A new energy vehicle charging pile space layout method and operation management platform

Abstract

The application relates to the technical field of new energy vehicles, and provides a new energy vehicle charging pile space layout method and an operation management platform.The method comprises the following steps: acquiring the position attributes of existing charging piles in a target area; determining hot spot areas according to the first clustering results of the position attributes of the existing charging piles; determining candidate construction sites based on the hot spot areas and a preset site selection strategy; creating virtual charging piles for each candidate construction site, and collecting user demand data based on the virtual charging piles; screening target charging piles from the virtual charging piles based on the user demand data, and generating a charging pile layout plan according to the target charging piles. Based on the above method, reasonable charging pile layout plans can be acquired in the preparation stage of new charging pile construction, so as to provide effective suggestions for the site selection of charging piles.

Description

[0001] Technology Neighborhood

[0002] This application relates to the field of new energy vehicle technology, and in particular to a spatial layout method, operation management platform and electronic equipment for new energy vehicle charging piles. Background Technology

[0003] With urban development, the construction of healthy cities has become an important guiding principle in urban planning. Healthy cities emphasize reducing reliance on traditional gasoline-powered vehicles and lowering air pollution and greenhouse gas emissions. As an essential infrastructure for new energy vehicles, the widespread availability and convenience of charging stations can encourage more residents to choose electric vehicles as their mode of transportation, thereby reducing negative environmental impacts and promoting green travel. Simultaneously, as a crucial supporting facility for the new energy vehicle industry, the technological innovation and industrial development of charging stations play a vital role in promoting the optimization and upgrading of urban economic structures. The widespread availability and rational layout of new energy vehicle charging stations can provide more convenient charging services, reduce "range anxiety" for electric vehicle users, and improve their travel experience and quality of life.

[0004] Therefore, under the guidance of healthy cities, how to rationally plan the spatial layout of charging piles has become a key research topic in the industry. Summary of the Invention

[0005] In order to rationally plan the spatial layout of charging piles and reduce and alleviate charging pressure in hot spots, this application provides a method for spatial layout of new energy vehicle charging piles, an operation management platform, and electronic equipment.

[0006] The spatial layout method for new energy vehicle charging piles provided in this application is applied to a new energy vehicle charging pile operation and management platform, and includes the following steps: obtaining the location attributes of existing charging piles within a target area; determining hotspot areas based on the first clustering results of the location attributes of each existing charging pile; determining candidate sites based on the hotspot areas and a preset site selection strategy; creating virtual charging piles for each candidate site and collecting user demand data based on each virtual charging pile; selecting target charging piles from each virtual charging pile based on the user demand data, and generating a charging pile layout plan based on the target charging piles.

[0007] Based on the above technical solution, the existing layout of charging piles in the target area is fully considered, and hotspot areas are directly identified based on these existing charging piles. This provides an accurate and reliable data analysis basis for determining candidate charging stations, ensuring that the planned charging pile layout can effectively alleviate user charging pressure and, to a certain extent, guarantee investment returns, thus promoting the healthy development of the industry. Furthermore, by creating virtual charging piles at each candidate site and collecting user demand data from these virtual charging piles, target charging piles with genuine user demand can be further filtered out, avoiding erroneous judgments due to inaccurate or incomplete preliminary data. Therefore, the above technical solution not only yields a charging pile layout plan that meets actual user needs, but also uses real-time, reliable, and highly accurate data in the planning process. Compared to existing technologies that rely on predictive analysis based on various big data including vehicles and users, the data is more timely and readily available, and the solution is more feasible to implement.

[0008] In one implementation, the target area completely covers and is larger than the site selection planning area.

[0009] Based on the above technical solution, by reasonably expanding the site selection planning area, it is possible to obtain more comprehensive data on existing charging piles, thereby providing a more accurate data foundation for the layout of charging piles at the edge of the site selection planning area.

[0010] In one implementation, obtaining the location attributes of existing charging piles within the target area includes: determining the geographical location information of the existing charging piles; querying a map to obtain the location area corresponding to the geographical location information as first feature information; if the location area is a roadside parking space, obtaining other feature information whose distance from the existing charging pile is within a preset range as second feature information; if the location area is a non-roadside parking space, obtaining other feature information whose distance from the location area is within a preset range as second feature information; and generating the location attributes of the existing charging piles based on the first feature information and the second feature information.

