Real-time power grid automatic composition method and system

Abstract

The invention discloses a real-time power grid automatic composition method and system, and the method comprises the steps: obtaining the position of a transformer substation, carrying out the layout of the position of the transformer substation through employing a layout algorithm, and carrying out the telescoping of the layout through employing a clustering algorithm according to the density distribution of the position, and obtaining a first position; based on the first position, determining positions of a bus and a line in the transformer substation to obtain a second position; building a first penalty model according to the second position, and carrying out overall layout on lines between the substations; building a second penalty model based on the overall layout result, and optimizing the layout between the lines; the parameters of the first penalty model and the second penalty model are initialized, the initialized parameters are used for mapping, the parameters are adjusted according to the mapping effect, the parameters are updated according to automatic learning, a power grid whole graph is obtained, and the generation efficiency and quality of the power grid wiring diagram are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of power grid wiring diagram automatic drawing, and particularly relates to a real-time power grid automatic mapping method and system. BACKGROUND

[0002] As the most intuitive and most comprehensive information in the power grid, the power grid wiring diagram plays an irreplaceable role in the operation and management process. With the rapid growth of power consumption, the dramatic increase in new energy installation capacity represented by photovoltaic, and the frequent changes in power grid wiring mode, the maintenance work of the wiring diagram is facing a huge test. On the other hand, with the increasing complexity of the power grid, the wiring diagram faced by the operation personnel is increasingly large, and the fixed wiring diagram cannot meet the needs of the daily efficient management of the operation personnel.

[0003] According to the topology of the power grid, the power system full map containing the in-station and out-station equipment is automatically generated by analyzing the position relationship of the power stations and the connection relationship between the lines of the power stations, so as to assist the operation personnel in comprehensively understanding the wiring mode and the operation mode of the power grid. SUMMARY

[0004] In view of the above existing problems, the present application is proposed.

[0005] Therefore, the present application provides a real-time power grid automatic mapping method and system to solve the problem that the fixed wiring diagram cannot meet the daily efficient management of the operation personnel due to the dramatic increase in new energy installation capacity represented by photovoltaic, the frequent changes in power grid wiring mode, and the increasingly large wiring diagram faced by the operation personnel.

[0006] To solve the above technical problems, the present application provides the following technical solutions:

[0007] In a first aspect, the present application provides a real-time power grid automatic mapping method, comprising:

[0008] Obtaining the position of the substation, using a layout algorithm to layout the position of the substation, and using a clustering algorithm to stretch and contract the layout according to the density distribution of the position to obtain a first position;

[0009] Based on the first position, the positions of the busbar and the line in the substation are determined to obtain a second position;

[0010] According to the second position, a first penalty model is built to layout the lines between the substations as a whole;

[0011] Based on the overall layout result, a second penalty model is built to optimize the layout between the lines;

[0012] The parameters of the first penalty model and the second penalty model are initialized and graphed with the initialized parameters, the parameters are adjusted according to the graphing effect, and the parameters are updated according to automatic learning, and a full grid of the power grid is obtained.

[0013] As a preferred scheme of the real-time power grid automatic graphing method, the layout algorithm is used to layout the substation positions, including:

[0014] The gravity of the substations, the repulsive force between the substations, and the elastic force between the substations are defined respectively;

[0015] The gravity, the repulsive force, and the elastic force of the substations are integrated to balance the force, and the positions of the substations are adjusted according to a set step size.

[0016] As a preferred scheme of the real-time power grid automatic graphing method, the layout is scaled according to the density distribution of the positions by using a clustering algorithm, including:

[0017] For each substation area, the distance of each substation in the area to the kth nearest substation is calculated to obtain a first distance set;

[0018] The median of the first distance set is taken, and the reciprocal of the median is taken as the density of the area;

[0019] According to the density of each area, the width of the scaled area is calculated to obtain the first positions of the substations.

[0020] As a preferred scheme of the real-time power grid automatic graphing method, the positions of the busbars and the lines in the substations are determined, including:

[0021] The gravity centers of each line interval and the gravity centers of the busbars are defined respectively;

[0022] The positions of the busbars are adjusted according to the positional relationship of the busbar gravity centers;

[0023] The positions of the outgoing line intervals are adjusted according to the positional relationship of the line interval gravity centers on the same group of busbars;

[0024] The internal wiring diagram of the substation is obtained in combination with the wiring mode of the power grid.

