A method and system for determining the location of a distribution network site

Abstract

The present invention discloses a method and system for determining the location of a distribution substation site. By using a semantic segmentation model and a sliding window to segment remote sensing images, topographic images are quickly obtained, and thus topographic features are jointly identified based on supervised and unsupervised models to improve the accuracy of topographic feature recognition. At the same time, based on the power demand and radiation circle within the selected site area, the power influence range of each topographic image within the selected site area is determined to calculate the site selection score, quantifying the power demand and topographic advantages to ensure the scientificity and rationality of the site selection. And based on the site selection score, the site selection location and location information are automatically matched, realizing the automation and high efficiency of the site selection process, thereby effectively reducing the site selection cost and improving the site selection efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of power planning, and particularly to a method and system for determining the location of a distribution substation site. Background Art

[0002] A distribution substation site refers to a facility in a power system that converts high-voltage electrical energy into low-voltage electrical energy and distributes it to end-users. It is mainly used for power conversion, power distribution, power fault handling, and load management. The location selection of a distribution substation site plays a key role in improving power transmission efficiency, reducing costs, enhancing power supply reliability, ensuring system security, meeting power demand, optimizing load management, and promoting regional development. The correct location selection can significantly improve the overall performance and economic benefits of the power system. The location selection of a distribution substation site is affected by various factors. A reasonable location selection can reduce the distance of transmission lines, thereby reducing power losses during transmission.

[0003] The existing methods for selecting the location of a distribution substation site rely on the experience of engineers or planners for location selection. Through historical data and empirical judgment, relatively stable and suitable locations are selected, but they have high labor costs, long time consumption, and low efficiency in the location selection of distribution substation sites. Summary of the Invention

[0004] The present invention provides a method and system for determining the location of a distribution substation site to reduce the cost of location selection of distribution substation sites and improve the efficiency of location selection of distribution substation sites.

[0005] To solve the above technical problems, an embodiment of the present invention provides a method for determining the location of a distribution substation site, including:

[0006] Obtain remote sensing images within the location selection area, segment the remote sensing images based on a semantic segmentation model and a sliding window, and obtain a terrain image set and corresponding location information;

[0007] Input the terrain image set into a supervised model and an unsupervised model respectively for feature recognition, and obtain the terrain features of each terrain image;

[0008] Based on the power demand data within the location selection area, determine several power demand points and a load center point within the location selection area;

[0009] Taking the center point of the terrain image as the midpoint, determine the radiation circle of each terrain image based on a preset radius length and the midpoint; and calculate the load score of each terrain image based on the radiation circle, the power demand points, and the load center point;

[0010] Calculate the site selection scores of each terrain image based on the load score and the terrain features, determine the site selection location based on the site selection scores, and determine the location information of the site selection location to complete the site selection of the substation site.

[0011] The present invention segments remote sensing images through a semantic segmentation model and a sliding window to quickly obtain terrain images, thereby jointly identifying terrain features based on supervised and unsupervised models to improve the accuracy of terrain feature recognition. At the same time, based on the power demand and radiation circle within the site selection area, determine the power influence range of each terrain image within the site selection area to calculate the site selection score, quantify the power demand and terrain advantages, and ensure the scientificity and rationality of the site selection; and automatically match the site selection location and location information based on the site selection score, realizing the automation and high efficiency of the site selection process, thereby effectively reducing the site selection cost and improving the site selection efficiency.

[0012] Further, the determining a plurality of power demand points and a load center point within the site selection area based on the power demand data within the site selection area includes:

[0013] Obtain the power demand data within the site selection area, where the power demand data includes power distribution data and load demand data;

[0014] Construct a power distribution map based on the power distribution data, and determine a plurality of power demand points based on the power distribution map and a preset power distribution threshold;

[0015] Construct a load prediction model based on a regression model, and determine the load center point based on the load demand data and the load prediction model.

[0016] Further, the calculating the load score of each terrain image based on the radiation circle, the power demand points, and the load center point includes:

[0017] Count the number of power demand points within each radiation circle, and calculate the load distance of each radiation circle based on the midpoint of each radiation circle and the load center point;

[0018] Calculate the load score of each terrain image based on the number of power demand points, the load distance, and the load score calculation formula.

[0019] Further, the load score calculation formula is specifically:

[0020]

[0021] Wherein, represents the load score, is the number of power demand points within the current radiation circle, is the total number of power demand points within the site selection area, is the load distance, and are the power demand point coefficient and the load distance coefficient respectively.

