer readable storage medium, which stores a computer program, characterized in that the computer program implements the steps of the power distribution network dynamic topology online identification method when executed by a processor.
[0034] The application has the following beneficial effects:
[0035] The power distribution network dynamic topology online identification method and related device provided by the present application can more comprehensively and accurately reflect the actual operation state of the power distribution network by constructing a graph structure model of the power distribution network according to the structure of the power distribution network, wherein the nodes in the graph structure model represent the devices in the power distribution network, and the edges in the graph structure model represent the connection relationship between the devices, and the coupling correlation of the electrical quantities of each node is fully mined through a graph information propagation mechanism. In addition, the present application aggregates the features of the nodes in the graph structure model into the features of the adjacent nodes. Based on the attention mechanism, the features of all the nodes in the graph structure model are weighted and summed to obtain weighted feature information, and the weighted feature information is input into a classifier to obtain the dynamic topology structure of the power distribution network at the current time, so as to quickly and online identify the dynamic topology of the power distribution network. The introduction of the attention mechanism can automatically focus on the node information that plays a key role in topology identification, avoid the interference of redundant information, effectively improve the sensitivity to the state change of the key nodes, and especially when the power distribution network fails or the important device switches, the topology change can be quickly and accurately identified. BRIEF DESCRIPTION OF DRAWINGS
[0036] The accompanying drawings, which form a part of the present application, are used to provide further understanding of the present application, and serve as an explanation of the illustrative embodiments of the present application and their description, and do not constitute improper limitations on the present application. In the drawings:
[0037] Figure 1 The flowchart of the method of the present application is shown in FIG. 1.
[0038] Figure 2 The system structure diagram of the present application is shown in FIG. 2. DETAILED DESCRIPTION
[0039] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.
[0040] In the description of the present application, it should be understood that the terms "include" and "contain" indicate the existence of the described features, whole, steps, operations, elements and / or components, but do not exclude the existence or addition of one or more other features, whole, steps, operations, elements, components and / or sets thereof.
[0041] It should also be understood that the terms used in the specification and the following claims are intended to describe certain embodiments and do not limit the present application unless other- wise explicitly indicated. As used in the specification and the appended claims, the singular forms "a," "an" and "the" are intended to include plural forms as well, unless the context clearly indicates otherwise.
[0042] It should also be further understood that the term "and / or" used in the specification and the appended claims, means one or more of the associated listed items conjunctively or disjunctively, and includes all possible combinations thereof, for example, A and / or B, can mean the three cases of A alone, A and B together, and B alone. In addition, the character " / " in the present application generally represents an "or" relationship between the front and rear associated objects.
[0043] It should be understood that although the terms first, second, third, etc. can be used in the embodiments of the present application to describe a certain range, etc., these ranges should not be limited to these terms. These terms are only used to distinguish the ranges from each other. For example, the first range can also be referred to as the second range, and similarly, the second range can also be referred to as the first range, without departing from the scope of the embodiments of the present application.
[0044] Depending on the context, the word "if" as used herein can be interpreted to mean "when" or "while" or "in response to determining" or "in response to detecting." Similarly, the phrase "if it is determined" or "if a stated condition or event occurs" can be interpreted to mean "when it is determined" or "in response to determining" or "when a stated condition or event occurs" or "in response to detecting a stated condition or event."
[0045] In order to make the purposes, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art without creative labor based on the embodiments in the present application belong to the scope of protection of the present application.
[0046] Various structural diagrams according to the disclosed embodiments of the present application are shown in the accompanying drawings. These diagrams are not drawn to scale, in which certain details are shown in a somewhat exaggerated manner for the purpose of clarity and understanding, and certain details can be omitted. The shapes of various regions, layers shown in the drawings and their relative sizes and positional relationships may, in actuality, deviate due to manufacturing tolerances or technical limitations, and regions / layers with different shapes, sizes, relative positions can be additionally designed by those skilled in the art according to actual needs.
