Site selection planning method, system and equipment for distribution network engineering transformer area and medium

Abstract

The invention discloses a distribution network engineering transformer area site selection planning method, system and device and a medium, and the method comprises the steps: processing the obtained power equipment information, load information and topological structure information around a target distribution network transformer area through a geographic information system technology, and generating visual transformer area information; acquiring all fire falling point data in the visual transformer area information, and processing the fire falling point data by using a gravity center algorithm to obtain transformer area load center coordinates corresponding to the visual transformer area information; inputting the load center coordinates into the trained region screening model to obtain a preliminary available plot region; inputting a knowledge graph constructed by map information in the preliminary available plot region into a graph neural network model to obtain a recommended available plot region; using an improved taboo search algorithm to determine a target recommended plot area from the recommended available plot areas to perform site selection and planning of the courts; according to the method, the distribution network planning area site selection efficiency can be remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of distribution networks, and in particular to a method, system, device and medium for site selection and planning of distribution network project substations. Background Art

[0002] With the in-depth promotion of the national "Digital China" strategy, the power industry, as a key infrastructure field, is accelerating its transformation towards digitalization and intelligentization. To fully promote the construction of digital power grids, the planning, operation and management efficiency of power systems will be improved through technical means. However, in the planning of distribution network projects, the site selection of substation land, as one of the core links, still highly depends on the traditional manual exploration and empirical judgment mode at present. This way will lead to problems such as low planning efficiency and uneven site selection quality, thus affecting the power supply reliability and stability.

[0003] Therefore, it can be seen that how to optimize the site selection method of substations in distribution network projects and improve the site selection efficiency and quality has become a technical problem that needs to be urgently solved by those skilled in the art. Summary of the Invention

[0004] The present invention provides a method, system, device and medium for site selection and planning of distribution network project substations, which solves the problem of how to replace manual work with digital and automated site selection means to improve the efficiency, quality and power supply stability of distribution network substation site selection.

[0005] To solve the above technical problems, an embodiment of the present invention provides a method for site selection and planning of distribution network project substations, including:

[0006] Processing the power equipment information, load information and topological structure information around the target distribution network substation obtained through geographic information system technology to generate visual substation information;

[0007] Obtaining all the fire drop point data in the visual substation information, and processing the fire drop point data by using the gravity center algorithm to obtain the substation load center coordinate data corresponding to the visual substation information;

[0008] Inputting the load center coordinate data into a trained area screening model, and outputting a preliminary available plot area;

[0009] Inputting the knowledge graph constructed from the map information data in the preliminary available plot area into a trained graph neural network model for analysis and screening to obtain a recommended available plot area;

[0010] Taking the target recommended plot area determined from the recommended available plot area by using the improved tabu search algorithm for site selection and planning of the substation.

[0011] Further, the process of processing the fire point data using the center of gravity algorithm to obtain the substation load center coordinate data corresponding to the visualized substation area information includes:

[0012] Based on the center of gravity algorithm, each fire point is regarded as a mass point, and according to the position information and relative distance of the current fire point, the substation load center coordinate data in the horizontal coordinate direction and the vertical coordinate direction are calculated; where, the substation load center coordinate data in the horizontal coordinate direction is expressed as:

[0013]

[0014] The substation load center coordinate data in the vertical coordinate direction is expressed as:

[0015]

[0016] In the formula, n is the number of fire points; (x i , y i ) is the coordinate of the i-th fire point; p i is the load of the i-th fire point; d ij is the distance between the i-th fire point and the j-th fire point; X and Y are the abscissa and ordinate of the substation load center respectively.

[0017] Further, the construction process of the area screening model includes:

[0018] The geographical information data set including terrain data, building distribution data and water system data around the target distribution substation area collected is divided and the plot availability is marked in sequence;

[0019] The marked geographical information data set is used to iteratively train the generator model and discriminator model created by the generative adversarial network to obtain the area screening model.

[0020] Further, inputting the knowledge graph constructed from the map information data in the preliminary available plot area into the trained graph neural network model for analysis and screening includes:

[0021] Integrate the account data, regulatory planning data and map information data in the preliminary available plot area to construct a multi-source data set;

[0022] Based on the multi-source data set, taking each plot in the preliminary available plot area as a node, and taking the attribute information of the plot, the spatial relationship between plots and the planning information of the plot in the regulatory planning as edges, construct the knowledge graph;

[0023] Vectorize the node features and edge features extracted from the knowledge graph and input them into the graph neural network model for analysis and screening.

