Charging station deployment strategy determination method and device, equipment and medium

Abstract

The embodiment of the invention discloses a charging station deployment strategy determination method and device, equipment and a medium. The method comprises the following steps: determining a regional terrain model and a regional object model of a to-be-deployed region according to a regional image; determining a parking space deployment area according to the regional terrain model and the regional object model, and determining a parking space deployment strategy according to the parking space deployment area, a preset parking space size and a preset point distance; according to the parking space coordinate set, a preset parking space size and a preset distribution box position, candidate charging pile strategies are determined, and a target charging pile strategy is determined from the candidate charging pile strategies; acquiring environment prediction parameters of the to-be-deployed area in a preset period, and inputting the environment prediction parameters into the trained daily load curve prediction model to obtain a daily load prediction curve; and determining a charging station deployment strategy of the to-be-deployed area according to the parking space deployment strategy, the target charging pile strategy and the daily load prediction curve. And the efficiency of determining the charging station deployment strategy is improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing technology, and in particular to a method, apparatus, equipment and medium for determining a charging station deployment strategy. Background Technology

[0002] Currently, the design of charging stations mainly adopts a sequential model of manual on-site measurement, two-dimensional drawing, experience-based load verification using spreadsheets, and step-by-step independent design. This means that designers must personally visit the site to manually measure and, based on experience, delineate the number and location of charging piles and parking spaces in drawing software. They then roughly calculate the load based on their experience and design the charging station deployment strategy according to the estimated plan. Therefore, improving the efficiency of determining the charging station deployment strategy is crucial. Summary of the Invention

[0003] This invention provides a method, apparatus, equipment, and medium for determining a charging station deployment strategy, thereby improving the efficiency of determining the charging station deployment strategy.

[0004] According to one aspect of the present invention, a method for determining a charging station deployment strategy is provided, comprising:

[0005] Obtain a region image of the area to be deployed, and determine the region terrain model and region object model of the area to be deployed based on the region image;

[0006] Based on the regional terrain model and the regional object model, the parking space deployment area within the area to be deployed is determined, and a parking space deployment strategy is determined based on the parking space deployment area, the preset parking space size, and the preset point distance; wherein, the parking space deployment strategy includes a set of parking space coordinates;

[0007] Based on the parking space coordinate set, the preset parking space size, and the preset power distribution box location, a candidate charging pile strategy is determined, and a target charging pile strategy is determined from the candidate charging pile strategies.

[0008] Obtain the environmental prediction parameters of the area to be deployed within a preset period, and input the environmental prediction parameters into the trained daily load curve prediction model to obtain the daily load prediction curve;

[0009] Based on the parking space deployment strategy, the target charging pile strategy, and the daily load forecast curve, the charging station deployment strategy for the area to be deployed is determined.

[0010] According to another aspect of the present invention, an apparatus for determining a charging station deployment strategy is provided, comprising:

[0011] The model determination module is used to acquire a regional image of the area to be deployed, and determine the regional terrain model and regional object model of the area to be deployed based on the regional image.

[0012] The parking space deployment strategy determination module is used to determine the parking space deployment area within the area to be deployed based on the area terrain model and the area object model, and to determine the parking space deployment strategy based on the parking space deployment area, the preset parking space size, and the preset point distance; wherein, the parking space deployment strategy includes a set of parking space coordinates;

[0013] The target charging pile strategy determination module is used to determine candidate charging pile strategies based on the parking space coordinate set, the preset parking space size and the preset power distribution box location, and to determine the target charging pile strategy from the candidate charging pile strategies.

[0014] The curve determination module is used to obtain the environmental prediction parameters of the area to be deployed within a preset period, and input the environmental prediction parameters into the trained daily load curve prediction model to obtain the daily load prediction curve;

[0015] The charging station deployment strategy determination module is used to determine the charging station deployment strategy for the area to be deployed based on the parking space deployment strategy, the target charging pile strategy, and the daily load forecast curve.

[0016] According to another aspect of the present invention, an electronic device is provided, comprising:

[0017] One or more processors;

[0018] Memory, used to store one or more programs;

[0019] When one or more programs are executed by one or more processors, the one or more processors are able to execute any of the charging station deployment strategy determination methods provided in the embodiments of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement any of the charging station deployment strategy determination methods provided in the embodiments of the present invention.

[0021] This invention provides a method for determining a charging station deployment strategy. The method involves acquiring a regional image of the area to be deployed, and determining a regional terrain model and a regional object model based on the image. Based on the terrain model and object model, a parking space deployment area is determined within the area to be deployed. A parking space deployment strategy is then determined based on the parking space deployment area, a preset parking space size, and a preset point distance. The parking space deployment strategy includes a set of parking space coordinates. Based on the parking space coordinate set, the preset parking space size, and the preset distribution box location, candidate charging pile strategies are determined, and a target charging pile strategy is determined from the candidate strategies. Environmental prediction parameters for the area to be deployed within a preset period are acquired and input into a trained daily load curve prediction model to obtain a daily load prediction curve. Finally, the charging station deployment strategy for the area to be deployed is determined based on the parking space deployment strategy, the target charging pile strategy, and the daily load prediction curve. The above solution determines the parking space deployment area based on the regional terrain model and regional object model of the area to be deployed. It then determines the parking space deployment strategy based on the deployment area, preset parking space size, and preset point distance. Next, it determines the target charging pile strategy based on the parking space coordinate set, preset parking space size, and preset distribution box location within the deployment strategy. Finally, it determines the daily load prediction curve within a preset period based on the daily load curve prediction model. Finally, it determines the charging station deployment strategy for the area to be deployed based on the parking space deployment strategy, the target charging pile strategy, and the daily load prediction curve. This automated determination of the charging station deployment strategy improves its efficiency.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a flowchart of a method for determining a charging station deployment strategy according to Embodiment 1 of the present invention;

[0025] Figure 2 This is a flowchart of a method for determining a charging station deployment strategy according to Embodiment 2 of the present invention;

[0026] Figure 3 This is a schematic diagram of the structure of a device for determining a charging station deployment strategy provided in Embodiment 4 of the present invention;

[0027] Figure 4 This is a schematic diagram of the structure of an electronic device that implements a method for determining a charging station deployment strategy, as provided in Embodiment 5 of the present invention. Detailed Implementation

[0028] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0029] Example 1

[0030] Figure 1 This is a flowchart of a method for determining a charging station deployment strategy according to Embodiment 1 of the present invention. This embodiment is applicable to the case of automatically determining the deployment strategy of a charging station. The method can be executed by a device for determining the deployment strategy of a charging station. The device can be implemented in software and / or hardware and can be configured in an electronic device that carries the function of determining the deployment strategy of a charging station.

