A method and system for intelligently generating power supply schemes based on mobile terminal graph operations

By generating a three-dimensional virtual power supply model in the operation on the mobile terminal diagram and applying an ant colony algorithm to optimize power supply facilities and lines, the problem of the inability to calculate power supply energy consumption in the existing technology is solved, and the reduction of power supply energy consumption and rational utilization of energy is achieved.

CN118446423BInactive Publication Date: 2024-11-26STATE GRID ANHUI ELECTRIC POWER CO LTD MARKETING SERVICE CENTER
View PDF 8 Cites 0 Cited by

Patent Information

Application Number
CN202410607572.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-16
Publication Date
2024-11-26
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

The existing power supply scheme cannot calculate the energy consumption of power facilities and power supply lines, resulting in the power supply scheme being unable to take into account the loss of power supply energy, resulting in waste of power resources.

Method used

Based on the operation on the mobile terminal diagram, power supply parameter information is obtained, a three-dimensional virtual power supply model is generated, and the ant colony algorithm is used to optimize power supply facilities and lines to reduce energy consumption.

Benefits of technology

通过精准识别和优化供电模型,生成实际能耗最小的供电方案,减少供电能耗,合理利用能源。

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118446423B_ABST
    Figure CN118446423B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and system for intelligently generating a power supply scheme based on a mobile terminal graph operation, which belongs to the field of electric power technology and solves the problem that the existing method cannot calculate the energy consumption of power facilities and power supply lines in the power supply scheme, so that the power supply scheme cannot take into account the power supply energy consumption loss, resulting in waste of electric power resources. The method comprises obtaining power supply parameter information, generating a three-dimensional virtual power supply model based on the power supply parameter information and the plane layout of the power network, finding the optimal reorganization relationship with the lowest comprehensive energy consumption in the optimal reorganization set, determining the power supply line corresponding to the optimal reorganization relationship based on the optimal reorganization relationship, and finally determining the power supply recommendation scheme with the minimum actual energy consumption; the present invention optimizes and reorganizes the power supply facilities and power supply lines in the three-dimensional virtual power supply model based on the ant colony algorithm, and generates a power supply recommendation scheme with the minimum actual energy consumption from the perspective of reducing power supply energy consumption.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the field of electric power technology, and specifically relates to a method and system for intelligently generating a power supply plan based on mobile terminal graph operations. Background Art

[0002] A power supply plan refers to a series of power supply solutions designed to meet the power demand of a specific area or place. It usually includes the selection of power sources, transmission methods, distribution network layout, capacity planning, safety measures, and emergency response plans. A reasonable power supply plan can ensure a reliable supply of electricity while taking into account economic and environmental impacts.

[0003] Chinese patent CN106684870A discloses a method and device for formulating a power supply plan; the method includes receiving power application information and on-site survey data of a user to be powered; the on-site survey data includes confirmation information of the power application information, grid access demand information, power receiving demand information and power point distribution information; extracting the parameter range of the power supply plan corresponding to the confirmed power application information; generating grid access mode data and power receiving mode data of the user to be powered based on the grid access demand information, power receiving demand information and parameter range; generating a component location distribution map and a line direction map based on the grid access mode data and the power receiving mode data; determining the grid access mode data, the power receiving mode data, the component location distribution map and the line direction map as the power supply plan for the user to be powered; however, the existing method cannot calculate the energy consumption of power facilities and power supply lines in the power supply plan, so that the power supply plan cannot take into account the power supply energy consumption loss, resulting in a waste of power resources. In order to solve the above problems, we propose a method and system for intelligently generating a power supply plan based on mobile terminal graph operations. Summary of the invention

[0004] The purpose of the present invention is to address the shortcomings of the prior art and provide a method and system for intelligently generating a power supply plan based on mobile terminal graph operations, which solves the problem that the prior method is unable to calculate the energy consumption of power facilities and power supply lines in the power supply plan, making it impossible for the power supply plan to take into account the power supply energy consumption loss, resulting in a waste of power resources.

[0005] Existing methods are unable to calculate the energy consumption of power facilities and power lines in power supply plans, making it impossible for power supply plans to take into account power supply energy consumption losses, resulting in a waste of power resources. In order to solve the above problems, we propose a method and system for intelligently generating power supply plans based on mobile terminal graph operations. In short, the method includes obtaining power supply parameter information, generating a three-dimensional virtual power supply model based on the power supply parameter information and the plane layout of the power network, and displaying the three-dimensional virtual power supply model in real life, traversing the three-dimensional virtual power supply model based on a pre-built energy consumption calculation model, calculating the transmission loss coefficients of power supply facilities and power lines in the three-dimensional virtual power supply model, optimizing and reorganizing the power supply facilities and power lines in the three-dimensional virtual power supply model based on the ant colony algorithm, generating an optimized reorganization set, and finding the optimized reorganization relationship with the lowest comprehensive energy consumption in the optimized reorganization set. In the present invention, the three-dimensional virtual power supply model is generated based on the power supply parameter information and the power network plane layout, which can accurately identify and judge the information input by the smart mobile terminal, thereby facilitating the construction of the three-dimensional virtual power supply model, so that the user can accurately obtain the three-dimensional virtual power supply model, and it is convenient for the user to customize the power supply plan for the three-dimensional virtual power supply model scene. At the same time, the present invention optimizes and reorganizes the power supply facilities and power supply lines in the three-dimensional virtual power supply model based on the ant colony algorithm, and generates a power supply recommendation plan with the minimum actual energy consumption from the perspective of reducing power supply energy consumption, thereby reducing power supply energy consumption, thereby rationally utilizing energy, and ensuring energy saving under the premise of optimizing the recommended power supply plan.

[0006] The present invention is implemented as follows: a method for intelligently generating a power supply scheme based on a mobile terminal graph operation, the method for intelligently generating a power supply scheme based on a mobile terminal graph operation comprises:

[0007] Acquire power supply parameter information, wherein the power supply parameter information includes power supply line load parameters, path parameters, reliability parameters, transmission loss parameters, and power supply coordinate parameters;

[0008] Identify the power network plane layout drawn on the input mobile terminal diagram interface, generate a three-dimensional virtual power supply model based on the power supply parameter information and the power network plane layout, and display the three-dimensional virtual power supply model in real scene;

[0009] Based on the pre-built energy consumption calculation model, the three-dimensional virtual power supply model is traversed to calculate the transmission loss coefficients of the power supply facilities and power supply lines in the three-dimensional virtual power supply model;

[0010] Based on the ant colony algorithm, the power supply facilities and power supply lines in the three-dimensional virtual power supply model are optimized and reorganized to generate an optimized reorganization set, and the optimized reorganization relationship with the lowest comprehensive energy consumption in the optimized reorganization set is found. Based on the optimized reorganization relationship, the power supply line corresponding to the optimized reorganization relationship is determined, and finally the recommended power supply plan with the lowest actual energy consumption is determined.

