Method and device for forming topological graph of power distribution network, electronic equipment and storage medium

Abstract

The invention discloses a power distribution network topological graph forming method and device, electronic equipment and a storage medium, and relates to the technical field of power system automation or other related fields, and the method comprises the steps: obtaining a memory topological model of a target power distribution network, and enabling the memory topological model to record N power distribution network components in the target power distribution network, n is a positive integer, and N is a positive integer; establishing a target decision tree according to the memory topology model; determining a drawing sequence of each element in the power distribution network topological graph based on the target decision tree, and drawing an initial topological graph according to the drawing sequence; and adjusting the initial topological graph according to a preset mapping rule to obtain a power distribution network topological graph of the target power distribution network. According to the invention, the technical problem that the power supply path cannot be timely scheduled and managed due to the fact that the distribution network scheduling system cannot quickly acquire the topological graph of the distribution network structure in the related technology is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of power system automation, and in particular to a method and device for drawing a distribution network topology map, electronic equipment, and a storage medium. Background Art

[0002] In the current construction of power system distribution automation, distribution network line diagrams are regarded as the main means for dispatchers to understand the overall structure and real-time operating status of the distribution network. These line diagrams graphically display the physical structure and connection relationship of the power system, allowing dispatchers to intuitively understand the layout, connection and operating status of the power grid. However, the existing distribution network topology diagrams have some limitations, which limit their application effect and practicality in distribution automation systems.

[0003] First, current distribution network topology maps are usually static and rarely or not updated after creation, but the structure and operating status of the power system will change over time, such as equipment modification, fault repair, etc. Due to the lack of timely updated topology information, the distribution network topology map lacks real-time performance, which affects the effective management and operation of the power system.

[0004] Secondly, the existing distribution network topology diagrams are usually drawn manually, which requires a lot of time and human resources. Especially when the low-voltage distribution network is large and equipment transformation is frequent, this method that relies on manual drawing is not only inefficient, but also prone to errors. It is not suitable for dealing with complex and frequently changing distribution systems.

[0005] In addition, existing distribution network topology diagrams usually lack in-depth analysis and optimization of the grid structure, such as analysis of node load balancing and grid capacity utilization, which limits the ability of grid managers to deeply understand and optimize the grid structure.

[0006] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0007] The embodiments of the present invention provide a method and device for drawing a distribution network topology map, an electronic device, and a storage medium, so as to at least solve the technical problem in the related art that the distribution network scheduling system cannot quickly obtain the distribution network structure topology map, resulting in the inability to perform real-time scheduling management of the power supply path.

[0008] According to one aspect of an embodiment of the present invention, a method for drawing a distribution network topology map is provided, comprising: obtaining a memory topology model of a target distribution network, wherein the memory topology model records N distribution network components in the target distribution network, and the physical connection relationship between the distribution network components, where N is a positive integer; establishing a target decision tree according to the memory topology model, wherein the target decision tree represents the distribution network components of different importance by tree nodes at different node positions, and represents the physical connection relationship by tree branches; determining the drawing order of each element in the distribution network topology map based on the target decision tree, and drawing an initial topology map according to the drawing order, wherein the elements include: device nodes and device branches; adjusting the initial topology map according to a preset drawing rule to obtain the distribution network topology map of the target distribution network.

[0009] Furthermore, before establishing the target decision tree based on the memory topology model, it includes: identifying the feeder ring network in the target distribution network based on the memory topology model, and recording the total number of feeder ring networks; identifying the power supply points and contact points in the target distribution network based on the memory topology model and the feeder ring network, and recording the total number of power supply points and the total number of contact points; determining the range of drawing the topology map based on the total number of feeder ring networks, the total number of power supply points and the total number of contact points.

[0010] Furthermore, the step of establishing a target decision tree based on the memory topology model includes: analyzing the memory topology model through a preset decision tree algorithm to obtain an analysis result, wherein the analysis result is used to record the importance ranking of N distribution network components in the power supply and distribution process of the target distribution network; for each distribution network component, determining the node position of the tree node corresponding to the distribution network component based on the importance ranking in the analysis result, and adding basic information of the distribution network component at the node position; after determining the node positions of the tree nodes corresponding to all the distribution network components, adding the tree branches based on the physical connection relationship to obtain the target decision tree.

[0011] Furthermore, the step of analyzing the memory topology model through a preset decision tree algorithm to obtain an analysis result includes: converting the N distribution network components in the memory topology model into N mapping sample points to obtain a mapping sample set, and recording the sample category information of each mapping sample point during the conversion process; for each mapping sample point, calculating the sample proportion information of the mapping sample point based on the mapping sample set; obtaining an attribute feature set corresponding to the target distribution network, wherein the attribute feature set includes R attribute feature values, each of which corresponds to a feature dimension, which is used to measure the importance of the feature dimension in the power supply and distribution process of the target distribution network, and R is a positive integer; initializing the preset decision tree algorithm based on the sample category information, the sample proportion information and the attribute feature set, and making importance decisions on the N distribution network components through the initialized preset decision tree algorithm to obtain the analysis result.

[0012] Furthermore, the step of initializing the preset decision tree algorithm based on the sample category information, the sample proportion information and the attribute feature set includes: calculating the information entropy of the mapped sample set based on the sample category information and the sample proportion information of all the mapped sample points; for each feature dimension, calculating the information gain value of the mapped sample set in the feature dimension based on the attribute feature value and the information entropy; sorting all the information gain values, and determining the feature dimension corresponding to the maximum information gain value based on the sorting result, and determining the feature dimension as the decision feature; and using the decision feature to initialize the preset decision tree algorithm.

[0013] Furthermore, the step of determining the drawing order of each element in the distribution network topology map based on the target decision tree includes: for each tree node in the target decision tree, determining the device node corresponding to the tree node in the distribution network topology map and the device branch line connected to the device node by analyzing the basic information carried by the tree node and all tree branches connected to the tree node; determining the drawing order of the device node and the device branch line during the drawing process by analyzing the node position of the tree node in the target decision tree and the relative position of the tree branch connected to the tree node.

