Battery swapping station site selection method and device, storage medium and computer program product

Abstract

This application discloses a method, apparatus, storage medium, and computer program product for selecting the location of a battery swapping station. The method includes: acquiring target data for each of multiple regional units within a first region, the target data including factor data that can influence battery swapping order data; performing battery swapping demand analysis on the regional information of each regional unit using a target battery swapping demand analysis model to determine the battery swapping order demand data for each regional unit; clustering the multiple regional units based on the battery swapping order demand data for each regional unit to obtain at least one cluster region; determining candidate cluster regions from the at least one cluster region based on the battery swapping order demand data corresponding to each cluster region; determining candidate addresses for the battery swapping station based on the cluster centers in the candidate cluster regions; and then making a location decision for the candidate addresses using a decision model with profit as the optimization objective, thereby improving the rationality of the battery swapping station location and increasing the utilization rate of the battery swapping station.

Description

Technical Field

[0001] This application relates to the field of battery swapping station planning technology, and in particular to a site selection method, apparatus, storage medium and computer program product for battery swapping stations. Background Technology

[0002] As a means of replenishing energy for electric vehicles, battery swapping stations can effectively solve the range anxiety problem and enable long-distance driving. However, improper site selection and planning for battery swapping stations not only makes swapping difficult but also leads to low station utilization and resource waste.

[0003] Therefore, improving the rationality of the site selection and planning of battery swapping stations is of great significance to improving the utilization rate of battery swapping stations. Summary of the Invention

[0004] This application provides a method, apparatus, storage medium, and computer program product for selecting a site for a battery swapping station, which can improve the rationality of the site selection and increase the utilization rate of the battery swapping station.

[0005] Firstly, this application provides a method for selecting the location of a battery swapping station. The method includes: acquiring target data for each of multiple regional units within a first region, the target data including factor data that can influence battery swapping order data; performing battery swapping demand analysis on the regional information of each regional unit using a target battery swapping demand analysis model to determine the corresponding battery swapping order demand data for each regional unit, wherein the target battery swapping demand analysis model is used to characterize the correlation between regional information and battery swapping order demand data; clustering the multiple regional units according to the battery swapping order demand data corresponding to each regional unit to obtain at least one cluster region; determining candidate cluster regions from the at least one cluster region based on the battery swapping order demand data corresponding to each cluster region; and determining candidate addresses for the battery swapping station based on the cluster centers in the candidate cluster regions.

[0006] In this embodiment, regional units are clustered based on their order demand data to aggregate regional units with the same order demand. Then, battery swapping demand analysis is performed on the clustered areas obtained after the aggregation of regional units to determine candidate clustered areas where battery swapping stations can be created. This enables the battery swapping stations to provide battery swapping services to vehicles in regional units with the same demand, solving the problem of resource waste caused by the over-concentration of battery swapping stations and the problem of difficulty in battery swapping caused by the over-sparseness of battery swapping stations.

[0007] In some embodiments, clustering multiple regional units based on battery swapping order demand data corresponding to each regional unit to obtain at least one clustered region includes: acquiring multidimensional feature data corresponding to each regional unit, wherein the multidimensional feature data corresponding to each regional unit includes the location information of the corresponding regional unit and the battery swapping order demand data corresponding to the corresponding regional unit; determining the distance between every two regional units in the multiple regional units based on the multidimensional feature data corresponding to the multiple regional units, wherein the distance between every two regional units is used to characterize the difference between the multidimensional feature data of every two regional units; and clustering the multiple regional units based on the distance between every two regional units in the multiple regional units to obtain at least one clustered region.

[0008] By clustering regional units based on their location information and battery swapping order demand data, regional units within the same cluster not only have the same or similar battery swapping needs, but are also spatially similar, thereby improving the rationality of regional unit clustering and providing a foundation for accurate recommendations for battery swapping station site selection.

[0009] In some embodiments, clustering multiple regional units based on the distance between every two regional units to obtain at least one clustered region includes: determining a clustering range with a first regional unit as the center and a preset clustering radius as the search radius, wherein the first regional unit is any one of the multiple regional units; determining at least one second regional unit from the other regional units within the clustering range whose distance is within a preset distance range based on the distance between the first regional unit and other regional units within the clustering range; and determining the region composed of the first regional unit and at least one second regional unit as a clustered region if the number of at least one second regional unit is greater than a preset number.

[0010] Clustering regional units within the clustering range can efficiently aggregate regional units with the same or similar battery swapping needs, improve clustering accuracy, and provide a basis for the rational site selection of subsequent battery swapping stations.

[0011] In some embodiments, determining the distance between any two regional units in the plurality of regional units based on the multidimensional feature data corresponding to the plurality of regional units includes: normalizing the multidimensional feature data corresponding to the third regional unit and the multidimensional feature data corresponding to the fourth regional unit respectively to obtain the first feature data and the second feature data, wherein the third regional unit and the fourth regional unit are any two of the plurality of regional units; and calculating the distance between the first feature data and the second feature data.

[0012] By normalizing the multidimensional feature data of regional units, the clustering effect can be effectively improved, thereby enhancing the rationality of the site selection for battery swapping stations.

[0013] In some embodiments, before performing battery swapping demand analysis on the regional information of each regional unit using the target battery swapping demand analysis model and determining the battery swapping order demand data corresponding to each regional unit, the target battery swapping demand analysis model associated with the first region is searched from the association relationship between the regional unit and the battery swapping demand analysis model.

[0014] Using a target battery swapping demand analysis model that matches the first region to analyze the battery swapping demand of regional units within the first region can improve the accuracy of the battery swapping demand analysis, thereby improving the accuracy of battery swapping station site selection.

[0015] In some embodiments, the site selection method for battery swapping stations further includes: if there is no target battery swapping demand analysis model associated with the first region in the association relationship, obtaining a second region with a similarity greater than a preset similarity to the first region; and determining the battery swapping demand analysis model associated with the second region as the target battery swapping demand analysis model.

[0016] Since the regional information of the first region and the second region is similar, using the battery swapping demand analysis model corresponding to the second region to analyze the battery swapping demand of the regional units contained in the first region can accurately determine the battery swapping demand of each regional unit, thereby improving the accuracy of the site selection recommendation for battery swapping stations in areas where no stations have been built.