[0025] As a preferred scheme of the real-time power grid automatic graphing method, the first penalty model is built, including:

[0026] Different-dimensional penalty functions and reward functions are defined respectively for the purposes of area control, channel density, avoiding excessively long length, and reducing unnecessary inflection points;

[0027] The overall layout of the line path is generated by combining the penalty function and the reward function in different dimensions, and a first penalty model constituting the overall layout of the line is obtained.

[0028] As a preferred scheme of the method for real-time power grid automatic mapping, the building of the second penalty model comprises:

[0029] The penalty functions of the number of line intersection points, unnecessary inflection points and lines with too close distances are respectively established.

[0030] The second penalty model constituting the layout detail optimization is obtained by combining the penalty functions.

[0031] As a preferred scheme of the method for real-time power grid automatic mapping, the initialization of the parameters of the first penalty model and the second penalty model and the mapping by using the initialized parameters comprise:

[0032] The parameters in different dimensions in the first penalty model and the second penalty model are compared by selecting a power grid dispatching expert to obtain an evaluation matrix, and initial values of the parameters in different dimensions in the first penalty model and the second penalty model are calculated.

[0033] The mapping is performed according to the topological relationship of the power grid model by using the initialized parameters in different dimensions.

[0034] According to the mapping effect, the parameters in the corresponding dimensions are improved based on the expert evaluation result.

[0035] In a second aspect, the application provides a system for real-time power grid automatic mapping, comprising:

[0036] A position layout module is configured to obtain substation positions, perform layout on the substation positions by using a layout algorithm, perform stretching and contraction on the layout by using a clustering algorithm according to the density distribution of the positions, and obtain first positions.

[0037] A position confirmation module is configured to determine the positions of busbars and lines in substations based on the first positions, and obtain second positions.

[0038] A first penalty model building module is configured to build a first penalty model according to the second positions, and perform overall layout on lines between substations.

[0039] A second penalty model building module is configured to build a second penalty model based on the overall layout result, and optimize the layout between lines.

[0040] A mapping module is configured to initialize parameters of the first penalty model and the second penalty model, and perform mapping by using the initialized parameters, adjust the parameters according to the mapping effect, and update the parameters according to automatic learning, and obtain a full map of the power grid.

[0041] In a third aspect, the present application provides a computing device, comprising:

[0042] a memory and a processor;

[0043] The memory is configured to store computer-executable instructions, and the processor is configured to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the method for real-time power grid automatic composition.

[0044] In a fourth aspect, the present application provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the method for real-time power grid automatic composition.

[0045] Compared with the prior art, the present application has the following beneficial effects: the present application automatically performs initial layout and scaling adjustment on substation positions by using force-directed layout algorithm and k-distance algorithm, reduces manual intervention, improves the efficiency and consistency of the layout, uses a penalty model and a reward function to automatically perform overall layout and detailed optimization on inter-station lines, ensures the rationality and aesthetics of the line paths, initializes parameters by using the analytic hierarchy process, and further optimizes the layout effect by performing coarse adjustment and automatic learning and updating parameters according to the mapping effect; through automatic layout and optimization adjustment, the generation efficiency and quality of the power grid wiring diagram are improved, the rationality and readability of the layout are enhanced, and the layout is adapted to changes in the power grid structure in different scenarios. BRIEF DESCRIPTION OF DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0047] Figure 1 The overall flow logic diagram of the method for real-time power grid automatic composition according to an embodiment of the present application is shown in the figure.

[0048] Figure 2 The initial layout effect diagram of the substation position in the method for real-time power grid automatic composition according to an embodiment of the present application is shown in the figure.

[0049] Figure 3 The layout effect diagram of the substation position after adjustment in the method for real-time power grid automatic composition according to an embodiment of the present application is shown in the figure.

[0050] Figure 4 The effect diagram of excessive line inflection points in the method for real-time power grid automatic composition according to an embodiment of the present application is shown in the figure.