[0011] Preferably, the method for generating a three-dimensional virtual power supply model based on power supply parameter information and a power network plane layout specifically includes:

[0012] Obtain the power network plane layout input in the mobile terminal diagram, split the real-time basic model in the power network plane layout, and generate a real-time model splitting library;

[0013] Traverse the basic model library in the mobile terminal graph, compare the real-time basic model in the real-time model splitting library with the historical standard model in the basic model library, and determine the similarity between the real-time basic model and the historical standard model;

[0014] Determine whether the similarity between the real-time basic model and the historical standard model is greater than the similarity preset threshold. If so, determine the historical standard model as the real-time basic model, and replace all real-time basic models in the real-time model splitting library based on the similarity preset threshold to generate a standard power network plane layout.

[0015] Preferably, the method for generating a three-dimensional virtual power supply model based on power supply parameter information and a power network plane layout further includes:

[0016] Loading power supply parameter information, reading power supply coordinate parameters in the power supply parameter information, and converting the power supply coordinate parameters into coordinate vectors;

[0017] Calculate the analog conversion ratio based on the power network plane layout and power supply parameter information;

[0018] The conversion coordinate vector of the power network plane layout is obtained according to the simulation conversion ratio and the coordinate vector to generate the three-dimensional virtual power supply model, and the three-dimensional virtual power supply model is extracted from the conversion coordinate vector based on the MarchingCubes algorithm.

[0019] Preferably, the method for determining the similarity between the real-time basic model and the historical standard model specifically includes:

[0020] Define the distribution weights of multiple groups of pixels in the real-time basic model as , the number of pixels is , multiple groups of pixel point vectors in the real-time basic model are represented as: , while the number of significant pixel clusters in the real-time basic model is , the vector representation set corresponding to the significant pixel cluster is ;

[0021] The edge distribution similarity probability in the real-time basic model is calculated based on the similarity potential function, wherein the edge distribution similarity probability is calculated by formula (1);

[0022] (1)

[0023] in, is the vector corresponding to the salient pixel cluster, is the number of pixels, Select values ​​for similarity, is the edge weight coefficient of the similarity potential function;

[0024] (2)

[0025] Obtain edge distribution similarity probability, and determine edge intersection node distribution similarity probability of the real-time basic model in combination with simulated annealing process;

[0026] (3)

[0027] in, is the similarity probability of edge crossing node distribution, is the number of edges of the real-time base model, is the edge distribution similarity probability in the real-time basic model, It is the number of iterations based on the Metropolis criterion in the combined simulated annealing process;

[0028] The predicted attribution of the real-time basic model is calculated based on the simulated annealing algorithm, and the predicted attribution is corrected to obtain the similarity between the real-time basic model and the historical standard model;

[0029] (4)

[0030] in, is the similarity between the real-time basic model and the historical standard model, is the number of edges of the real-time base model, is the similarity penalty coefficient in the simulated annealing algorithm, is the predicted attribution of the real-time base model, is the correction value of attribution degree;

[0031] (5)

[0032] (6)

[0033] in, is the number of edges of the real-time base model, is the similarity penalty coefficient in the simulated annealing algorithm.

[0034] Preferably, the method for constructing the energy consumption calculation model specifically includes:

[0035] Collect power supply energy consumption parameters corresponding to the publicly available power supply facilities and power supply lines to obtain a power supply energy consumption parameter set;

[0036] Based on the VMD step-by-step decomposition method, the training set and the test set are extracted from the power supply energy consumption parameter set, where the ratio of the training set to the test set is 7:3;

[0037] Based on gradient enhancement, an initial calculation model combining wavelet extreme learning machine and echo state network is constructed. With the training set as input, the gradient descent algorithm is used to reduce the loss between the predicted value and the measured value, and the hyperparameters of the initial calculation model are adjusted to realize the pre-training of the model.

[0038] The model parameters were verified by 10-fold cross validation to obtain an optimized initial calculation model, which was then retrained. The performance of the initial calculation model was evaluated based on pinball loss, interval sharpness, and prediction interval coverage to obtain an initial calculation model with the best loss prediction results.

[0039] Obtain a test set, input the test set into the initial calculation model, obtain the prediction result of the test set, and determine whether the prediction result is greater than the preset accuracy threshold. If it is greater than the preset accuracy threshold, output the energy consumption calculation model.

[0040] Preferably, the method for calculating the transmission loss coefficients of power supply facilities and power supply lines in the three-dimensional virtual power supply model specifically includes:

[0041] Acquire power supply parameter information, extract and decompose a feature sequence of the power supply parameter information to obtain a feature factor set, and perform feature cleaning on the feature factor set to obtain a feature cleaning set;

[0042] Loading a feature cleaning set, taking the feature cleaning set as input, executing an energy consumption calculation model, the energy consumption calculation model generating energy consumption load curves of power supply facilities and power supply lines in a three-dimensional virtual power supply model based on a partial autocorrelation function;

[0043] Obtain the energy consumption load curves of power supply facilities and power supply lines in the three-dimensional virtual power supply model, and calculate the predicted energy consumption of power supply facilities and power supply lines by combining the Markov chain state probability function;

[0044] Based on the predicted energy consumption of power supply facilities and power lines, the PageRank function is introduced to calculate the transmission loss coefficients of power supply facilities and power lines in the three-dimensional virtual power supply model.

[0045] Preferably, the method for optimizing and reorganizing power supply facilities and power supply lines in a three-dimensional virtual power supply model based on an ant colony algorithm specifically includes:

[0046] Determine the energy consumption weight value based on the energy consumption coefficient of the power supply facility coordinate position;

[0047] (7)

[0048] in, is the energy consumption weight value of power supply facilities, is the energy consumption coefficient of power supply facilities, is the number of power supply facilities directly connected to the current power supply facilities, is the number of power supply facilities, is the coupling coefficient of the ant colony algorithm, The longest transmission distance between the current power supply facility and the directly connected power supply facility. is the average transmission distance between the current power supply facility and the directly connected power supply facility;

[0049] Randomly change the power supply lines between power supply facilities based on energy consumption weight values ​​to generate an optimized reorganization set;

[0050] Among them, the power supply lines between power supply facilities are randomly changed in the following ways:

[0051] (8)

[0052] in, Indicates the power supply line associated with the current power supply facility After the power supply lines are randomly changed, is the energy consumption weight value of power supply facilities, and , is one of the randomly changing power supply lines, and ≠ .

[0053] Preferably, the method for optimizing and reorganizing power supply facilities and power supply lines in a three-dimensional virtual power supply model based on an ant colony algorithm specifically further includes:

[0054] Load and generate an optimized reorganization set, randomly change the power supply parameter information associated with power supply facilities and power supply lines based on the ant colony algorithm, and use key parameters to determine the optimized reorganization relationship with the lowest comprehensive energy consumption in the optimized reorganization set;

[0055] (9)

[0056] in, is the comprehensive energy consumption prediction value, The number of power supply facilities directly connected to the current power supply facilities.