[0017] In some embodiments, the target battery swapping demand analysis model is constructed as follows: an initial demand analysis model and sample data are obtained, wherein the sample data includes sample data of a sample area and sample battery swapping order demand data of the corresponding sample area; the sample data of the sample area is input into the initial demand analysis model; the demand analysis results output by the initial demand analysis model are obtained; based on the demand analysis results and the sample battery swapping order demand data of the corresponding sample area, the model parameters of the initial demand analysis model are adjusted to obtain the target battery swapping demand analysis model.

[0018] A target battery swapping demand analysis model is constructed using regional information corresponding to the sample area and battery swapping order demand data. This model enables targeted battery swapping demand analysis of the sample area, improving the accuracy of the analysis and thus enhancing the rationality and accuracy of battery swapping station site selection recommendations.

[0019] In some embodiments, before determining candidate cluster regions from at least one cluster region based on the battery swapping order demand data corresponding to each cluster region, the battery swapping order demand data of the regional units contained in each cluster region are weighted and calculated to obtain the battery swapping order demand data corresponding to each cluster region.

[0020] By weighted summing of the battery swapping order demand data of regional units, the battery swapping order demand data of the cluster area is obtained. This reduces the risk that abnormalities in the battery swapping order demand data of regional units will lead to abnormalities in the battery swapping order demand data of the cluster area, thereby improving the stability and accuracy of the battery swapping order demand data of the cluster area.

[0021] In some embodiments, determining candidate cluster regions from at least one cluster region based on the battery swapping order demand data corresponding to each cluster region includes: sorting the cluster regions in descending order of the battery swapping order demand data corresponding to each cluster region to obtain a cluster region sequence; and selecting the cluster regions ranked in the top N positions from the cluster region sequence to obtain candidate cluster regions, where N is a positive integer.

[0022] By sorting cluster regions according to battery swapping order demand data, and selecting cluster regions with higher battery swapping demand as candidate cluster regions, the battery swapping stations in the candidate cluster regions can fully provide battery swapping services, improve the utilization rate of battery swapping stations, and reduce resource waste.

[0023] In some embodiments, the site selection method for battery swapping stations further includes: inputting the battery swapping order demand data corresponding to the candidate cluster area into the decision model to obtain the target cluster area and the scale of the target battery swapping station.

[0024] By using a decision model to make site selection decisions for candidate cluster areas, the created battery swapping stations can be of an appropriate scale, thereby improving their utilization rate.

[0025] In some embodiments, the decision model is constructed as follows: a battery swapping profit function corresponding to the decision model is constructed based on the revenue data and cost data of the battery swapping station; multiple constraints of the decision model are constructed based on the battery swapping order supply data, battery swapping order demand data, and the power supply of the target cluster area, wherein the battery swapping order supply data is the order data for providing battery swapping services to the target battery swapping station; and the decision model is constructed based on the battery swapping profit function and multiple constraints.

[0026] A decision-making model is constructed with the profit of the battery swapping station as the optimization objective. Since profit = revenue - cost, the decision-making model in this application embodiment takes into account both cost and revenue, that is, it uses multiple objectives to make site selection decisions for the battery swapping station, thereby improving the rationality of the selection decision.

[0027] In some embodiments, multiple constraints include: the supply data of battery swapping orders is less than the demand data of battery swapping orders; the ratio between the supply data of battery swapping orders and the demand data of battery swapping orders is greater than a preset ratio; the supply data of battery swapping orders at a battery swapping station is less than the supply data of battery swapping orders at the corresponding battery swapping scale; the power demand data of a battery swapping station is less than the power supply of the target cluster area; and the number of battery swapping stations in the target cluster area is less than or equal to a preset number.

[0028] By constructing constraints on the decision-making model to ensure that the values ​​of the decision variables are feasible in actual operation, the feasibility of the decision-making model is improved, and the rationality of the site selection decision is also guaranteed.

[0029] In some embodiments, revenue data includes battery swapping revenue corresponding to each battery swapping order, and cost data includes land occupation cost corresponding to the target cluster area, battery swapping cost of the target battery swapping station, and distance cost corresponding to the target battery swapping station. The battery swapping profit function for the decision model is constructed based on the revenue and cost data of the battery swapping stations, including: constructing a cost function based on the land occupation cost, battery swapping cost, and distance cost of the target cluster area; constructing a revenue function based on the battery swapping revenue corresponding to each battery swapping order and the battery swapping supply of the battery swapping stations in the target cluster area; and constructing a battery swapping profit function based on the cost function and the revenue function.

[0030] By constructing a cost function and a revenue function, and then constructing a battery swapping profit function, it can be seen that in this embodiment of the application, cost and revenue are used as objectives when making site selection decisions in order to improve the rationality of the selection decision.

[0031] In some embodiments, the decision model is constructed as follows: a cost function corresponding to the decision model is constructed based on the cost data of the battery swapping station; a battery swapping profit function corresponding to the decision model is constructed based on the revenue data and cost data of the battery swapping station; multiple constraints of the decision model are constructed based on the battery swapping order supply data, the battery swapping order demand data, and the power supply of the target cluster area, wherein the battery swapping order supply data is the order data for providing battery swapping services to the target battery swapping station; and the decision model is constructed based on the battery swapping profit function, the cost function corresponding to the battery swapping station, and multiple constraints.

[0032] A decision-making model is constructed with the profit and cost of battery swapping stations as optimization objectives. This model takes into account both costs and revenues, thus improving the rationality of the site selection decision by using multiple objectives.

[0033] Secondly, this application also provides a site selection device for a battery swapping station, the device comprising: a data acquisition module, used to acquire target data for each of multiple regional units contained in a first region, the target data including factor data that can affect battery swapping order data; a demand analysis module, used to perform battery swapping demand analysis on the regional information of each regional unit using a target battery swapping demand analysis model, and determine the battery swapping order demand data corresponding to each regional unit, wherein the target battery swapping demand analysis model is used to characterize the correlation between regional information and battery swapping order demand data; a cluster analysis module, used to cluster multiple regional units according to the battery swapping order demand data corresponding to each regional unit, to obtain at least one cluster region; a cluster determination module, used to determine candidate cluster regions from the at least one cluster region according to the battery swapping order demand data corresponding to each cluster region; and a site selection module, used to determine the candidate address of the battery swapping station according to the cluster centers in the candidate cluster regions.