[0031] See Figure 1 The method for determining the charging station deployment strategy shown includes:

[0032] S110. Obtain the area image of the area to be deployed, and determine the area terrain model and area object model of the area to be deployed based on the area image.

[0033] The "area to be deployed" refers to the area where charging stations need to be deployed. The "area image" refers to an image of the area to be deployed. The "area terrain model" refers to a surface model of the area to be deployed, which can be used to represent the terrain undulations of the area. For example, the area terrain model can be a digital elevation model, containing only the elevation information of the ground surface and removing all objects on the ground, such as buildings and trees.

[0034] The region object model refers to the obstacle model of the area to be deployed, which can be used to represent the distribution of obstacles within the area. The region object model represents the terrain as seen from the air and can be used for conflict detection, precise spatial planning, and 3D visualization. For example, the region object model can be a digital surface model, containing the top elevation information of the ground surface and all objects on it, such as buildings, trees, and bridges.

[0035] For example, the process involves acquiring a regional image of the area to be deployed; constructing an initial 3D model corresponding to the regional image based on a geographic information system; and performing terrain feature recognition and classification on the initial 3D model to obtain a regional terrain model and a regional object model. Here, the initial 3D model refers to the regional 3D model corresponding to the regional image.

[0036] S120. Based on the regional terrain model and regional object model, determine the parking space deployment area within the area to be deployed, and determine the parking space deployment strategy based on the parking space deployment area, the preset parking space size, and the preset point distance; wherein, the parking space deployment strategy includes a set of parking space coordinates.

[0037] The parking space deployment area refers to the area within the deployment area where parking spaces can be deployed. The preset parking space size refers to the pre-set parking space size. The preset point distance refers to the pre-set minimum distance between the center points of any two individual parking space areas. This embodiment of the invention does not impose any limitations on the size of the preset parking space size and the preset point distance; these can be set by technicians based on experience or needs, or determined through extensive experimentation.

[0038] The parking space deployment strategy refers to the deployment strategy for parking spaces within the area to be deployed. For example, the parking space deployment strategy includes a set of parking space coordinates and the number of parking spaces. The set of parking space coordinates refers to the set of coordinates of the center point of each individual parking space area. The number of parking spaces refers to the number of parking spaces arranged within the area to be deployed.

[0039] S130. Based on the set of parking space coordinates, the preset parking space size, and the preset location of the electrical distribution box, determine the candidate charging pile strategy, and then determine the target charging pile strategy from the candidate charging pile strategies.

[0040] The preset distribution box location refers to the location of the main distribution box that is set in advance. This embodiment of the invention does not impose any limitations on the preset distribution box location; it can be set by technicians based on experience or needs.

[0041] Here, the candidate charging pile strategy refers to the optional deployment strategies for charging piles within the area to be deployed. The target charging pile strategy refers to the actual deployment strategy for charging piles within the area to be deployed. The target charging pile type refers to the type of charging pile determined in the target charging pile strategy. For example, the number of target charging pile types in the target charging pile strategy can be at least one.

[0042] For example, the target charging pile strategy may include the target charging pile type, number of charging piles, charging pile power, charging pile installation location, cable type and quantity, etc.

[0043] In one optional embodiment, determining the target charging pile strategy from the candidate charging pile strategies includes: determining the candidate total power corresponding to each candidate charging pile strategy, and determining a reference charging pile strategy based on the candidate total power and a preset total power threshold; determining the strategy evaluation data corresponding to the reference charging pile strategy, and determining the corresponding strategy evaluation score based on the strategy evaluation data; and determining the target charging pile strategy from the reference charging pile strategies based on the strategy evaluation score.

[0044] The candidate total power refers to the sum of the maximum electrical power output by all charging piles simultaneously in the candidate charging pile strategy. This embodiment of the invention does not impose any limitation on the size of the preset total power threshold; it can be set by technicians based on experience or needs, or determined through repeated experiments.

[0045] The reference charging pile strategy refers to the candidate charging pile strategy where the total power of the candidates does not exceed the preset total power threshold.

[0046] For example, determining a reference charging pile strategy based on the candidate total power and a preset total power threshold includes: for any candidate charging pile strategy, if the candidate total power of the candidate charging pile strategy is less than or equal to the preset total power threshold, then the candidate charging pile strategy is used as a reference charging pile strategy; if the candidate total power of the candidate charging pile strategy is greater than the preset total power threshold, then the candidate charging pile strategy is prohibited from being used as a reference charging pile strategy.

[0047] The strategy evaluation data refers to the data used to assess the disadvantages of the corresponding reference charging pile strategy. For example, the strategy evaluation data may include strategy cost data, strategy convenience data, and strategy security data.

[0048] Among them, the strategy cost data refers to the total cost corresponding to the reference charging pile strategy. The strategy convenience data refers to the reciprocal of the average distance between the charging pile and the charging station exit in the reference charging pile strategy. The strategy safety data refers to the minimum distance between charging piles in the reference charging pile strategy.

[0049] For example, determining the corresponding strategy evaluation score based on strategy evaluation data includes: for any reference charging pile strategy, determining the strategy cost data, strategy convenience data, and strategy security data of the reference charging pile strategy, and weighting and summing the strategy cost data, strategy convenience data, and strategy security data according to preset cost dimension weights, preset convenience dimension weights, and preset security dimension weights to obtain the strategy evaluation score of the reference charging pile strategy.

[0050] Specifically, the cost dimension weight can be used to quantify the importance of strategy cost data in the strategy evaluation score. The convenience dimension weight can be used to quantify the importance of strategy convenience data in the strategy evaluation score. The security dimension weight can be used to quantify the importance of strategy security data in the strategy evaluation score.