[0022] Furthermore, calculating the site selection scores of each terrain picture based on the load score and the terrain feature includes:

[0023] Obtaining the terrain features of each terrain picture and matching the terrain scores based on the terrain features;

[0024] Performing weighted averaging based on the load score and the terrain score to calculate the site selection scores of each terrain picture; specifically:

[0025]

[0026] Among them, represents the site selection score, is the load score, is the terrain score, and are the terrain score coefficient and the load score coefficient respectively, which are obtained based on the regression analysis method, and .

[0027] Furthermore, segmenting the remote sensing picture based on the semantic segmentation model and the sliding window to obtain a number of terrain pictures and their corresponding position information includes:

[0028] Constructing an initial semantic segmentation model and training the initial semantic segmentation model based on the remote sensing annotation data to output a trained semantic segmentation model;

[0029] Initializing the sliding window based on the preset window size and step length, and segmenting the remote sensing picture based on the sliding window to obtain a first set of segmented pictures;

[0030] Inputting the first set of segmented pictures into the semantic segmentation model for feature recognition, extracting the terrain information of each first segmented picture to generate a set of terrain pictures, and obtaining the position information corresponding to each terrain picture.

[0031] Furthermore, inputting the set of terrain pictures into the supervised model and the unsupervised model respectively for feature recognition to obtain the terrain features of each terrain picture includes:

[0032] Constructing a supervised model based on the vector machine and inputting the set of terrain pictures into the supervised model to obtain the first recognition result of the supervised model;

[0033] Constructing an unsupervised model based on the generative adversarial network and inputting the set of terrain pictures into the unsupervised model to obtain the second recognition result of the unsupervised model;

[0034] Integrate the first recognition result and the second recognition result to obtain the terrain features of each terrain picture.

[0035] In a second aspect, the present invention provides a distribution substation site selection determination system, including: a segmentation module, a feature recognition module, a demand determination module, a load score calculation module, and a site selection module;

[0036] The segmentation module is configured to obtain a remote sensing picture within the site selection area, segment the remote sensing picture based on a semantic segmentation model and a sliding window, and obtain a terrain picture set and corresponding position information;

[0037] The feature recognition module is configured to input the terrain picture set into a supervised model and an unsupervised model respectively for feature recognition, and obtain the terrain features of each terrain picture;

[0038] The demand determination module is configured to determine a plurality of power demand points and a load center point within the site selection area based on the power demand data within the site selection area;

[0039] The load score calculation module is configured to use the center point of the terrain picture as the midpoint, determine the radiation circle of each terrain picture based on a preset radius length and the midpoint; and calculate the load score of each terrain picture based on the radiation circle, the power demand points, and the load center point.

[0040] The site selection module is configured to calculate the site selection score of each terrain picture based on the load score and the terrain features, determine the site selection location based on the site selection score, and determine the position information of the site selection location to complete the distribution substation site selection.

[0041] Further, the demand determination module is configured to:

[0042] Obtain the power demand data within the site selection area, where the power demand data includes power distribution data and load demand data;

[0043] Construct a power distribution map based on the power distribution data, and determine a plurality of power demand points based on the power distribution map and a preset power distribution threshold;

[0044] Construct a load prediction model based on a regression model, and determine the load center point based on the load demand data and the load prediction model.

[0045] Further, the load score calculation module is configured to:

[0046] Count the number of power demand points within each radiation circle, and calculate the load distance of each radiation circle based on the midpoint of each radiation circle and the load center point;

[0047] Calculate the load scores of each terrain picture based on the number of power demand points, load distance, and load score calculation formula. Description of the Drawings

[0048] Figure 1 It is a schematic flowchart of a method for determining the location of a distribution substation site provided in an embodiment of the present invention;

[0049] Figure 2 It is a schematic structural diagram of a system for determining the location of a distribution substation site provided in an embodiment of the present invention. Detailed Embodiments

[0050] The following combines the drawings and embodiments to further describe in detail the specific embodiments of the present invention. The following embodiments are used to illustrate the present invention, but are not used to limit the scope of the present invention.

[0051] The terms "first" and "second" in the specification, claims, and drawings of this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed, or optionally further includes other steps or units inherent to these processes, methods, products, or devices.