[0034] Fourthly, this application provides a readable storage medium storing computer program instructions that, when executed by a processor, implement the site selection method for the battery swapping station as described in the first aspect.

[0035] Fifthly, this application provides a computer program product in which the instructions, when executed by a processor of an electronic device, cause the electronic device to perform the site selection method for a battery swapping station as described in the first aspect.

[0036] The above description is only an overview of the technical solution of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this application more obvious and understandable, specific embodiments of this application are given below. Attached Figure Description

[0037] The features, advantages, and technical effects of exemplary embodiments of this application will now be described with reference to the accompanying drawings.

[0038] Figure 1 A flowchart illustrating a method for selecting a battery swapping station according to an embodiment of this application;

[0039] Figure 2 This is a flowchart illustrating the determination of a target battery swapping demand analysis model according to one embodiment of this application.

[0040] Figure 3 This is a flowchart illustrating the construction of a target battery swapping demand analysis model according to one embodiment of this application.

[0041] Figure 4 This is a flowchart illustrating the determination of a cluster region according to an embodiment of this application;

[0042] Figure 5 This is a flowchart of a clustering method according to an embodiment of this application;

[0043] Figure 6 This is a flowchart illustrating the determination of battery swapping needs in a cluster area according to one embodiment of this application.

[0044] Figure 7 This is an overall flowchart of a battery swapping station site selection recommendation according to one embodiment of this application;

[0045] Figure 8 A flowchart illustrating site selection planning for one embodiment of this application;

[0046] Figure 9 This is a flowchart illustrating the construction of a decision model according to one embodiment of this application;

[0047] Figure 10 This is a flowchart illustrating the determination of the battery swapping profit function according to one embodiment of this application.

[0048] Figure 11 This is a flowchart illustrating the construction of a decision model according to one embodiment of this application;

[0049] Figure 12 This is an overall flowchart of the site selection decision for a battery swapping station according to one embodiment of this application;

[0050] Figure 13 This is a schematic diagram of a site selection device for a battery swapping station according to another embodiment of this application.

[0051] The accompanying drawings are not necessarily drawn to scale. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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, 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.

[0053] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0054] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0055] In this application, the term "embodiment" is used to mean that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application can be combined with other embodiments.

[0056] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0057] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple groups" refers to two or more (including two groups), and "multiple pieces" refers to two or more (including two pieces).

[0058] In the description of the embodiments in this application, the technical terms "center," "longitudinal," and "lateral" are used.

[0059] Length, Width, Thickness, Top, Bottom, Front, Back, Left, Right

[0060] "Vertical", "Horizontal", "Top", "Bottom", "Inner", "Outer", "Clockwise", "Counterclockwise"

[0061] The orientation or positional relationship indicated by "axial", "radial", "circumferential", etc., is based on the orientation or positional relationship shown in the accompanying drawings and is only for the purpose of facilitating the description of the embodiments of this application and simplifying the description. It is not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation on the embodiments of this application.

[0062] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0063] Battery swapping stations are energy stations that provide rapid battery replacement for electric vehicles. During charging, the battery is not mounted on the vehicle but is charged on a charging rack at the station. Lithium-ion batteries have advantages such as high energy density, high voltage, wide operating temperature range, and long storage life, and are commonly used as the power batteries in vehicles.

[0064] During battery swapping, the vehicle enters the swapping station, where the battery swapping equipment removes the vehicle's power battery and immediately replaces it with another power battery. Swapping stations allow vehicles to quickly replenish their power without having to wait at the station.

[0065] The site selection and planning of battery swapping stations mainly includes two aspects: site recommendation and site selection decision. Site recommendation mainly determines candidate sites for building battery swapping stations, while site selection decision mainly determines the scale of the battery swapping stations.

[0066] Existing site selection recommendations are geared towards cities with existing battery swapping stations. These recommendations rely on identifying commonalities among existing stations to suggest locations for new stations. However, this approach heavily depends on human experience, making it unsuitable for widespread adoption. Existing stations can only serve as data references; the limitations of quantifying demand indicators for new stations are significant, and the method is not applicable to cities without existing stations.

[0067] For site selection decisions, existing site selection decision schemes use operations research models to solve for the location of the battery swapping station with the minimum total cost. However, the objectives of site selection are usually not only cost factors, but also other factors such as revenue. Moreover, the constraints of existing site selection decision schemes are not sound, with some constraints lacking, and they do not take into account the actual situation of battery swapping station construction, thus leading to unreasonable site selection decisions, reduced utilization of battery swapping stations, and waste of resources.

[0068] To address the problems existing in existing site selection recommendation and decision-making schemes, this application clusters regional units based on their battery swapping demand, thereby making the distribution of clustered regions more closely match the actual scenario. Then, the clustered regions are sorted from highest to lowest according to battery swapping demand, and candidate clusters with higher demand are recommended for building battery swapping stations. Next, decisions are made regarding candidate clusters based on at least two factors: land cost, regional power supply capacity, regional demand capacity, existing battery swapping stations, and the scale (or capacity) of existing stations, with profit as the optimization objective.

[0069] In the site selection recommendation scheme of this application, the site selection of battery swapping stations is recommended based on different regions (regional units and / or cluster regions), which is also applicable to cities where battery swapping stations have not yet been built. In the site selection decision scheme, profit is used as the optimization objective, which essentially considers both cost and revenue factors. That is, in this application, the site selection decision is achieved through a multi-objective approach, thereby making the site selection decision of battery swapping stations more reasonable.

[0070] The following describes the site selection method for battery swapping stations provided in the embodiments of this application.

[0071] In one embodiment, Figure 1 A flowchart of the site selection method for a battery swapping station provided in this application embodiment is shown. This method can be applied to a site selection decision system, which may include a data acquisition unit and a data processing unit. The data acquisition unit can collect relevant data of the city where the battery swapping station needs to be built and / or relevant data of other cities (e.g., cities with similar economies and environments) that are related to the city where the battery swapping station needs to be built through various means (e.g., web crawling). The data processing unit is used to analyze the data collected by the data acquisition unit to determine the site for the battery swapping station and the scale of the battery swapping station.