[0051] In this embodiment of the invention, the magnitudes of the weights for the cost dimension, convenience dimension, and security dimension are not limited. They can be set by technical personnel based on experience or needs, or determined repeatedly through a large number of experiments. It is only necessary to ensure that the sum of the weights for the cost dimension, convenience dimension, and security dimension is 1.

[0052] It should be noted that after determining the strategy evaluation data, the strategy evaluation data can be normalized to facilitate the subsequent determination of the strategy evaluation score.

[0053] Among them, the strategy evaluation score can be used to quantify the overall disadvantage of the reference charging pile strategy.

[0054] For example, determining the target charging pile strategy from the reference charging pile strategies based on the strategy evaluation score includes: taking the reference charging pile strategy corresponding to the lowest strategy evaluation score as the target charging pile strategy.

[0055] Understandably, using the reference charging pile strategy corresponding to the lowest strategy evaluation score as the target charging pile strategy improves the accuracy of the determined target charging pile strategy.

[0056] Understandably, by determining reference charging pile strategies from candidate charging pile strategies based on the candidate total power and a preset total power threshold, the participation of candidate charging pile strategies with excessively high total power in the subsequent determination of target charging pile strategies is avoided. This achieves preliminary screening of candidate charging pile strategies, reduces resource waste, and improves the efficiency of determining target charging pile strategies. At the same time, based on the strategy evaluation data corresponding to each reference charging pile strategy, a strategy evaluation score is determined, and then the target charging pile strategy is determined based on the strategy evaluation score, thereby improving the accuracy of the determined target charging pile strategy.

[0057] S140. Obtain the environmental prediction parameters of the area to be deployed within a preset period, and input the environmental prediction parameters into the trained daily load curve prediction model to obtain the daily load prediction curve.

[0058] The preset period refers to a pre-set timeframe in the future. Environmental prediction parameters refer to environmental parameters within the preset period. For example, environmental parameters may include date types and weather data. For example, date types may include holidays and weekdays, etc. Weather data may include sunny, rainy, and snowy conditions, etc.

[0059] The daily load curve prediction model can be used to predict the daily load curve of charging stations based on parking space deployment strategies and target charging pile strategies within a preset period. The daily load prediction curve refers to the daily load curve output by the daily load curve prediction model within the preset period.

[0060] In one optional embodiment, the daily load curve prediction model is trained as follows: based on the target charging pile strategy, preset vehicle charging simulation data, and target charging characteristic curve, the vehicle charging behavior under different sample charging environment parameters is simulated to determine the daily load label curve under the corresponding sample charging environment parameters; the sample charging environment parameters are input into the constructed daily load curve prediction model to obtain the corresponding daily load sample curve; based on the daily load label curve and the daily load sample curve, the model loss value is determined, and the daily load curve prediction model is trained based on the model loss value.

[0061] The vehicle charging simulation data can be used to simulate the vehicle's charging environment. For example, the vehicle charging simulation data may include vehicle arrival rate, initial vehicle charge level, and battery capacity. The initial vehicle charge level refers to the battery charge level when the vehicle begins charging. The target charging characteristic curve is a pre-set curve showing the change in charge level when a charging station of the target charging station type is charging the vehicle. For example, the target charging characteristic curve is the characteristic curve of the charging station itself, which can be directly obtained.

[0062] Among these, the sample charging environment parameters refer to the environmental parameters used for model training. The daily load label curve refers to the daily load curve obtained based on simulated vehicle charging behavior; that is, the daily load label curve can be understood as the actual daily load curve of the charging pile under the sample charging environment parameters. The daily load sample curve refers to the daily load curve output by the daily load curve prediction model, used for model training. The model loss value refers to the loss value of the daily load curve prediction model.

[0063] Understandably, by simulating vehicle charging behavior under different sample charging environment parameters based on the target charging pile strategy, vehicle charging simulation data, and target charging characteristic curve, the daily load label curve under the corresponding sample charging environment parameters is determined. Then, the sample charging environment parameters are input into the constructed daily load curve prediction model to obtain the corresponding daily load sample curve. Finally, the daily load curve prediction model is trained based on the model loss value determined by the daily load label curve and the daily load sample curve, thereby improving the accuracy of training the daily load curve prediction model.

[0064] S150. Based on the parking space deployment strategy, target charging pile strategy, and daily load forecast curve, determine the charging station deployment strategy for the area to be deployed.

[0065] Among them, the charging station deployment strategy refers to the deployment strategy of charging stations in the area to be deployed.

[0066] In one optional embodiment, the charging station deployment strategy for the area to be deployed is determined based on the parking space deployment strategy, the target charging pile strategy, and the daily load forecast curve, including: determining the power distribution equipment deployment strategy based on the daily load forecast curve, and determining the charging station deployment strategy based on the parking space deployment strategy, the target charging pile strategy, and the power distribution equipment deployment strategy.

[0067] Among them, the power distribution equipment deployment strategy refers to the deployment strategy of power distribution equipment in the area to be deployed.

[0068] For example, based on the daily load forecast curve, the associated data of the power distribution equipment is determined, and based on the associated data, the deployment strategy of the power distribution equipment is determined. The associated data of the power distribution equipment refers to the data used to determine the deployment strategy. For instance, the associated data may include the maximum load value, the load value that will not be exceeded with a 95% probability, and the total electricity consumption.

[0069] Understandably, determining the power distribution equipment deployment strategy based on the daily load forecast curve improves the accuracy of the determined power distribution equipment deployment strategy. At the same time, determining the charging station deployment strategy based on the parking space deployment strategy, the target charging pile strategy, and the power distribution equipment deployment strategy improves the accuracy of the charging station deployment strategy.