[0047] Embodiment One
[0048] With reference to Figure 1 The power distribution network dynamic topology online identification method described in the present application comprises the following steps:
[0049] 1) Convert the power distribution network wiring diagram into graph structure data and embed static topology constraints;
[0050] 11) Abstract each electrical device (such as transformers, switches, lines, etc.) in the power distribution network as a node of the graph, and the connection relationship between the devices as an edge of the graph, to construct a graph structure model of the power distribution network;
[0051] For example, connect the transformer node and the connected line node through an edge, and the attributes of the edge can include parameters such as the impedance and capacity of the line.
[0052] 12) Embed static topology constraints in the graph structure model, for example, type constraints of nodes (distinguish power supply nodes, load nodes, tie nodes, etc.), connectivity constraints of edges (ensure that the nodes connected by the edge are physically connected in the actual power distribution network).
[0053] Taking the power supply node as an example, it can be set to have a specific identification attribute, and serve as the starting point of power injection in topology analysis.
[0054] 2) Use graph information propagation mechanism to collect features and extract coupling relationships;
[0055] 21) Use the information propagation mechanism in the graph neural network (such as Graph Convolutional Network, GCN or Graph Attention Network, GAT) to make the nodes in the graph structure model aggregate the feature information of their adjacent nodes.
[0056] For example, GCN updates the feature representation of a node by weighted summation of its own features and the features of adjacent nodes. For each node, its new feature vector representation is:
[0057]
[0058] wherein, is the feature vector of node v at the (l+1)th layer, N(v) is the set of neighboring nodes of node v, deg(v) and deg(u) are the degrees of node v and node u respectively, W l is the weight matrix of the lth layer, and σ is a nonlinear activation function.
[0059] 22) Through the propagation of information in multiple layers, the coupling relationship between the electrical quantities (such as voltage amplitude, phase, current, etc.) of each node is extracted. For example, after multiple GCN calculations, the feature vector of a node will contain the comprehensive information of the electrical quantities of the nodes within a certain range around it, thereby reflecting the mutual influence between them.
[0060] 3) Distribute the feature weight values using the attention mechanism;
[0061] 31) Introduce the attention mechanism into the graph neural network to calculate the importance weights of the features of each node and the features of neighboring nodes. For example, in GAT, the attention coefficient α ij is used to measure the degree of attention of node i to the features of node j, and the attention coefficient α ij is:
[0062]
[0063] where a is a learnable attention vector, W is a weight matrix, || represents the vector concatenation operation, and LeakyReLU is an activation function.
[0064] 22) According to the calculated attention weights, the features of each node are weighted and summed, so that the model can focus on key node information and improve the calculation efficiency. For example, when updating the node features, the weighted feature information is:
[0065] h i =∑ j∈N(i) α ij Wh j
[0066] 3) Develop a distribution network topology identification;
[0067] 31) Input the weighted feature information into a classifier (such as a Softmax classifier) to obtain the dynamic topology structure of the distribution network at the current time.
[0068] 32) Collect electrical quantity data of the distribution network in real time, constantly update the graph structure data and node features, and repeat the above steps to realize online tracking of the dynamic topology of the distribution network. For example, collect the latest voltage and current data at certain time intervals (such as 1 minute), recalculate the node features and topology state to adapt to the real-time changes of the operation state of the distribution network.
[0069] Example Two
[0070] Reference Figure 2 The power distribution network dynamic topology online identification system comprises:
[0071] A construction module is configured to construct a graph structure model of the power distribution network according to a structure of the power distribution network, wherein a node in the graph structure model represents a device in the power distribution network, and an edge in the graph structure model represents a connection relationship between devices.
[0072] An aggregation module is configured to aggregate features of a node in the graph structure model with features of adjacent nodes of the node.
[0073] A weighted summation module is configured to perform weighted summation on the features of all nodes in the graph structure model based on an attention mechanism to obtain weighted feature information.
[0074] A classification module is configured to input the weighted feature information into a classifier to obtain a dynamic topology structure of the power distribution network at a current time.
[0075] In this embodiment, the process of aggregating the features of a node in the graph structure model with the features of adjacent nodes of the node is as follows:
[0076] The features of the node in the graph structure model are aggregated with the features of adjacent nodes of the node by using an information propagation mechanism in a graph neural network.