[0072] like Figure 1 As shown, the method may include the following steps S101 to S105:

[0073] Step S101: Obtain the target data of each of the multiple regional units contained in the first region.

[0074] In step S101, the first region is a region with battery swapping needs, such as a city with battery swapping needs. The first region can be a region with existing battery swapping stations or a region without existing stations. The first region can include multiple regional units, which can be obtained by dividing the first region using a preset grid map. The grid map can be a map with the same shape as the first region and multiple grids of the same size. The grid density in the grid map can be determined based on the geographical characteristics of the first region and the actual requirements for data processing efficiency. A higher grid density results in smaller grid sizes and a greater number of corresponding regional units, leading to more accurate battery swapping station site recommendations, but requiring a larger amount of data analysis and slower data processing speed. Conversely, a lower grid density results in larger grid sizes and a smaller number of corresponding regional units, leading to less accurate battery swapping station site recommendations, but requiring a smaller amount of data analysis and faster data processing speed.

[0075] In step S101, the target data includes factor data that can influence battery swapping order data. Battery swapping order data refers to data related to the battery swapping service provided by the battery swapping station. Each battery swapping service provided by a station generates one battery swapping order. Battery swapping order data can include the amount of battery swapped (e.g., battery capacity) and the number of battery swapping orders. Factor data includes three types: vehicle-to-everything (V2X) factors, Point of Interest (POI) factors, and other factors. Vehicle-to-everything (V2X) factors characterize concentrated areas of vehicle activity, such as the vehicle's permanent residence. These factors are crucial for understanding the demand for battery swapping stations. POI factors characterize the surrounding environment and demand of vehicles (e.g., electric vehicles, new energy vehicles) around the battery swapping station. These are important indicators for assessing the attractiveness of the station, such as passenger flow index, new energy vehicle traffic, the resident population index with new energy vehicles, the working population index with new energy vehicles, and the number of new energy vehicles in operation. Other factors characterize the competitive relationship between battery swapping stations and the impact of geographical distribution on battery swapping order data, such as the number of surrounding battery swapping stations.

[0076] It should be noted that in practical applications, battery swapping order data from existing battery swapping stations within a recent period (e.g., one month) can be used as a research sample for data analysis to identify factors influencing battery swapping order data. For example, battery swapping stations with an average daily number of battery swapping orders exceeding M orders within the past month can be used as the research sample, where M is a positive integer. The factors influencing battery swapping order data are usually the same across different regions, namely the three types of factors mentioned above; however, the weights of these three types of factors vary across different regions.

[0077] Step S102: Use the target battery swapping demand analysis model to analyze the regional information of each regional unit to determine the battery swapping order demand data corresponding to each regional unit.

[0078] In step S102, the target battery swapping demand analysis model is used to characterize the correlation between regional information and battery swapping order demand data. This model analyzes the regional information of each regional unit to obtain the battery swapping order demand data for that unit. The target battery swapping demand analysis model can be trained using machine learning. Different regions may have different battery swapping demand analysis models, primarily differing in the weights of the three factors mentioned above when analyzing regional information. For regions without existing battery swapping stations, battery swapping demand analysis models from other battery swapping regions with similar or identical regional information can be used.

[0079] In step S102, the battery swapping order demand data is used to characterize the demand of the regional unit for the battery swapping station, which may include, but is not limited to, the battery swapping capacity and the address of the battery swapping station.

[0080] Step S103: Based on the battery swapping order demand data corresponding to each regional unit, cluster multiple regional units to obtain at least one clustered region.

[0081] In step S103, a density clustering algorithm can be used to cluster multiple regional units to obtain at least one clustered region. The density clustering algorithm can divide high-density regions into clusters and can detect clusters of arbitrary shapes in noise. In this embodiment, clustering is performed based on the battery swapping order demand data of the regional units, thereby aggregating regional units with the same or similar battery swapping needs together; that is, a clustered region contains regional units with the same or similar battery swapping needs.

[0082] It should be noted that by aggregating regional units with the same order demand, the battery swapping stations can provide battery swapping services to vehicles within the same regional units, thus solving the problem of resource waste caused by overly concentrated battery swapping stations and the problem of difficulty in battery swapping caused by overly sparse battery swapping stations.

[0083] Step S104: Based on the battery swapping order demand data corresponding to each cluster region, determine the candidate cluster region from at least one cluster region.

[0084] In step S104, the battery swapping order demand data for each cluster region can be determined by the battery swapping order demand data of the regional units contained in the cluster region. For example, the battery swapping order demand data for a cluster region can be the sum or weighted sum of the battery swapping order demand data of the regional units it contains, or the median, mode, etc.

[0085] In addition, in step S104, the candidate cluster area can be a cluster area with high battery swapping demand in at least one cluster area, or it can be determined according to actual needs. For example, if two cluster areas are adjacent and a large-scale battery swapping station can meet the needs of both areas, then one of the two cluster areas can be determined as a candidate cluster area.

[0086] Step S105: Determine the candidate addresses of the battery swapping stations based on the cluster centers in the candidate cluster regions.

[0087] In step S105, after determining the candidate cluster regions, the location of the cluster center of the candidate cluster region is the candidate address for creating a battery swapping station. The cluster center of the candidate cluster region can be a regional unit located at the cluster center. In this case, the center point of that regional unit, or a location that meets the conditions for creating a battery swapping station, is the candidate address for the station. Alternatively, if two cluster regions are adjacent, and building a large-scale battery swapping station can meet the needs of both regions, then one of the two cluster regions can be determined as a candidate cluster region, and its cluster center can be used as the candidate address for the battery swapping station. Alternatively, the candidate address for the battery swapping station can be determined from other locations within the two candidate cluster regions based on actual needs.

[0088] Based on the scheme defined in steps S101 to S105 above, it can be understood that in this embodiment of the application, the regional units are clustered according to the order demand data of the regional units to aggregate regional units with the same order demand. Then, the battery swapping demand analysis is performed on the clustered areas obtained after the aggregation of regional units to determine the candidate clustered areas that can create battery swapping stations. This enables the battery swapping stations to provide battery swapping services for vehicles in regional units with the same demand, solving the problem of resource waste caused by the over-concentration of battery swapping stations and the problem of difficulty in battery swapping for vehicles caused by the over-sparseness of battery swapping stations.