[0070] This invention provides a method for determining a charging station deployment strategy. The method involves acquiring a regional image of the area to be deployed, and determining a regional terrain model and a regional object model based on the image. Based on the terrain model and object model, a parking space deployment area is determined within the area to be deployed. A parking space deployment strategy is then determined based on the parking space deployment area, a preset parking space size, and a preset point distance. The parking space deployment strategy includes a set of parking space coordinates. Based on the parking space coordinate set, the preset parking space size, and the preset distribution box location, candidate charging pile strategies are determined, and a target charging pile strategy is determined from the candidate strategies. Environmental prediction parameters for the area to be deployed within a preset period are acquired and input into a trained daily load curve prediction model to obtain a daily load prediction curve. Finally, the charging station deployment strategy for the area to be deployed is determined based on the parking space deployment strategy, the target charging pile strategy, and the daily load prediction curve. The above solution determines the parking space deployment area based on the regional terrain model and regional object model of the area to be deployed. It then determines the parking space deployment strategy based on the deployment area, preset parking space size, and preset point distance. Next, it determines the target charging pile strategy based on the parking space coordinate set, preset parking space size, and preset distribution box location within the deployment strategy. Finally, it determines the daily load prediction curve within a preset period based on the daily load curve prediction model. Finally, it determines the charging station deployment strategy for the area to be deployed based on the parking space deployment strategy, the target charging pile strategy, and the daily load prediction curve. This automated determination of the charging station deployment strategy improves its efficiency.

[0071] Example 2

[0072] Figure 2 This is a flowchart of a method for determining a charging station deployment strategy according to Embodiment 2 of the present invention. Based on the above embodiments, this embodiment further refines the operation of "determining the parking space deployment strategy according to the parking space deployment area, preset parking space size, and preset point distance" into "dividing the parking space deployment area based on a preset graph algorithm to obtain candidate parking space sub-regions, and determining the center point of candidate parking spaces in the candidate parking space sub-regions according to the preset parking space size and preset point distance; performing iterative clustering and filtering on the candidate parking space center points to determine the target center point cluster, and determining the parking space deployment strategy based on the target center point cluster," thereby improving the mechanism for determining the parking space deployment strategy. It should be noted that for parts not detailed in this embodiment, please refer to the descriptions in other embodiments.

[0073] See Figure 2 The method for determining the charging station deployment strategy shown includes:

[0074] S210. Obtain the area image of the area to be deployed, and determine the area terrain model and area object model of the area to be deployed based on the area image.

[0075] S220. Based on the regional terrain model and regional object model, determine the parking space deployment area within the area to be deployed.

[0076] S230. Based on the preset map algorithm, the parking space deployment area is divided to obtain candidate parking space sub-regions, and the center point of the candidate parking space in the candidate parking space sub-region is determined according to the preset parking space size and preset point distance.

[0077] The preset map algorithm refers to a pre-set algorithm used to divide the parking space deployment area. A candidate parking space sub-region refers to a portion of the area obtained after dividing the parking space deployment area. The candidate parking space center point refers to the center point of an individual parking space region. For example, a candidate parking space sub-region may contain multiple individual parking space regions, and each individual parking space region contains one candidate parking space center point. An individual parking space region refers to an area used to park one vehicle.

[0078] For example, for a candidate parking space sub-area, at least one individual parking space area is determined within the candidate parking space sub-area based on the preset parking space size and preset point distance, and the center point of the candidate parking space within the individual parking space area is determined.

[0079] S240. Iteratively cluster and filter the center points of candidate parking spaces to determine the target center point cluster, and determine the parking space deployment strategy based on the target center point cluster; wherein, the parking space deployment strategy includes a set of parking space coordinates.

[0080] In an optional embodiment, iterative clustering and filtering of candidate parking space center points to determine a target center point cluster includes: for any iterative clustering and filtering process, clustering the candidate parking space center points of the current iteration to obtain a candidate center point cluster, and determining a reference center point cluster from the candidate center point cluster; filtering the candidate parking space center points in the reference center point cluster according to a preset point distance to obtain the filtered reference center point cluster obtained in the current iteration; and taking the filtered reference center point cluster obtained in the last iteration as the target center point cluster.

[0081] Here, the candidate centroid cluster refers to the cluster obtained after clustering the candidate parking space centroids in this iteration. The reference centroid cluster refers to a relatively concentrated cluster of candidate centroids. The target centroid cluster refers to the cluster obtained after iteratively clustering and filtering the candidate parking space centroids in the reference centroid cluster.

[0082] For example, after clustering the candidate parking space center points to obtain candidate center point clusters, the inter-cluster distance of the candidate center point clusters is determined, and a reference center point cluster is determined based on the inter-cluster distance and a preset maximum distance. The inter-cluster distance can be used to characterize the degree of dispersion between candidate center point clusters.

[0083] Specifically, candidate center point clusters with distances less than or equal to a preset maximum value are used as reference center point clusters. This embodiment of the invention does not impose any limitation on the size of the preset maximum value; it can be set by technicians based on experience or needs, or determined through numerous experiments.

[0084] For example, if any two adjacent reference center point clusters are reference center point cluster A and reference center point cluster B, and the distance between candidate parking space center point A1 in reference center point cluster A and candidate parking space center point B2 in reference center point cluster B is less than the preset point distance, then candidate parking space center point A1 or candidate parking space center point B2 needs to be deleted to avoid the situation where two adjacent individual parking space areas overlap.

[0085] For example, in the clustering process of the candidate parking space center points in this iteration, the candidate parking space center points in this iteration are the candidate parking space center points left over from the previous iteration; the candidate parking space center points in the first iteration are the candidate parking space center points in all the candidate parking space sub-regions determined at the beginning. It can be understood that by clustering and filtering for any iteration, a reference center point cluster is determined from the candidate center point clusters obtained in this iteration, and the candidate parking space center points in the reference center point cluster are filtered according to the preset point distance to obtain the filtered reference center point clusters obtained in this iteration. The filtered reference center point clusters obtained in the last iteration are used as the target center point clusters, which improves the accuracy of the determined target center point clusters.

[0086] For example, determining a parking space deployment strategy based on a cluster of target center points includes: adjusting the spacing between clusters of target center points according to preset spacing adjustment data, and determining the parking space deployment strategy based on the adjusted clusters of target center points.

[0087] The preset spacing adjustment data refers to data pre-set for adjusting the spacing between clusters. For example, the preset spacing adjustment data may include the minimum turning radius of the vehicle and the minimum width of the passageway. The minimum width of the passageway refers to the minimum width of the passageway between two rows of parking spaces. This embodiment of the invention does not impose any limitations on the size of the minimum turning radius of the vehicle and the minimum width of the passageway; these can be set by technicians based on experience or needs, or determined through repeated trials. For example, the individual parking space area where the center point of the target parking space in the adjusted target center point cluster is located is taken as the target individual area, and a parking space deployment strategy is determined based on the target individual area. The target individual area refers to the individual parking space area used to determine the parking space deployment strategy.