[0057] On the other hand, the present invention further provides a power supply scheme intelligent generation system based on mobile terminal graph operation, the power supply scheme intelligent generation system based on mobile terminal graph operation comprises:

[0058] A parameter acquisition module, wherein the parameter acquisition module is used to acquire power supply parameter information, wherein the power supply parameter information includes power supply line load parameters, path parameters, reliability parameters, transmission loss parameters, and power supply coordinate parameters;

[0059] An intelligent mobile terminal, the intelligent mobile terminal is used to identify the power network plane layout drawn on the input mobile terminal diagram interface, generate a three-dimensional virtual power supply model based on the power supply parameter information and the power network plane layout, and display the three-dimensional virtual power supply model in real scene;

[0060] A loss coefficient calculation module, which traverses the three-dimensional virtual power supply model based on a pre-built energy consumption calculation model to calculate the transmission loss coefficients of power supply facilities and power supply lines in the three-dimensional virtual power supply model;

[0061] A scheme recommendation module, which optimizes and reorganizes the power supply facilities and power supply lines in the three-dimensional virtual power supply model based on the ant colony algorithm, generates an optimized reorganization set, finds the optimized reorganization relationship with the lowest comprehensive energy consumption in the optimized reorganization set, determines the power supply line corresponding to the optimized reorganization relationship based on the optimized reorganization relationship, and finally determines the power supply recommendation scheme with the lowest actual energy consumption.

[0062] Preferably, the smart mobile terminal includes:

[0063] A plane layout input unit obtains the power network plane layout input in the mobile terminal image, splits the real-time basic model in the power network plane layout, and generates a real-time model splitting library;

[0064] A similarity determination unit, the similarity determination unit is used to traverse the basic model library in the mobile terminal graph, compare the real-time basic model in the real-time model splitting library with the historical standard model in the basic model library, and determine the similarity between the real-time basic model and the historical standard model;

[0065] A judgment unit, the judgment unit is used to judge whether the similarity between the real-time basic model and the historical standard model is greater than a similarity preset threshold. If it is greater than the similarity preset threshold, the historical standard model is determined as the real-time basic model, and all the real-time basic models in the real-time model splitting library are replaced based on the similarity preset threshold to generate a standard power network plane layout;

[0066] A coordinate parameter conversion unit, the coordinate parameter conversion unit is used to load the power supply parameter information, read the power supply coordinate parameter in the power supply parameter information, and convert the power supply coordinate parameter into a coordinate vector;

[0067] A model generation unit, wherein the model generation unit calculates a simulation conversion ratio based on the power network plane layout and power supply parameter information, obtains a conversion coordinate vector of the power network plane layout to generate a three-dimensional virtual power supply model according to the simulation conversion ratio and the coordinate vector, and extracts the three-dimensional virtual power supply model from the conversion coordinate vector based on the MarchingCubes algorithm.

[0068] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0069] In the present invention, the three-dimensional virtual power supply model is generated based on the power supply parameter information and the power network plane layout, which can accurately identify and judge the information input by the smart mobile terminal, thereby facilitating the construction of the three-dimensional virtual power supply model, so that the user can accurately obtain the three-dimensional virtual power supply model, and it is convenient for the user to customize the power supply plan for the three-dimensional virtual power supply model scene. At the same time, the present invention optimizes and reorganizes the power supply facilities and power supply lines in the three-dimensional virtual power supply model based on the ant colony algorithm, and generates a power supply recommendation plan with the minimum actual energy consumption from the perspective of reducing power supply energy consumption, thereby reducing power supply energy consumption, thereby rationally utilizing energy, and ensuring energy saving under the premise of optimizing the recommended power supply plan.

[0070] In the present invention, a three-dimensional virtual power supply model can be generated based on the power supply parameter information and the power network plane layout, thereby facilitating the real-time presentation of the power supply network in the background and facilitating the staff to adjust and optimize the power supply network design. At the same time, when regenerating the three-dimensional virtual power supply model, the staff can flexibly manually draw the power network plane layout, and the intelligent mobile terminal can accurately identify the power network plane layout, thereby ensuring the modeling accuracy of the three-dimensional virtual power supply model.

[0071] In the present invention, the similarity between the real-time basic model and the historical standard model is determined by combining the simulated annealing algorithm. Compared with the existing technology, the judgment result is more efficient and accurate. At the same time, the simulated annealing algorithm is combined with the similarity potential function to perform edge detection, feature extraction and pixel segmentation on the real-time basic model, thereby improving the accuracy and efficiency of real-time basic model recognition.

[0072] In the present invention, by constructing an energy consumption calculation model, the parameter characteristics that affect the energy consumption of power supply facilities and power supply lines can be extracted. At the same time, the energy consumption calculation model can utilize multi-source heterogeneous parameter data, and has a stronger ability to predict and judge the energy consumption of power supply facilities and power supply lines. The energy consumption calculation model is a combined prediction model, which can effectively combine the wavelet extreme learning machine and the echo state network, and carry out combined prediction, thereby reducing the risk of single model application. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 It is a schematic diagram of the implementation flow of the method for intelligently generating a power supply scheme based on mobile terminal graph operations provided by the present invention.

[0074] Figure 2 It is a schematic diagram of the implementation process of the method for generating a three-dimensional virtual power supply model based on power supply parameter information and power network plane layout provided by the present invention.

[0075] Figure 3 It is a schematic diagram of the implementation flow of the method for determining the similarity between the real-time basic model and the historical standard model provided by the present invention.

[0076] Figure 4 It is a schematic diagram of the implementation flow of the method for constructing the energy consumption calculation model provided by the present invention.

[0077] Figure 5 It is a schematic diagram of the implementation flow of the method for calculating the transmission loss coefficient of power supply facilities and power supply lines in a three-dimensional virtual power supply model provided by the present invention.

[0078] Figure 6 It is a schematic diagram of the implementation flow of the method for optimizing and reorganizing power supply facilities and power supply lines in a three-dimensional virtual power supply model based on the ant colony algorithm provided by the present invention.

[0079] Figure 7 It is a structural schematic diagram of the power supply scheme intelligent generation system based on mobile terminal map operation provided by the present invention.