[0024] Furthermore, the target recommended plot area determined from the recommended available plot area by using the improved taboo search algorithm includes:

[0025] Randomly determine a plurality of taboo solutions composed of a plurality of plots from the recommended available plot area, and assign a corresponding taboo table to each taboo solution;

[0026] In the process of dynamically adjusting the updating frequency of the taboo table according to the quality change of the taboo solution, the search range of the taboo table is collaboratively optimized and adjusted according to the density of the plot distribution in the recommended available plot area to determine the target recommended plot area.

[0027] Furthermore, dynamically adjusting the updating frequency of the taboo table according to the quality change of the taboo solution includes:

[0028] Based on the preset quality change threshold, the update frequency of the taboo table is dynamically adjusted by real-time monitoring of the improvement of the taboo solution optimization target.

[0029] Furthermore, the target recommended plot area determined from the recommended available plot area by using the improved taboo search algorithm further includes:

[0030] The geological stability, line terminal voltage, line loss and relative load center distance in the recommended available land area are uniformly quantified, and the value of each land in the recommended available land area is scored according to the quantitative indicators;

[0031] Aggregate the value scoring results corresponding to each plot of land to obtain the comprehensive value scoring results corresponding to each taboo solution;

[0032] The high-order taboo solutions whose comprehensive value score results exceed the set score threshold are pardoned, so that the plot combination corresponding to the high-order taboo solution is introduced into the search range of the taboo table.

[0033] Another embodiment of the present invention provides a distribution network engineering substation site selection planning system, including:

[0034] The substation information visualization module is used to process the power equipment information, load information and topological structure information around the target distribution network substation obtained through geographic information system technology to generate visualized substation information.

[0035] The load center coordinate acquisition module is used to obtain all the fire point data in the visualized area information, process the fire point data using the gravity center algorithm, and obtain the area load center coordinate data corresponding to the visualized area information.

[0036] The preliminary available plot acquisition module is used to input the load center coordinate data into a trained area screening model and output the preliminary available plot area.

[0037] The available plot screening module is used to input the knowledge graph constructed from the map information data in the preliminary available plot area into a trained graph neural network model for analysis and screening to obtain the recommended available plot area;

[0038] The site selection and planning module is used to perform the site selection and planning of the substation area with the target recommended plot area determined from the recommended available plot area by using the improved tabu search algorithm.

[0039] Another embodiment of the present invention provides a computer device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the above-mentioned distribution network project substation area site selection and planning method is implemented.

[0040] Another embodiment of the present invention provides a computer-readable storage medium. The computer-readable storage medium stores a computer program. When the device where the computer-readable storage medium is located executes the computer program, the above-mentioned distribution network project substation area site selection and planning method is implemented.

[0041] Compared with the prior art, the beneficial effects of the embodiments of the present invention are at least one of the following:

[0042] The embodiments of the present invention integrate high-precision map data through geographic information system technology, provide an intuitive graphical interface, reduce the manual exploration time, adopt the gravity center algorithm, regard the fire drop points under the problem substation area as mass points, and can accurately calculate the load center coordinates; based on the generative adversarial network combined with the knowledge graph, graph neural network and improved tabu search algorithm, screen out the recommended available plot area and generate the comprehensive optimal recommended plot, improving the accuracy and reliability of the recommended result, thereby ensuring the stable and reliable power supply of the power grid. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a schematic flowchart of the distribution network project substation area site selection and planning method in one embodiment of the present invention;

[0044] Figure 2 is a schematic structural diagram of the distribution network project substation area site selection and planning system in one embodiment of the present invention;

[0045] Figure 3 is a structural block diagram of a preferred embodiment of a computer device provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The purpose of providing these embodiments is to make the disclosure of the present invention more thorough and comprehensive. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts belong to the scope of protection of the present invention.

[0047] In the description of the present application, the terms "first", "second", "third", etc. are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first", "second", "third", etc. may explicitly or implicitly include one or more of such features. In the description of the present application, unless otherwise stated, the meaning of "a plurality" is two or more.