[0088] Understandably, by adjusting the spacing between target center point clusters based on preset spacing adjustment data, and then determining the parking space deployment strategy based on the adjusted target center point clusters, the accuracy of the determined parking space deployment strategy is improved.

[0089] S250. Based on the set of parking space coordinates, preset parking space size, and preset electrical distribution box location, determine the candidate charging pile strategy, and then determine the target charging pile strategy from the candidate charging pile strategies.

[0090] S260. Obtain the environmental prediction parameters of the area to be deployed within a preset period, and input the environmental prediction parameters into the trained daily load curve prediction model to obtain the daily load prediction curve.

[0091] S270. Based on the parking space deployment strategy, target charging pile strategy, and daily load forecast curve, determine the charging station deployment strategy for the area to be deployed.

[0092] This invention provides a method for determining a charging station deployment strategy. The method refines the process of determining the parking space deployment strategy based on the parking space deployment area, preset parking space size, and preset point distance into a method based on a preset graph algorithm. This involves dividing the parking space deployment area into candidate parking space sub-regions, determining the center point of each candidate parking space within these sub-regions based on the preset parking space size and preset point distance, iteratively clustering these center points to determine target center point clusters, and finally determining the parking space deployment strategy based on these target center point clusters. This improves the mechanism for determining the parking space deployment strategy. The above scheme, by dividing the parking space deployment area into candidate parking space sub-regions, determining the center points of each candidate parking space within these sub-regions based on the preset parking space size and preset point distance, and finally determining the parking space deployment strategy based on the target center point clusters obtained through iterative clustering of the candidate parking space center points, improves the accuracy of the determined parking space deployment strategy.

[0093] Example 3

[0094] This invention provides an optional example based on the above embodiments. It should be noted that for parts not described in detail in this invention's embodiments, please refer to the descriptions in other embodiments.

[0095] This invention relates to the field of electric vehicle charging infrastructure design technology, specifically to an automatic design software system for public charging stations based on intelligent algorithms, including an integrated solution with functions such as automatic terrain surveying, automatic parking space allocation, intelligent layout of charging piles, automatic load calculation, and automatic generation of supporting electrical equipment.

[0096] Currently, the design of charging piles mainly adopts a sequential model of manual on-site measurement, two-dimensional drawing, empirical load verification using spreadsheets, and step-by-step independent design. Designers must personally visit the site to manually measure and, based on experience, delineate the number and location of charging piles in drawing software. They then roughly calculate the load based on their experience, including terrain surveying, parking space allocation, equipment selection, cable routing, and fire evacuation plans. Equipment selection, electrical design, and construction are then carried out according to the estimated plan.

[0097] Existing technologies suffer from the following drawbacks: they rely on designers to manually measure parking spaces, passageways, and existing pipelines on-site, followed by two-dimensional drawings using drafting software. This process is highly subjective, inefficient, time-consuming, and requires extensive manual surveying and drafting, necessitating multiple revisions and failing to visually represent three-dimensional spatial conflicts. The number and location of charging piles are determined entirely by personal experience, leading to inconsistent solutions and wasted space. The lack of scientific optimization algorithms and real-time coupling verification of electrical constraints such as transformer capacity, load factor, voltage drop, and harmonic margin results in both over- and under-matching. Load calculations rely solely on spreadsheets and rough summaries based on empirical coefficients, without dynamic simulation of charging power time-division curves, vehicle arrival distribution, and distribution network short-circuit capacity. This results in insufficient calculation accuracy and a high risk of transformer overload and excessive line temperature rise. Sub-steps such as terrain surveying, parking space allocation, equipment selection, cable routing, communication wiring, and fire evacuation are carried out sequentially in a linear fashion, leading to severe information silos, difficulties in professional coordination, and a lack of intelligent tools, hindering automation and standardization.

[0098] This invention provides a software system for automatically designing public charging stations. By integrating multiple advanced algorithms and technologies, it achieves full automation of the charging station design process. The system includes the following core functional modules: automatic terrain survey module, automatic parking space allocation module, intelligent charging pile layout module, automatic load calculation module, and automatic generation module for supporting equipment.

[0099] The automatic terrain survey module can be used to determine the regional terrain model and regional object model of the area to be deployed. For example, high-precision terrain data (i.e., regional images) is acquired based on UAV remote sensing technology; a three-dimensional terrain model is established using a geographic information system; a convolutional neural network is used for terrain feature recognition and classification; and a digital elevation model (DEM) (i.e., regional terrain model) and a digital surface model (DSM) (i.e., regional object model) are generated.

[0100] For example, a digital elevation model (DEM) contains only the elevation information of the ground surface, removing all objects on the ground, such as buildings and trees. It represents the terrain undulations and is mainly used for macro-planning and earthwork calculations. In this embodiment of the invention, its functions are as follows: Analyzing terrain slope: determining whether the site is too steep, whether leveling is needed, and whether vehicle access is convenient. Areas that are too steep are unsuitable for parking spaces; Calculating drainage direction: analyzing water flow direction based on elevation to ensure the charging station has a reasonable drainage system to avoid flooding; key equipment such as power distribution rooms should be located away from low-lying areas; Estimating earthwork volume: if site leveling is required, the DEM can be used to calculate how much earthwork needs to be excavated or filled, directly affecting cost and construction period.

[0101] For example, a digital surface model contains the top elevation information of the ground surface and all objects on it, such as buildings, trees, and bridges. It represents the ground morphology as seen from the air and is used for conflict detection, precise spatial planning, and 3D visualization. In this embodiment of the invention, its functions are as follows: 1. Detecting spatial conflicts: This is the core function of the digital surface model. It can identify existing buildings, rooftops, tall trees, utility poles, etc., on the site. The system can automatically determine whether the planned charging pile locations, cable tray paths, or large transformers will collide with these existing objects. 2. Assisting in parking space allocation: After identifying large obstacles, such as buildings, it can automatically reserve safe or passage areas around them, thereby more accurately allocating available parking spaces. 3. Shadow analysis: Using the digital surface model, the solar altitude angle at different seasons and times can be simulated to analyze the shadows cast by tall buildings or trees. This helps optimize the layout of charging piles, avoid placing the piles in dark and damp environments for extended periods, or assess the installation potential of photovoltaic canopies.