[0080] Figure 8 It is a schematic diagram of the control structure of the intelligent mobile terminal provided by the present invention. DETAILED DESCRIPTION

[0081] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit this application; the terms "including" and "having" and any variations thereof in the specification and claims of this application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of this application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0082] Existing methods are unable to calculate the energy consumption of power facilities and power lines in power supply plans, making it impossible for power supply plans to take into account power supply energy consumption losses, resulting in a waste of power resources. In order to solve the above problems, we propose a method and system for intelligently generating power supply plans based on mobile terminal graph operations. In short, the method includes obtaining power supply parameter information, generating a three-dimensional virtual power supply model based on the power supply parameter information and the plane layout of the power network, and displaying the three-dimensional virtual power supply model in real life, traversing the three-dimensional virtual power supply model based on a pre-built energy consumption calculation model, calculating the transmission loss coefficients of power supply facilities and power lines in the three-dimensional virtual power supply model, optimizing and reorganizing the power supply facilities and power lines in the three-dimensional virtual power supply model based on the ant colony algorithm, generating an optimized reorganization set, and finding the optimized reorganization relationship with the lowest comprehensive energy consumption in the optimized reorganization set. In the present invention, the three-dimensional virtual power supply model is generated based on the power supply parameter information and the power network plane layout, which can accurately identify and judge the information input by the smart mobile terminal 200, thereby facilitating the construction of the three-dimensional virtual power supply model, so that the user can accurately obtain the three-dimensional virtual power supply model, and it is convenient for the user to customize the power supply plan for the three-dimensional virtual power supply model scene. At the same time, the present invention optimizes and reorganizes the power supply facilities and power supply lines in the three-dimensional virtual power supply model based on the ant colony algorithm, and generates a power supply recommendation plan with the minimum actual energy consumption from the perspective of reducing power supply energy consumption, thereby reducing power supply energy consumption, thereby rationally utilizing energy, and ensuring energy saving under the premise of optimizing the recommended power supply plan.

[0083] The embodiment of the present invention provides a method for intelligently generating a power supply scheme based on a mobile terminal graph operation. Figure 1 The schematic diagram of the implementation process of the method for intelligently generating a power supply scheme based on the operation on the mobile terminal diagram is shown. The method for intelligently generating a power supply scheme based on the operation on the mobile terminal diagram specifically includes:

[0084] Step S10, obtaining power supply parameter information, wherein the power supply parameter information includes power supply line load parameters, path parameters, reliability parameters, transmission loss parameters, and power supply coordinate parameters;

[0085] It should be noted that the power supply parameter information includes but is not limited to power supply line load parameters, path parameters, reliability parameters, transmission loss parameters, power supply coordinate parameters, and may also include power supply limitation parameters, constraint parameters, capacity planning parameters, cost-effectiveness parameters, power demand parameters and power supply selection parameters.

[0086] Step S20, identifying the power network plane layout drawn on the input mobile terminal diagram interface, generating a three-dimensional virtual power supply model based on the power supply parameter information and the power network plane layout, and displaying the three-dimensional virtual power supply model in real scene;

[0087] Step S30, traversing the three-dimensional virtual power supply model based on the pre-built energy consumption calculation model, and calculating the transmission loss coefficients of the power supply facilities and power supply lines in the three-dimensional virtual power supply model;

[0088] Step S40, based on the ant colony algorithm, the power supply facilities and power supply lines in the three-dimensional virtual power supply model are optimized and reorganized to generate an optimized reorganization set, the optimized reorganization relationship with the lowest comprehensive energy consumption in the optimized reorganization set is found, and the power supply line corresponding to the optimized reorganization relationship is determined based on the optimized reorganization relationship, and finally the recommended power supply plan with the lowest actual energy consumption is determined.

[0089] In the present invention, the three-dimensional virtual power supply model is generated based on the power supply parameter information and the power network plane layout, which can accurately identify and judge the information input by the smart mobile terminal 200, thereby facilitating the construction of the three-dimensional virtual power supply model, so that the user can accurately obtain the three-dimensional virtual power supply model, and it is convenient for the user to customize the power supply plan for the three-dimensional virtual power supply model scene. At the same time, the present invention optimizes and reorganizes the power supply facilities and power supply lines in the three-dimensional virtual power supply model based on the ant colony algorithm, and generates a power supply recommendation plan with the minimum actual energy consumption from the perspective of reducing power supply energy consumption, thereby reducing power supply energy consumption, thereby rationally utilizing energy, and ensuring energy saving under the premise of optimizing the recommended power supply plan.

[0090] The embodiment of the present invention provides a method for generating a three-dimensional virtual power supply model based on power supply parameter information and a power network plane layout. Figure 2 The schematic diagram of the implementation process of the method for generating a three-dimensional virtual power supply model based on power supply parameter information and a power network plane layout is shown. The method for generating a three-dimensional virtual power supply model based on power supply parameter information and a power network plane layout specifically includes:

[0091] Step S101, obtaining the power network plane layout input in the mobile terminal diagram, splitting the real-time basic model in the power network plane layout, and generating a real-time model splitting library;

[0092] It should be noted that the power network plan layout is a power network topology diagram manually input or selected by users or staff. The power network plan layout is generated based on the smart mobile terminal 200, and the implementation basic model is a virtual model representing the equipment, facilities, nodes, and power supply lines in the power supply network. It can be a rectangular frame, circle, node, straight line or broken line, and a standard basic model is stored in the smart mobile terminal 200. The real-time basic model in the power network plan layout can be split and decomposed by Boolean operations.

[0093] Step S102, traversing the basic model library in the mobile terminal graph, comparing the real-time basic model in the real-time model splitting library with the historical standard model in the basic model library, and determining the similarity between the real-time basic model and the historical standard model;

[0094] Step S103, determine whether the similarity between the real-time basic model and the historical standard model is greater than the similarity preset threshold. If it is greater than the similarity preset threshold, the historical standard model is determined as the real-time basic model, and all real-time basic models in the real-time model splitting library are replaced based on the similarity preset threshold to generate a standard power network plane layout. In this embodiment, the similarity preset threshold can be set to 0.85-1. When judging, if it is less than the similarity preset threshold, the real-time basic model and the historical standard model are determined to be dissimilar.

[0095] Step S104, loading power supply parameter information, reading power supply coordinate parameters in the power supply parameter information, and converting the power supply coordinate parameters into coordinate vectors;

[0096] Step S105, calculating the analog conversion ratio based on the power network plane layout and power supply parameter information;

[0097] Step S106, obtaining a conversion coordinate vector of the power network plane layout to generate a three-dimensional virtual power supply model according to the simulation conversion ratio and the coordinate vector, and extracting the three-dimensional virtual power supply model from the conversion coordinate vector based on the MarchingCubes algorithm.

[0098] It should be noted that when extracting the three-dimensional virtual power supply model from the converted coordinate vector based on the MarchingCubes algorithm, auxiliary modeling can be performed with the help of three-dimensional modeling software such as Autodesk Inventor, SketchUp, Cinema 4D, and Blender.

[0099] In this embodiment, when modeling the three-dimensional virtual power supply model, considering that the coordinate system of the power supply network in the original power supply scheme is different from that of the three-dimensional virtual power supply model, it is necessary to perform coordinate transformation on the three-dimensional virtual power supply model to generate a three-dimensional virtual power supply model with the same structure as the actual power supply network. The ratio of the three-dimensional virtual power supply model to the actual power supply network structure can be 1:100-1000. In the present invention, a three-dimensional virtual power supply model can be generated based on power supply parameter information and the plane layout of the power network, thereby facilitating the real-time presentation of the power supply network in the background and facilitating the staff to adjust and optimize the power supply network design. At the same time, when regenerating the three-dimensional virtual power supply model, the staff can flexibly manually draw the plane layout of the power network, and the smart mobile terminal 200 accurately identifies the plane layout of the power network, thereby ensuring the modeling accuracy of the three-dimensional virtual power supply model.