[0052] Referring to "embodiment" herein means that a specific feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of this application. The phrase appears in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0053] Embodiment 1

[0054] Refer to Figure 1 , Figure 1 It is a schematic flowchart of a method for determining the location of a distribution substation site provided in an embodiment of the present invention. An embodiment of the present invention provides a method for determining the location of a distribution substation site, including steps 101 to 105, specifically as follows:

[0055] Step 101: Obtain remote sensing images within the site selection area, and segment the remote sensing images based on a semantic segmentation model and a sliding window to obtain a set of terrain images and corresponding location information;

[0056] In this embodiment, the segmenting the remote sensing images based on a semantic segmentation model and a sliding window to obtain a number of terrain images and corresponding location information includes:

[0057] Construct an initial semantic segmentation model, and train the initial semantic segmentation model based on remote sensing annotation data, and output a trained semantic segmentation model;

[0058] Initialize a sliding window based on a preset window size and stride, and segment the remote sensing image based on the sliding window to obtain a first set of segmented images;

[0059] Input the first set of segmented images into the semantic segmentation model for feature recognition, extract the terrain information of each first segmented image, generate a set of terrain images, and obtain the position information corresponding to each terrain image.

[0060] In this embodiment, an initial semantic segmentation model is constructed. The initial semantic segmentation model may include U-Net, DeepLab, Mask R-CNN, etc.

[0061] In this embodiment, remote sensing annotation data is obtained. The remote sensing annotation data includes remote sensing images and corresponding terrain contour annotations and terrain type annotations. Remote sensing images are usually taken by satellites or drones and contain high-resolution ground information. Preprocess the remote sensing images, including denoising, calibration, and normalization, etc., to improve the accuracy of subsequent processing.

[0062] In this embodiment, a sliding window is initialized with a preset window size and stride, and the window is moved pixel by pixel to generate a series of overlapping rectangular regions covering the entire image. Each step of sliding generates a small sub-region image.

[0063] In this embodiment, the initial semantic segmentation model is trained based on the sub-region images and their annotation information. During the training process, the hyperparameters of the semantic segmentation model are adjusted, and the model is optimized based on the cross-entropy loss function, and a trained semantic segmentation model is output.

[0064] In this embodiment, a remote sensing image of the site selection area is obtained, and a sliding window is initialized based on a preset window size and stride. The remote sensing image is segmented based on the sliding window to obtain a first set of segmented images; the first set of segmented images is input into the semantic segmentation model for feature recognition, and the terrain information contained in the first segmented images is extracted from the output of the semantic segmentation model to generate corresponding terrain images. These images contain terrain types and terrain contours.

[0065] In this embodiment, the global coordinates or pixel coordinates of the original remote sensing image are used to determine the position information of each terrain image, associate position information with each terrain image, and finally generate a series of terrain images. Each terrain image corresponds to a sub-region in the remote sensing image. These terrain images contain terrain contours and position information.

[0066] In this embodiment, based on the semantic segmentation model and the sliding window method, terrain information can be efficiently and accurately extracted from remote sensing images, generating several terrain images and corresponding location information. This process not only improves the accuracy and scientific nature of site selection analysis but also greatly enhances the degree of automation of data processing.

[0067] Step 102: Input the terrain images into a supervised model and an unsupervised model respectively for feature recognition to obtain the terrain features of each terrain image.

[0068] In this embodiment, the step of inputting the terrain image set into a supervised model and an unsupervised model respectively for feature recognition to obtain the terrain features of each terrain image includes:

[0069] Build a supervised model based on a vector machine and input the terrain image set into the supervised model to obtain the first recognition result of the supervised model.

[0070] Build an unsupervised model based on a generative adversarial network and input the terrain image set into the unsupervised model to obtain the second recognition result of the unsupervised model.

[0071] Integrate the first recognition result and the second recognition result to obtain the terrain features of each terrain image.

[0072] In this embodiment, a supervised model is built based on a vector machine, and the optimization parameters of the supervised model are determined. Specifically, the optimization parameter of the supervised model is C, where C is the reciprocal of a regularization strength. C controls the tolerance of the model to misclassifications. A larger C value means the model pays more attention to the errors in the training data and tries to reduce these errors, which may lead to an increase in model complexity and overfitting. A smaller C value means the model is more inclined to use a simple model, even if it means accepting more training errors.

[0073] In this embodiment, an unsupervised model is built based on a generative adversarial network. The generative adversarial network (GANs) is a deep learning framework composed of two main parts: a generator and a discriminator. The unsupervised model is trained based on historical terrain images until its recognition accuracy reaches a preset threshold, and then the trained unsupervised model is output.