[0014] Furthermore, the step of adjusting the initial topology map according to preset drawing rules includes: adjusting the drawing order of the device nodes connected to the device branches whose branch lengths are greater than the preset length according to the long line priority principle in the preset drawing rules; and confirming the drawing direction of the device branches connected to each of the device nodes according to the adjusted drawing order and the node balance principle in the preset drawing rules.

[0015] According to another aspect of an embodiment of the present invention, there is also provided a device for drawing a distribution network topology map, comprising: an acquisition unit, used to acquire a memory topology model of a target distribution network, wherein the memory topology model records N distribution network components in the target distribution network, and the physical connection relationship between the distribution network components, where N is a positive integer; an establishment unit, used to establish a target decision tree based on the memory topology model, wherein the target decision tree represents the distribution network components of different importance by tree nodes at different node positions, and represents the physical connection relationship by tree branches; a determination unit, used to determine the drawing order of each element in the distribution network topology map based on the target decision tree, and draw an initial topology map according to the drawing order, wherein the elements include: device nodes and device branches; an adjustment unit, used to adjust the initial topology map according to a preset drawing rule to obtain the distribution network topology map of the target distribution network.

[0016] Furthermore, the distribution network topology map drawing device also includes: a first identification module, used to identify the feeder ring network in the target distribution network based on the memory topology model, and record the total number of feeder ring networks; a second identification module, used to identify the power supply points and contact points in the target distribution network based on the memory topology model and the feeder ring network, and record the total number of power supply points and the total number of contact points; a first determination module, used to determine the topology map drawing range based on the total number of feeder ring networks, the total number of power supply points and the total number of contact points.

[0017] Furthermore, the establishment unit includes: an analysis module, which is used to analyze the memory topology model through a preset decision tree algorithm to obtain an analysis result, wherein the analysis result is used to record the importance rankings of the N distribution network components in the power supply and distribution process of the target distribution network; a second determination module, which is used to determine, for each of the distribution network components, the node position of the tree node corresponding to the distribution network component based on the importance ranking in the analysis result, and add the basic information of the distribution network component at the node position; an adding module, which is used to add the tree branches based on the physical connection relationship after determining the node positions of the tree nodes corresponding to all the distribution network components to obtain the target decision tree.

[0018] Furthermore, the analysis module includes: a conversion submodule, used to convert the N distribution network components in the memory topology model into N mapping sample points, obtain a mapping sample set, and record the sample category information of each mapping sample point during the conversion process; a first calculation submodule, used to calculate the sample proportion information of the mapping sample point based on the mapping sample set for each mapping sample point; an acquisition submodule, used to obtain the attribute feature set corresponding to the target distribution network, wherein the attribute feature set includes R attribute feature values, each of which corresponds to a feature dimension, which is used to measure the importance of the feature dimension in the power supply and distribution process of the target distribution network, and R is a positive integer; an initialization submodule, used to initialize the preset decision tree algorithm based on the sample category information, the sample proportion information and the attribute feature set, and make importance decisions on the N distribution network components through the initialized preset decision tree algorithm to obtain the analysis result.

[0019] Furthermore, the analysis module also includes: a second calculation submodule, which is used to calculate the information entropy of the image sample set based on the sample category information and the sample proportion information of all the image sample points; a third calculation submodule, which is used to calculate the information gain value of the image sample set in the feature dimension for each feature dimension based on the attribute feature value and the information entropy; a sorting submodule, which is used to sort all the information gain values, and determine the feature dimension corresponding to the maximum information gain value based on the sorting result, and determine the feature dimension as the decision feature; a setting submodule, which is used to use the decision feature to initialize the preset decision tree algorithm.

[0020] Furthermore, the determination unit includes: a third determination module, which is used to determine, for each tree node in the target decision tree, the device node corresponding to the tree node in the distribution network topology map and the device branch line connected to the device node by analyzing the basic information carried by the tree node and all the tree branches connected to the tree node; a fourth determination module, which is used to determine the drawing order of the device node and the device branch line during the drawing process by analyzing the node position of the tree node in the target decision tree and the relative position of the tree branch connected to the tree node.

[0021] Furthermore, the adjustment unit includes: an adjustment module, used to adjust the drawing order of the device nodes connected to the device branches whose branch lengths are greater than a preset length according to the long line priority principle in the preset drawing rules; a confirmation module, used to confirm the drawing direction of the device branches connected to each of the device nodes according to the adjusted drawing order and the node balance principle in the preset drawing rules.

[0022] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned methods for drawing a distribution network topology map.

[0023] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement any one of the above-mentioned methods for drawing a distribution network topology map.

[0024] In the present invention, a method for drawing a distribution network topology map is proposed, firstly, a memory topology model of a target distribution network is obtained, wherein the memory topology model records N distribution network components in the target distribution network, and the physical connection relationship between the distribution network components, N is a positive integer, and then a target decision tree is established according to the memory topology model, wherein the target decision tree represents distribution network components of different importance through tree nodes at different node positions, and represents the physical connection relationship through tree branches, and then the drawing order of each element in the distribution network topology map is determined based on the target decision tree, and an initial topology map is drawn according to the drawing order, wherein the elements include: device nodes and device branches, and finally the initial topology map is adjusted according to a preset drawing rule to obtain the distribution network topology map of the target distribution network.