[0011] Based on the above technical solution, by using the location area corresponding to the geographical location of existing charging piles as the location attribute, subsequent analysis can use locations such as roads and parks as the basis for determining hotspot areas, thereby enabling a more accurate analysis of the charging pile layout in various location areas. Compared to analyzing only the coordinates of existing charging piles, this effectively expands the scope of analysis.

[0012] In one implementation, determining the hotspot area based on the first clustering result of the location attributes of each of the existing charging piles includes performing clustering analysis on the coordinates corresponding to each feature information in the location attributes of each of the existing charging piles based on the DBSCAN algorithm.

[0013] Cluster analysis based on the DBSCAN algorithm can yield different clustering possibilities by adjusting the neighborhood radius and the minimum number of sample points.

[0014] In one implementation, the method further includes acquiring noise points determined by the DBSCAN algorithm and determining hotspot regions based on the noise points.

[0015] Identifying hotspots based on noise can, to some extent, help uncover potential areas that have not yet been effectively developed.

[0016] In one implementation, determining candidate charging stations based on the hotspot area and a preset site selection strategy includes: dividing all available charging stations into multiple batches; for each batch of available charging stations, constructing an input layer based on the coordinates of each available charging station, the coordinates of each feature information in the location attributes of existing charging piles in each hotspot area, and other parameters used when determining the hotspot area; calculating each input layer based on the DBSCAN algorithm to obtain corresponding second clustering results; determining the hotspot area to which each available charging station belongs in the second clustering results; if the hotspot area to which the available charging station belongs contains the hotspot area, then the available charging station is determined as a candidate charging station.

[0017] Based on the above technical solution, obtaining the corresponding second clustering results in batches can avoid a large deviation between the hotspot areas in the second clustering results and the first clustering results when the number of potential sites is large, thus deviating from the actual situation. Simultaneously, directly determining the hotspot areas to which potential sites belong based on the second clustering results, and then determining candidate sites based on the relationship between these hotspot areas and the hotspot areas in the first clustering results, not only ensures that candidate sites are planned based on real hotspot areas, but also uncovers potential sites.

[0018] In one implementation, the method for selecting target charging piles from the virtual charging piles based on the user demand data further includes obtaining the predicted investment returns of each virtual charging pile and selecting the virtual charging piles whose predicted investment returns meet the investment expectations as target charging piles.

[0019] In one implementation, the method for obtaining the predicted investment return of the virtual charging pile includes: obtaining the energy efficiency attributes and coordinates of all existing charging piles within the hotspot area to which the virtual charging pile belongs; constructing a utilization rate prediction model based on the utilization rate and coordinates in the energy efficiency attributes of each existing charging pile; calculating the utilization rate prediction model using the coordinates of the virtual charging pile as the input layer to obtain a predicted utilization rate value; constructing an energy consumption prediction model based on the equipment energy consumption and coordinates in the energy efficiency attributes of all existing charging piles; calculating the energy consumption prediction model using the coordinates of the virtual charging pile as the input layer to obtain a predicted energy consumption value; and estimating the investment return period of the virtual charging pile based on the predicted utilization rate value and the predicted energy consumption value.

[0020] Based on the above technical solution, by predicting the utilization rate and energy consumption of virtual charging piles, the accuracy of investment return prediction can be improved, thereby providing a certain guarantee for the investment return of the target charging pile.

[0021] Based on the same inventive concept, this application also provides a new energy vehicle charging pile operation and management platform, which is used to implement the above method.

[0022] Furthermore, this application also provides an electronic device, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the above-described method. Attached Figure Description

[0023] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments of this application and their descriptions are used to explain this application and do not constitute an undue limitation of this application.

[0024] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 A flowchart illustrating the spatial layout method for new energy vehicle charging piles provided in the embodiments of this application is shown.

[0026] Figure 2 A flowchart illustrating the method for obtaining the location attributes of existing charging piles in an embodiment of this application is shown.

[0027] Figure 3 A flowchart illustrating the method for determining candidate construction sites in an embodiment of this application is shown.

[0028] Figure 4 A flowchart illustrating the method for obtaining the predicted investment return of a virtual charging pile in an embodiment of this application is shown. Detailed Implementation

[0029] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0030] In the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more, and "first", "second" and various numerical designations are only for the convenience of description and are not used to limit the scope of the embodiments of this application.