[0074] In this embodiment, a first recognition result is obtained based on the supervised model; a second recognition result is obtained based on the unsupervised model; wherein, the first recognition result and the second recognition result include the terrain features and terrain types of each terrain image, and the terrain types include plain terrain, hilly terrain, mountain terrain, and valley terrain.

[0075] In this embodiment, if the first recognition result and the second recognition result differ in the recognition of the terrain type of a certain terrain picture, the position of the terrain picture in the remote sensing picture is matched, and the terrain picture is regenerated based on the position information for recognition.

[0076] In this embodiment, the supervised model and the unsupervised model can extract features from different perspectives. The supervised model relies on labeled data and can learn clear terrain classification criteria; the unsupervised model discovers natural feature structures through the similarity between data.

[0077] In this embodiment, the supervised model may deviate due to inaccurate labeling or insufficient training data, while the unsupervised model does not rely on labels and can provide different perspectives and judgments. By comparing and integrating the results of both, it helps to improve the overall recognition accuracy and robustness.

[0078] In this embodiment, if the classification results of the supervised model and the unsupervised model for a certain terrain picture are inconsistent, the position information in the remote sensing image can be used for matching and correction, reducing the terrain picture recognition error rate and improving the terrain recognition accuracy.

[0079] Step 103: Determine a number of power demand points and a load center point within the site selection area based on the power demand data within the site selection area;

[0080] In this embodiment, the determining a number of power demand points and a load center point within the site selection area based on the power demand data within the site selection area includes:

[0081] Obtain the power demand data within the site selection area, where the power demand data includes power distribution data and load demand data;

[0082] Construct a power distribution map based on the power distribution data, and determine a number of power demand points based on the power distribution map and a preset power distribution threshold;

[0083] Construct a load prediction model based on a regression model, and determine the load center point based on the load demand data and the load prediction model.

[0084] In this embodiment, power distribution data and load demand data are two key data types in power system planning, operation, and management. Power distribution data includes the transmission path and network structure of power from power plants to end users. Specifically, it includes power grid topology, line characteristics, substation information, and facility status. Load demand data is the power consumption demand of the power system, that is, the power consumption situation of power users at different times and locations. It includes load curves, load demands, and load characteristics, etc.;

[0085] In this embodiment, a power distribution map is obtained based on circuit distribution data, and the main structure and key nodes of the power grid, such as substations, main transmission lines, etc., are identified based on the power distribution map. And using GIS technology, data such as population distribution and building density are overlaid and analyzed with the power distribution map to determine the power distribution values and power demand values of each key node within the selected site area, and nodes with power distribution values greater than a preset power distribution threshold are set as power demand points.

[0086] In this embodiment, historical load demand data is cleaned and transformed to generate training data. A load prediction model is constructed based on a support vector machine regression model, and the load prediction model is trained based on the training data to obtain a trained load prediction model.

[0087] In this embodiment, the load demand within the selected site area is identified based on the load prediction model, and the area with a load demand higher than the preset load threshold is used as a load demand point, and the load demand points are clustered based on a clustering algorithm to identify the load center point.

[0088] In this embodiment, by identifying power demand points and load center points, the location selection of the distribution substation can be closer to the load center, ensuring the reliability of power supply, reducing losses during power transmission. Locating near the load center point can shorten the length of the transmission line, reduce power losses caused by power transmission, and improve the overall power supply efficiency. At the same time, locating the distribution substation in the area where the load demand is concentrated can reduce the power outage risk caused by equipment failures or fault response times.

[0089] Step 104: Taking the center point of the terrain picture as the midpoint, determine the power circles of each terrain picture based on a preset radius length and the midpoint; and calculate the load scores of each terrain picture based on the power circles, the power demand points, and the load center points.

[0090] In this embodiment, calculating the load scores of each terrain picture based on the radiation circles, the power demand points, and the load center points includes:

[0091] Count the number of power demand points within each radiation circle, and calculate the load distance of each radiation circle based on the midpoint of each radiation circle and the load center point;

[0092] Calculate the load scores of each terrain picture based on the number of power demand points, the load distance, and the load score calculation formula.

[0093] In this embodiment, the load score calculation formula is specifically:

[0094] (1)

[0095] Where represents the load score, is the number of power demand points within the current radiation circle, is the total number of power demand points within the site selection area, is the load distance, and are the power demand point coefficient and the load distance coefficient respectively.

[0096] In this embodiment, the power demand point coefficient and the load distance coefficient are constants, which are obtained by analyzing the power distribution network site selection data.