[0025] In the present invention, by acquiring the memory topology model of the target distribution network, all distribution network components and physical connection relationships existing in the distribution network are clarified, and then by establishing a target decision tree, the importance of each component in the power supply and distribution process of the target distribution network is intuitively characterized. On this basis, the corresponding drawing order of each component when converted into an element in the distribution network topology map is determined, and an initial topology map including elements such as device nodes and device branches is drawn according to the drawing order. The initial topology map is further adjusted according to preset drawing rules to obtain a distribution network topology map that can intuitively display the target distribution network structure information and power flow information, which can be used by the distribution dispatching system to capture the distribution network power supply path in real time and perform real-time dispatching management, thereby solving the technical problem in the related art that the distribution network dispatching system cannot quickly obtain the distribution network structure topology map, resulting in the inability to perform real-time dispatching management of the power supply path. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0027] Figure 1is a flow chart of an optional method for drawing a distribution network topology map according to an embodiment of the present invention;

[0028] Figure 2 is a flow chart of an optional method for automatically mapping a low-voltage distribution network power supply path according to an embodiment of the present invention;

[0029] Figure 3 It is a flow chart of an optional layout adjustment method of a low-voltage distribution network power supply path diagram according to an embodiment of the present invention;

[0030] Figure 4 It is a flowchart of an optional power supply path layout adjustment method based on a node balancing strategy according to an embodiment of the present invention;

[0031] Figure 5 is a schematic diagram of an optional distribution network topology map generating device according to an embodiment of the present invention;

[0032] Figure 6 The present invention is a hardware structure block diagram of an electronic device (or mobile device) for a method for drawing a distribution network topology map according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] To facilitate those skilled in the art to understand the present invention, some terms or nouns involved in the embodiments of the present invention are explained below:

[0036] Graph theory is a branch of mathematics that studies graph (network) structures and their properties. In the automatic drawing method of the distribution network structure topology diagram in the embodiment of the present invention, the concepts and algorithms of graph theory are used to process the connection relationship between nodes and branches, and to calculate the structural characteristics and topological relationship of the network.

[0037] The decision tree algorithm is a machine learning algorithm based on a tree structure, which is used for classification and regression tasks. It simulates the human decision-making process and classifies or predicts data through a series of simple rules. In the embodiment of the present invention, it is used to process the layout, optimization and adjustment of the topological graph, including calculating the connection relationship between nodes, determining the direction of branches, optimizing the layout to ensure node balance, etc.

[0038] The following embodiments of the present invention can be applied to various systems / applications / devices that require automatic drawing of distribution network topology maps and real-time scheduling of power supply paths, and can realize automatic generation of distribution network topology maps based on memory topology models and decision tree algorithms. The present invention obtains the memory topology model to clarify all the distribution network components and physical connection relationships, and then establishes a target decision tree to intuitively characterize the importance of each component in the power supply and distribution process. On this basis, the drawing order of the topology map elements is determined, and then the topology map is drawn.

[0039] The present invention is described in detail below in conjunction with various embodiments.

[0040] Embodiment 1

[0041] According to an embodiment of the present invention, an embodiment of a method for drawing a distribution network topology map is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0042] Figure 1 is a flow chart of an optional method for drawing a distribution network topology map according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0043] Step S101, obtaining a memory topology model of a target distribution network, wherein the memory topology model records N distribution network components in the target distribution network and the physical connection relationship between the distribution network components, where N is a positive integer.

[0044] Step S102, establishing a target decision tree according to the memory topology model, wherein the target decision tree represents distribution network components of different importance through tree nodes at different node positions, and represents physical connection relationships through tree branches.

[0045] Step S103, determining the drawing order of each element in the distribution network topology map based on the target decision tree, and drawing the initial topology map according to the drawing order, wherein the elements include: device nodes and device branches.

[0046] Step S104, adjusting the initial topology map according to a preset mapping rule to obtain a distribution network topology map of the target distribution network.

[0047] Through the above steps, the memory topology model of the target distribution network can be obtained first, wherein the memory topology model records N distribution network components in the target distribution network, and the physical connection relationship between the distribution network components, where N is a positive integer, and then a target decision tree is established based on the memory topology model, wherein the target decision tree represents distribution network components of different importance through tree nodes at different node positions, and represents the physical connection relationship through tree branches, and then the drawing order of each element in the distribution network topology map is determined based on the target decision tree, and an initial topology map is drawn according to the drawing order, wherein the elements include: device nodes and device branches, and finally the initial topology map is adjusted according to the preset drawing rules to obtain the distribution network topology map of the target distribution network.

[0048] In an embodiment of the present invention, by acquiring the memory topology model of the target distribution network, all distribution network components and physical connection relationships existing in the distribution network are clarified, and then by establishing a target decision tree, the importance of each component in the power supply and distribution process of the target distribution network is intuitively represented. On this basis, the corresponding drawing order of each component when converted into an element in the distribution network topology map is determined, and an initial topology map including elements such as device nodes and device branches is drawn according to the drawing order. The initial topology map is further adjusted according to preset drawing rules to obtain a distribution network topology map that can intuitively display the target distribution network structure information and power flow information, which can be used by the distribution dispatching system to capture the distribution network power supply path in real time and perform real-time dispatching management, thereby solving the technical problem in the related technology that the distribution network dispatching system cannot quickly obtain the distribution network structure topology map, resulting in the inability to perform real-time dispatching management of the power supply path.

[0049] The embodiment of the present invention is described in detail below in combination with the above steps.

[0050] The implementing subject of the embodiment of the present invention can be a distribution system or a power dispatching system. It combines engineering graph theory, artificial intelligence technology and decision tree algorithm to provide a distribution network power supply path automatic mapping technology to solve the problem that the power supply path of the distribution network in the power supply guarantee scenario cannot be automatically mapped, thereby causing difficulties in carrying out power real-time dispatching business.

[0051] Step S101, obtaining a memory topology model of a target distribution network, wherein the memory topology model records N distribution network components in the target distribution network and the physical connection relationship between the distribution network components, where N is a positive integer.

[0052] Specifically, the target distribution network may be a distribution network for which a power transmission path is to be determined in different application scenarios, including but not limited to: an urban distribution network, an industrial distribution network, a rural distribution network, a microgrid or a distribution network in a special location.

[0053] In an embodiment of the present invention, a distribution network memory topology model diagram is obtained by mapping a distribution system database into a diagram. Optionally, step S101 includes: querying the distribution system database and extracting power supply and distribution information of the target distribution network; determining N distribution network components in the target distribution network based on the equipment information in the power supply and distribution information, such as substations, feeders, distribution transformers, switchgear, etc., for constituting nodes of the memory topology model; determining the physical connection relationship between the N distribution network components based on the line configuration information in the power supply and distribution information, for example, connecting through cables, wires, etc., for constituting edges of the memory topology model; calling the distribution network components from the memory model library, and connecting the N distribution network components according to the physical connection relationship to obtain the memory topology model.