[0031] The features, structures, or characteristics in this application can be combined in any suitable manner in one or more embodiments. In the various embodiments of this application, the sequence number of each process does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0032] Some optional features in the embodiments of this application can be implemented independently without relying on other features in certain scenarios to solve the corresponding technical problems and achieve the corresponding effects. They can also be combined with other features according to needs in certain scenarios.

[0033] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments of this application, unless otherwise specified or there is a logical conflict, the terminology and / or descriptions between different embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships. The implementation methods of this application do not constitute a limitation on the scope of protection of this application.

[0034] The embodiments of this application will be described in detail below with reference to the figures.

[0035] The spatial layout method for new energy vehicle charging piles provided in this application embodiment is applied to a new energy vehicle charging pile operation and management platform. Please refer to... Figure 1 The method specifically includes the following steps.

[0036] S101, Obtain the location attributes of existing charging piles within the target area.

[0037] Specifically, the target area is determined based on the site selection planning area of ​​the charging station to be built. In one example, the target area is the site selection planning area; in another example, the target area is determined by extending a preset distance outward from the site selection planning area as the center. Therefore, the target area completely covers and is larger than the site selection planning area. The preset distance can be adjusted according to actual conditions. The site selection planning area is the area where charging stations are planned to be built.

[0038] Location attributes are used to indicate characteristic information related to the geographical location of existing charging stations, including but not limited to road signs and area names.

[0039] In one example, please refer to Figure 2 The method for obtaining the location attributes of existing charging piles includes the following steps.

[0040] S201, determine the geographical location information of existing charging piles.

[0041] The geographic location information includes location coordinates.

[0042] S202, query the map to obtain the location area corresponding to the geographical location information, and use it as the first feature information.

[0043] The corresponding location area refers to the area where existing charging piles are located, such as parks, buildings, roadside parking spaces, office buildings, and residential buildings.

[0044] S203, if the location area is a roadside parking space, then obtain other feature information that is within a preset range from the existing charging pile, as the second feature information.

[0045] The preset range can be set to a fixed value or dynamically adjusted according to the number of other feature information obtained, so as to ensure that the number of other feature information obtained is not less than the preset threshold.

[0046] S204, if the location area is a non-road parking space, then obtain other feature information that is within a preset range from the location area, as the second feature information.

[0047] S205, Generate the location attributes of existing charging piles based on the first feature information and the second feature information.

[0048] This allows for more accurate and comprehensive feature information contained in location attributes, providing an effective data foundation for subsequent planning and analysis.

[0049] For example, suppose charging pile A is installed in the parking lot of park P, which is located at the intersection of main roads R1 and R2 and adjacent to library L. When determining the location attributes of charging pile A, we can first query the map based on the coordinate information of charging pile A to determine the park P where A is located, as the first feature information. Then, we can query the road and other area information within 20 meters of park P, namely R1, R2 and L, as the second feature information. Thus, the location attributes of charging pile A are generated as: P, R1, R2, L.

[0050] Understandably, information about existing charging stations can be obtained from publicly available service platforms, such as various map applications, charging station query applications, and relevant data within operation and management systems. It is worth noting that to obtain accurate information about existing charging stations in a target area, data from various channels can be integrated and cross-validated to obtain complete and accurate data.

[0051] In one implementation, the working status of each existing charging pile, such as charging in progress or idle, can also be obtained through a publicly available service platform. Based on this, the utilization rate of each existing charging pile within a preset statistical period can be calculated, including but not limited to the average daily utilization rate and the maximum daily utilization rate.

[0052] In another implementation, the total power consumption and charging power consumption of each existing charging pile can be combined to determine the equipment energy consumption of each existing charging pile.

[0053] Utility attributes are generated based on the above utilization rate and equipment energy consumption data.

[0054] S102, based on the first clustering results of the location attributes of each existing charging pile, hotspot areas are determined.