[0048] In the description of the present application, it should be noted that, unless otherwise clearly defined and limited, the terms "installed", "connected", "connected" should be understood in a broad sense. For example, it may be a fixed connection, a detachable connection, or an integral connection; it may be a mechanical connection or an electrical connection; it may be directly connected, or indirectly connected through an intermediate medium, and it may be the communication inside two elements. The terms "vertical", "horizontal", "left", "right", "up", "down" and similar expressions used herein are only for the purpose of illustration, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus cannot be construed as a limitation of the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0049] In the description of the present application, it should be noted that, unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as commonly understood by those of ordinary skill in the technical field to which this technology belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0050] An embodiment of the present invention provides a method for locating and planning a distribution network project substation area. Specifically, please refer to Figure 1 , Figure 1 which shows a schematic flow chart of the method for locating and planning a distribution network project substation area in one of the embodiments of the present invention, including the following steps:

[0051] S1. Process the power equipment information, load information, and topological structure information around the target distribution network substation area obtained through geographic information system technology to generate visual substation area information.

[0052] In the power system, the substation area specifically refers to the power supply area range of a certain transformer (installed and operating), which is the most basic power supply unit in the distribution network. A problematic substation area refers to a substation area that has certain problems or challenges during the power supply and distribution process. In this embodiment, the target distribution network substation area refers to the problematic substation area.

[0053] Through geographic information system (GIS) technology, the topological structure of the substation area is visually presented in the form of a geographic layer + dynamic rendering + network analysis. In this embodiment, a visual function of the problematic substation area and its surrounding substation area topologies is provided for planners in the form of a high-precision map. Specifically, with the help of graphic rendering, not only are the information of each substation area, topological structure information, and various power equipment information around the obtained problematic substation area, including transformer, distribution cabinet, and user electricity meter coordinates, rendered in different colors, but also the real-time current, voltage, and power data of its related load information, and the color depth or hue can be dynamically adjusted according to the real-time change of the load to generate visual substation area information, facilitating planners to more intuitively grasp the situation of the substation area.

[0054] The presentation of the visual substation area information provides a clear and accessible data basis and a convenient decision-making basis for subsequent intelligent algorithms.

[0055] S2. Obtain all the fire point data in the visual substation area information, and process the fire point data using the gravitational center algorithm to obtain the substation area load center coordinate data corresponding to the visual substation area information.

[0056] It should be understood that after finding all the fire points in the visual substation area information, each of the fire points is regarded as a mass point with a certain mass based on the gravitational center algorithm, and the mass size is proportional to the load borne by the fire point. According to the idea of Newton's law of universal gravitation, the load center is the position where all the fire points "attract" each other to reach equilibrium.

[0057] Calculate the substation area load center coordinate data in the horizontal and vertical coordinate directions according to the position information of the current fire point and the relative distance between the current fire point and other fire points.

[0058] As an example, in some embodiments of the present invention, assuming there are n fire points, the coordinates of the i-th fire point are (x i , y i ), and the load is p i . The substation area load center coordinate data in the horizontal coordinate direction is expressed as:

[0059]

[0060] In the vertical direction, the coordinate data of the load center in the substation area is expressed as:

[0061]

[0062] In the formula, X and Y are respectively the abscissa and ordinate of the load center; d ij is the distance between the i-th fire point and the j-th fire point. Specifically,

[0063] It should be understood that the above two formulas represent the influence of the resultant gravitational force in the x direction on the abscissa / ordinate of the load center.

[0064] In the power system, the load center needs to be as close as possible to the high-load area to reduce line losses. The gravitational algorithm simulates the "center of gravity" of the load distribution by weighting the distance and the load size, which is more in line with the actual situation of the load distribution than the simple weighted average, especially when the distribution of the fire points is uneven.

[0065] S3. Input the coordinate data of the load center into the trained area screening model, and output the initially available plot area.

[0066] In order to quickly generate a large number of candidate areas and reduce the workload of manual screening, the embodiment of the present invention uses a generative adversarial network (GAN) to generate the initially available plot area from the massive map data.

[0067] Collect the map data of a specific area around the target distribution network substation area, including various geographical information such as terrain, building distribution, water system, etc., and divide it into a training set and a test set as the geographical information data set. Accurately label the available and unavailable plots in the training set as the supervision information of the discriminator.