[0097] In this embodiment, by counting the number of power demand points within the radiation circle, the system can accurately identify the areas with concentrated power demand, helping to determine which areas need to be prioritized for power supply. At the same time, by calculating the load distance between the points within the radiation circle and the load center point, it helps to optimize the layout of the substations, shorten the power supply distance, and reduce transmission losses. Calculating the load score based on the load score formula can evaluate the power demand and power supply costs in different regions. Selecting a site in an area with a high load score can improve the power supply efficiency and reduce energy losses.

[0098] In this embodiment, through accurate load score calculation, it is possible to maximize the return on investment while meeting the power supply requirements, and optimize the construction and operation costs.

[0099] In this embodiment, by counting the number of power demand points and calculating the load distance, combined with the load score calculation formula, it is possible to accurately evaluate the demand and power supply effects in each region. Selecting a site in an area with a high load score will improve the power supply efficiency, optimize energy utilization, and ultimately achieve double benefits in terms of economy and environment.

[0100] Step 105: Calculate the site selection scores of each terrain picture based on the load score and the terrain features, determine the site selection location based on the site selection scores, and determine the location information of the site selection location to complete the site selection of the substation.

[0101] In this embodiment, the calculating the site selection scores of each terrain picture based on the load score and the terrain features includes:

[0102] Obtain the terrain features of each terrain picture, and match the terrain scores based on the terrain features;

[0103] Perform weighted averaging based on the load score and the terrain score to calculate the site selection scores of each terrain picture; specifically:

[0104] (2)

[0105] Wherein, represents the site selection score, is the load score, is the terrain score, and are the terrain score coefficient and the load score coefficient respectively, which are obtained based on the regression analysis method, and .

[0106] In this embodiment, the terrain type is identified based on the terrain characteristics. The terrain types include plain terrain, hilly terrain, mountain terrain, and river valley terrain. A terrain score table is generated based on the terrain type. Please refer to Table 1. Table 1 is a terrain score table for a method for determining the location of a distribution substation site provided in an embodiment of the present invention.

[0107] Table 1

[0108]

[0109] In this embodiment, the plain terrain, hilly terrain, mountain terrain, and river valley terrain in the terrain type are divided into four grades. Since the plain terrain is flat and the geological structure is relatively stable, it is conducive to the construction and maintenance of the distribution substation site. The flat terrain is also conducive to the laying of lines and the arrangement of pipelines, facilitating the transportation and installation of equipment. Therefore, the plain terrain is an ideal location for the distribution substation site. The hilly terrain has undulations and relatively complex geological conditions, and there may be many unstable areas and slopes. These problems may lead to unstable foundations, increasing the construction difficulty and cost. However, as long as the unstable areas and geological disaster-prone areas are avoided and appropriate foundation treatment is carried out, it can still be used as the location of the distribution substation site. The mountain terrain has complex landforms and changing geological conditions, and is prone to geological disasters such as landslides and mudslides. High-altitude areas may also face problems such as harsh climate conditions, such as low temperature and strong wind. The river valley area has a low terrain and is easily invaded by floods. The geological conditions may be relatively soft and the foundation stability is poor. Therefore, the terrain scores of the mountain terrain and the river valley area are relatively low.

[0110] In this embodiment, the terrain score is used as the terrain score of each terrain picture.

[0111] In another alternative embodiment, the terrain score further includes an environmental assessment score.

[0112] In another alternative embodiment, the environmental assessment impact factors include climate conditions (such as temperature, rainfall, wind speed, etc.) and ecological environment (such as protected areas). The environmental assessment score of the location where each terrain picture is located is calculated based on the environmental assessment model and the environmental assessment impact factors. Finally, the environmental assessment score and the terrain score are integrated to obtain the terrain score.

[0113] In this embodiment, historical distribution site selection data is collected on the Internet, and the historical distribution site selection data is labeled based on expert experience to generate sample data, where the sample data includes site selection scores, terrain scores, and load scores, and the weight coefficients of the terrain scores and load scores are estimated based on the least squares method.

[0114] In this embodiment, load scores and terrain features are used for site selection scoring, which relies on a large amount of data analysis and modeling, increases the objectivity of the decision-making process, reduces the deviation caused by subjective judgment. At the same time, by combining the load score (reflecting power demand) and the terrain score (considering the natural environment), the impact of different terrains on the construction of power facilities can be comprehensively evaluated, so as to select the optimal area; the score model can be flexibly adjusted according to the actual situation of different regions to ensure that the site selection meets specific environments and requirements.