[0054] It should be noted that the memory model library is a database or library that stores memory models of various distribution network components. These memory models carry information such as the structure, characteristics, and connection methods of the components, and can be called as needed to build a memory topology model of the distribution network.

[0055] The power distribution system database in the embodiment of the present invention supports query and retrieval functions, which facilitates the retrieval of power supply and distribution information of the target distribution network, including at least equipment information and line configuration information, such as the location, capacity, voltage and other data of distribution stations, transformer substations, distribution lines, cables, switchgear, etc. Optionally, after obtaining the memory topology model, before executing step S102, it also includes: identifying the feeder ring network in the target distribution network according to the memory topology model, and recording the total number of feeder ring networks; identifying the power supply points and contact points in the target distribution network according to the memory topology model and the feeder ring network, and recording the total number of power supply points and the total number of contact points; determining the topology map drawing range based on the total number of feeder ring networks, the total number of power supply points and the total number of contact points.

[0056] It should be noted that the feeder ring network refers to the loop in the distribution network, the contact point refers to the node connecting different loops, and the power supply point refers to the power supply point in the distribution network. The purpose of recording the total number of feeder ring networks is to accurately present the structure of the distribution network in the topology map, and to determine the area to be displayed in the topology map to ensure the clarity and readability of the topology map.

[0057] In an optional embodiment, after determining the drawing range of the topology map, it is also possible to determine whether to include the distribution transformer (i.e., distribution transformer) and the trunk of the ring network (i.e., the main loop of the distribution network) in the topology map according to user needs or drawing purposes.

[0058] Step S102, establishing a target decision tree according to the memory topology model, wherein the target decision tree represents distribution network components of different importance through tree nodes at different node positions, and represents physical connection relationships through tree branches.

[0059] Optionally, step S102 includes: analyzing the memory topology model through a preset decision tree algorithm to obtain an analysis result, wherein the analysis result is used to record the importance ranking of N distribution network components in the power supply and distribution process of the target distribution network; for each distribution network component, determining the node position of the tree node corresponding to the distribution network component based on the importance ranking in the analysis result, and adding basic information of the distribution network component at the node position; after determining the node positions of the tree nodes corresponding to all distribution network components, adding tree branches based on the physical connection relationship to obtain the target decision tree.

[0060] It should be noted that the preset decision tree algorithm is a machine learning algorithm used to make decisions based on the attribute characteristics of the input data. In the embodiment of the present invention, it is used to automatically complete the initial layout of the power supply path based on the attribute characteristics carried in the topology model (i.e., the relevant information of each distribution network component).

[0061] In the embodiment of the present invention, the importance ranking of the distribution network components is obtained by analyzing the attribute characteristics of the components, and the attribute characteristics refer to the characteristics of the device type, current direction, connection relationship, etc. Before the analysis, it is necessary to use the memory topology model to weaken the spatial attributes of each component and the physical connection line, and abstract the distribution network into the structural relationship between nodes and connection lines, which is convenient for analysis and calculation. Optionally, the memory topology model is analyzed by a preset decision tree algorithm to obtain the analysis result, including: converting N distribution network components in the memory topology model into N mapping sample points to obtain a mapping sample set, and recording the sample category information of each mapping sample point during the conversion process; for each mapping sample point, calculating the sample ratio information of the mapping sample point based on the mapping sample set; obtaining the attribute feature set corresponding to the target distribution network, wherein the attribute feature set contains R attribute feature values, each attribute feature value corresponds to a feature dimension, which is used to measure the importance of the feature dimension in the power supply and distribution process of the target distribution network, and R is a positive integer; initializing the preset decision tree algorithm based on the sample category information, the sample ratio information and the attribute feature set, and making importance decisions on the N distribution network components through the initialized preset decision tree algorithm to obtain the analysis result.

[0062] Optionally, the step of initializing a preset decision tree algorithm based on sample category information, sample proportion information and an attribute feature set includes: calculating the information entropy of the mapped sample set based on the sample category information and sample proportion information of all mapped sample points; for each feature dimension, calculating the information gain value of the mapped sample set in the feature dimension based on the attribute feature value and the information entropy; sorting all information gain values, and determining the feature dimension corresponding to the maximum information gain value based on the sorting result, and determining the feature dimension as the decision feature; and using the decision feature to initialize the preset decision tree algorithm.

[0063] In an embodiment of the present invention, distribution network components extracted from a memory topology model, such as transformers, switchgear, etc., are converted into input samples of a decision tree algorithm; the category information to which each mapped sample point belongs is usually classified according to the type or function of the distribution network component, so that the decision tree algorithm can perform classification and analysis; the information on the proportion of each mapped sample point in the entire mapped sample set is used to reflect the importance of the mapped sample point; and the discrete degree value is used to measure the degree of connection between distribution network components.

[0064] In an optional embodiment, the information entropy of the image sample set can also be calculated. For example, Z can be used to represent the image sample set, k can represent the sample category, and p can represent the sample category. k Representing the proportion of sample point k in the graph sample set, the information entropy expression of the topological graph sample set Z is as follows:

[0065] In another optional embodiment, the information gain of the image sample set based on all sample points can be further calculated. Let the discrete attribute set A contain the discrete attribute value a corresponding to each image sample point. Based on the value a, all image sample points are divided into V branch nodes. The image sample point is in the corresponding branch node V, and the branch node contains the value number A. v The information gain calculation formula obtained by dividing the image sample set Z by attribute A is:

[0066] Furthermore, the information gain values ​​of other discrete attributes b, c, etc. can be obtained through the above process, and the information gain values ​​ax{Gain(Z,A), Gain(Z,B),…} corresponding to all discrete attributes are integrated. The discrete attribute corresponding to the maximum information gain value is set as the indicator of the decision tree algorithm to evaluate the importance of the component to divide the topology map nodes. After the division is completed, the remaining nodes are further divided using the attributes with the maximum information gain. The above process is repeated and iterated until the target decision tree for automatic mapping of the low-voltage distribution network topology map is established.