[0068] Iteratively train the generator model and the discriminator model created by the generative adversarial network using the training set in the labeled geographical information data set. During the training process, first, based on the generative adversarial network, initialize the generator and the discriminator. The generator will try to generate potential available plot areas, and the discriminator will distinguish the generated areas from the real unavailable areas. The generator continuously adjusts the parameters to make the generated areas closer to the real available plots, and the discriminator continuously improves its discrimination ability. The two confront each other and co-evolve. After multiple rounds of iterative training, when the available plot areas generated by the generator can be accurately recognized by the discriminator in the test set and conform to the actual geographical rules, it is considered that the model training is successful, that is, the area screening model is obtained.

[0069] At that time, the load center coordinate data and the map data are input into the trained area screening model, and the model will output a reasonable preliminary available land area. The preliminary available land area will contain many candidate plots.

[0070] S4. Input the knowledge graph constructed by the map information data in the preliminary available land area into the trained graph neural network model for analysis and screening to obtain the recommended available land area.

[0071] In order to further accurately screen the obtained preliminary available land areas, the embodiment of the present invention verifies the compliance and availability of the preliminary available land through knowledge graph and graph neural network (GAT).

[0072] It can be understood that the preliminary available plot area contains multi-source data such as available land ledger data (property information such as plot ownership, purpose, area, etc.), control planning data (planned purpose information of the plot), and map information data (such as the spatial coordinates of the plot, and the adjacent relationship with the surrounding plots). The embodiment of the present invention integrates these data to construct a multi-source data set for knowledge graph generation. Specifically, in some embodiments of the present invention, each plot in the preliminary available plot area is used as a node, and the attribute information of the plot, the spatial relationship between the plots, and the planning information of the plot in the control plan are used as edges to construct the knowledge graph.

[0073] The knowledge graph is analyzed using the graph neural network algorithm, and the information of node features and edge features extracted from the knowledge graph is vectorized and input into the graph neural network model.

[0074] Preferably, the embodiment of the present invention uses a graph attention network (GAT) algorithm, which is expressed by the following formula:

[0075]

[0076] in, and are the feature vectors of nodes i and j respectively, W is the weight matrix, is the parameter vector of the attention mechanism, e ij is the attention coefficient between nodes i and j. In the process of analyzing and screening the preliminary available plot areas by the graph attention network model, the model can learn the complex relationships between nodes, explore the potential availability of plots, thereby excluding unavailable plots and determining the recommended available plot areas.

[0077] For example, by analyzing whether the use of a certain plot of land in the control plan matches the construction of a power substation, and the degree of correlation between the plot of land and the surrounding identified available plots, its availability can be comprehensively judged.

[0078] S5. Use the target recommended plot area determined from the recommended available plot areas by means of the improved tabu search algorithm to conduct the site selection and planning of the substation area.

[0079] Tabu search is used to solve combinatorial optimization problems. By maintaining a tabu list, it avoids repeatedly searching for solutions that have already been visited, thus jumping out of the local optimum. To improve the search efficiency and effect, the embodiments of the present invention introduce mechanisms for dynamically adjusting the tabu list, adaptive neighborhood search, and enhanced aspiration criteria, which specifically include the following steps:

[0080] 1. Randomly determine multiple tabu solutions composed of several plots from the recommended available plot areas, and assign corresponding independent tabu lists to each tabu solution. That is, randomly generate multiple plot selection schemes, each scheme containing multiple plot combinations, as the starting points of the tabu search.

[0081] 2. Dynamically adjust the update frequency of the tabu list according to the quality change of the tabu solution. In this process, in this embodiment, based on a preset quality change threshold, the improvement amplitude of the tabu solution optimization target is monitored in real time, and the update frequency of the tabu list is dynamically adjusted according to the monitoring situation. Specifically,

[0082] Set a quality change threshold ε of a tabu solution, which is set according to historical data or experience (such as ε = 5%), representing the critical value of the solution quality improvement amplitude. Monitor the improvement amplitude of the solution in each round of iteration in real time. The embodiments of the present invention will comprehensively consider the improvement degrees of optimization targets such as distance, line end voltage, and line loss. Preferably, if the improvement amplitude of the solution is less than ε in 5 consecutive iterations, it indicates that the search is likely to fall into the local optimum. At this time, shorten the tabu list update period by half to prompt the search to jump out of the current local optimum solution faster. If the solution quality improves rapidly, appropriately extend the update period to consolidate the current search direction.