[0051] Figure 5 The effect diagram of excessive adjustment of line inflection points in the real-time power grid automatic composition method described in an embodiment of the present application;

[0052] Figure 6 The effect diagram of region block boundary jump in the real-time power grid automatic composition method described in an embodiment of the present application;

[0053] Figure 7 The effect diagram of region block boundary jump adjustment in the real-time power grid automatic composition method described in an embodiment of the present application;

[0054] Figure 8 The final mapping effect diagram in the real-time power grid automatic composition method described in an embodiment of the present application. DETAILED DESCRIPTION

[0055] To make the above objectives, characteristics and advantages of the present application more apparent, obvious and easy to understand, the specific embodiments of the present application are described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor should fall within the scope of protection of the present application.

[0056] Embodiment 1

[0057] Reference Figure 1 For an embodiment of the present application, a real-time power grid automatic composition method is provided, comprising:

[0058] S100: Obtain the positions of substations, layout the positions of substations by using a layout algorithm, and stretch and shrink the layout according to the density distribution of the positions by using a clustering algorithm to obtain first positions;

[0059] S200: Determine the positions of busbars and lines in the substations based on the first positions to obtain second positions;

[0060] S300: Build a first penalty model according to the second positions, and perform overall layout on the lines between substations;

[0061] S400: Build a second penalty model based on the overall layout result, and optimize the layout between the lines;

[0062] S500: Initialize the parameters of the first penalty model and the second penalty model, and map by using the initialized parameters, adjust the parameters according to the mapping effect, and update the parameters according to automatic learning to obtain a full grid map.

[0063] It should be noted that the barycentric method is used to determine the reasonable positions of different busbars and lines in the substation, combined with the wiring mode of the power grid and the mapping habit, to draw the internal wiring diagram of the plant station, to ensure the rationality and standardization of the layout, to reduce the intersection between lines and unnecessary inflection points by establishing a line intersection point penalty function and an unnecessary inflection point penalty function, and to improve the clarity and readability of the layout.

[0064] In the embodiment of the present application, the above step S100 comprises the following sub-steps A1-A2.

[0065] In A1: respectively define the gravity of the substation, the repulsive force between the substations, and the elastic force between the substations;

[0066] In A2: comprehensively balance the gravity, repulsive force and elastic force of the substations, and adjust the positions of the substations according to the set step length.

[0067] Specifically, the force-oriented layout algorithm is used to layout the positions of the substations, the gravity of the substations is defined based on the number of lines contained in the substations, the repulsive force between the substations is defined according to the gravity of the substations, similar to the universal gravitation, the elastic force between the substations is defined based on the original position relationship between the substations using the spring theory, the positions of the substations are adjusted according to a certain step length based on the balance of the gravity, the repulsive force and the elastic force between the substations, and the positions of the substations on the graph are optimized;

[0068] Define the gravity of the substation:

[0069] For the substation S k , containing {l1, l2, …, l n}, the more lines the substation contains, the longer the lines are, and the greater the image around the substation is. The gravity calculation is represented as:

[0070]

[0071] Wherein, len(l i ) is the length of the line l i , λ1 is a parameter in the interval (0, 1), and is 0.5;

[0072] Define the repulsive force between the substations:

[0073] For two substations S i , S j , the repulsive force between them is related to the distance between the substations and the gravity of each substation, similar to the universal gravitation. The definition of the repulsive force between the substations is represented as:

[0074]

[0075] Wherein, dis(S i , S j ) is the distance between the two substations, and λ2 is a parameter in the interval (0, 1), and is 0.5.i S j ) is the Euclidean distance between substations S i 、S j , λ2 is a parameter in the interval (0, 1), G(S i ), G(S j ) are the gravities of two substations S i 、S j , respectively.

[0076] The elastic force between substations is defined as:

[0077] The attractive force between substations is actually the constraint force of the line between two substations on the two substations. According to the spring theory, the elastic force between two substations is represented as:

[0078] F 弹 (S i ,S j )=k 弹 ×[dis(S i ,S j )-dis 坐标 (S i ,S j )]

[0079] where k 弹 is the elastic coefficient, k 弹 =λ3G(S i )G(S j ), dis(S i ,S j ) is the Euclidean distance between substations S i 、S j , and dis 坐标 (S i ,S j ) is the Euclidean distance between the longitude and latitude coordinates between two substations.

[0080] Specifically, the relative orientation relationship between substations remains stable as a whole; the angle between the relative position direction line between substations and the actual position direction line represented by the longitude and latitude coordinates is ∠α, then for substation j, there is a force perpendicular to the actual position direction line (and pointing to this direction line), the size is represented as:

[0081] F 角 (S i ,S j )=λ4×G(S j )×sin(∠α)

[0082] where λ4 is a parameter in the interval (0, 1).