[0055] In one implementation, classification and statistics can be directly performed based on the feature information in the location attributes of existing charging piles to obtain the first clustering result. From this first clustering result, hotspot areas with more than N charging piles or those ranking among the top M in terms of charging pile count can be selected. For example, if the number of charging piles along the main road R1 in the location attribute is greater than N, then R1 can be identified as a hotspot area. The values ​​of N and M can be set as empirical values ​​or determined based on the required number of hotspot areas. For example, if there should be no fewer than 5 hotspot areas, the values ​​of N and M can be adjusted to meet this requirement. Based on this, the feature information recorded in the location attributes can be used as a clustering dimension for classification and statistics to obtain the number of charging piles within the area indicated by each feature information.

[0056] However, during the initial data collection process, there may be issues such as differences in the recording methods of the same feature information, and inaccurate control over the granularity of the initial feature information collection. For example, if charging pile A is located in the parking lot of park P, the final recorded information may be either park P or parking lot AP of park A. Therefore, the first clustering result may be inaccurate.

[0057] To address the issue of inaccurate initial clustering results due to prior data collection, another implementation involves constructing an input layer based on the coordinates corresponding to the feature information in the location attributes of each existing charging pile, and then performing clustering analysis based on a clustering algorithm to obtain hotspot areas.

[0058] In one example, the clustering algorithm used is DBSCAN (Density-Based Spatial Clustering of Applications with Noise). After obtaining the hotspot regions output by the algorithm, it is possible to further determine whether to adjust the neighborhood radius and minimum number of sample points in the input layer based on whether the number of hotspot regions or the corresponding coordinate range of the algorithm output meets the preset requirements, so as to finally obtain hotspot regions that meet the preset requirements.

[0059] Specifically, the preset requirements may include one or more of the following: the number of hotspot regions is not less than a first threshold; the number of hotspot regions is not greater than a second threshold; the type of feature information contained in the hotspot regions does not exceed a third threshold; or the coordinate range of the hotspot regions does not exceed a fourth threshold. The number of each threshold can be set according to actual needs. When the output hotspot regions do not meet the preset requirements, the neighborhood radius and / or the minimum number of sample points can be adjusted to reconstruct the input layer and perform calculations. This process is repeated until the output hotspot regions meet the preset requirements. It is worth noting that charging piles identified as noise during the clustering algorithm calculation can be further obtained to provide a data analysis basis for subsequent planning.

[0060] In some embodiments of this application, hotspot areas can be determined by combining the two methods described above. For example, based on the first embodiment, existing charging piles with the location attribute of road parking spaces can be clustered to obtain hotspot areas determined by roads, thus revealing the deployment of existing charging piles along each road. Simultaneously, based on the second embodiment, existing charging piles with the location attribute of non-road parking spaces can be clustered to obtain hotspot areas determined by the density of charging pile areas. It is worth noting that the hotspot areas obtained based on the second embodiment are used to indicate the clustering of existing charging piles and correspond to a coordinate range. Therefore, it may be a single feature or a collection of multiple features. For example, the coordinate range indicated by the first clustering result may be the range of park P, or it may include the range of park P and library L. Thus, the hotspot areas determined by combining the two methods can include hotspot roads and dense areas.

[0061] In some implementations, to ensure the utilization rate of charging piles, hotspot areas can be further determined by combining the utility attributes of the charging piles with the above-described implementations. Specifically, after obtaining the first clustering results of the location attributes of each existing charging pile, the average utilization rate of each category is calculated based on the utilization rate of existing charging piles within each category. Hotspot areas are then identified by eliminating clusters with average utilization rates below a threshold. In other words, hotspot areas include clusters with a large number of charging piles and high utilization rates. This avoids the problem of charging piles being idle due to being built in low-utilization clusters.

[0062] S103, based on hotspot areas and preset site selection strategies, determines candidate sites for construction.

[0063] In implementation, potential charging stations within the site selection planning area can be identified in advance. The methods for identifying potential charging stations may include using map data to determine areas with suitable geographical conditions for station construction, such as parking lots, roadside parking spaces, and planned parking areas within the site selection planning area. These locations can then be inspected in person to screen out areas that meet other conditions for building charging stations as potential charging stations.

[0064] The preset site selection strategy is used to limit the location relationship between candidate sites and hotspot areas.

[0065] In one implementation, the preset site selection strategy includes identifying candidate charging stations based on map data. In one example, optional charging stations located within hotspot areas can be identified as candidate charging stations. In another example, optional charging stations whose driving distance from the hotspot area does not exceed a preset range and whose traffic conditions along the driving route meet the requirements can be further identified as candidate charging stations. Specifically, the traffic conditions of the driving route can be determined based on the average daily congestion time of the driving route. For example, if the average congestion time does not exceed 2 hours, candidate charging stations located near and easily accessible to the hotspot area can be selected, thus having the ability to alleviate the charging pressure in the hotspot area.