[0083] In the process of dynamically adjusting the update frequency of the tabu list according to the quality change of the tabu solution, in order to balance the global exploration and local optimization capabilities of the tabu search algorithm, the embodiments of the present invention introduce an adaptive neighborhood search mechanism. That is, according to the density of plot distribution in the recommended available plot areas, collaboratively optimize and adjust the search range of the tabu list. The density of plot distribution is judged by calculating the average distance between plots to judge. Exemplarily, assume that there are m plots in the recommended available plot area, and d kl represents the distance between the kth plot and the lth plot, then is expressed as:

[0084]

[0085] If If it is less than the set value d0, it is determined as a dense area, and the neighborhood search range is reduced to 1 / 3 of the original to improve the search accuracy and avoid excessive search in a small range. If it is greater than the set value d0, it is determined as a sparse area, and the neighborhood search range is expanded to increase the global nature of the search and prevent omission of potential high-quality solutions.

[0086] In the embodiment of the present invention, through the collaborative tabu search algorithm and the adaptive domain search, when the algorithm performs fine search in the dense area, if the improvement of the tabu solution quality stagnates (triggering the update of the dynamic tabu list), it will accelerate to jump out of the current area; and after expanding the neighborhood in the sparse area, if the tabu solution quality improves rapidly (the update of the dynamic tabu list slows down), it will maintain a large-scale search, and the two jointly balance exploration and exploitation.

[0087] Furthermore, in the embodiment of the present invention, in order to ensure that high-value plots are not excluded from the search by the algorithm, a comprehensive evaluation mechanism is introduced as the amnesty criterion of the algorithm. Specifically:

[0088] The stability degrees of the plots in the recommended available plot area, such as the geological stability, the voltage at the end of the line, the line loss, the distance from the relative load center, and the future development potential, such as whether it is in the development area of the urban planning, etc., are uniformly quantified, and each plot in the recommended available plot area is scored according to the quantification index.

[0089] Preferably, the embodiment of the present invention uses the analytic hierarchy process to calculate the comprehensive value score. Specifically:

[0090] Assume that there are n factors affecting the plot, which are F1, F2, …, F n , and their corresponding weights are w1, w2, …, w n , and the score value of the i-th plot on the j-th factor is x ij , then the value score of the i-th plot is:

[0091] Among them, the distance D from the load center can be calculated through the geographical coordinates; the voltage at the end of the line can be estimated according to the power transmission formula (U0 is the initial voltage, P is the transmission power, L is the line length, A is the cross-sectional area of the wire, and U is the voltage at the end of the line); the line loss can be calculated according to the formula S = I 2 R (I is the current, R is the line resistance), and the corresponding value is obtained by combining the line parameters connecting the plot and the load center and scored.

[0092] Since each tabu solution contains a combination of multiple plots, in this embodiment, the value score results corresponding to each plot are aggregated to obtain the comprehensive value score result corresponding to each tabu solution. Exemplarily, the comprehensive value score result is expressed as:

[0093] The high-order tabu solutions with comprehensive value scoring results exceeding the set scoring threshold are amnestied, so as to introduce the plot combinations corresponding to the high-order tabu solutions into the search scope of the tabu list. Exemplarily, when the comprehensive value scoring result of the tabu solution corresponding to a plot combination is higher than the preset threshold, it is regarded as a high-order tabu solution. Even if the power performance (such as distance, line loss) of this plot combination is not currently optimal, the amnesty is still triggered and it is re-incorporated into the search scope, ensuring that such high-potential and high-value plot combinations are not excluded from the search.

[0094] After introducing the above dynamic update, adaptive neighborhood search, and amnesty mechanism into the tabu search algorithm, iterative search is performed from the recommended available plot areas to screen out the determined target recommended plot areas. Exemplarily, three plots that are the closest to the load center and have the highest comprehensive value are selected from multiple search results as the final target recommendation results. For example, 5 search processes are started simultaneously, each process starts searching from a different initial plot combination, and finally, the final results of all processes are compared to select the optimal three plots, and the plot with the best comprehensive performance in the area is selected as the target recommended plot.

[0095] Finally, the planner can use the location of the finally recommended target recommended plot area as the substation site selection, or can finally determine the optimal site selection according to the recommended three preferred locations in combination with the on-site investigation situation.