[0102] The automatic parking space allocation module can be used to determine parking space deployment strategies. For example, based on a regional terrain model and a regional object model, the module determines the available area of ​​the site (i.e., the parking space deployment area) through slope analysis and obstacle recognition. Subsequently, a preset graph algorithm, such as the Voronoi diagram algorithm, is used to generate a uniformly distributed set of candidate parking space center points within the available area. To obtain a regular parking space layout that conforms to driving habits, this module introduces a K-center point clustering algorithm to optimize the aforementioned candidate parking space center point set. This algorithm uses the candidate parking space center points as objects and minimizes the sum of intra-cluster distances as the objective function, dividing them into K clusters (i.e., candidate center point clusters), each cluster representing a row of parking spaces. The algorithm iteratively updates the cluster center points, ultimately obtaining the optimal clustering result, i.e., the target center point cluster. After clustering, the system aligns and adjusts the center points of candidate parking spaces within the same cluster to form a regular parking space layout. Based on the minimum turning radius of vehicles and the minimum width of passageways, the system verifies and optimizes the distance between clusters, thereby automatically outputting the parking space configuration scheme with the highest space utilization. That is, the system adjusts the distance between target center point clusters according to preset spacing adjustment data, and determines the parking space deployment strategy based on the adjusted target center point clusters.

[0103] The intelligent charging pile layout module can be used to determine the target charging pile strategy. For example, the intelligent charging pile layout module takes the parking space coordinate set (i.e., parking space coordinate set), preset parking space size, and preset distribution box location as inputs. It focuses on multi-objective optimization of cost, convenience, and safety, and uses an improved particle swarm optimization algorithm for solution. The specific steps are as follows: Establish a multi-objective optimization function: The strategy evaluation score is composed of a weighted average of total cost (i.e., strategy cost data), negative user convenience (i.e., strategy convenience data), and safety penalty (i.e., strategy safety data), with a hard constraint penalty term for exceeding the total power limit added. That is, based on the preset total power threshold, a reference charging pile strategy is determined from the candidate charging pile strategies; the strategy cost data, strategy convenience data, and strategy safety data of the reference charging pile strategy are determined, and the strategy cost data, strategy convenience data, and strategy safety data are weighted and summed according to the weights of the cost dimension, convenience dimension, and safety dimension to obtain the strategy evaluation score of the corresponding reference charging pile strategy.

[0104] For example, the improved PSO algorithm is implemented as follows: Encoding and Initialization: Each particle is encoded as a vector representing a reference charging pile strategy, and the particle swarm is randomly initialized. Iterative Optimization: Evaluation: The fitness value of each particle, i.e., the strategy evaluation score, is calculated. Update: The velocity and position of each particle are updated according to the standard PSO (Particle Swarm Optimization) formula; where the inertia weight ω adopts a linear decreasing strategy to balance the exploration and development capabilities at different stages of the algorithm; Perturbation: If the global optimal solution becomes stagnant, a random perturbation mechanism is introduced to escape local optima. Output: After iterative convergence, the global optimal solution is output as the final intelligent charging pile deployment scheme, i.e., the target charging pile strategy. The target charging pile strategy explicitly specifies the installation location and equipment type of each charging pile and provides a basis for downstream cable path planning.

[0105] The automatic load calculation module can be used to determine the daily load forecast curve. For example, the automatic load calculation module takes the target charging pile scheme, preset vehicle charging simulation data, and the target charging characteristic curve as inputs, and achieves accurate load forecasting through two-level calculations. First, Monte Carlo simulation is used to generate probabilistic load scenarios. Based on random parameters such as vehicle arrival rate, vehicle initial charge, and vehicle battery capacity, the random charging behavior of a large number of vehicles throughout the day is simulated. By superimposing the instantaneous power of all charging piles in a charging state, a massive number of daily load label curves are generated. Then, a factor hidden Markov model is applied for accurate time-series forecasting. Typical load curves obtained from the Monte Carlo simulation are used as observation sequences, and external observable variables such as date type and weather are used as factors to construct a daily load curve forecasting model. This model attributes the dynamic changes in load to a series of hidden operating states, such as peak, off-peak, and valley periods. After training the model parameters using the Baum-Welch algorithm, a trained daily load curve prediction model is obtained. Subsequently, based on this model, the Viterbi algorithm, combined with future factor information, can be used to decode the most probable future load curve (i.e., the daily load prediction curve). Finally, this module outputs an accurate load report based on the trained daily load curve prediction model, including the daily load prediction curve for a specific future period, the maximum load value, the load value that will not be exceeded with a 95% probability, and the total electricity consumption. This provides a reliable basis for subsequent power distribution equipment selection.

[0106] The automatic equipment generation module can be used to determine the deployment strategy for power distribution equipment. For example, it can automatically select the transformer capacity based on the load calculation results; automatically generate cable routes and specifications according to the parking space deployment strategy, target charging pile strategy, and power distribution equipment deployment strategy; intelligently configure high and low voltage switchgear, switchgear, etc.; and generate a complete equipment list and bill of materials.

[0107] The method for determining the deployment strategy of charging stations provided in this invention requires protection in the following aspects: Overall system architecture: A system for automatically designing public charging stations, comprising an integrated architecture of an automatic terrain survey module, an automatic parking space allocation module, an intelligent charging pile layout module, an automatic load calculation module, and an automatic generation module for supporting equipment; Core algorithm integration: A technical solution that integrates multiple intelligent algorithms such as convolutional neural networks, preset graph algorithms, particle swarm optimization algorithms, and Monte Carlo simulations into charging station design; Automated workflow: A fully automated design method from terrain data acquisition, 3D modeling, parking space allocation, layout optimization, load calculation to equipment selection; Multi-objective optimization method: A charging pile layout optimization algorithm that comprehensively considers multiple objective functions such as cost, convenience, safety, and scalability; Precise load forecasting technology: Charging load forecasting technology based on factor hidden Markov models (i.e., daily load curve prediction models) and Monte Carlo methods; Intelligent equipment selection: A technical solution that automatically selects transformer capacity, cable specifications, and supporting equipment based on load calculation results.