[0100] The embodiment of the present invention provides a method for determining the similarity between the real-time basic model and the historical standard model. Figure 3A schematic diagram of the implementation flow of a method for determining the similarity between the real-time basic model and the historical standard model is shown. The method for determining the similarity between the real-time basic model and the historical standard model specifically includes:

[0101] Step S1021, defining the distribution weights of multiple groups of pixels in the real-time basic model as , the number of pixels is , multiple groups of pixel point vectors in the real-time basic model are represented as: , while the number of significant pixel clusters in the real-time basic model is , the vector representation set corresponding to the significant pixel cluster is ;

[0102] It should be noted that the real-time basic model contains multiple groups of pixels. A pixel is the smallest controllable light point on a display or electronic image, representing a single color or brightness value in the image. In technical terms, a pixel can usually only display one color, and its size depends on the resolution and screen size of the device. The concepts of pixel and pixel are closely related but different. A pixel is a two-dimensional matrix composed of several pixels, which is used to describe the size and clarity of a digital image. In image processing, each pixel has a specific position, which represents the color or brightness information of the point. By processing and combining these pixels, a complete digital image can be obtained and recognized.

[0103] Step S1022, calculating the edge distribution similarity probability in the real-time basic model based on the similarity potential function, wherein the edge distribution similarity probability is calculated by formula (1);

[0104] (1)

[0105] in, is the vector corresponding to the salient pixel cluster, is the number of pixels. In this embodiment, the number of pixels can be 1-10000. Select values ​​for similarity, is the edge weight coefficient of the similarity potential function. In this embodiment, the edge weight coefficient is 0.1-0.8;

[0106] (2)

[0107] Step S1023, obtaining edge distribution similarity probability, and determining edge intersection node distribution similarity probability of the real-time basic model in combination with the simulated annealing process;

[0108] (3)

[0109] in, is the similarity probability of edge crossing node distribution, is the number of edges of the real-time base model, is the similarity probability of edge distribution in the real-time basic model, In order to combine the number of iterations based on the Metropolis criterion in the simulated annealing process, in this embodiment, the number of iterations may be 3-10 times;

[0110] Step S1024, calculating the predicted attribution degree of the real-time basic model based on the simulated annealing algorithm, correcting the predicted attribution degree, and obtaining the similarity between the real-time basic model and the historical standard model;

[0111] (4)

[0112] in, is the similarity between the real-time basic model and the historical standard model, is the number of edges of the real-time base model, is the similarity penalty coefficient in the simulated annealing algorithm, is the predicted attribution of the real-time base model, is the correction value of attribution degree;

[0113] (5)

[0114] (6)

[0115] in, is the number of edges of the real-time base model, is a similarity penalty coefficient in the simulated annealing algorithm. In this embodiment, the similarity penalty coefficient is an integer between 1 and 4.

[0116] In the present invention, the similarity between the real-time basic model and the historical standard model is determined by combining the simulated annealing algorithm. Compared with the existing technology, the judgment result is more efficient and accurate. At the same time, the simulated annealing algorithm is combined with the similarity potential function to perform edge detection, feature extraction and pixel segmentation on the real-time basic model, thereby improving the accuracy and efficiency of real-time basic model recognition.

[0117] The embodiment of the present invention provides a method for constructing an energy consumption calculation model. Figure 4 The schematic diagram of the implementation process of the method for constructing the energy consumption calculation model is shown. The method for constructing the energy consumption calculation model specifically includes:

[0118] Step S201, collecting power supply energy consumption parameters corresponding to the disclosed power supply facilities and power supply lines to obtain a power supply energy consumption parameter set;

[0119] Step S202, extracting a training set and a test set from the power supply energy consumption parameter set based on the VMD stepwise decomposition method, wherein the ratio of the training set to the test set is 7:3;

[0120] Step S203, constructing an initial calculation model combining a wavelet extreme learning machine and an echo state network based on gradient enhancement, taking the training set as input, using a gradient descent algorithm to reduce the loss of predicted values ​​and measured values, adjusting the hyperparameters of the initial calculation model, and realizing pre-training of the model;

[0121] Step S204, verifying the model parameters by combining the 10-fold cross validation method, obtaining an optimized initial calculation model, implementing model retraining, and evaluating the performance of the initial calculation model based on pinball loss, interval sharpness, and prediction interval coverage, to obtain an initial calculation model with the best loss prediction result;

[0122] Step S205, obtaining a test set, inputting the test set into the initial calculation model, and obtaining a prediction result of the test set;

[0123] Step S206, determining whether the prediction result is greater than a preset accuracy threshold. In this embodiment, the accuracy threshold may be 0.9-0.95;

[0124] Step S207: if it is greater than the preset accuracy threshold, the energy consumption calculation model is output; if it is less than the preset accuracy threshold, the process returns to step S203.

[0125] It should be noted that the energy consumption calculation model consists of an input layer, a reservoir, a hidden layer and an output layer, and the input layer is connected to the reservoir, the reservoir is connected to the hidden layer, and the hidden layer is connected to the output layer. At the same time, the neurons of the hidden layer are based on the wavelet basis function as the activation function. The number of hidden layers can be 3-10 groups, and each group of hidden layers contains 8-32 neurons. The role of the reservoir is to map the input data to a higher-dimensional space and capture the time dependency in the input data. The neurons in the reservoir can exhibit complex dynamic behaviors.

[0126] In the present invention, by constructing an energy consumption calculation model, the parameter characteristics that affect the energy consumption of power supply facilities and power supply lines can be extracted. At the same time, the energy consumption calculation model can utilize multi-source heterogeneous parameter data, and has a stronger ability to predict and judge the energy consumption of power supply facilities and power supply lines. The energy consumption calculation model is a combined prediction model, which can effectively combine the wavelet extreme learning machine and the echo state network, and carry out combined prediction, thereby reducing the risk of single model application.

[0127] The embodiment of the present invention provides a method for calculating the transmission loss coefficient of power supply facilities and power supply lines in a three-dimensional virtual power supply model. Figure 5 The schematic diagram of the implementation flow of the method for calculating the transmission loss coefficient of the power supply facilities and power supply lines in the three-dimensional virtual power supply model is shown. The method for calculating the transmission loss coefficient of the power supply facilities and power supply lines in the three-dimensional virtual power supply model specifically includes:

[0128] Step S301, obtaining power supply parameter information, extracting and decomposing a feature sequence of the power supply parameter information to obtain a feature factor set, and performing feature cleaning on the feature factor set to obtain a feature cleaning set;

[0129] Step S302, loading a feature cleaning set, taking the feature cleaning set as input, executing an energy consumption calculation model, the energy consumption calculation model generating energy consumption load curves of power supply facilities and power supply lines in a three-dimensional virtual power supply model based on a partial autocorrelation function;

[0130] Step S303, obtaining energy consumption load curves of power supply facilities and power supply lines in the three-dimensional virtual power supply model, and calculating the predicted energy consumption of power supply facilities and power supply lines by combining the Markov chain state probability function;

[0131] Step S304, based on the predicted energy consumption of power supply facilities and power supply lines, a PageRank function is introduced to calculate the transmission loss coefficients of power supply facilities and power supply lines in the three-dimensional virtual power supply model.