[0066] In another implementation, please refer to Figure 3 The method for determining candidate sites based on hotspot areas and preset site selection strategies includes the following steps.

[0067] S301 divides all optional site construction into multiple batches.

[0068] The quantity in each batch is no greater than a preset quantity. In one example, the preset quantity can be 1.

[0069] S302, for each batch of optional construction sites, constructs an input layer based on the coordinates of each optional construction site, the coordinates of each feature information in the location attributes of existing charging piles in each hotspot area, and other parameters used when determining the hotspot area.

[0070] Specifically, other parameters are determined based on the clustering algorithm, including, in one example, the neighborhood radius and the minimum number of sample points.

[0071] S303, calculate each input layer based on the clustering algorithm to obtain the corresponding second clustering results.

[0072] It is worth noting that the clustering algorithm used in this step is the same as the clustering algorithm corresponding to the first clustering result.

[0073] S304. Determine the hotspot region to which each optional site belongs in the second clustering result. If the hotspot region to which it belongs includes the hotspot region determined according to the first clustering result, then determine the optional site as a candidate site.

[0074] The hotspot region determined based on the first clustering result indicates that the coordinate range of the hotspot region to which the optional site belongs is the same as or covers at least one hotspot region determined based on the first clustering result.

[0075] Specifically, with the clustering algorithm, neighborhood radius, and minimum number of sample points remaining unchanged, the output result of the input layer constructed based on the existing charging piles corresponding to each hotspot area after clustering analysis is consistent with the first clustering result. Therefore, if the hotspot area to which the potential charging station belongs has the same coordinate range as a certain hotspot area in the first clustering result, it indicates that the potential charging station is located within that hotspot area, and thus the potential charging station can be identified as a candidate charging station. If the hotspot area to which the potential charging station belongs covers at least one hotspot area in the first clustering result, it indicates that the potential charging station is close to a hotspot area and has been included in that hotspot area, thereby expanding the range of the hotspot area, and thus the potential charging station can also be identified as a candidate charging station. In this way, candidate charging stations can be quickly identified based on the same clustering algorithm, while also uncovering potential areas.

[0076] For example, the first clustering result includes hotspot areas Z1 and Z2. However, when a batch of optional construction sites is introduced for clustering, Z1 and Z2 are covered by Z3 in the second clustering result. This indicates that the optional construction site is located between Z1 and Z2 and has the opportunity to share the charging demand of the two hotspot areas, thus belonging to a potential area.

[0077] It is worth noting that in other embodiments of this application, different second clustering results can be obtained by dynamically adjusting a preset number, and whether an optional construction site should be used as a candidate construction site can be determined based on the clustering situation of the optional construction site under each second clustering result. In one example, different preset numbers can be used to obtain corresponding second clustering results, and whether an optional construction site can be used as a candidate construction site can be determined based on the distance of the optional construction site to the existing charging pile with the highest utilization rate in the hotspot area under each second clustering result, and the utilization rate of the nearest existing charging pile.

[0078] For example, the preset quantities can be set to 1 and 3 respectively. The batch corresponding to the optional site D1 is batch B1 which only contains D1, and batch B2 which contains D1, D2 and D3. D2 and D3 are randomly selected from other optional sites, or they can be selected based on permutation and combination. It can be understood that when the optional sites of each batch are selected based on permutation and combination, the number of batches containing D1 is related to the total number of optional sites. In this way, more second clustering results can be obtained to explore more possibilities.

[0079] Suppose that in the second clustering result corresponding to batch B1, D1 is identified as noise, therefore D1 cannot be used as a candidate site. However, in the second clustering result corresponding to batch B2, D1 is included in the hotspot region Z4, and the hotspot region Z4 covers Z5 in the first clustering result. It can be seen that due to the addition of D2 and D3, the clustering distribution has been differentiated. Based on this, D1 can be identified as a candidate region. However, in order to prevent the preset number from being set too large, which would cause the hotspot region output in the second clustering result to be much larger than the hotspot region in the first clustering result and deviate from the actual needs, it is possible to further determine whether D1 should be used as a candidate site by checking whether the distance between D1 and the existing charging pile with the highest utilization rate in its hotspot region or the utilization rate of the nearest existing charging pile meets the preset conditions.