[0089] The implementation process of the method provided in the embodiments of this application is described below.

[0090] After obtaining the target data for each regional unit, a demand analysis needs to be performed on each regional unit. In this embodiment, a target battery swapping demand analysis model can be used to realize the battery swapping demand analysis of the regional unit.

[0091] In this embodiment of the application, before performing battery swapping demand analysis on the regional information of each regional unit using the target battery swapping demand analysis model and determining the battery swapping order demand data corresponding to each regional unit, the target battery swapping demand analysis model associated with the first region is searched from the association relationship between the regional unit and the battery swapping demand analysis model.

[0092] In one embodiment, such as Figure 2 As shown, before conducting battery swapping demand analysis on the regional unit, it is necessary to determine the target battery swapping demand analysis model for the regional unit. This process includes the following steps S201 to S203:

[0093] Step S201: From the association between regional units and battery swapping demand analysis models, find the target battery swapping demand analysis model associated with the first region.

[0094] In this embodiment, each area with existing battery swapping stations has an associated battery swapping demand analysis model. The site selection decision system may also include a data storage unit (e.g., a database) that stores the association between areas and the battery swapping demand analysis models. In practical applications, the data processing unit can query the corresponding battery swapping demand analysis model from the data storage unit based on the area identifier of the first area, and use the retrieved model to perform demand analysis on the area units contained within the first area.

[0095] It should be noted that using a target battery swapping demand analysis model that matches the first region to perform battery swapping demand analysis on the regional units within the first region can improve the accuracy of battery swapping demand analysis, thereby improving the accuracy of battery swapping station site selection.

[0096] Step S202: If there is no target battery swapping demand analysis model associated with the first region in the association relationship, obtain a second region with a similarity greater than the preset similarity to the first region.

[0097] Step S203: The battery swapping demand analysis model associated with the second region is determined as the target battery swapping demand analysis model.

[0098] In steps S202 to S203, for areas where no battery swapping stations have been built, the battery swapping demand analysis model of the area with the most similar geographical, economic, and population characteristics to that area (i.e., the second area) is selected to perform battery swapping demand analysis on the regional units contained in the first area. Since the regional information of the first and second areas is similar, using the battery swapping demand analysis model corresponding to the second area to perform battery swapping demand analysis on the regional units contained in the first area can accurately determine the battery swapping demand of each regional unit, improving the accuracy of battery swapping station site selection recommendations for areas without existing stations.

[0099] In one embodiment, the target battery swapping demand analysis model can be obtained through, for example... Figure 3 It is constructed in the manner shown, as follows: Figure 3 As shown, the process includes the following steps S301 to S304:

[0100] Step S301: Obtain the initial requirements analysis model and sample data.

[0101] In step S301, the sample data includes sample data of the sample area and sample data of battery swapping order demand corresponding to the sample area. The sample data includes factor data that can affect the battery swapping order data of the sample area.

[0102] Step S302: Input the sample data of the sample area into the initial demand analysis model.

[0103] Step S303: Obtain the requirements analysis results output by the initial requirements analysis model.

[0104] Step S304: Based on the demand analysis results and the battery swapping order demand data samples corresponding to the sample area, adjust the model parameters of the initial demand analysis model to obtain the target battery swapping demand analysis model.

[0105] In one example, the data processing unit uses battery swapping order demand data as the target, quantifies and evaluates the impact of the above-mentioned factors on the battery swapping order demand data, establishes the weight of each factor, and builds a battery swapping demand analysis model based on the battery swapping order demand data. This model can be expressed by formula (1):

[0106] b = a * θ (1)

[0107] In formula (1), a * Let θ be the transpose of vector a, where a is a column vector representing the data of each factor, i.e., the independent variable; θ is a column vector representing the weights of each factor; and b is the battery swapping order demand data, which is the dependent variable.

[0108] After completing the construction of the battery swapping demand analysis model, the demand solution weight θ is determined.

[0109] To avoid the problem of ill-conditioned coefficient matrix and overfitting after substituting real data into the above battery swapping demand analysis model, which would lead to unstable solutions, the ridge regression method is used in this embodiment to determine whether the weights obtained are reasonable. That is, in this embodiment, the weight solution problem can be represented by formula (2):

[0110] Aθ=B (2)

[0111] In formula (2), A is a coefficient matrix, representing the true value of each factor data; B is a column vector, representing the true value of battery swapping order demand data; and θ is the weight corresponding to each factor data.

[0112] However, in actual solutions, formula (2) may not have a solution. To avoid this, a regularization term is added during the solution process to improve the stability of the solution values ​​while minimizing the loss function of the battery swapping demand analysis model. This process can be represented by formula (3):

[0113]

[0114] In formula (3), Γ=αE is a constant matrix, where E is the identity matrix and α is a preset coefficient.

[0115] To solve the above optimization problem, gradient descent can be used to iteratively solve for θ. This solution can also be solved quickly using machine learning.

[0116] A target battery swapping demand analysis model is constructed using regional information corresponding to the sample area and battery swapping order demand data. This model enables targeted battery swapping demand analysis of the sample area, improving the accuracy of the analysis and thus enhancing the rationality and accuracy of battery swapping station site selection recommendations.

[0117] Furthermore, after determining the target battery swapping demand analysis model corresponding to the first region, the data processing unit uses the aforementioned target battery swapping demand analysis model to calculate the battery swapping order demand data for each regional unit. For each regional unit, the center point of the regional unit can be used as its location information. For example, the location information of the regional unit can be represented by latitude and longitude.

[0118] Furthermore, after determining the battery swapping order demand data for each regional unit, the data processing unit clusters multiple regional units based on the corresponding battery swapping order demand data to obtain at least one clustered region. For example... Figure 4 As shown, the cluster area can be determined through the following steps S401 to S403:

[0119] Step S401: Obtain the multidimensional feature data corresponding to each region unit.

[0120] In step S401, the multidimensional feature data corresponding to each regional unit includes the location information of the corresponding regional unit and the battery swapping order demand data corresponding to the corresponding regional unit. In this embodiment of the application, the multidimensional feature data can be represented by (x, y, Order), where x and y are the location information of the regional unit, which can be represented by latitude and longitude; and Order is the battery swapping order demand data.