[0067] Step S103, determine the drawing order of each element in the distribution network topology map based on the target decision tree, and draw the initial topology map according to the drawing order, wherein the elements include: device nodes and device branches. The embodiment of the present invention uses a decision tree algorithm to complete the initial automatic layout of the power supply path according to the attribute characteristics of the topology map.

[0068] Optionally, step S103 includes: for each tree node in the target decision tree, determining the device node corresponding to the tree node in the distribution network topology map and the device branch connected to the device node by analyzing the basic information carried by the tree node and all the tree branches connected to the tree node; determining the drawing order of the device nodes and the device branches during the drawing process by analyzing the node position of the tree node in the target decision tree and the relative position of the tree branches connected to the tree node.

[0069] Step S104, adjusting the initial topology map according to the preset drawing rules to obtain the distribution network topology map of the target distribution network. The embodiment of the present invention can further adjust the device branch line drawing direction and the node position of different devices through the topology map layout adjustment method to achieve the layout adjustment of the low-voltage distribution network power supply path map.

[0070] Optionally, step S104 includes: adjusting the drawing order of device nodes connected to device branches whose branch lengths are greater than a preset length according to a long line priority principle in a preset drawing rule; and confirming the drawing direction of the device branches connected to each device node according to the adjusted drawing order and a node balance principle in a preset drawing rule.

[0071] An optional embodiment is to give priority to the longest branches when drawing the topology map, and distribute the longer straight lines on both sides of the main line to make the layout more uniform; assign drawing directions to the brother branches in the topology map according to the sorting order, and follow the principle of arranging even numbers and odd numbers first up and then down, and first right and then left, to reduce the overlapping and crossing of branches.

[0072] For example, when the branch line is an even-numbered branch line and the branch line is sorted as an odd number, the initial direction of the branch line is assigned to upward, and if the branch line is sorted as an even number, the initial direction is assigned to downward; when the branch line is an odd-numbered branch line and the branch line is sorted as an odd number, the initial direction of the branch line is assigned to the right, and if the branch line is sorted as an even number, the initial direction is assigned to the left.

[0073] In the embodiment of the present invention, the initial direction of the branch line can also be set to b, and the drawn branch line can be adjusted according to the balance of nodes on both sides of the trunk line and the branch line ratio, where the branch line ratio is the ratio of the number of each branch line node to the total number of all brother branch line nodes.

[0074] In an optional embodiment, when the branch line node ratio is higher than 0.5 during the adjustment process based on the branch line ratio, it indicates that the branch line node ratio is high and needs to occupy the initial drawing direction b alone. In order to make the nodes on both sides of the trunk line have high uniformity, the drawing directions of other unadjusted branches are set to the opposite direction of b. The exemplary calculation formula for the branch line ratio is: Among them, M represents the total number of brother branches, C i It refers to the total number of nodes in the brother branch when the sorting number is i.

[0075] For example, after determining the initial direction b, the number of branches of the branch node adjacent to the trunk line is calculated and represented by (N1, N2). The possible values ​​of the number of branches are 0, 1, and 2. Without considering the order, the number of adjacent node branches includes six combinations, such as Figure 4 As shown, when only one adjacent node is occupied in the same direction, the number of adjacent node branches takes the value of (0, 1) or (2, 1), and the updated initial direction is opposite to the direction represented by b; when the number of adjacent node branches takes the value of (1, 1), it is necessary to determine whether the drawing directions of adjacent brother branches are the same. If they are the same, the updated initial direction is opposite to the direction. If they are opposite, the updated initial direction is opposite to the drawing direction of the brother branches of the adjacent node with a larger number of nodes; when the drawing direction of the adjacent node is not occupied or is completely occupied, the number of adjacent node branches takes the value of (0, 0), (2, 2) or (0, 2), and there is no need to update the initial direction b.

[0076] In an embodiment of the present invention, the initial drawing of the low-voltage distribution network power supply path diagram can be completed based on the decision tree algorithm, and then the layout can be adjusted according to the actual situation to obtain the best layout result. When drawing the low-voltage distribution network power supply path, the nodes in the topology diagram can be evenly distributed to avoid the intersection and overlap of straight lines, thereby improving the quality and efficiency of the topology diagram.

[0077] In the embodiment of the present invention, the low-voltage distribution network topology map can be automatically drawn, and the existence of intersections and the like can be avoided. The automatic drawing effectiveness is high, the generated topology map can be directly used by dispatchers, and the drawing process has low time complexity.

[0078] The present invention is described below in conjunction with another specific implementation manner.

[0079] In order to solve the problem that the power supply path of the distribution network cannot be automatically mapped in the power supply guarantee scenario, which makes business development difficult, the implementation mode of the present invention provides a low-voltage distribution network power supply path automatic mapping process, and effectively obtains the distribution network memory topology model through the mapping of the distribution automation database, so as to realize the automatic mapping of the low-voltage distribution network topology map.

[0080] Figure 2is a flow chart of an optional method for automatically mapping a low-voltage distribution network power supply path according to an embodiment of the present invention, such as Figure 2 As shown, the process includes: obtaining a memory topology model; obtaining contact points and power supply points of different feeder ring networks; calculating the number of feeder ring networks required in the model; drawing the range of the topology map; obtaining whether to draw the distribution transformer and the ring network trunk into the topology map; establishing a decision tree for automatic drawing of the low-voltage distribution network topology map when determining the drawing; and completing the initial automatic layout of the topology map.

[0081] It should be noted that, regarding the application of the decision tree algorithm (i.e., the preset decision tree algorithm in the first embodiment), a set of map samples can be established, in which the sample points are used to characterize the map components in the distribution network topology map, such as substations, feeders, distribution transformers, switchgear, etc. The map sample set is used to establish the target decision tree. Z can be used to represent the map sample set, k represents the sample category, p represents the sample type, k Representing the proportion of sample point k in the graph sample set, the information entropy expression of the set Z is as follows:

[0082] Furthermore, the information gain of the image sample set based on all sample points is calculated. Let the discrete attribute set A contain the discrete attribute a of the image component corresponding to each image sample point. Based on the value of a, all image sample points are divided into V branch nodes. The image sample point is in the corresponding branch node V, which contains the value number A. v The information gain calculation formula obtained by dividing the image sample set Z by attribute A is:

[0083]

[0084] Through the above process, the information gain values ​​of other discrete attributes such as b and c can be obtained, and the information gain values ​​ax{Gain(Z,A),Gain(Z,B),…} corresponding to all discrete attributes can be integrated. The discrete attribute corresponding to the maximum information gain value is set as the indicator of the decision tree algorithm for evaluating the importance of the component to divide the topology map nodes. After the division is completed, the remaining nodes are further divided using the attribute with the maximum information gain. The above process is repeated and iterated until a decision tree for automatically mapping the low-voltage distribution network topology map is established.