[0080] Based on this, by dynamically adjusting the preset number, the hotspot areas to which each optional site belongs can be obtained under different preset numbers. Combined with the utilization rate of existing charging piles in the hotspot areas, candidate sites can be determined to explore more potential demand areas.

[0081] S104. Create virtual charging piles for each candidate site and collect user demand data based on each virtual charging pile.

[0082] In one implementation, virtual charging piles can be created at each candidate site on various charging pile query software, platforms, and map query software. The number of times each virtual charging pile is queried can be determined based on the user access data of each software platform, thereby identifying the user demand data for each virtual charging pile.

[0083] Specifically, virtual charging stations can be created on the maps of various query software based on the geographical coordinates of the candidate charging stations. These virtual charging stations can be visible to users or not. When visible, they can be presented as non-idle charging stations to avoid inconveniencing users. After creating the virtual charging stations, the number of virtual charging stations included in the query results pushed to users based on their search criteria can be collected to determine the corresponding user demand data.

[0084] For example, when a user searches for charging stations near address A using the software, the software performs the search based on both real and virtual charging station information, and then pushes information on charging stations near A to the user. If the pushed information includes virtual charging stations, it is recorded as a user demand data point. In this way, the software can directly accumulate user demand data for virtual charging stations while determining the search results, and can provide corresponding search records. Compared to matching candidate stations based on search records, this method better ensures the authenticity and accuracy of the data.

[0085] S105 selects the target charging station from various virtual charging stations based on user demand data.

[0086] In one implementation, virtual charging piles whose user demand data meets preset conditions can be directly selected from various virtual charging piles and identified as target charging piles. These preset conditions include that the proportion of user demand to total user demand is not less than a preset proportion threshold, or that the number of user demands is not less than a preset demand threshold. The preset proportion threshold and preset demand threshold can be determined based on the minimum proportion and minimum number of user demands among existing charging piles in the target area that meet investment expectations in terms of return on investment. This ensures, to a certain extent, that the expected return on investment for the target charging pile meets expectations and mitigates risks. The return on investment for existing charging piles can be calculated based on utilization rate and related costs, including equipment energy consumption in the energy efficiency attribute.

[0087] In other embodiments of this application, the target charging pile can be selected based on the predicted investment return of each virtual charging pile, provided that the predicted investment return meets the investment expectations. Please refer to... Figure 4 The method for obtaining the predicted investment return of virtual charging piles specifically includes the following steps.

[0088] S401: Obtain the energy efficiency attributes and coordinates of all existing charging piles within the hotspot area to which the virtual charging pile belongs.

[0089] The coordinates of the existing charging piles refer to the coordinates of their installation locations.

[0090] S402, based on the utilization rate and coordinates in the energy efficiency attributes of each existing charging pile, constructs a utilization rate prediction model.

[0091] The utilization rate prediction model is used to predict the utilization rate of charging piles at a certain coordinate location based on the mapping relationship between coordinates and utilization rate. Specifically, it can be obtained by selecting modeling methods such as linear regression, logistic regression, decision tree, random forest, and neural network, and training the model based on the utilization rate and coordinates of the energy efficiency attributes of existing charging piles in the hotspot area.

[0092] It is worth noting that, in order to improve the accuracy of the prediction, the utilization rate prediction model is built based on hotspot areas. That is, one utilization rate prediction model corresponds to one hotspot area, which is used to predict the utilization rate of virtual charging piles belonging to that hotspot area.

[0093] S403 uses the coordinates of the virtual charging pile as the input layer to calculate the utilization rate prediction model and obtain the utilization rate prediction value.

[0094] S404: Based on the equipment energy consumption and coordinates in the energy efficiency attributes of all existing charging piles, an energy consumption prediction model is constructed.

[0095] Specifically, even charging piles of the same model may exhibit different energy consumption under varying environmental and installation conditions. Therefore, constructing an energy consumption prediction model based on the energy consumption and coordinates of all existing charging piles' energy efficiency attributes can reveal the impact of geographical location on energy consumption, thus enabling more accurate predictions of the energy consumption of virtual charging piles. In implementation, modeling methods such as linear regression, logistic regression, decision trees, random forests, and neural networks can be used, and the model can be trained based on the energy consumption and coordinates of existing charging piles within the target area to obtain the energy consumption prediction model.