[0083] In the embodiments of the present application, after the steps A1-A2 are completed in the step S100, the following steps A3-A5 are further included.

[0084] In A3: for each substation area, the distance of each substation in the area to the kth nearest substation is calculated, obtaining a first distance set;

[0085] In A4: the median of the first distance set is taken, and the reciprocal of the median is taken as the density of the area;

[0086] In A5: according to the density of each area, the scaled area width is calculated, obtaining the first position of the substation.

[0087] Specifically, according to the transverse and longitudinal density distribution of the substation, the layout is scaled according to the k-distance algorithm;

[0088] Using the k-distance algorithm, for the ith area from left to right, the substation set {S1, S2, …, Si} is included; K For each substation in the set, the distance of each substation in the area to the kth nearest substation is calculated, where k is 2, obtaining a first distance set {D1, D2, …, Di}, and the reciprocal of the median is taken as the density of the area ρi. K i

[0089] The scaled width of each area is calculated to support the adjustment of the position of each substation in the subsequent area, which is represented as:

[0090]

[0091] Where W is the total width of the drawing area. 总

[0092] In order to keep the automatic layout of the equipment in the station consistent with the drawing habits of the traditional station primary wiring diagram, the layout mode of high-voltage side, medium-voltage side and low-voltage side located at the upper left, right and lower left of the station area is adopted, and the middle area is the layout area of the main transformer; if the substation has only two voltage levels, the upper and lower structure will be adopted.

[0093] It should be noted that by defining the gravity, repulsion and elastic force of the substation, the interaction force between each substation is automatically calculated, the automatic layout of the substation position is realized, the manual intervention is reduced, the efficiency and consistency of the layout are improved, the density of the substation position is more balanced on the premise of keeping the original relative position relationship, the problem of local excessive density or sparseness is avoided, the clarity and readability of the layout are improved through the penalty function and reward function, and the rationality and aesthetics of the line layout are ensured. ​​​

[0094] In the embodiments of the present application, the step S200 comprises the following sub-steps B1-B4.

[0095] In B1, the gravity center of each line interval and the gravity center of the busbar are defined respectively.

[0096] In B2, the position of the busbar is adjusted according to the positional relationship of the busbar gravity center.

[0097] In B3, the position of the line interval is adjusted according to the positional relationship of the line interval gravity center on the same group of busbars.

[0098] In B4, the internal wiring diagram of the substation is obtained in combination with the wiring mode of the power grid.

[0099] Specifically, for each line, the gravity center of each line interval is defined according to the orientation of the external substation connected thereto, the gravity center of the busbar is defined according to the gravity center of the line interval contained on the busbar, the position of the busbar in the layout diagram is adjusted according to the left-right positional relationship of the busbar gravity center, the position of the line interval in the layout diagram is adjusted according to the left-right positional relationship of the line interval gravity center on the same group of busbars, and the internal wiring diagram of the substation is drawn in combination with the wiring mode (supporting 3 / 2, double busbar, double busbar segmentation, single busbar, single busbar segmentation) of the power grid, drawing habits, and gravity center optimization results.

[0100] The line gravity center is defined as:

[0101] The gravity center component of each line is calculated and represented as:

[0102] L(l i )=k(l i )×(1+λ5sinα i )

[0103] wherein, for the line l i , when the opposite end substation is on the right side of the substation, k(l i ) takes 1, otherwise k(l i ) takes -1, λ5 is a coefficient, taking a value range of (0, 1], and by default taking 1, and α i takes the included angle between the directional line between the two substations and the horizontal line, and taking positive when the directional line is below the horizontal line.

[0104] The busbar gravity center is defined as:

[0105] The gravity center of the busbar is represented as:

[0106]

[0107] wherein, n is the total number of line intervals, and L(l i ) is the gravity center position of the i-th line interval.

[0108] According to the gravity center of each group of busbars, the left and right positions of the busbar group are determined, and the positions between different intervals on the same busbar group are sorted according to the gravity center of the line;

[0109] For the wiring mode with busbar segmentation, the positions between busbars are determined according to the gravity center of the busbar; for the line intervals on the same busbar, the interval positions are determined according to the gravity center of the line, and the bus coupler and the segmentation interval are fixed and placed according to the wiring mode.