[0085] The implementation mode of the present invention utilizes a decision tree algorithm to complete the initial automatic layout of the power supply path according to the attribute characteristics of the topology map. The topology map layout adjustment method can further be used to adjust the device branch line drawing direction and the node positions of different devices to achieve the layout adjustment of the low-voltage distribution network power supply path map.

[0086] An optional embodiment is to give priority to the longest branches when drawing the topology map, and distribute the longer straight lines on both sides of the main line to make the layout more uniform; assign drawing directions to the brother branches in the topology map according to the sorting order, and follow the principle of arranging even numbers and odd numbers first up and then down, and first right and then left, to reduce the overlapping and crossing of branches.

[0087] Figure 3 It is a flowchart of an optional layout adjustment method of a low-voltage distribution network power supply path diagram according to an embodiment of the present invention, the method comprising: traversing all branch lines of the topology diagram; for each branch line, determining whether the branch line is an even-numbered branch line; when the branch line is an even-numbered branch line and the branch line is sorted as an odd number, assigning the initial direction of the branch line to upward, and if the branch line is sorted as an even number, assigning the initial direction to downward; when the branch line is an odd-numbered branch line and the branch line is sorted as an odd number, assigning the initial direction of the branch line to right, and if the branch line is sorted as an even number, assigning the initial direction to left.

[0088] Furthermore, the initial direction of the branch line can be set to b, and the drawn branch line can be adjusted according to the balance of nodes on both sides of the trunk line and the branch line ratio, where the branch line ratio is the ratio of the number of each branch line node to the total number of all brother branch line nodes.

[0089] In an optional embodiment, when the branch line node ratio is higher than 0.5 during the adjustment process based on the branch line ratio, it indicates that the branch line node ratio is high and needs to occupy the initial drawing direction b alone. In order to make the nodes on both sides of the trunk line have high uniformity, the drawing directions of other unadjusted branches are set to the opposite direction of b. The exemplary calculation formula for the branch line ratio is: Among them, M represents the total number of brother branches, C i It refers to the total number of nodes in the brother branch when the sorting number is i.

[0090] In another optional embodiment, Figure 4 The flowchart of an optional power supply path layout adjustment method based on a node balancing strategy according to an embodiment of the present invention is shown in FIG. 1 . In this method, after determining the initial direction b, the number of adjacent node branches of the branch node on the trunk line is calculated and represented by (N1, N2). The possible values ​​of the number of branches are 0, 1, and 2. Regardless of the order, the number of adjacent node branches includes six combinations, such as Figure 4As shown, when only one adjacent node is occupied in the same direction, the number of adjacent node branches takes the value of (0, 1) or (2, 1), and the updated initial direction is opposite to the direction represented by b; when the number of adjacent node branches takes the value of (1, 1), it is necessary to determine whether the drawing directions of adjacent brother branches are the same. If they are the same, the updated initial direction is opposite to the direction. If they are opposite, the updated initial direction is opposite to the drawing direction of the brother branches of the adjacent node with a larger number of nodes; when the drawing direction of the adjacent node is not occupied or is completely occupied, the number of adjacent node branches takes the value of (0, 0), (2, 2) or (0, 2), and there is no need to update the initial direction b.

[0091] In an embodiment of the present invention, the initial drawing of the low-voltage distribution network power supply path diagram can be completed based on the decision tree algorithm, and then the layout can be adjusted according to the actual situation to obtain the best layout result. When drawing the low-voltage distribution network power supply path, the nodes in the topology diagram can be evenly distributed to avoid the intersection and overlap of straight lines, thereby improving the quality and efficiency of the topology diagram.

[0092] In the embodiment of the present invention, the low-voltage distribution network topology map can be automatically drawn, and the existence of intersections and the like can be avoided. The automatic drawing effectiveness is high, the generated topology map can be directly used by dispatchers, and the drawing process has low time complexity.

[0093] The embodiments of the present invention have the functions of real-time updating, automatic generation, in-depth analysis and optimization adjustment to meet the needs of power grid management and improve the operating efficiency and reliability of the distribution system.

[0094] The present invention is described below in conjunction with another optional embodiment.

[0095] Embodiment 2

[0096] The distribution network topology map drawing device provided in this embodiment includes multiple implementation units, each implementation unit corresponds to each implementation step in the above-mentioned embodiment 1.

[0097] Figure 5 is a schematic diagram of an optional distribution network topology diagram drawing device according to an embodiment of the present invention, such as Figure 5 As shown, the device may include: an acquisition unit 51, an establishment unit 52, a determination unit 53, and an adjustment unit 54.

[0098] The acquisition unit 51 is used to acquire a memory topology model of the target distribution network, wherein the memory topology model records N distribution network components in the target distribution network and the physical connection relationship between the distribution network components, where N is a positive integer;

[0099] An establishing unit 52 is used to establish a target decision tree according to the memory topology model, wherein the target decision tree represents distribution network components of different importance through tree nodes at different node positions, and represents physical connection relationships through tree branches;

[0100] A determination unit 53 is used to determine the drawing order of each element in the distribution network topology diagram based on the target decision tree, and draw the initial topology diagram according to the drawing order, wherein the elements include: device nodes and device branches;

[0101] The adjusting unit 54 is used to adjust the initial topology map according to a preset mapping rule to obtain a distribution network topology map of the target distribution network.