[0096] In summary, the embodiment of the present invention determines the load center point by simulating the law of universal gravitation, solves the accuracy problem of the traditional weighted average method when the distribution of fire points is uneven, uses a generative adversarial network to analyze map data to generate a preliminary available area, combines a knowledge graph and a graph neural network for multi-source data fusion and screening, and introduces an improved tabu search algorithm that combines dynamic tabu list update, adaptive neighborhood search, and enhanced amnesty criteria to further optimize the plot recommendation efficiency and globality.

[0097] An embodiment of the present invention provides a substation site selection and planning system for a distribution network project. Specifically, please refer to Figure 2 , Figure 2 which shows a schematic structural diagram of the substation site selection and planning system for a distribution network project in one embodiment of the present invention, including:

[0098] The substation information visualization module M1 is used to process the power equipment information, load information, and topological structure information around the target distribution network substation obtained through geographic information system technology to generate visual substation information.

[0099] The load center coordinate acquisition module M2 is used to acquire all the fire point data in the visual substation information, and process the fire point data by using the gravity center algorithm to obtain the substation load center coordinate data corresponding to the visual substation information.

[0100] The preliminary available plot acquisition module M3 is configured to input the load center coordinate data into a trained area screening model, and output a preliminary available plot area.

[0101] The available plot screening module M4 is configured to input a knowledge graph constructed from the map information data in the preliminary available plot area into a trained graph neural network model for analysis and screening, and obtain a recommended available plot area;

[0102] The site selection and planning module M5 is configured to perform the site selection and planning of the substation area with respect to a target recommended plot area determined from the recommended available plot area by using an improved tabu search algorithm.

[0103] As Figure 3 shown, an embodiment of the present invention further provides a computer device, Figure 3 which is a structural block diagram of a preferred embodiment of a computer device provided by the present invention. The computer device includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the above-described distribution network project substation area site selection and planning method is implemented.

[0104] Preferably, the computer program can be divided into one or more modules / units (such as computer program 1, computer program 2,...). The one or more modules / units are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units can be a series of computer program instruction segments capable of performing specific functions, and these instruction segments are used to describe the execution process of the computer program in the computer device.

[0105] The processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor, or the processor may also be any conventional processor. The processor is the control center of the terminal device, and connects various parts of the terminal device through various interfaces and lines.

[0106] The memory mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function, etc., and the data storage area can store relevant data, etc. In addition, the memory can be a high-speed random access memory, or a non-volatile memory, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a Flash Card, etc., or the memory can also be other volatile solid-state storage devices.

[0107] It should be noted that the above terminal device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that Figure 3 The structural block diagram is only an example of the terminal device and does not constitute a limitation on the terminal device. It may include more or fewer components than shown in the figure, or combine some components, or different components. Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, the storage medium can be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), etc.

[0108] Correspondingly, an embodiment of the present invention provides a computer-readable storage medium. The computer-readable storage medium includes a stored computer program. Among them, when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the steps in the method of the above embodiment.

[0109] The technical features and technical effects of the distribution network engineering substation location planning system proposed in the embodiment of the present invention are the same as those of the distribution network engineering substation location planning method proposed in the embodiment of the present invention, and will not be elaborated here.

[0110] The above embodiments only represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the present invention patent. It should be pointed out that for those of ordinary skill in the art, without departing from the concept of the present invention, several deformations and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention patent should be subject to the appended claims.

Claims

1. A method for selecting and planning the location of a distribution network project area, characterized in that Including: Processing the power equipment information, load information, and topological structure information around the target distribution network substation area obtained through geographic information system technology to generate visual substation area information; Obtaining all the fire point data in the visual substation area information, and processing the fire point data using the gravitational center algorithm to obtain the substation area load center coordinate data corresponding to the visual substation area information; Inputting the load center coordinate data into the trained area screening model to output a preliminary available plot area; Inputting the knowledge graph constructed from the map information data in the preliminary available plot area into the trained graph neural network model for analysis and screening to obtain a recommended available plot area; Using the improved tabu search algorithm to determine the target recommended plot area from the recommended available plot area for the site selection and planning of the substation area.