[0115] In this embodiment, through regression analysis, the weights of the factors affecting the site selection score can be accurately adjusted to respond to changes in a timely manner and optimize the site selection strategy. Quantifying the impacts of load and terrain features makes the site selection decision more scientific, and the model can reflect the actual situation, improving the analysis accuracy. It saves time and labor costs, thus improving the efficiency of site selection analysis.

[0116] In this embodiment, various terrain pictures are sorted based on the site selection scores to generate a site selection list for medical site selection personnel to refer to. At the same time, the terrain picture with the highest site selection score is used as the site selection location, and it is matched in the remote sensing picture based on this terrain picture to determine the position information of this terrain picture, thereby completing the distribution site selection. Among them, the position information includes the longitude and latitude of the site selection location.

[0117] In this embodiment, through remote sensing pictures and semantic segmentation models, terrain information can be accurately obtained to generate detailed terrain pictures. This enables site selection analysis to consider not only power demand but also actual geographical and terrain features, ensuring the scientificity and rationality of site selection. At the same time, through sliding window and model recognition technologies, a large amount of remote sensing data can be processed quickly and automatically to generate terrain pictures and perform feature recognition, greatly improving the efficiency of data processing and analysis. In addition, through supervised and unsupervised models for feature recognition of terrain pictures, terrain features can be effectively extracted to ensure that the terrain complexity is fully considered during site selection, improving the accuracy of site selection.

[0118] In this embodiment, power demand points and load centers are determined based on actual power demand data to ensure that the site selection can effectively cover and serve the actual power demand area, avoiding the disconnection between site selection and actual demand. And by analyzing the influence range of each terrain picture through the radiation circle, the potential of each terrain picture in power transmission and coverage can be evaluated more intuitively.

[0119] In this embodiment, the site selection score is calculated by weighted average, comprehensively considering the load score and terrain characteristics, ensuring that the site selection not only meets the power demand but also takes into account the practical feasibility of construction and maintenance.

[0120] In this embodiment, through the combination of multiple technical means such as remote sensing images, semantic segmentation models, sliding windows, supervised and unsupervised models, etc., the automation and efficiency of the site selection process are achieved. At the same time, through the comprehensive analysis of the load score and terrain characteristics, the scientificity and rationality of the site selection are ensured, thereby effectively reducing the site selection cost and improving the site selection efficiency.

[0121] Please refer to Figure 2 , Figure 2 FIG.

[0122] is a schematic structural diagram of a distribution substation site selection determination system provided by an embodiment of the present invention, including: a segmentation module 201, a feature recognition module 202, a demand determination module 203, a load score calculation module 204, and a site selection module 205;

[0123] The segmentation module 201 is configured to obtain a remote sensing image within the site selection area, and segment the remote sensing image based on a semantic segmentation model and a sliding window to obtain a terrain image set and corresponding position information;

[0124] The feature recognition module 202 is configured to input the terrain image set into a supervised model and an unsupervised model respectively for feature recognition to obtain the terrain characteristics of each terrain image;

[0125] The demand determination module 203 is configured to determine a plurality of power demand points and a load center point within the site selection area based on the power demand data within the site selection area;

[0126] The load score calculation module 204 is configured to use the center point of the terrain image as the midpoint, determine the radiation circle of each terrain image based on a preset radius length and the midpoint; and calculate the load score of each terrain image based on the radiation circle, the power demand points, and the load center point.

[0127] In this embodiment, the demand determination module is configured to:

[0128] Obtain the power demand data within the site selection area, where the power demand data includes power distribution data and load demand data;

[0129] Construct a power distribution map based on the power distribution data, and determine a number of power demand points based on the power distribution map and a preset power distribution threshold;

[0130] Construct a load prediction model based on a regression model, and determine the load center point based on the load demand data and the load prediction model.

[0131] In this embodiment, the load score calculation module is used for:

[0132] Count the number of power demand points in each radiation circle, and calculate the load distance of each radiation circle based on the midpoint of each radiation circle and the load center point;

[0133] Calculate the load score of each topographic picture based on the number of power demand points, the load distance, and the load score calculation formula.

[0134] In this embodiment, the load score calculation formula is specifically:

[0135]

[0136] Wherein, represents the load score, is the number of power demand points in the current radiation circle, is the total number of power demand points in the site selection area, is the load distance, and are the power demand point coefficient and the load distance coefficient respectively.