[0077] In this embodiment, after the features of a node in the graph structure model are aggregated with the features of adjacent nodes of the node, the features of the node are represented as:
[0078]
[0079] wherein N(v) is a set of neighbor nodes of the node v, deg(v) and deg(u) are degrees of the node v and the node u respectively, W is a weight matrix of the lth layer, and σ is a nonlinear activation function. l
[0080] In this embodiment, the weighted feature information is as follows:
[0081] h i =∑ j∈N(i) α ij Wh j
[0082] wherein W is a weight matrix, α ij is an attention coefficient, and the attention coefficient α ij is used to measure a degree of attention of the node i to the feature of the node j, wherein the weights in the weight matrix are determined based on the attention mechanism.
[0083] The division of the modules in the embodiments of the present application is illustrative, and is merely a logical function division. In actual implementation, another division manner can be used. In addition, the function modules in each of the embodiments of the present application can be integrated in one processor, or can be physically separated, or two or more modules can be integrated in one module. The integrated module can be realized in the form of hardware or in the form of a software function module.
[0084] Embodiment three
[0085] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the steps of the power distribution network dynamic topology online identification method when executing the computer program, for example, including: constructing a graph structure model of the power distribution network according to the structure of the power distribution network, wherein the nodes in the graph structure model represent the devices in the power distribution network, and the edges in the graph structure model represent the connection relationship between the devices; aggregating the features of the nodes in the graph structure model into the features of their adjacent nodes; based on an attention mechanism, performing weighted summation on the features of all nodes in the graph structure model to obtain weighted feature information; inputting the weighted feature information into a classifier to obtain the dynamic topology structure of the power distribution network at the current time. The memory can include a memory, for example, a high-speed random access memory, and can also include a non-volatile memory, for example, at least one disk memory. The processor, network interface, and memory are connected to each other through an internal bus, which can be an industry standard architecture bus, a peripheral component interconnect standard bus, an extended industry standard architecture bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The memory is used to store programs, and specifically, the programs can include program codes, and the program codes include computer operation instructions. The memory can include a memory and a non-volatile memory, and provide instructions and data to the processor.
[0086] Embodiment four
[0087] A computer readable storage medium stores a computer program, the computer program is executed by a processor to implement steps of the power distribution network dynamic topology online identification method, for example, comprising: constructing a graph structure model of the power distribution network according to a power distribution network structure, wherein a node in the graph structure model represents a device in the power distribution network, and an edge in the graph structure model represents a connection relationship between the devices; aggregating a feature of a node in the graph structure model into features of adjacent nodes of the node; performing weighted summation on the features of all nodes in the graph structure model based on an attention mechanism to obtain weighted feature information; and inputting the weighted feature information into a classifier to obtain a dynamic topology structure of the power distribution network at a current time. Specifically, the computer readable storage medium includes but is not limited to, for example, volatile memory and / or non-volatile memory. The volatile memory can include random access memory and / or cache memory, etc. The non-volatile memory can include read-only memory, hard disk, flash memory, optical disc, magnetic disc, etc.
[0088] Those skilled in the art will appreciate that embodiments of the application can be provided as methods, systems, or computer program products. Accordingly, the application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the application can be embodied in the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied thereon.
[0089] The application is described with reference to flowcharts and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It should be understood that each flow and / or block in the flowcharts and / or block diagrams, as well as combinations of flows and / or blocks in the flowcharts and / or block diagrams, 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 apparatus to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing apparatus produce an apparatus that implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The functions specified in a flow or multiple flows and / or blocks
[0090] These computer program instructions can also be stored in a computer readable storage medium that can direct the computer or other programmable data processing apparatus to work in a specific manner, so that the instructions stored in the computer readable storage medium produce a manufactured product including instruction apparatus, which implements the functions specified in the flowcharts and / or block diagrams. Figure 1 The functions specified in a flow or multiple flows and / or blocks Figure 1 The functions specified in a flow or multiple flows and / or blocks
[0091] These computer program instructions can also be loaded into a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart block or blocks. Figure 1 Figure 1
[0092] Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. It is intended that the specification and examples be considered as exemplary only, with the true scope and spirit of the application being indicated by the following claims.