[0096] It is worth noting that in other variant embodiments of this application, other characteristic parameters, such as equipment power and line length, can be introduced into the construction of the equipment energy consumption prediction model to improve prediction accuracy.

[0097] S405 uses the coordinates of the virtual charging pile as the input layer to calculate the energy consumption prediction model and obtain the predicted energy consumption value.

[0098] S406 estimates the return on investment cycle of virtual charging piles based on utilization rate forecasts and energy consumption forecasts.

[0099] In practical implementation, the charging service fee revenue of virtual charging piles can be estimated based on the utilization rate prediction value. The energy consumption prediction value of the equipment is added when calculating operating costs. Then, combined with other revenues such as government subsidies and advertising revenue, the annual revenue is calculated. Finally, combined with other costs, the annual operating cost and initial investment cost are calculated, and the investment payback period is determined. It is understood that, based on the embodiments of this application, the utilization rate prediction value and energy consumption prediction value of each virtual charging pile can be obtained for calculating investment revenue and costs, respectively. The specific calculation method can be set according to actual needs, and this application is not limited thereto.

[0100] It is worth noting that in other embodiments of this application, virtual charging piles that meet the relevant requirements can be determined by combining user demand data and the predicted investment returns of each virtual charging pile, and then used as target charging piles.

[0101] S106, Generate a charging pile layout plan based on the target charging piles.

[0102] Specifically, candidate construction sites corresponding to the target charging pile can be identified as target construction sites for the purpose of constructing new charging piles.

[0103] In implementation, the specific number of charging piles to be installed at each target site can be further planned. In one example, the number of charging piles can be determined based on the service saturation level of the hotspot area where the target site is located. The saturation level can be determined based on factors such as the longest daily service duration of existing charging piles, the longest service duration of the nearest existing charging pile at the target site, and the total utilization rate of existing charging piles during peak hours. The higher the saturation level, the more charging piles are planned to be installed.

[0104] In another example, the number of charging piles can be planned based on the predicted utilization rate of the target charging stations. Specifically, the total number of charging piles planned to be built can be determined first, and then weights can be assigned according to the predicted utilization rate of each target charging station to ultimately determine the planned number of charging piles for each target charging station. The higher the predicted utilization rate, the greater the weight, and the more charging piles will be planned. The predicted utilization rate of the target charging station is the predicted utilization rate of the corresponding virtual charging pile.

[0105] Based on the above technical solution, the location and utility attributes of existing charging piles within the target area can be obtained through a public query platform. This information can then be used to generate a layout plan for new charging piles, ensuring the rationality and practicality of the layout plan. Furthermore, since the data on existing charging piles can be obtained directly and in real-time from the public query platform, the authenticity and timeliness of the data are guaranteed, providing a solid data foundation for planning analysis and ensuring the accuracy and effectiveness of the analysis process.

[0106] Furthermore, by identifying candidate sites based on hotspot areas, it can be ensured that the final target sites meet certain user needs. This not only alleviates the charging pressure on users in the area but also guarantees the return on investment for investors. Consequently, it helps alleviate users' charging anxiety and optimizes industry returns to meet the requirements of healthy city construction.

[0107] In other embodiments of this application, potential investment areas can also be identified based on noise points in the first clustering results. Specifically, the charging demand in the area can be determined based on the utilization rate of existing charging piles corresponding to the noise points. If the utilization rate of an existing charging pile is higher than the average level, the area where the existing charging pile is located can be identified as a potential area. Thus, sites within a preset distance from existing charging piles can be selected from the available construction sites as candidate construction sites. This allows for early positioning in potential areas.

[0108] Furthermore, this application also provides an electronic device, which includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor. When the program or instructions are executed by the processor, they implement the method in any of the implementations in this application. The processor may be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), a graphics processing unit (GPU), or one or more integrated circuits, used to execute related programs to implement the method in any of the implementations in this application.

[0109] The processor can also be an integrated circuit electronic device with signal processing capabilities. In implementation, each step of the method in any of the embodiments of this application can be completed by the integrated logic circuitry in the processor's hardware or by software instructions.