[0121] Step S402: Determine the distance between every two regional units based on the multidimensional feature data corresponding to the multiple regional units.

[0122] In step S402, the distance between every two regional units is used to characterize the difference between the multidimensional feature data between every two regional units. The distance between every two regional units can be Euclidean distance, Manhattan distance, etc.

[0123] Step S403: Based on the distance between every two regional units, cluster the multiple regional units to obtain at least one clustered region.

[0124] In step S403, regional units that meet the preset distance conditions can be aggregated into the same cluster area. For example, regional units that are less than the preset distance threshold can be aggregated together to obtain a cluster area formed by multiple regional units with the same battery swapping needs.

[0125] It should be noted that the regional units are clustered based on their location information and battery swapping order demand data. This ensures that regional units within the same cluster not only have the same or similar battery swapping needs, but are also spatially similar, thereby improving the rationality of regional unit clustering and providing a foundation for accurate recommendations for battery swapping station site selection.

[0126] In one embodiment, the data processing unit may employ, for example... Figure 5 The clustering method shown is used to cluster regional units, such as Figure 5 As shown, the process (i.e., step S403) includes the following steps S501 to S504:

[0127] Step S501: Determine the clustering range using the first region unit as the center and the preset clustering radius as the search radius.

[0128] In step S501, the first regional unit is any one of multiple regional units. The clustering radius can be adjusted multiple times according to actual needs so that the clustering result can reflect the battery swapping needs of each regional unit within the cluster area.

[0129] Step S502: Based on the distance between the first region unit and other region units within the cluster range, determine at least one second region unit whose distance is within a preset distance range from the other region units within the cluster range.

[0130] Step S503: If the number of at least one second region unit is greater than a preset number, the region composed of the first region unit and at least one second region unit is determined as a cluster region.

[0131] In step S503, the number of at least one second region unit can characterize the cluster density, and correspondingly, a preset number is used to characterize the density threshold.

[0132] In steps S501 to S503 above, each region unit is considered as a point. First, a search point is randomly selected. Within the cluster radius corresponding to the search point, other points whose distances meet certain conditions are searched. When the number of searched points reaches a certain threshold, a cluster is formed, i.e., a clustered region. By repeatedly adjusting the cluster radius and density threshold, the clustering results can be optimized, and the clustering effect can be improved.

[0133] By clustering regional units within the clustering range through steps S501 to S503, regional units with the same or similar battery swapping needs can be efficiently aggregated together, improving clustering accuracy and providing a basis for the reasonable site selection of subsequent battery swapping stations.

[0134] In one embodiment, the data processing unit may normalize the multidimensional feature data corresponding to the third region unit and the multidimensional feature data corresponding to the fourth region unit to obtain the first feature data and the second feature data; and then calculate the distance between the first feature data and the second feature data.

[0135] In the above embodiments, the third and fourth region units are any two of the multiple region units. To improve the accuracy of the clustering results, in this embodiment, when calculating the distance between two region units, it is necessary to perform feature engineering data cleaning and dimensionless processing on the multidimensional feature data corresponding to the two region units. As an example, the normalization processing of multidimensional feature data can be achieved through formula (4):

[0136]

[0137] In formula (4), c represents multidimensional feature data, c ′ The data represents the normalized multidimensional feature data, where γ is a preset coefficient and S is the root mean square of the variance. Let S be the variance. 2 For variance, is the mean of the multidimensional feature data, and n is the number of multidimensional feature data.

[0138] It should be noted that in formula (4), the influence of a certain piece of information on the clustering result can be changed by adjusting γ. In this embodiment, the influence of battery swapping order demand data on the clustering result is set to be higher than that of location information on the clustering result.

[0139] After normalizing the multidimensional feature data, formula (5) can be used to calculate the distance between two regional units:

[0140]

[0141] In formula (5), d ijx represents the distance between the i-th region unit and the j-th region unit; i y i Order represents the location information of the i-th region unit. i This represents the battery swapping order demand data for the i-th regional unit; x j y j Order represents the location information of the j-th region unit. j This represents the battery swapping order demand data for the j-th regional unit.

[0142] By normalizing the multidimensional feature data of regional units, the clustering effect can be effectively improved, thereby enhancing the rationality of the site selection for battery swapping stations.

[0143] Furthermore, such as Figure 6 As shown, before determining candidate cluster regions from at least one cluster region based on the battery swapping order demand data corresponding to each cluster region, the data processing unit further performs step S601 to perform weighted calculation on the battery swapping order demand data of the regional units contained in each cluster region to obtain the battery swapping order demand data corresponding to each cluster region.

[0144] In step S601, the data processing unit can perform weighted summation on the battery swapping order demand data of the regional units to obtain the battery swapping order demand data of the cluster area. This reduces the risk that abnormalities in the battery swapping order demand data of the regional units (e.g., too high or too low) will cause abnormalities in the battery swapping order demand data of the cluster area, thereby improving the stability and accuracy of the battery swapping order demand data of the cluster area.

[0145] It should be noted that in practical applications, the calculation method for battery swapping order demand data in cluster areas is not limited to the weighted method. The median, mode, and other feasible methods can also be used for calculation, which will not be listed here.

[0146] Based on the cluster analysis described above, the total demand in the cluster area can be calculated. This value reflects the concentration and scale of demand for battery swapping services in each regional unit.

[0147] Furthermore, after obtaining the battery swapping order demand data corresponding to each cluster region, the data processing unit sorts the cluster regions according to the order of battery swapping order demand data from largest to smallest, thus obtaining a cluster region sequence; from the cluster region sequence, the cluster regions ranked in the top N positions are selected to obtain candidate cluster regions, where N is a positive integer.

[0148] In this embodiment, cluster regions are sorted from highest to lowest according to the size of battery swapping order demand data. This sorting clearly reveals areas with greater potential for battery swapping demand. The top-ranked cluster regions are selected as candidate cluster regions, and available land within these candidate cluster regions is used as alternative battery swapping station locations to provide battery swapping services to users within these candidate cluster regions. Whether land is available in a cluster region needs to be determined based on the current situation; similarly, multiple plots of land may be available in a cluster region.