[0110] It should be noted that through accurate gravity center calculation and position adjustment, the layout of the internal wiring diagram of the substation is optimized, the quality and readability of the generated diagram are improved, and a variety of wiring modes are adapted, which has important practical and technical values.

[0111] In the embodiment of the application, the above step S300 includes the following sub-steps C1-C2.

[0112] In C1: different dimension penalty functions and reward functions are defined respectively for the purpose of regional control, channel density, avoiding too long length, and reducing unnecessary inflection points;

[0113] In C2: the overall layout of the line path is generated in combination with the penalty functions and reward functions of different dimensions, and a first penalty model constituting the overall layout of the line is obtained.

[0114] Specifically, for the purpose of regional control, a penalty function is defined for the line path exceeding the effective region; for the purpose of channel density control, a penalty function related to the line density of the channel is defined; for the purpose of avoiding too long length, a penalty function for length waste is defined; for the purpose of reducing unnecessary inflection points, a reward function for inertia retention is defined. In combination with the penalty functions of different dimensions, the overall layout of the line path is automatically generated.

[0115] Regional control penalty function:

[0116] A rectangular effective region is constructed with two substations as diagonals For a certain routing scheme of the line, the points at each channel intersection through which the line passes are taken as the passing points. For the passing point sequence {C1, C2, …, C n}, if each passing point is out of the effective region, a score is deducted according to the minimum distance between the passing point and the effective region, which is represented as:

[0117]

[0118] Wherein, λ6 is a coefficient, is the distance from C j to the region , and is the line l​i the area where the user is located, the area the maximum value in the x-axis direction, the area the minimum value in the x-axis direction, the area the maximum value in the y-axis direction, the area the minimum value in the y-axis direction;

[0119] Channel density penalty function:

[0120] Modeling with the intersection of channels as points and two adjacent points as edges;

[0121] Shortest path calculation: for each line, according to the rectangular area of the two end substations, calculate the number of passing points and edges of a horizontal edge and a vertical edge;

[0122] Optimal channel density calculation: for each line, according to the shortest path, calculate the optimal density of each point and edge in the area, and the average density of points is represented as:

[0123]

[0124] where C P (l i ) is the number of effective points of line l i , and C P (Range) is the number of effective points in the area;

[0125] The average density of edges is represented as:

[0126]

[0127] where C L (l i ) is the number of effective edges of line l i , and C L (Range) is the number of effective edges in the area;

[0128] For each scheme, calculate the actual average density A ′ P , A ′ L ;

[0129] The loss function of channel density is represented as:

[0130]

[0131] where λ7 and λ8 are parameters, A P is the average density of points, and AL is the edge average density, A ′ P is the actual point average density, A ′ L is the actual edge average density;

[0132] Length waste penalty function:

[0133] According to the shortest path, the actual path, the optimal length, the actual length, and further calculating the loss function related to the length waste, which is expressed as:

[0134]

[0135] Wherein, λ9is a parameter, Len 实 (l i ) is the actual length of the line l i , Len 优 (l i ) is the optimal length of the line l i ;

[0136] Inertia retention penalty function:

[0137] In order to reduce the line inflection, the number of inflection points needs to be reduced, and the path in the original direction is rewarded by inertia, and the inflection points on the path are punished, which is expressed as:

[0138]

[0139] Wherein, λ 10 is a parameter, T(l i ) is the number of inflection points of the line;

[0140] According to the area control penalty function, the channel density penalty function, the length waste penalty function and the inertia retention penalty function, the penalty model of the overall layout of the line is formed, that is, the first penalty model.

[0141] It should be noted that through the multi-dimensional penalty function and reward function, the overall layout of the line path is generated, forming the first penalty model, which not only improves the readability and aesthetics of the wiring diagram, but also adapts to various wiring methods, and has important practical value and technical value.

[0142] In the embodiment of the application, the above step S400 includes the following sub-steps D1-D2;

[0143] In D1: the penalty functions of the number of line intersections, unnecessary inflection points and lines with too close distances are established respectively;

[0144] In D2: combined with the penalty function, the second penalty model constituting the layout detail optimization is obtained.