[0110] The aforementioned processor can also be a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly manifested as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor.

[0111] The software module can reside in a mature storage medium in this field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in the memory. The processor reads information from the memory and, in conjunction with its hardware, performs the functions required by the units included in the data processing apparatus of this application embodiment, or executes the methods in any implementation of this application embodiment.

[0112] Those skilled in the art will understand that all or part of the steps in the above-described embodiments can be implemented by a program instructing related hardware. This program is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0113] The above are all preferred embodiments of this application and are not intended to limit the scope of protection of this application. Therefore, all equivalent changes made in accordance with the structure, shape and principle of this application should be covered within the scope of protection of this application.

Claims

1. A spatial layout method for charging piles for new energy vehicles, characterized in that, The method is applied to a new energy vehicle charging pile operation and management platform, and includes the following steps: Obtain the location attributes of existing charging piles within the target area; Based on the first clustering results of the location attributes of each existing charging pile, hotspot areas are determined; Based on the aforementioned hotspot areas and preset site selection strategies, candidate sites are determined. Virtual charging piles are created for each of the candidate construction sites, and user demand data is collected based on each of the virtual charging piles; Based on the user demand data, target charging piles are selected from each of the virtual charging piles, and a charging pile layout plan is generated according to the target charging piles. The process of obtaining the location attributes of existing charging piles within the target area includes: Determine the geographical location information of the existing charging piles; The location area corresponding to the aforementioned geographical location information is obtained by querying the map and used as the first feature information; If the location area is a roadside parking space, other feature information that is within a preset range from the existing charging pile is obtained as the second feature information; If the location area is a non-road parking space, other feature information that is within a preset range from the location area is obtained as the second feature information; The location attributes of the existing charging pile are generated based on the first feature information and the second feature information; The step of determining the hotspot area based on the first clustering result of the location attributes of each of the existing charging piles includes performing clustering analysis on the coordinates corresponding to each feature information in the location attributes of each of the existing charging piles based on the DBSCAN algorithm. The method for selecting target charging piles from the virtual charging piles based on the user demand data further includes obtaining the predicted investment returns of each virtual charging pile and selecting the virtual charging piles whose predicted investment returns meet the investment expectations as target charging piles.

2. The method according to claim 1, characterized in that, The target area completely covers and is larger than the site selection planning area.

3. The method according to claim 1, characterized in that, The method further includes acquiring noise points determined by the DBSCAN algorithm and determining hotspot regions based on the noise points.

4. The method according to claim 1, characterized in that, The process of determining candidate sites based on the hotspot areas and preset site selection strategies includes: Divide all available sites into multiple batches; For each batch of optional construction sites, an input layer is constructed based on the coordinates of each optional construction site, the coordinates of each feature information in the location attributes of existing charging piles in each hotspot area, and other parameters used to determine the hotspot area; The DBSCAN algorithm is used to calculate the corresponding second clustering results for each input layer. The hotspot regions to which each of the optional construction sites belongs in the second clustering result are determined. If the hotspot region to which the optional construction site belongs contains the hotspot region, then the optional construction site is determined as a candidate construction site.

5. The method according to claim 1, characterized in that, The method for obtaining the predicted investment return of the virtual charging pile includes: Obtain the energy efficiency attributes and coordinates of all existing charging piles within the hotspot area to which the virtual charging pile belongs; Based on the utilization rate and coordinates of the energy efficiency attributes of each existing charging pile, a utilization rate prediction model is constructed. Using the coordinates of the virtual charging pile as the input layer, the utilization rate prediction model is calculated to obtain the utilization rate prediction value; Based on the equipment energy consumption and coordinates in the energy efficiency attributes of all existing charging piles, an energy consumption prediction model is constructed. Using the coordinates of the virtual charging pile as the input layer, the energy consumption prediction model is calculated to obtain the predicted energy consumption value; The investment return period of the virtual charging pile is estimated based on the predicted utilization rate and the predicted energy consumption.

6. A new energy vehicle charging pile operation and management platform, characterized in that, The platform is used to implement the method according to any one of claims 1 to 5.

7. An electronic device, characterized in that, It includes a processor, a memory, and a program or instructions stored in the memory and executable on the processor, wherein the program or instructions, when executed by the processor, implement the method as described in any one of claims 1-5.

Images