[0132] In the present invention, by calculating the transmission loss coefficients of power supply facilities and power supply lines in the three-dimensional virtual power supply model, the transmission loss coefficients of power supply facilities and power supply lines can be presented in real time, which facilitates the staff to replace and optimize the power supply facilities and power supply lines in the design stage, thereby reducing the difficulty of generating power supply plans.

[0133] The embodiment of the present invention provides a method for optimizing and reorganizing power supply facilities and power supply lines in a three-dimensional virtual power supply model based on an ant colony algorithm. Figure 6 The schematic diagram of the implementation process of the method for optimizing and reorganizing the power supply facilities and power supply lines in the three-dimensional virtual power supply model based on the ant colony algorithm is shown. The method for optimizing and reorganizing the power supply facilities and power supply lines in the three-dimensional virtual power supply model based on the ant colony algorithm specifically includes:

[0134] Step S401, determining an energy consumption weight value based on an energy consumption coefficient of a power supply facility coordinate position;

[0135] (7)

[0136] in, is the energy consumption weight value of power supply facilities, is the energy consumption coefficient of power supply facilities, is the number of power supply facilities directly connected to the current power supply facility. In this embodiment, the number of power supply facilities directly connected to the current power supply facility may be 1-100. is the number of power supply facilities, the number of power supply facilities is 1-10000, is the coupling coefficient of the ant colony algorithm. In this embodiment, the coupling coefficient of the ant colony algorithm is 1-5. The longest transmission distance between the current power supply facility and the directly connected power supply facility. is the average transmission distance between the current power supply facility and the directly connected power supply facility;

[0137] Step S402, randomly changing the power supply lines between the power supply facilities based on the energy consumption weight values ​​to generate an optimized reorganization set;

[0138] Among them, the power supply lines between power supply facilities are randomly changed in the following ways:

[0139] (8)

[0140] in, Indicates the power supply line associated with the current power supply facility After the power supply lines are randomly changed, is the energy consumption weight value of power supply facilities, and , is one of the randomly changing power supply lines, and ≠ .

[0141] Step S403, loading and generating an optimized reorganization set, randomly changing the power supply parameter information associated with the power supply facilities and power supply lines based on the ant colony algorithm, and using key parameters to determine the optimized reorganization relationship with the lowest comprehensive energy consumption in the optimized reorganization set;

[0142] (9)

[0143] in, is the comprehensive energy consumption prediction value, The number of power supply facilities directly connected to the current power supply facilities.

[0144] It should be noted that the Ant Colony Optimization (ACO) is a heuristic algorithm that simulates the foraging behavior of ants and is mainly used to solve combinatorial optimization problems, especially path optimization problems. The present invention combines the ant colony algorithm when optimizing and reorganizing power supply facilities and power supply lines. The positive feedback mechanism in the ant colony algorithm helps to enhance the probability of selecting excellent solutions, so that the algorithm can continuously approach the optimal solution during the iteration process, which is very helpful for the dynamic optimization problems of the power system.

[0145] The embodiment of the present invention provides a system for intelligently generating a power supply solution based on a mobile terminal map operation. Figure 7 The schematic diagram of the structure of the power supply scheme intelligent generation system based on the mobile terminal graph operation is shown, and the power supply scheme intelligent generation system based on the mobile terminal graph operation specifically includes:

[0146] A parameter acquisition module 100, wherein the parameter acquisition module 100 is used to acquire power supply parameter information, wherein the power supply parameter information includes power supply line load parameters, path parameters, reliability parameters, transmission loss parameters, and power supply coordinate parameters;

[0147] The smart mobile terminal 200 is used to identify the power network plane layout drawn by the input mobile terminal diagram interface, generate a three-dimensional virtual power supply model based on the power supply parameter information and the power network plane layout, and display the three-dimensional virtual power supply model in real scene;

[0148] A loss coefficient calculation module 300, which traverses the three-dimensional virtual power supply model based on a pre-built energy consumption calculation model to calculate the transmission loss coefficients of power supply facilities and power supply lines in the three-dimensional virtual power supply model;

[0149] A scheme recommendation module 400, which optimizes and reorganizes the power supply facilities and power supply lines in the three-dimensional virtual power supply model based on the ant colony algorithm, generates an optimized reorganization set, finds the optimized reorganization relationship with the lowest comprehensive energy consumption in the optimized reorganization set, determines the power supply line corresponding to the optimized reorganization relationship based on the optimized reorganization relationship, and finally determines the recommended power supply scheme with the lowest actual energy consumption.

[0150] In this embodiment, the smart mobile terminal 200 can be a laptop computer, a personal digital assistant (PDA), a mobile phone or other communication device, and the parameter acquisition module 100, the smart mobile terminal 200, the loss coefficient calculation module 300 and the solution recommendation module 400 realize data interaction through 5G communication or local area network.

[0151] The embodiment of the present invention provides a smart mobile terminal 200, Figure 8 The control structure diagram of the smart mobile terminal 200 is shown. The smart mobile terminal 200 specifically includes:

[0152] The plane layout input unit 210 obtains the power network plane layout input in the mobile terminal diagram, splits the real-time basic model in the power network plane layout, and generates a real-time model splitting library;

[0153] A similarity determination unit 220, which is used to traverse the basic model library in the mobile terminal graph, compare the real-time basic model in the real-time model splitting library with the historical standard model in the basic model library, and determine the similarity between the real-time basic model and the historical standard model;

[0154] A judgment unit 230, the judgment unit is used to judge whether the similarity between the real-time basic model and the historical standard model is greater than a first preset threshold value, if it is greater than the first preset threshold value, the historical standard model is determined as the real-time basic model, and all the real-time basic models in the real-time model splitting library are replaced based on the first preset threshold value to generate a standard power network plane layout;

[0155] A coordinate parameter conversion unit 240, the coordinate parameter conversion unit is used to load the power supply parameter information, read the power supply coordinate parameter in the power supply parameter information, and convert the power supply coordinate parameter into a coordinate vector;

[0156] A model generation unit 250 calculates a simulation conversion ratio based on the power network plane layout and power supply parameter information, obtains a conversion coordinate vector of the power network plane layout to generate a three-dimensional virtual power supply model according to the simulation conversion ratio and the coordinate vector, and extracts the three-dimensional virtual power supply model from the conversion coordinate vector based on the MarchingCubes algorithm.

[0157] In this embodiment, the plane layout input unit 210, the similarity determination unit 220, the judgment unit 230, the coordinate parameter conversion unit 240, and the model generation unit 250 can be connected by electrical or Bluetooth communication, and the modules / units integrated in the smart mobile terminal 200 of the present invention can be stored in a computer-readable storage medium if they are implemented in the form of software functional units and sold or used as independent products. Based on this understanding, the present invention implements all or part of the modules / units in the above-mentioned embodiment system, and can also be completed by instructing related hardware through a computer program. The above-mentioned computer program can be stored in a computer-readable storage medium, and the computer program can realize the functions of the above-mentioned various system embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form. Computer-readable media may include: any entity or device that can carry computer program code, recording media, USB flash drives, mobile hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc.