[0145] Specifically, a penalty function of the number of intersection points between lines is established to avoid excessive intersection between lines; a penalty function of the number of inflection points inside the channel is established to avoid excessive position switching of the line within the channel; a penalty function of too close distance between lines and stations is established to avoid too close distance between objects. Combined with the penalty functions of different dimensions, the layout of the line is optimized in detail;

[0146] The number of line intersection points penalty function is:

[0147] The calculation is represented as:

[0148]

[0149] Wherein, λ 11 is a parameter, J(l i ,l j ) is the number of intersection points of line l i ,l j .

[0150] Unnecessary inflection point penalty function:

[0151] The line changes the detailed position in the same horizontal or vertical channel is counted as:

[0152]

[0153] Wherein, λ 12 is a parameter, T ′ (l i ) is the number of inflection points of the line in the channel;

[0154] The line penalty function of too close distance is:

[0155] The calculation is represented as:

[0156]

[0157] Wherein, λ 13 is a parameter, min dis (l i ) is the nearest distance of line l i to the surrounding substation or line;

[0158] The penalty functions of the number of line intersection points, unnecessary inflection points and too close distance lines are combined to form the penalty function of layout detail optimization;

[0159] It should be noted that by reducing the intersection and overlap between lines, the clarity and readability of the wiring diagram are improved, by reducing unnecessary inflection points, the line path is smoother, the aesthetics of the wiring diagram is improved, by avoiding too close distance between objects, electromagnetic interference is reduced, and the operation safety of the power grid is improved.

[0160] In the embodiment of the present application, the step S500 includes the following sub-steps E1-E3.

[0161] In E1: select a power grid dispatching expert, compare the parameters of different dimensions in the first penalty model and the second penalty model, obtain an evaluation matrix, and calculate the initial values of the parameters of different dimensions in the first penalty model and the second penalty model;

[0162] In E2: use the initialized parameter combination of different dimensions, and perform graphing according to the topological relationship of the power grid model;

[0163] In E3: according to the graphing effect, improve the parameters of the corresponding dimensions based on the expert evaluation result.

[0164] Specifically, the analytic hierarchy process is used to initialize the parameters of different dimensions; the parameters are coarsely adjusted according to the graphing effect; the graphing effect is manually adjusted in daily operation and maintenance, and the system automatically learns and updates the parameters. According to the adjusted parameters, a station-in and station-out integrated wiring diagram is automatically generated in combination with the wiring mode of the power grid;

[0165] The parameters in the process of rough layout of the line are automatically calculated according to the importance of the parameters by the analytic hierarchy process, including:

[0166] Select three power grid dispatching experts, compare the parameters of different dimensions two by two, and obtain an evaluation matrix;

[0167] Calculate the evaluation matrix to obtain the initial values of the parameters of different dimensions;

[0168] The same method is used to initialize and set the parameters in the process of optimization of the line layout details;

[0169] For the studied power grid, use the parameter combination to automatically perform graphing according to the topological relationship of the power grid model, according to the graphing effect, the system expert evaluates which aspect of the problem is more serious, and improves the parameters of the corresponding dimensions. In order to make the parameters more representative, a plurality of power grid models are randomly selected to verify and manually adjust the graphing effect.

[0170] After the system automatically performs graphing, the power grid operator will manually adjust the places where the graphing effect is poor according to the use habit, the system will learn the influence of the manual adjustment, automatically adjust the parameters of different dimensions, and finally automatically generate a dynamic power grid full diagram containing station-in and station-out equipment according to the wiring mode of the power grid after optimization.

[0171] It should be noted that by selecting power grid dispatching experts, the parameters of different dimensions are compared with each other to obtain an evaluation matrix, ensuring the scientificity and rationality of parameter initialization, reflecting the experience and judgment of experts, and calculating the evaluation matrix to obtain initial values of parameters of different dimensions, providing a basis for subsequent layout optimization, ensuring that the initial setting of parameters has reference value, and through the analytic hierarchy process, the parameters of different dimensions are initialized, coarsely adjusted, and automatically learned and updated, optimizing the generation of the power grid wiring diagram.

[0172] The above is a schematic scheme of the real-time power grid automatic composition method of the embodiment. It should be noted that the technical scheme of the real-time power grid automatic composition system belongs to the same concept as the technical scheme of the real-time power grid automatic composition method described above. The technical scheme of the real-time power grid automatic composition system in the embodiment is not described in detail, and the description of the technical scheme of the real-time power grid automatic composition method can be referred to.