[0137] In this embodiment, the site selection module is used for:

[0138] Obtain the terrain features of each topographic picture, and match the terrain score based on the terrain features;

[0139] Perform weighted averaging based on the load score and the terrain score to calculate the site selection score of each topographic picture; specifically:

[0140]

[0141] Wherein, represents the site selection score, is the load score, is the terrain score, and are the terrain score coefficient and the load score coefficient respectively, which are obtained based on regression analysis, and .

[0142] In this embodiment, the segmentation module is used for:

[0143] Construct an initial semantic segmentation model, and train the initial semantic segmentation model based on remote sensing annotation data, and output the trained semantic segmentation model;

[0144] Initialize a sliding window based on a preset window size and stride, and segment the remote sensing image based on the sliding window to obtain a first set of segmented images;

[0145] Input the first set of segmented images into the semantic segmentation model for feature recognition, extract the terrain information of each first segmented image, generate a set of terrain images, and obtain the position information corresponding to each terrain image.

[0146] In this embodiment, the feature recognition module is used for:

[0147] Construct a supervised model based on a vector machine, and input the set of terrain images into the supervised model to obtain a first recognition result of the supervised model;

[0148] Construct an unsupervised model based on a generative adversarial network, and input the set of terrain images into the unsupervised model to obtain a second recognition result of the unsupervised model;

[0149] Integrate the first recognition result and the second recognition result to obtain the terrain features of each terrain image.

[0150] In an embodiment of the present invention, a terminal device is further provided, 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 power distribution site location determination method is implemented.

[0151] In an embodiment of the present invention, a computer-readable storage medium is further provided. The computer-readable storage medium includes a stored computer program, wherein when the computer program runs, it controls the device where the computer-readable storage medium is located to execute the above-mentioned power distribution site location determination method.

[0152] Exemplarily, the computer program may be divided into one or more modules. One or more modules are stored in the memory and executed by the processor to complete the present invention. One or more modules may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program in the terminal device.

[0153] The terminal device may be a computing device such as a desktop computer, a notebook, a palm computer, and a cloud server. The terminal device may include, but is not limited to, a processor, a memory, and a display. Those skilled in the art can understand that the above components are only examples of the terminal device and do not constitute a limitation on the terminal device. It may include more or fewer components than those described, or combine certain components, or have different components. For example, the terminal device may also include input / output devices, network access devices, a bus, etc.

[0154] The so-called 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, etc. The processor is the control center of the terminal device and connects all parts of the entire terminal device through various interfaces and lines.

[0155] The memory can be used to store computer programs and / or modules. The processor realizes various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and by calling the data stored in the memory. The memory may mainly include a program storage area and a data storage area. Among them, the program storage area may store an operating system, application programs required for at least one function (such as a sound playback function, a text conversion function, etc.); the data storage area may store data created according to the use of the mobile phone (such as audio data, text message data, etc.). In addition, the memory may include high-speed random access memory and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one magnetic disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0156] Among them, when the module based on the multi-device access platform processing is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned various method embodiments can be implemented. 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, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0157] The specific embodiments described above further elaborate on the purpose, technical solutions, and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the protection scope of the present invention. In particular, it is pointed out that for those skilled in the art, any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for determining the site selection of a distribution network, characterized in that: include: Acquire remote sensing images within the selected area, segment the remote sensing images based on a semantic segmentation model and a sliding window, and acquire a terrain image set and corresponding location information; Inputting the terrain image set into the supervised model and the unsupervised model respectively for feature recognition to obtain the terrain features of each terrain image; Determine a plurality of power demand points and a load center point within the site selection area based on the power demand data within the site selection area; Taking the center point of the terrain image as the midpoint, determining the radiation circle of each terrain image based on a preset radius length and the midpoint; and calculating the load score of each terrain image based on the radiation circle, the power demand point and the load center point; Calculating the site selection score of each terrain image based on the load score and the terrain features, determining the site selection location based on the site selection score, and determining the location information of the site selection location to complete the site selection of the distribution network site; The calculating the load score of each terrain picture based on the radiation circle, the power demand point and the load center point includes: Count the number of power demand points in each radiation circle, and calculate the load distance of each radiation circle based on the midpoint of each radiation circle and the load center point; Calculate the load score of each terrain image based on the number of power demand points, load distance and load score calculation formula; The load score calculation formula is specifically: ； in, represents the load score, is the number of power demand points within the current radiation circle, is the total number of power demand points in the site selection area, is the load distance, and They are the power demand point coefficient and the load distance coefficient respectively; The step of inputting the terrain image set into the supervised model and the unsupervised model for feature recognition to obtain the terrain features of each terrain image includes: Building a supervised model based on a vector machine, and inputting a terrain picture set into the supervised model to obtain a first recognition result of the supervised model; Building an unsupervised model based on a generative adversarial network, and inputting a terrain picture set into the unsupervised model to obtain a second recognition result of the unsupervised model; The first recognition result and the second recognition result are integrated to obtain the terrain features of each terrain image.