[0158] In another aspect of the embodiments of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer program instructions, and the computer program instructions can be executed by a processor. When the computer program instructions are executed, the method of any one of the above embodiments is implemented.

[0159] The computer-readable storage medium (e.g., memory) herein may be a volatile memory or a nonvolatile memory, or may include both a volatile memory and a nonvolatile memory. As an example and not by way of limitation, a nonvolatile memory may include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), or a flash memory. A volatile memory may include a random access memory (RAM), which may act as an external cache memory. As an example and not by way of limitation, RAM may be obtained in a variety of forms, such as synchronous RAM (DRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct Rambus RAM (DRRAM). The storage devices of the disclosed aspects are intended to include, but are not limited to, these and other suitable types of memory.

[0160] The various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure herein may be implemented or executed using the following components designed to perform the functions herein: a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination of these components. A general-purpose processor may be a microprocessor, but alternatively, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, for example, a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP, and / or any other such configuration.

[0161] In summary, the present invention provides a method and system for intelligently generating a power supply plan based on mobile terminal map operations. In the present invention, a three-dimensional virtual power supply model is generated based on power supply parameter information and the plane layout of the power network, which can accurately identify and judge the information input by the intelligent mobile terminal 200, thereby facilitating the construction of the three-dimensional virtual power supply model, so that users can accurately obtain the three-dimensional virtual power supply model, and it is convenient for users to customize the power supply plan for the three-dimensional virtual power supply model scene. At the same time, the present invention optimizes and reorganizes the power supply facilities and power supply lines in the three-dimensional virtual power supply model based on the ant colony algorithm, and generates a recommended power supply plan with the minimum actual energy consumption from the perspective of reducing power supply energy consumption, thereby reducing power supply energy consumption, thereby rationally utilizing energy, and ensuring energy saving under the premise of optimizing the recommended power supply plan.

[0162] It should be noted that, for the above-mentioned embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described order of actions, because according to the present invention, some steps may be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.

[0163] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as 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 communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection between devices or units can be in the form of telecommunication or other forms.

[0164] The units described above 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 network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0165] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the scope of protection of the invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on these embodiments, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in this field can still combine, add, delete or make other adjustments to the features in the various embodiments of the present invention according to the circumstances without conflict, without making creative work, so as to obtain different other technical solutions that do not deviate from the concept of the present invention in essence, and these technical solutions also belong to the scope of protection of the present invention.

Claims

1. A method for intelligently generating power supply schemes based on mobile terminal graph operations. It is characterized in that The method for intelligently generating a power supply scheme based on mobile terminal graph operations includes: Acquire power supply parameter information, wherein the power supply parameter information includes power supply line load parameters, path parameters, reliability parameters, transmission loss parameters, and power supply coordinate parameters; Identify the power network plane layout drawn on the input mobile terminal diagram interface, generate a three-dimensional virtual power supply model based on the power supply parameter information and the power network plane layout, and display the three-dimensional virtual power supply model in real scene; Based on the pre-built energy consumption calculation model, the three-dimensional virtual power supply model is traversed to calculate the transmission loss coefficients of the power supply facilities and power supply lines in the three-dimensional virtual power supply model; Based on the ant colony algorithm, the power supply facilities and power supply lines in the three-dimensional virtual power supply model are optimized and reorganized to generate an optimized reorganization set, find the optimized reorganization relationship with the lowest comprehensive energy consumption in the optimized reorganization set, determine the power supply line corresponding to the optimized reorganization relationship based on the optimized reorganization relationship, and finally determine the recommended power supply plan with the lowest actual energy consumption; The method for generating a three-dimensional virtual power supply model based on power supply parameter information and a power network plane layout specifically includes: Obtain the power network plane layout input in the mobile terminal diagram, split the real-time basic model in the power network plane layout, and generate a real-time model splitting library; Traverse the basic model library in the mobile terminal graph, compare the real-time basic model in the real-time model splitting library with the historical standard model in the basic model library, and determine the similarity between the real-time basic model and the historical standard model; Determine whether the similarity between the real-time basic model and the historical standard model is greater than a preset similarity threshold. If so, determine the historical standard model as the real-time basic model, and replace all the real-time basic models in the real-time model splitting library based on the preset similarity threshold to generate a standard power network plane layout. The method for generating a three-dimensional virtual power supply model based on power supply parameter information and a power network plane layout specifically includes: Loading power supply parameter information, reading power supply coordinate parameters in the power supply parameter information, and converting the power supply coordinate parameters into coordinate vectors; Calculate the analog conversion ratio based on the power network plane layout and power supply parameter information; Obtaining a conversion coordinate vector of a power network plane layout to generate a three-dimensional virtual power supply model according to a simulation conversion ratio and a coordinate vector, and extracting the three-dimensional virtual power supply model from the conversion coordinate vector based on a MarchingCubes algorithm; The method for determining the similarity between the real-time basic model and the historical standard model specifically includes: Define the distribution weights of multiple groups of pixels in the real-time basic model as , the number of pixels is , multiple groups of pixel point vectors in the real-time basic model are represented as: , while the number of significant pixel clusters in the real-time basic model is , the vector representation set corresponding to the significant pixel cluster is ; The edge distribution similarity probability in the real-time basic model is calculated based on the similarity potential function, wherein the edge distribution similarity probability is calculated by formula (1); (1) in, is the vector corresponding to the salient pixel cluster, is the number of pixels, Select values ​​for similarity, is the edge weight coefficient of the similarity potential function; (2) Obtain edge distribution similarity probability, and determine edge intersection node distribution similarity probability of the real-time basic model in combination with simulated annealing process; (3) in, is the similarity probability of edge crossing node distribution, is the number of edges of the real-time base model, is the similarity probability of edge distribution in the real-time basic model, It is the number of iterations based on the Metropolis criterion in the combined simulated annealing process; The predicted attribution of the real-time basic model is calculated based on the simulated annealing algorithm, and the predicted attribution is corrected to obtain the similarity between the real-time basic model and the historical standard model; (4) in, is the similarity between the real-time basic model and the historical standard model, is the number of edges of the real-time base model, is the similarity penalty coefficient in the simulated annealing algorithm, is the predicted attribution of the real-time base model, is the correction value of attribution degree; (5) (6) in, is the number of edges of the real-time base model, is the similarity penalty coefficient in the simulated annealing algorithm.