[0102] The above-mentioned distribution network topology drawing device can first obtain the memory topology model of the target distribution network through the acquisition unit 51, wherein the memory topology model records N distribution network components in the target distribution network, and the physical connection relationship between each distribution network component, N is a positive integer, and then establish a target decision tree according to the memory topology model through the establishment unit 52, wherein the target decision tree represents distribution network components of different importance through tree nodes at different node positions, and represents the physical connection relationship through tree branches, and then determine the drawing order of each element in the distribution network topology map based on the target decision tree through the determination unit 53, and draw the initial topology map according to the drawing order, wherein the elements include: device nodes and device branches, and finally adjust the initial topology map according to the preset drawing rules through the adjustment unit 54 to obtain the distribution network topology map of the target distribution network.

[0103] In an embodiment of the present invention, by acquiring the memory topology model of the target distribution network, all distribution network components and physical connection relationships existing in the distribution network are clarified, and then by establishing a target decision tree, the importance of each component in the power supply and distribution process of the target distribution network is intuitively represented. On this basis, the corresponding drawing order of each component when converted into an element in the distribution network topology map is determined, and an initial topology map including elements such as device nodes and device branches is drawn according to the drawing order. The initial topology map is further adjusted according to preset drawing rules to obtain a distribution network topology map that can intuitively display the target distribution network structure information and power flow information, which can be used by the distribution dispatching system to capture the distribution network power supply path in real time and perform instant dispatching management, thereby solving the technical problem in the related technology that the distribution network dispatching system cannot quickly obtain the distribution network structure topology map, resulting in the inability to perform instant dispatching management of the power supply path.

[0104] Optionally, the acquisition unit includes: a query module, used to query the distribution system database and extract the power supply and distribution information of the target distribution network; a fifth determination module, used to determine the N distribution network components in the target distribution network based on the equipment information in the power supply and distribution information; a sixth determination module, used to determine the physical connection relationship between the N distribution network components based on the line configuration information in the power supply and distribution information; a connection module, used to call the distribution network components from the memory model library, and connect the N distribution network components according to the physical connection relationship to obtain the memory topology model.

[0105] Optionally, the distribution network topology map drawing device also includes: a first identification module, used to identify the feeder ring network in the target distribution network based on the memory topology model, and record the total number of feeder ring networks; a second identification module, used to identify the power points and contact points in the target distribution network based on the memory topology model and the feeder ring network, and record the total number of power points and the total number of contact points; a first determination module, used to determine the topology map drawing range based on the total number of feeder ring networks, the total number of power points and the total number of contact points.

[0106] Optionally, the establishment unit includes: an analysis module, which is used to analyze the memory topology model through a preset decision tree algorithm to obtain an analysis result, wherein the analysis result is used to record the importance rankings of N distribution network components in the power supply and distribution process of the target distribution network; a second determination module, which is used to determine the node position of the tree node corresponding to each distribution network component based on the importance ranking in the analysis result, and add basic information of the distribution network component at the node position; an adding module, which is used to add tree branches based on the physical connection relationship after determining the node positions of the tree nodes corresponding to all distribution network components to obtain a target decision tree.

[0107] Optionally, the analysis module includes: a conversion submodule, which is used to convert N distribution network components in the memory topology model into N mapped sample points, obtain a mapped sample set, and record the sample category information of each mapped sample point during the conversion process; a first calculation submodule, which is used to calculate the sample proportion information of the mapped sample point based on the mapped sample set for each mapped sample point; an acquisition submodule, which is used to obtain an attribute feature set corresponding to the target distribution network, wherein the attribute feature set contains R attribute feature values, each attribute feature value corresponds to a feature dimension, which is used to measure the importance of the feature dimension in the power supply and distribution process of the target distribution network, and R is a positive integer; an initialization submodule, which is used to initialize the preset decision tree algorithm based on the sample category information, sample proportion information and attribute feature set, and make importance decisions on N distribution network components through the initialized preset decision tree algorithm to obtain analysis results.

[0108] Optionally, the analysis module also includes: a second calculation submodule, which is used to calculate the information entropy of the mapped sample set based on the sample category information and sample proportion information of all mapped sample points; a third calculation submodule, which is used to calculate the information gain value of the mapped sample set in the feature dimension for each feature dimension based on the attribute feature value and the information entropy; a sorting submodule, which is used to sort all information gain values, and determine the feature dimension corresponding to the maximum information gain value based on the sorting result, and determine the feature dimension as the decision feature; a setting submodule, which is used to use the decision feature to initialize the preset decision tree algorithm.

[0109] Optionally, the determination unit includes: a third determination module, which is used to determine, for each tree node in the target decision tree, the device node corresponding to the tree node in the distribution network topology map and the device branch connected to the device node by analyzing the basic information carried by the tree node and all the tree branches connected to the tree node; a fourth determination module, which is used to determine the drawing order of the device nodes and the device branches during the drawing process by analyzing the node position of the tree node in the target decision tree and the relative position of the tree branches connected to the tree node.

[0110] Optionally, the adjustment unit includes: an adjustment module for adjusting the drawing order of device nodes connected to device branches whose branch lengths are greater than a preset length according to a long line priority principle in a preset drawing rule; and a confirmation module for confirming the drawing direction of device branches connected to each device node according to the adjusted drawing order and a node balance principle in a preset drawing rule.

[0111] The above-mentioned distribution network topology map drawing device may also include a processor and a memory. The above-mentioned acquisition unit 51, establishment unit 52, determination unit 53, adjustment unit 54, etc. are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize the corresponding functions.

[0112] The processor includes a kernel, and the kernel retrieves the corresponding program unit from the memory. One or more kernels can be set, and the drawing order of each element in the distribution network topology map is determined based on the target decision tree by adjusting kernel parameters, and the initial topology map is drawn according to the drawing order, and the initial topology map is adjusted according to the preset drawing rules to obtain the distribution network topology map of the target distribution network.

[0113] The above-mentioned memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0114] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing a program that is initialized with the following method steps: obtaining a memory topology model of a target distribution network, wherein the memory topology model records N distribution network components in the target distribution network, and the physical connection relationship between each distribution network component, where N is a positive integer; establishing a target decision tree based on the memory topology model, wherein the target decision tree represents distribution network components of different importance through tree nodes at different node positions, and represents the physical connection relationship through tree branches; determining the drawing order of each element in the distribution network topology map based on the target decision tree, and drawing an initial topology map according to the drawing order, wherein the elements include: device nodes and device branches; adjusting the initial topology map according to a preset drawing rule to obtain the distribution network topology map of the target distribution network.