[0108] The method for determining charging station deployment strategies provided in this invention improves design efficiency by over 80%, reducing the cycle from 2-4 weeks to 1-2 days, minimizing manual labor and repetitive tasks, and supporting rapid iteration. Algorithm optimization enhances space utilization, improves load calculation and equipment selection accuracy, eliminates human error, and achieves optimal overall performance. Investment costs are reduced, avoiding over-configuration and significantly decreasing later maintenance expenses, thus comprehensively improving the economic benefits of charging stations. Simultaneously, standardized and regulated processes ensure consistent and reproducible solutions, facilitating experience accumulation and inheritance, further guaranteeing the high quality and reliability of design results, and possessing broad engineering applicability and promotional value.

[0109] Example 4

[0110] Figure 3 This is a schematic diagram of a charging station deployment strategy determination device provided in Embodiment 4 of the present invention. This embodiment is applicable to the case of automatically determining the deployment strategy of charging stations. The method can be executed by the charging station deployment strategy determination device, which can be implemented in software and / or hardware and can be configured in an electronic device that carries the function of determining the charging station deployment strategy.

[0111] like Figure 3 As shown, the device includes: a model determination module 310, a parking space deployment strategy determination module 320, a target charging pile strategy determination module 330, a curve determination module 340, and a charging station deployment strategy determination module 350. Among them,

[0112] The model determination module 310 is used to acquire a region image of the area to be deployed, and determine the region terrain model and region object model of the area to be deployed based on the region image.

[0113] The parking space deployment strategy determination module 320 is used to determine the parking space deployment area within the area to be deployed based on the area terrain model and the area object model, and to determine the parking space deployment strategy based on the parking space deployment area, the preset parking space size, and the preset point distance; wherein, the parking space deployment strategy includes a set of parking space coordinates;

[0114] The target charging pile strategy determination module 330 is used to determine candidate charging pile strategies based on the parking space coordinate set, the preset parking space size and the preset distribution box location, and to determine the target charging pile strategy from the candidate charging pile strategies.

[0115] The curve determination module 340 is used to obtain the environmental prediction parameters of the area to be deployed within a preset period, and input the environmental prediction parameters into the trained daily load curve prediction model to obtain the daily load prediction curve;

[0116] The charging station deployment strategy determination module 350 is used to determine the charging station deployment strategy for the area to be deployed based on the parking space deployment strategy, the target charging pile strategy, and the daily load forecast curve.

[0117] This invention provides a method for determining a charging station deployment strategy. The method involves acquiring a regional image of the area to be deployed, and determining a regional terrain model and a regional object model based on the image. Based on the terrain model and object model, a parking space deployment area is determined within the area to be deployed. A parking space deployment strategy is then determined based on the parking space deployment area, a preset parking space size, and a preset point distance. The parking space deployment strategy includes a set of parking space coordinates. Based on the parking space coordinate set, the preset parking space size, and the preset distribution box location, candidate charging pile strategies are determined, and a target charging pile strategy is determined from the candidate strategies. Environmental prediction parameters for the area to be deployed within a preset period are acquired and input into a trained daily load curve prediction model to obtain a daily load prediction curve. Finally, the charging station deployment strategy for the area to be deployed is determined based on the parking space deployment strategy, the target charging pile strategy, and the daily load prediction curve. The above solution determines the parking space deployment area based on the regional terrain model and regional object model of the area to be deployed. It then determines the parking space deployment strategy based on the deployment area, preset parking space size, and preset point distance. Next, it determines the target charging pile strategy based on the parking space coordinate set, preset parking space size, and preset distribution box location within the deployment strategy. Finally, it determines the daily load prediction curve within a preset period based on the daily load curve prediction model. Finally, it determines the charging station deployment strategy for the area to be deployed based on the parking space deployment strategy, the target charging pile strategy, and the daily load prediction curve. This automated determination of the charging station deployment strategy improves its efficiency.

[0118] Optionally, the parking space deployment strategy determination module 320 includes:

[0119] The parking space center point determination unit is used to divide the parking space deployment area based on a preset map algorithm to obtain candidate parking space sub-regions, and determine the center point of the candidate parking space in the candidate parking space sub-regions according to the preset parking space size and the preset point distance.

[0120] The parking space deployment strategy determination unit is used to perform iterative clustering and filtering on the candidate parking space center points to determine the target center point cluster, and determine the parking space deployment strategy based on the target center point cluster.

[0121] Optionally, the parking space deployment strategy determination unit is specifically used for:

[0122] For any iterative clustering and screening process, the candidate parking space center points of the current iteration are clustered to obtain candidate center point clusters, and a reference center point cluster is determined from the candidate center point clusters.

[0123] Based on the preset point distance, the candidate parking space center points in the reference center point cluster are filtered to obtain the filtered reference center point cluster obtained in this iteration;

[0124] The filtered reference center point cluster obtained from the last iteration is used as the target center point cluster.

[0125] Optionally, the target charging pile strategy determination module 330 includes:

[0126] A reference charging pile strategy determination unit is used to determine the candidate total power corresponding to each of the candidate charging pile strategies, and to determine the reference charging pile strategy based on the candidate total power and a preset total power threshold.

[0127] The strategy evaluation score determination unit is used to determine the strategy evaluation data corresponding to the reference charging pile strategy, and determine the corresponding strategy evaluation score based on the strategy evaluation data.

[0128] A target charging pile strategy determination unit is used to determine the target charging pile strategy from the reference charging pile strategies based on the strategy evaluation score.

[0129] Optionally, the target charging pile strategy determination unit is specifically used for:

[0130] The reference charging pile strategy corresponding to the lowest strategy evaluation score is taken as the target charging pile strategy.

[0131] Optionally, the daily load curve prediction model is trained based on the following device:

[0132] The daily load curve determination module is used to simulate vehicle charging behavior under different sample charging environment parameters based on the target charging pile strategy, preset vehicle charging simulation data, and target charging characteristic curve, and to determine the daily load label curve under the corresponding sample charging environment parameters.

[0133] The daily load sample curve determination module is used to input the sample charging environment parameters into the constructed daily load curve prediction model to obtain the corresponding daily load sample curve.