[0173] The real-time power grid automatic composition system in the embodiment comprises:

[0174] A position layout module is configured to obtain a substation position, perform layout on the substation position by using a layout algorithm, and perform stretching and contraction on the layout by using a clustering algorithm according to the density distribution of the position to obtain a first position.

[0175] A position confirmation module is configured to determine the positions of busbars and lines in the substation based on the first position to obtain a second position.

[0176] A first penalty model building module is configured to build a first penalty model according to the second position to perform overall layout on lines between substations.

[0177] A second penalty model building module is configured to build a second penalty model based on the overall layout result to optimize the layout between lines.

[0178] A diagram forming module is configured to initialize parameters of the first penalty model and the second penalty model and form a diagram by using the initialized parameters, adjust the parameters according to the diagram forming effect, and update the parameters according to automatic learning to obtain a power grid diagram.

[0179] The embodiment also provides a computing device suitable for real-time power grid automatic composition, comprising:

[0180] A memory and a processor; the memory is configured to store computer executable instructions, and the processor is configured to execute the computer executable instructions to implement the method for realizing real-time power grid automatic composition proposed in the above embodiment.

[0181] The embodiment also provides a storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method for realizing real-time power grid automatic mapping.

[0182] The storage medium provided by the embodiment belongs to the same inventive concept as the method for realizing real-time power grid automatic mapping, and the technical details not described in the embodiment can be referred to the above embodiment, and the embodiment has the same beneficial effects as the above embodiment.

[0183] Through the above description of the embodiments, those skilled in the art can clearly understand that the present application can be realized by means of software and necessary general hardware, and of course can also be realized by hardware. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, and the computer software product can be stored in a computer readable storage medium, such as a floppy disk, a read-only memory (ROM), a random access memory (RAM), a FLASH memory, a hard disk, or an optical disc, and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods of various embodiments of the present application.

[0184] Embodiment 2

[0185] Referring to Figures 2-8 The embodiment is different from the first embodiment in that a verification test of the method for realizing real-time power grid automatic mapping is provided to verify the technical effects used in the method.

[0186] Taking a 220kV and above transformer substation in a certain region as an example;

[0187] As shown in Figure 2 , due to unbalanced economic development, the density of transformer substations is unbalanced, resulting in unreasonable layout of transformer substation positions, and there are very obvious sparse areas and dense areas in the entire mapping area, which brings great difficulty to the subsequent drawing work, and it is necessary to perform stretching and transformation on the relative position relationship of transformer substations, so that the density of transformer substation positions is more balanced on the premise of maintaining the original relative position relationship.

[0188] As shown in Figure 3 , by using the adjustment of the method of the present application, the adjusted effect of the layout of transformer substation positions is obtained, and in terms of the overall layout of inter-station lines, the default parameters are used for layout, and two problems occur.

[0189] Problem one: too many line inflection points

[0190] As shown in Figure 4As shown, this layout will result in too many unnecessary turning points on the line, with the red line being the line with unnecessary turning points.

[0191] The analysis of the causes of the problem revealed that the factors related to inertia played a relatively small role, and the line was pushed by the repulsive forces between the line and the substation, resulting in an increase in the number of inflection points on the line.

[0192] like Figure 5 As shown, the adjustment results are obtained by adjusting the parameters related to inertia retention and rearranging the layout;

[0193] Question 2: Jumping between region partition boundaries;

[0194] like Figure 6 As shown, when the line is laid out in different areas, the main consideration is the rationality of the layout in each area, which results in jumps at the boundary positions.

[0195] like Figure 7 As shown, the layout is automatically adjusted by increasing the influence coefficient of the relative position of lines between regions;

[0196] like Figure 8 As shown, the final image is obtained;

[0197] The k-distance algorithm proposed in this application is used to scale and transform the locations of substations, making the density of substations more balanced while maintaining their original relative positions. The adjusted substation layout is more reasonable and the density is more balanced, laying a good foundation for subsequent line layout. It solves the problems of too many line turning points and jumping regional block boundaries. The adjusted line paths are smoother, and the final map effect is more reasonable and clear. The substation locations are balanced, the line paths are smooth, the regional block boundaries are smooth, and the overall layout is more beautiful and coordinated.