[0149] By sorting cluster regions according to battery swapping order demand data, and selecting cluster regions with higher battery swapping demand as candidate cluster regions, the battery swapping stations in the candidate cluster regions can fully provide battery swapping services, improve the utilization rate of battery swapping stations, and reduce resource waste.

[0150] This concludes the introduction to the recommended locations for battery swapping stations.

[0151] As an example, Figure 7 The overall flowchart for recommending battery swapping station locations is shown, such as... Figure 7 As shown, the process includes the following steps:

[0152] Step S701: Obtain the first region.

[0153] Step S702: Determine whether a battery swapping station has been built in the first area. If a battery swapping station has been built, proceed to step S704; otherwise, proceed to step S703.

[0154] Step S703: Select a second region with existing battery swapping stations that has the same or similar geographical, economic, and population characteristics as the first region, and determine the battery swapping demand analysis model of the second region as the target battery swapping demand analysis model for each regional unit in the first region.

[0155] Step S704: Obtain the area information of the first area.

[0156] Step S705: Based on the correlation between the regional unit and the battery swapping demand analysis model, determine the target battery swapping demand analysis model corresponding to the first region.

[0157] Step S706: Perform battery swapping demand analysis on each regional unit within the first region using the target battery swapping demand analysis model.

[0158] Step S707: Cluster the regional units with similar battery swapping needs using a density clustering algorithm to obtain at least one cluster region.

[0159] Step S708: Check whether the cluster area division is reasonable. If it is reasonable, proceed to step S709; otherwise, proceed to step S710.

[0160] Step S709: Calculate the battery swapping order demand data for the cluster area, sort the cluster areas, and select the cluster centers of the top-ranked cluster areas as candidate addresses for battery swapping stations.

[0161] Step S710: Adjust the cluster radius and / or the cluster density threshold.

[0162] After recommending suitable locations for battery swapping stations, site planning is also required, such as... Figure 8 As shown, the data processing unit also executes step S801, inputting the battery swapping order demand data corresponding to the candidate cluster area into the decision model to obtain the target cluster area and the scale of the target battery swapping station.

[0163] In step S801, the size of the target battery swapping station can be determined by the number of batteries it has. For ease of description below, here we set m candidate addresses for battery swapping stations, denoted by i; n candidate cluster areas, denoted by j; and β sizes of battery swapping stations to choose from, denoted by k.

[0164] It should be noted that in practical applications, due to differences in the number of stations and optimization goals, the cluster areas may not be sorted according to the total battery swapping demand, and stations may not be built sequentially from high to low demand. For example, if two candidate locations are close to each other, it may be possible to meet the needs of both cluster areas by building only one large-scale battery swapping station.

[0165] In addition, it should be noted that by using a decision model to make site selection decisions for candidate cluster areas, the created battery swapping stations can have an appropriate scale and improve their utilization rate.

[0166] In this application embodiment, the decision model can be determined through battery swapping profits. In one embodiment, the decision model can be determined through... Figure 9 It is constructed in the manner shown, as follows: Figure 9 As shown, the construction of the decision model includes the following steps S901 to S903:

[0167] Step S901: Construct the battery swapping profit function corresponding to the decision model based on the revenue data and cost data of the battery swapping station.

[0168] In step S901, the revenue data includes the battery swapping revenue corresponding to each battery swapping order, and the cost data includes the land occupation cost corresponding to the target cluster area, the battery swapping cost of the target battery swapping station, and the distance cost corresponding to the target battery swapping station.

[0169] Step S902: Based on the battery swapping order supply data, battery swapping order demand data, and the power supply of the target cluster area, construct multiple constraints for the decision model.

[0170] In step S902, the battery swapping order supply data is the order data for providing battery swapping services to the target battery swapping station.

[0171] Step S903: Construct a decision model based on the battery swapping profit function and multiple constraints.

[0172] As an example, the decision model described above can be represented by formula (6):

[0173] min F(x)=C total -I total (6)

[0174] In formula (6), F(x) represents the loss of the battery swapping station, and C total I represents the cost function of a battery swapping station. total This represents the revenue function of a battery swapping station.

[0175] Formula (6) can be explained by formula (7):

[0176]

[0177] That is, the maximum profit of a battery swapping station is equivalent to the minimum loss of the battery swapping station.

[0178] It should be noted that, through steps S901 to S903, a decision model is constructed with the profit of the battery swapping station as the optimization objective. Since profit = revenue - cost, the decision model in this application embodiment takes into account both cost and revenue, that is, it uses multiple objectives to make site selection decisions for the battery swapping station, thereby improving the rationality of the selection decision.

[0179] In one embodiment, the battery swapping profit function can be obtained through... Figure 10 The method shown is used to determine:

[0180] Step S1001: Construct a cost function based on the land occupation cost corresponding to the target cluster area, the battery swapping cost of the battery swapping station, and the distance cost corresponding to the battery swapping station;

[0181] Step S1002: Construct a revenue function based on the battery swapping revenue corresponding to each battery swapping order and the battery swapping supply of the battery swapping stations in the target cluster area;

[0182] Step S1003: Construct a battery swapping profit function based on the cost function and the revenue function.

[0183] In step S1001, the cost function consists of three parts: land occupation cost, battery swapping cost, and distance cost. Therefore, the cost function can be expressed by formula (8):

[0184] C total=C1+C2+C3 (8)

[0185] In formula (8), C total C1 represents the total cost; C2 represents the land occupation cost, which can vary depending on the land type and / or location; C3 represents the battery swapping cost, which can vary depending on the scale of the battery swapping station; and C4 represents the distance cost corresponding to the battery swapping station, which is borne by the user but can be seen as a penalty to limit the coverage area of ​​the battery swapping station. C3 can be represented by formula (9):

[0186] C3=α∑ i ∑ j d ij *x ij (9)

[0187] In formula (9), α is the unit price of distance cost, which can be the average of the cost of taking a taxi and the cost of driving; d ij Let be the distance from candidate address i to the center of region j.

[0188] The revenue function can be determined by the number of battery swapping orders and the average revenue per order, as shown in formula (10):

[0189] I total =∑ i ∑ j x ij *I (10)

[0190] In formula (10), I represents the average revenue per order.