[0115] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is further provided, the computer-readable storage medium including a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the method for drawing a distribution network topology map of any one of the above-mentioned embodiments one.

[0116] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by one or more processors, the one or more processors implement the method for drawing a distribution network topology map of any one of the above-mentioned embodiments one.

[0117] Figure 6 1 is a hardware structure block diagram of an electronic device (or mobile device) for a method for drawing a distribution network topology map according to an embodiment of the present invention. Figure 6 As shown, the electronic device may include one or more ( Figure 6 602a, 602b, ..., 602n are used to illustrate) processor 602 (processor 602 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), and memory 604 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the I / O interface), a network interface, a keyboard, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 6 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 6 More or fewer components as shown, or with Figure 6 Different configurations shown.

[0118] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0119] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0120] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0121] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0122] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0123] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server or a 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: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0124] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for drawing a distribution network topology map, characterized in that: include: Obtaining a memory topology model of a target distribution network, wherein the memory topology model records N distribution network components in the target distribution network and a physical connection relationship between the distribution network components, where N is a positive integer; Establishing a target decision tree according to the memory topology model, wherein the target decision tree represents the distribution network components of different importance through tree nodes at different node positions, and represents the physical connection relationship through tree branches; Determine the drawing order of each element in the distribution network topology diagram based on the target decision tree, and draw an initial topology diagram according to the drawing order, wherein the elements include: device nodes and device branches; The initial topology map is adjusted according to a preset mapping rule to obtain the distribution network topology map of the target distribution network.

2. The mapping method according to claim 1, characterized in that: Before establishing a target decision tree according to the memory topology model, the following steps are included: Identify the feeder ring network in the target distribution network according to the memory topology model, and record the total number of feeder ring networks; Identify power supply points and contact points in the target distribution network according to the memory topology model and the feeder ring network, and record the total number of power supply points and the total number of contact points; The topology map drawing range is determined based on the total number of the feeder ring networks, the total number of power supply points and the total number of contact points.

3. The mapping method according to claim 1, characterized in that: The step of establishing a target decision tree according to the memory topology model includes: Analyze the memory topology model by a preset decision tree algorithm to obtain an analysis result, wherein the analysis result is used to record the importance ranking of the N distribution network components in the power supply and distribution process of the target distribution network; For each of the distribution network components, determine the node position of the tree node corresponding to the distribution network component based on the importance ranking in the analysis result, and add basic information of the distribution network component at the node position; After determining the node positions of the tree nodes corresponding to all the power distribution network components, the tree branches are added based on the physical connection relationship to obtain the target decision tree.

4. The mapping method according to claim 3, characterized in that: The step of analyzing the memory topology model by using a preset decision tree algorithm to obtain an analysis result includes: Convert the N distribution network components in the memory topology model into N mapping sample points to obtain a mapping sample set, and record the sample category information of each mapping sample point during the conversion process; For each of the mapping sample points, calculating sample ratio information of the mapping sample point based on the mapping sample set; Obtain an attribute feature set corresponding to the target distribution network, wherein the attribute feature set includes R attribute feature values, each of which corresponds to a feature dimension, which is used to measure the importance of the feature dimension in the power supply and distribution process of the target distribution network, and R is a positive integer; The preset decision tree algorithm is initialized based on the sample category information, the sample proportion information and the attribute feature set, and the importance decision is made on the N distribution network components through the initialized preset decision tree algorithm to obtain the analysis result.

5. The mapping method according to claim 4, characterized in that: The step of initializing the preset decision tree algorithm based on the sample category information, the sample ratio information and the attribute feature set includes: Calculate the information entropy of the image sample set based on the sample category information and the sample ratio information of all the image sample points; For each feature dimension, calculating the information gain value of the image sample set in the feature dimension based on the attribute feature value and the information entropy; Sorting all the information gain values, and determining the feature dimension corresponding to the maximum information gain value based on the sorting result, and determining the feature dimension as the decision feature; The preset decision tree algorithm is initialized using the decision feature.

6. The mapping method according to claim 1, characterized in that: The step of determining the drawing order of each element in the distribution network topology diagram based on the target decision tree includes: For each tree node in the target decision tree, by analyzing the basic information carried by the tree node and all tree branches connected to the tree node, determine the device node corresponding to the tree node in the distribution network topology map and the device branch line connected to the device node; The drawing order of the device nodes and the device branches in the drawing process is determined by analyzing the node position of the tree node in the target decision tree and the relative position of the tree branches connected to the tree node.

7. The mapping method according to claim 1, characterized in that: The step of adjusting the initial topological map according to a preset mapping rule comprises: According to the long line priority principle in the preset drawing rule, the drawing order of the device nodes connected to the device branch line whose branch line length is greater than the preset length is adjusted; According to the adjusted drawing order and the node balance principle in the preset drawing rule, the drawing direction of the device branch line connected to each device node is confirmed.

8. A device for drawing a distribution network topology map, characterized in that: include: An acquisition unit, used to acquire a memory topology model of a target distribution network, wherein the memory topology model records N distribution network components in the target distribution network and a physical connection relationship between the distribution network components, where N is a positive integer; An establishing unit, configured to establish a target decision tree according to the memory topology model, wherein the target decision tree represents the distribution network components of different importance through tree nodes at different node positions, and represents the physical connection relationship through tree branches; A determination unit, configured to determine a drawing order of elements in a distribution network topology diagram based on the target decision tree, and draw an initial topology diagram according to the drawing order, wherein the elements include: device nodes and device branches; An adjustment unit is used to adjust the initial topology map according to a preset mapping rule to obtain the distribution network topology map of the target distribution network.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the method for drawing a distribution network topology map according to any one of claims 1 to 7.

10. An electronic device, characterized in that: It includes one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method for drawing a distribution network topology map as described in any one of claims 1 to 7.

Images