[0134] The model training module is used to determine the model loss value based on the daily load label curve and the daily load sample curve, and to train the daily load curve prediction model based on the model loss value.

[0135] Optionally, the charging station deployment strategy determination module 350 includes:

[0136] The charging station deployment strategy determination unit is used to determine the power distribution equipment deployment strategy based on the daily load forecast curve, and to determine the charging station deployment strategy based on the parking space deployment strategy, the target charging pile strategy, and the power distribution equipment deployment strategy.

[0137] The charging station deployment strategy determination device provided in this embodiment of the invention can execute the charging station deployment strategy determination method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects for executing the charging station deployment strategy determination method.

[0138] The collection, storage, use, processing, transmission, provision, and disclosure of regional images and environmental prediction parameters involved in the technical solution of this invention all comply with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0139] Example 5

[0140] Figure 4 This is a schematic diagram of an electronic device for implementing a method for determining a charging station deployment strategy, as provided in Embodiment 5 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0141] like Figure 4As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0142] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0143] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as the method for determining a charging station deployment strategy.

[0144] In some embodiments, the method for determining a charging station deployment strategy may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the method for determining a charging station deployment strategy described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the method for determining a charging station deployment strategy by any other suitable means (e.g., by means of firmware).

[0145] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0146] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0147] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0148] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0149] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0150] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0151] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0152] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for determining a charging station deployment strategy, characterized in that, include: Obtain a region image of the area to be deployed, and determine the region terrain model and region object model of the area to be deployed based on the region image; Based on the regional terrain model and the regional object model, the parking space deployment area within the area to be deployed is determined, and a parking space deployment strategy is determined based on the parking space deployment area, the preset parking space size, and the preset point distance; wherein, the parking space deployment strategy includes a set of parking space coordinates; Based on the parking space coordinate set, the preset parking space size, and the preset power distribution box location, a candidate charging pile strategy is determined, and a target charging pile strategy is determined from the candidate charging pile strategies. Obtain the environmental prediction parameters of the area to be deployed within a preset period, and input the environmental prediction parameters into the trained daily load curve prediction model to obtain the daily load prediction curve; Based on the parking space deployment strategy, the target charging pile strategy, and the daily load forecast curve, the charging station deployment strategy for the area to be deployed is determined.

2. The method according to claim 1, characterized in that, The step of determining the parking space deployment strategy based on the parking space deployment area, preset parking space size, and preset point distance includes: Based on the preset map algorithm, the parking space deployment area is divided to obtain candidate parking space sub-regions, and the center point of the candidate parking space in the candidate parking space sub-region is determined according to the preset parking space size and the preset point distance. The candidate parking space center points are iteratively clustered and filtered to determine the target center point cluster, and the parking space deployment strategy is determined based on the target center point cluster.

3. The method according to claim 2, characterized in that, The iterative clustering and filtering of the candidate parking space center points to determine the target center point cluster includes: For any iterative clustering and screening process, the candidate parking space center points of the current iteration are clustered to obtain candidate center point clusters, and a reference center point cluster is determined from the candidate center point clusters. Based on the preset point distance, the candidate parking space center points in the reference center point cluster are filtered to obtain the filtered reference center point cluster obtained in this iteration; The filtered reference center point cluster obtained from the last iteration is used as the target center point cluster.

4. The method according to claim 1, characterized in that, The step of determining the target charging pile strategy from the candidate charging pile strategies includes: The candidate total power corresponding to each of the candidate charging pile strategies is determined, and a reference charging pile strategy is determined based on the candidate total power and a preset total power threshold. Determine the strategy evaluation data corresponding to the reference charging pile strategy, and determine the corresponding strategy evaluation score based on the strategy evaluation data; The target charging pile strategy is determined from the reference charging pile strategies based on the strategy evaluation score.

5. The method according to claim 4, characterized in that, The step of determining the target charging pile strategy from the reference charging pile strategies based on the strategy evaluation score includes: The reference charging pile strategy corresponding to the lowest strategy evaluation score is taken as the target charging pile strategy.

6. The method according to claim 1, characterized in that, The daily load curve prediction model was trained using the following method: Based on the target charging pile strategy, the preset vehicle charging simulation data, and the target charging characteristic curve, simulate the vehicle charging behavior under different sample charging environment parameters, and determine the daily load label curve under the corresponding sample charging environment parameters. The sample charging environment parameters are input into the constructed daily load curve prediction model to obtain the corresponding daily load sample curve; Based on the daily load label curve and the daily load sample curve, the model loss value is determined, and the daily load curve prediction model is trained based on the model loss value.

7. The method according to claim 1, characterized in that, The step of determining the charging station deployment strategy for the area to be deployed based on the parking space deployment strategy, the target charging pile strategy, and the daily load forecast curve includes: Based on the daily load forecast curve, a power distribution equipment deployment strategy is determined, and based on the parking space deployment strategy, the target charging pile strategy, and the power distribution equipment deployment strategy, a charging station deployment strategy is determined.

8. A device for determining a charging station deployment strategy, characterized in that, include: The model determination module is used to acquire a regional image of the area to be deployed, and determine the regional terrain model and regional object model of the area to be deployed based on the regional image. The parking space deployment strategy determination module is used to determine the parking space deployment area within the area to be deployed based on the area terrain model and the area object model, and to determine the parking space deployment strategy based on the parking space deployment area, the preset parking space size, and the preset point distance; wherein, the parking space deployment strategy includes a set of parking space coordinates; The target charging pile strategy determination module is used to determine candidate charging pile strategies based on the parking space coordinate set, the preset parking space size and the preset power distribution box location, and to determine the target charging pile strategy from the candidate charging pile strategies. The curve determination module is used to obtain the environmental prediction parameters of the area to be deployed within a preset period, and input the environmental prediction parameters into the trained daily load curve prediction model to obtain the daily load prediction curve; The charging station deployment strategy determination module is used to determine the charging station deployment strategy for the area to be deployed based on the parking space deployment strategy, the target charging pile strategy, and the daily load forecast curve.

9. An electronic device, characterized in that, include: One or more processors; Memory, used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement a method for determining a charging station deployment strategy as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements a method for determining a charging station deployment strategy as described in any one of claims 1-7.

Images