2. A method for determining the site selection of a distribution network site according to claim 1, characterized in that: The determining of a plurality of power demand points and a load center point in the site selection area based on the power demand data in the site selection area includes: Acquiring power demand data in the site selection area, wherein the power demand data includes power distribution data and load demand data; constructing a power distribution map based on the power distribution data, and determining a plurality of power demand points based on the power distribution map and a preset power distribution threshold; A load forecasting model is constructed based on the regression model, and the load center point is determined based on the load demand data and the load forecasting model.

3. A method for determining the site selection of a distribution network site according to claim 1, characterized in that: The calculating the site selection score of each terrain image based on the load score and the terrain feature includes: Acquire terrain features of each terrain image, and match terrain scores based on the terrain features; Based on the load score and the terrain score, a weighted average is performed to calculate the site selection score of each terrain image; specifically: ； in, represents the site selection score, is the load score, Score for terrain, and are terrain score coefficient and load score coefficient, respectively, which are obtained based on regression analysis, and .

4. A method for determining the site selection of a distribution network site according to claim 3, characterized in that: The remote sensing image is segmented based on the semantic segmentation model and the sliding window to obtain a plurality of terrain images and corresponding location information, including: Constructing an initial semantic segmentation model, and training the initial semantic segmentation model based on remote sensing annotation data, and outputting a trained semantic segmentation model; Initialize a sliding window based on a preset window size and step size, segment the remote sensing image based on the sliding window, and obtain a first segmented image set; The first segmented picture set is input into the semantic segmentation model for feature recognition, terrain information of each first segmented picture is extracted, a terrain picture set is generated, and location information corresponding to each terrain picture is obtained.

5. A distribution network site selection and determination system, characterized in that: include: Segmentation module, feature recognition module, demand determination module, load score calculation module and site selection module; The segmentation module is used to obtain remote sensing images within the site selection area, segment the remote sensing images based on the semantic segmentation model and the sliding window, and obtain a terrain image set and corresponding location information; The feature recognition module is used to input the terrain image set into the supervised model and the unsupervised model respectively for feature recognition, so as to obtain the terrain features of each terrain image; The demand determination module is used to determine a plurality of power demand points and a load center point in the site selection area based on the power demand data in the site selection area; The load score calculation module is used to determine the radiation circle of each terrain image based on a preset radius length and the midpoint, taking the center point of the terrain image as the midpoint; and calculate the load score of each terrain image based on the radiation circle, the power demand point and the load center point; The site selection module is used to calculate the site selection score of each terrain picture based on the load score and the terrain characteristics, determine the site selection location based on the site selection score, and determine the location information of the site selection location to complete the site selection of the distribution network site; The load score calculation module is used to: Count the number of power demand points in each radiation circle, and calculate the load distance of each radiation circle based on the midpoint of each radiation circle and the load center point; Calculate the load score of each terrain image based on the number of power demand points, load distance and load score calculation formula; The load score calculation formula is specifically: ； in, represents the load score, is the number of power demand points within the current radiation circle, is the total number of power demand points in the site selection area, is the load distance, and They are the power demand point coefficient and the load distance coefficient respectively; The step of inputting the terrain image set into the supervised model and the unsupervised model for feature recognition to obtain the terrain features of each terrain image includes: Building a supervised model based on a vector machine, and inputting a terrain picture set into the supervised model to obtain a first recognition result of the supervised model; Building an unsupervised model based on a generative adversarial network, and inputting a terrain picture set into the unsupervised model to obtain a second recognition result of the unsupervised model; The first recognition result and the second recognition result are integrated to obtain the terrain features of each terrain image.

6. A distribution network site selection and determination system as claimed in claim 5, characterized in that: The demand determination module is used to: Acquiring power demand data in the site selection area, wherein the power demand data includes power distribution data and load demand data; constructing a power distribution map based on the power distribution data, and determining a plurality of power demand points based on the power distribution map and a preset power distribution threshold; A load forecasting model is constructed based on the regression model, and the load center point is determined based on the load demand data and the load forecasting model.

Images