[0093] It is to be understood that the application is not limited to the precise details of construction and the method described above and illustrated in the drawings. Various modifications and changes can be made thereunto without departing from the scope of the application. The scope of the application is indicated by the appended claims, rather than by the foregoing description.
[0094] The above description is only preferred embodiments of the present application, not any limitation thereto, any simple modification, change and equivalent structure change of the above embodiments according to the technical essence of the present application are still within the protection scope of the technical scheme of the present application.
Claims
1. A power distribution network dynamic topology online identification method, characterized in that, The method comprises the following steps: constructing a graph structure model of the power distribution network according to a structure of the power distribution network, wherein a node in the graph structure model represents a device in the power distribution network, and an edge in the graph structure model represents a connection relationship between devices; aggregating features of a node in the graph structure model to features of adjacent nodes of the node; performing weighted summation on the features of all nodes in the graph structure model based on an attention mechanism to obtain weighted feature information; inputting the weighted feature information into a classifier to obtain a dynamic topology structure of the power distribution network at a current time.
2. The power distribution network dynamic topology online identification method according to claim 1, characterized in that, The process of aggregating the features of the node in the graph structure model to the features of the adjacent nodes of the node comprises the following steps: adopting an information propagation mechanism in a graph neural network to aggregate the features of the node in the graph structure model to the features of the adjacent nodes of the node.
3. The power distribution network dynamic topology online identification method according to claim 1, characterized in that, aggregating the features of a node in the graph structure model after the features of its neighboring nodes is represented as: where N(v) is the neighbor set of node v, deg(v) and deg(u) are the degrees of node v and node u, respectively, W l is the weight matrix of the l-th layer, and σ is a nonlinear activation function.
4. The power distribution network dynamic topology online identification method according to claim 1, characterized in that, The weighted feature information comprises: h i =∑ j∈N(i) α ij Wh j wherein W is a weight matrix, a ij is an attention coefficient, the attention coefficient a ij is used to measure the degree of attention of node i to the features of node j, wherein the weights in the weight matrix are determined based on an attention mechanism.
5. A power distribution network dynamic topology online identification system, characterized in that, The method comprises the following steps: constructing a graph structure model of the power distribution network according to a structure of the power distribution network, wherein a node in the graph structure model represents a device in the power distribution network, and an edge in the graph structure model represents a connection relationship between devices; aggregating features of a node in the graph structure model to features of adjacent nodes of the node; performing weighted summation on the features of all nodes in the graph structure model based on an attention mechanism to obtain weighted feature information; inputting the weighted feature information into a classifier to obtain a dynamic topology structure of the power distribution network at a current time.
6. The power distribution network dynamic topology online identification system according to claim 5, characterized in that, The process of aggregating the features of the node in the graph structure model to the features of the adjacent nodes of the node comprises the following steps: adopting an information propagation mechanism in a graph neural network to aggregate the features of the node in the graph structure model to the features of the adjacent nodes of the node.
7. The power distribution network dynamic topology online identification system of claim 5, wherein, aggregating the features of a node in the graph structure model after the features of its neighboring nodes is represented as: where N(v) is the neighbor set of node v, deg(v) and deg(u) are the degrees of node v and node u, respectively, W l is the weight matrix of the l-th layer, and σ is a nonlinear activation function.
8. The power distribution grid dynamic topology online identification system of claim 5, wherein, The weighted feature information comprises: h i =∑ j∈N(i) α ij Wh j wherein W is a weight matrix, a ij is an attention coefficient, the attention coefficient a ij is used to measure the degree of attention of node i to the features of node j, wherein the weights in the weight matrix are determined based on an attention mechanism.
9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the steps of the power distribution network dynamic topology online identification method according to any one of claims 1-4.
10. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 9. The computer program is executed by the processor to implement the steps of the power distribution network dynamic topology online identification method according to any one of claims 1-4.