2. The method for intelligently generating a power supply scheme based on mobile terminal graph operation according to claim 1, Features: The method for constructing the energy consumption calculation model specifically includes: Collect power supply energy consumption parameters corresponding to the publicly available power supply facilities and power supply lines to obtain a power supply energy consumption parameter set; Based on the VMD step-by-step decomposition method, the training set and the test set are extracted from the power supply energy consumption parameter set, where the ratio of the training set to the test set is 7:3; Based on gradient enhancement, an initial calculation model combining wavelet extreme learning machine and echo state network is constructed. With the training set as input, the gradient descent algorithm is used to reduce the loss between the predicted value and the measured value, and the hyperparameters of the initial calculation model are adjusted to realize the pre-training of the model. The model parameters were verified by 10-fold cross validation to obtain an optimized initial calculation model, which was then retrained. The performance of the initial calculation model was evaluated based on pinball loss, interval sharpness, and prediction interval coverage to obtain the initial calculation model with the best loss prediction results. Obtain a test set, input the test set into the initial calculation model, obtain the prediction result of the test set, and determine whether the prediction result is greater than a preset accuracy threshold. If it is greater than the preset accuracy threshold, output the energy consumption calculation model.

3. The method for intelligently generating a power supply scheme based on mobile terminal graph operation as claimed in claim 2, Features: The method for calculating the transmission loss coefficient of power supply facilities and power supply lines in the three-dimensional virtual power supply model specifically includes: Acquire power supply parameter information, extract and decompose a feature sequence of the power supply parameter information to obtain a feature factor set, and perform feature cleaning on the feature factor set to obtain a feature cleaning set; Loading a feature cleaning set, taking the feature cleaning set as input, executing an energy consumption calculation model, the energy consumption calculation model generating energy consumption load curves of power supply facilities and power supply lines in a three-dimensional virtual power supply model based on a partial autocorrelation function; Obtain the energy consumption load curves of power supply facilities and power supply lines in the three-dimensional virtual power supply model, and calculate the predicted energy consumption of power supply facilities and power supply lines by combining the Markov chain state probability function; Based on the predicted energy consumption of power supply facilities and power lines, the PageRank function is introduced to calculate the transmission loss coefficients of power supply facilities and power lines in the three-dimensional virtual power supply model.

4. The method for intelligently generating a power supply scheme based on mobile terminal graph operation as claimed in claim 3, Features: The method for optimizing and reorganizing power supply facilities and power supply lines in a three-dimensional virtual power supply model based on an ant colony algorithm specifically includes: Determine the energy consumption weight value based on the energy consumption coefficient of the power supply facility coordinate position; (7) in, is the energy consumption weight value of power supply facilities, is the energy consumption coefficient of power supply facilities, is the number of power supply facilities directly connected to the current power supply facilities, is the number of power supply facilities, is the coupling coefficient of the ant colony algorithm, The longest transmission distance between the current power supply facility and the directly connected power supply facility. is the average transmission distance between the current power supply facility and the directly connected power supply facility; Randomly change the power supply lines between power supply facilities based on energy consumption weight values ​​to generate an optimized reorganization set; Among them, the power supply lines between power supply facilities are randomly changed in the following ways: (8) in, Indicates the power supply line associated with the current power supply facility After the power supply lines are randomly changed, is the energy consumption weight value of power supply facilities, and , is one of the randomly changing power supply lines, and ≠ .

5. The method for intelligently generating a power supply scheme based on mobile terminal graph operation as claimed in claim 4, Features: The method for optimizing and reorganizing power supply facilities and power supply lines in a three-dimensional virtual power supply model based on an ant colony algorithm specifically includes: Load and generate an optimized reorganization set, randomly change the power supply parameter information associated with power supply facilities and power supply lines based on the ant colony algorithm, and use key parameters to determine the optimized reorganization relationship with the lowest comprehensive energy consumption in the optimized reorganization set; (9) in, is the comprehensive energy consumption prediction value, The number of power supply facilities directly connected to the current power supply facilities.

6. A system for intelligently generating a power supply scheme based on mobile terminal graph operations, implemented by the method for intelligently generating a power supply scheme based on mobile terminal graph operations as described in any one of claims 1 to 5, Features: The power supply scheme intelligent generation system based on mobile terminal map operation includes: A parameter acquisition module, wherein the parameter acquisition module is used to acquire power supply parameter information, wherein the power supply parameter information includes power supply line load parameters, path parameters, reliability parameters, transmission loss parameters, and power supply coordinate parameters; An intelligent mobile terminal, the intelligent mobile terminal is used to identify the power network plane layout drawn on the input mobile terminal diagram interface, generate a three-dimensional virtual power supply model based on the power supply parameter information and the power network plane layout, and display the three-dimensional virtual power supply model in real scene; A loss coefficient calculation module, which traverses the three-dimensional virtual power supply model based on a pre-built energy consumption calculation model to calculate the transmission loss coefficients of power supply facilities and power supply lines in the three-dimensional virtual power supply model; A scheme recommendation module, which optimizes and reorganizes the power supply facilities and power supply lines in the three-dimensional virtual power supply model based on the ant colony algorithm, generates an optimized reorganization set, finds the optimized reorganization relationship with the lowest comprehensive energy consumption in the optimized reorganization set, determines the power supply line corresponding to the optimized reorganization relationship based on the optimized reorganization relationship, and finally determines the power supply recommendation scheme with the lowest actual energy consumption.

7. The power supply scheme intelligent generation system based on mobile terminal map operation as claimed in claim 6, Features: The smart mobile terminal includes: A plane layout input unit obtains the power network plane layout input in the mobile terminal image, splits the real-time basic model in the power network plane layout, and generates a real-time model splitting library; A similarity determination unit, the similarity determination unit is used to traverse the basic model library in the mobile terminal graph, compare the real-time basic model in the real-time model splitting library with the historical standard model in the basic model library, and determine the similarity between the real-time basic model and the historical standard model; A judgment unit, the judgment unit is used to judge whether the similarity between the real-time basic model and the historical standard model is greater than a similarity preset threshold. If it is greater than the similarity preset threshold, the historical standard model is determined as the real-time basic model, and all the real-time basic models in the real-time model splitting library are replaced based on the similarity preset threshold to generate a standard power network plane layout; A coordinate parameter conversion unit, the coordinate parameter conversion unit is used to load the power supply parameter information, read the power supply coordinate parameter in the power supply parameter information, and convert the power supply coordinate parameter into a coordinate vector; A model generation unit, wherein the model generation unit calculates a simulation conversion ratio based on the power network plane layout and power supply parameter information, obtains a conversion coordinate vector of the power network plane layout to generate a three-dimensional virtual power supply model according to the simulation conversion ratio and the coordinate vector, and extracts the three-dimensional virtual power supply model from the conversion coordinate vector based on the MarchingCubes algorithm.

Citation Information

Patent Citations

  • Power supply scheme formulation method and device

    CN106684870A

  • Real-time predictive systems for intelligent energy monitoring and management of electrical power networks

    CA2882796A1

  • Method for reconstructing power distribution network based on double-ant-colony optimization

    CN103903062A

  • Multi-technology fused electricity stealing behavior identification method and system

    CN113379049A

  • Electric energy intelligent management and control method, device and system based on Internet of Things

    CN115423301A