2. The distribution network project substation site selection and planning method according to claim 1, characterized in that The process of processing the fire point data using the gravitational center algorithm to obtain the substation area load center coordinate data corresponding to the visual substation area information includes: Based on the gravitational center algorithm, each fire point is regarded as a mass point, and according to the position information and relative distance of the current fire point, the substation area load center coordinate data in the horizontal and vertical coordinate directions is calculated; where the substation area load center coordinate data in the horizontal coordinate direction is expressed as: The substation area load center coordinate data in the vertical coordinate direction is expressed as: where n is the number of fire landing points; (x i , y i ) is the coordinate of the i-th fire landing point; p i is the load of the i-th fire landing point; d ij is the distance between the i-th fire landing point and the j-th fire landing point; X and Y are the abscissa and ordinate of the load center of the substation area, respectively.

3. The distribution network project substation site selection and planning method according to claim 1, characterized in that The construction process of the area screening model includes: Successively dividing and marking the availability of plots for the geographic information data set including terrain data, building distribution data, and water system data around the target distribution network substation area collected; Using the labeled geographic information data set to iteratively train the generator model and discriminator model created by the generative adversarial network to obtain the area screening model.

4. The distribution network project substation site selection and planning method according to claim 1, characterized in that, The process of inputting the knowledge graph constructed from the map information data in the preliminary available plot area into the trained graph neural network model for analysis and screening includes: Integrating the account data, regulatory planning data, and map information data in the preliminary available plot area to construct a multi-source data set; Based on the multi-source data set, using each plot in the preliminary available plot area as a node, and using the attribute information of the plot, the spatial relationship between plots, and the planning information of the plot in the regulatory planning as edges to construct the knowledge graph; Vectorizing the node features and edge features extracted from the knowledge graph and inputting them into the graph neural network model for analysis and screening.

5. The distribution network project substation site selection and planning method according to claim 1, characterized in that The process of using the improved tabu search algorithm to determine the target recommended plot area from the recommended available plot area includes: Randomly determining multiple tabu solutions composed of several plots from the recommended available plot area, and assigning a corresponding tabu list to each tabu solution; During the process of dynamically adjusting the update frequency of the tabu list according to the quality change of the tabu solution, synergistically optimizing and adjusting the search range of the tabu list according to the density of plot distribution in the recommended available plot area to determine the target recommended plot area.

6. The distribution network project substation site selection and planning method according to claim 5, wherein, The process of dynamically adjusting the update frequency of the tabu list according to the quality change of the tabu solution includes: Based on a preset quality change threshold, by monitoring the improvement amplitude of the tabu solution optimization objective in real time, dynamically adjust the update frequency of the tabu list.

7. The distribution network project substation site selection and planning method according to claim 5, characterized in that, The target recommended plot area determined from the recommended available plot areas by using the improved tabu search algorithm further includes: Uniformly quantify the geological stability degree, line end voltage, line loss, and distance from the relative load center in the recommended available plot areas, and perform value scoring on each plot in the recommended available plot areas according to the quantification indexes; Aggregate the value scoring results corresponding to each plot to obtain the comprehensive value scoring results corresponding to each tabu solution; Grant amnesty to the high-order tabu solutions whose comprehensive value scoring results exceed the set scoring threshold, so as to introduce the plot combinations corresponding to the high-order tabu solutions into the search scope of the tabu list.

8. A distribution network project substation site selection and planning system, characterized in that, Including: A substation area information visualization module, configured to process the power equipment information, load information, and topological structure information around the target distribution network substation area obtained by using geographic information system technology to generate visualized substation area information. A load center coordinate acquisition module, configured to acquire all the fire point data in the visualized substation area information, and process the fire point data by using the gravity center algorithm to obtain the substation area load center coordinate data corresponding to the visualized substation area information. A preliminary available plot acquisition module, configured to input the load center coordinate data into a trained area screening model and output a preliminary available plot area. An available plot screening module, configured to input the knowledge graph constructed from the map information data in the preliminary available plot area into a trained graph neural network model for analysis and screening to obtain a recommended available plot area; A site selection and planning module, configured to perform site selection and planning of the substation area with the target recommended plot area determined from the recommended available plot areas by using the improved tabu search algorithm.

9. A computer device, characterized in that, Including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the distribution network project substation area site selection and planning method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein when the device where the computer-readable storage medium is located executes the computer program, the distribution network project substation area site selection and planning method according to any one of claims 1 to 7 is implemented.

Images