[0198] Through multi-dimensional optimization methods, the balance of substation location layout was significantly improved, line turning points were reduced, regional block boundaries were optimized, and mapping quality was improved.

[0199] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for real-time automatic power grid mapping, characterized in that, include: The substation locations are obtained, and a layout algorithm is used to lay out the substation locations. Based on the density distribution of the locations, a clustering algorithm is used to scale the layout to obtain the first location. Based on the first location, the locations of the busbars and lines within the substation are determined, thus obtaining the second location; Based on the second location, the first penalty model is built, and the overall layout of the lines between substations is carried out; A second penalty model is built based on the overall layout results to optimize the layout between lines; The parameters of the first penalty model and the second penalty model are initialized and the initialized parameters are used to generate a map. The parameters are adjusted according to the map generation effect and updated according to automatic learning to obtain a complete map of the power grid.

2. The method for real-time automatic power grid mapping as described in claim 1, characterized in that, The layout of the substation location using a layout algorithm includes: Define the substation gravity, the repulsive force between substations, and the elastic force between substations respectively; The substation's position is adjusted based on a set step size, taking into account gravity, repulsion, and elastic forces, with force balance as the guiding principle.

3. The method for real-time automatic power grid mapping as described in claim 2, characterized in that, Scaling the layout based on the density distribution of locations using clustering algorithms includes: For each substation area, calculate the distance from each substation in that area to the kth nearest substation to other substations, and obtain the first distance set; Take the median of the first distance set, and use the reciprocal of the median as the density of the region; Based on the density of each area, the width of the expanded area is calculated to obtain the first location of the substation.

4. The method for real-time automatic power grid mapping as described in claim 3, characterized in that, Determining the location of busbars and lines within a substation includes: Define the centroid of each line bay and the centroid of the busbar separately; Adjust the position of the busbars according to the relative positions of their centers of gravity; Adjust the position of the outgoing line bay according to the positional relationship of the center of gravity of the line bays on the same group of busbars; By combining the wiring method of the power grid, the internal wiring diagram of the substation is obtained.

5. The method for real-time automatic power grid mapping as described in claim 4, characterized in that, Building the first penalty model includes: With the objectives of regional control, channel density, avoiding excessive length, and reducing unnecessary inflection points, penalty and reward functions of different dimensions are defined respectively. By combining penalty and reward functions of different dimensions, the overall layout of the route is generated, resulting in the first penalty model that constitutes the overall layout of the route.

6. The method for real-time automatic power grid mapping as described in claim 5, characterized in that, Building the second penalty model includes: Establish penalty functions for the number of line intersections, unnecessary inflection points, and lines that are too close together; By combining the penalty function, a second penalty model for optimizing layout details is obtained.

7. The method for real-time automatic power grid mapping as described in any one of claims 1-6, characterized in that, Initialize the parameters of the first penalty model and the second penalty model, and generate a graph using the initialized parameters, including: Power grid dispatching experts were selected to compare the parameters of different dimensions in the first and second penalty models to obtain the evaluation matrix, and the initial values ​​of the parameters of different dimensions in the first and second penalty models were calculated. Using different combinations of parameters after initialization, a graph is generated based on the topological relationship of the power grid model; Based on the resulting image quality and expert evaluation, the parameters for the corresponding dimensions will be improved.

8. A system applying the real-time automatic power grid mapping method as described in any one of claims 1-7, characterized in that, include: The location layout module is used to obtain the substation location, use a layout algorithm to lay out the substation location, and use a clustering algorithm to scale the layout according to the density distribution of the location to obtain the first location. The location confirmation module is used to determine the location of the busbars and lines within the substation based on the first location, and obtain the second location; The first penalty model building module is used to build the first penalty model based on the second location and to make an overall layout of the lines between substations. The second penalty model building module is used to build a second penalty model based on the overall layout results to optimize the layout between lines; The mapping module is used to initialize the parameters of the first penalty model and the second penalty model, generate a map using the initialized parameters, adjust the parameters according to the mapping effect, and update the parameters according to automatic learning to obtain a complete map of the power grid.

9. An electronic device, comprising: Memory and processor; The memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions, which, when executed by the processor, implement the steps of the real-time power grid automatic mapping method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing computer-executable instructions that, when executed by a processor, implement the steps of the method for real-time automatic grid mapping as described in any one of claims 1 to 7.

Images