[0191] To achieve the above objectives, decision variable x needs to be defined. ij and y ik These decision variables form the skeleton of the decision model, and they are the key unknowns that need to be solved in the process of optimizing the decision model.

[0192] x ij Let be the order supply from candidate address i to region j, where the order supply should not be less than 0. The supply capacity of each battery swapping station to region j may be limited, or in other words, a battery swapping station should not only affect the battery swapping orders in its own region. That is, the order supply and order demand can satisfy formula (11):

[0193] 0≤x ij ≤D,for i=0,1…,m,j=0,1…,n (11)

[0194] In formula (11), D represents the order demand.

[0195] y ik It is a 0-1 variable, indicating whether to create a space of size P at address i.k For battery swapping stations, 1 represents enabled, and 0 represents disabled:

[0196] y ik ∈{0,1},for i=0,1…,m,k=0,1…,β (12)

[0197] It should be noted that by constructing a cost function and a revenue function, and then constructing a battery swapping profit function, it can be seen that in this embodiment of the application, cost and revenue are used as objectives when making site selection decisions in order to improve the rationality of the selection decision.

[0198] After identifying the decision variables, the constraints of the decision model can be constructed. These constraints form the boundaries of the model, ensuring that the values ​​of the decision variables are feasible in practice. They also reflect business rules and external constraints, constituting the framework of the optimization problem.

[0199] In one embodiment, the above-mentioned multiple constraints include at least two of the following five constraints:

[0200] Constraint 1: The supply data for battery swapping orders is less than the demand data for battery swapping orders;

[0201] Constraint 2: The ratio between battery swapping order supply data and battery swapping order demand data is greater than the preset ratio;

[0202] Constraint 3: The supply data of battery swapping orders for battery swapping stations is less than the supply data of battery swapping orders for the corresponding battery swapping scale;

[0203] Constraint 4: The power demand data of the battery swapping station is less than the power supply of the target cluster area.

[0204] Constraint 5: The number of battery swapping stations within the target cluster area is less than or equal to the preset number.

[0205] Regarding constraint one, it means that the supply data of battery swapping orders for region j from each candidate address should be less than the demand data of battery swapping orders for region j, i.e., formula (13):

[0206] ∑ i x ij ≤D j for j=0,1…,n (13)

[0207] In supply (8), D j Let J represent the order demand for region J.

[0208] Regarding constraint two, it states that when constructing a battery swapping station, it is necessary to ensure that its service capacity can meet the total order demand in the region, and avoid insufficient supply capacity due to excessive pursuit of low cost, as shown in formula (14):

[0209] ∑ i ∑ j x ij ≥θ∑ j D j (14)

[0210] In formula (14), θ is a percentage, which represents the minimum percentage of order demand that must be met based on business needs.

[0211] Regarding constraint three, it means that the order supply capacity of a single battery swapping station should be limited by its own scale, as shown in formula (15):

[0212] ∑ j x ij ≤∑ k y ik *P k for i = 0, 1, ..., m (15)

[0213] In formula (15), P k To determine the ability of a battery swapping station to fulfill orders at the k-th scale.

[0214] Regarding constraint four, it indicates that the total scale of battery swapping stations within the same area is limited by the power supply capacity of the regional power grid or a certain area power grid, as shown in formula (16):

[0215] ∑ i ∑ k y ik p k ≤A (16)

[0216] In formula (16), p k Let K be the electricity demand index for a power swapping station of scale k; A is the power supply capacity index for the same area.

[0217] Regarding constraint five, it means that at most one battery swapping station of a certain size is allowed to be built at the same candidate address. That is, at address i, it is possible to choose whether to build a station and what size battery swapping station to build, as shown in formula (17):

[0218] ∑ k y ik ≤1, for i=0,1…m (17)

[0219] At this point, comprehensive constraints have been established, marking the complete construction of the decision-making model's framework. Decision variables can then be determined during the solution process, thereby identifying the construction plan for the battery swapping station.

[0220] By constructing constraints on the decision-making model to ensure that the values ​​of the decision variables are feasible in actual operation, the feasibility of the decision-making model is improved, and the rationality of the site selection decision is also guaranteed.

[0221] In this embodiment of the application, when constructing the decision model, both profit and cost objectives can be considered simultaneously. In this scenario, the decision model is constructed as follows: Figure 11 As shown:

[0222] Step S1101: Construct the cost function corresponding to the decision model based on the cost data of the battery swapping station;

[0223] Step S1102: Construct the battery swapping profit function corresponding to the decision model based on the revenue data and cost data of the battery swapping station;

[0224] Step S1103: Based on the battery swapping order supply data, battery swapping order demand data, and the power supply of the target cluster area, construct multiple constraints for the decision model. Among them, the battery swapping order supply data is the order data that provides battery swapping services to the target battery swapping station.

[0225] Step S1104: Construct a decision model based on the battery swapping profit function, the cost function corresponding to the battery swapping station, and multiple constraints.

[0226] In one example, a hierarchical objective optimization method can be used to construct a decision model, that is, to assign a priority to each objective, such as minimizing cost while maximizing profit, or maximizing profit while minimizing cost, as shown in formula (18):

[0227] minf1(x)=C total minf2(x)=C total -I total (18)

[0228] To address multi-objective problems, assign different weights to the objectives. m , making The optimization objective of the decision model can then be expressed by formula (19):

[0229]

[0230] However, weights represent importance, and it is often difficult to determine the priority among various objectives. To address the difficulty in selecting weights, this application utilizes the Pareto optimization concept, employing methods such as the weighted approach and the Non-Dominated Sorting Genetic Algorithm (NSGA-II), to search for the Pareto front of the objective function—that is, the point where no better solution exists among multiple objectives. The algorithm iterates, continuously updating the set of solutions, until the Pareto optimal solution set is finally obtained.

[0231] It should be noted that since multiple objectives are often contradictory, each solution in the Pareto optimal solution set is an optimal solution, and a more acceptable solution can be selected according to actual needs.

[0232] Furthermore, it should be noted that by constructing a decision-making model with the profit and cost of the battery swapping station as optimization objectives, the decision-making model simultaneously considers both costs and revenues. In other words, by using multiple objectives to make site selection decisions for battery swapping stations, the rationality of the selection decision is improved.

[0233] This concludes the introduction to the site selection decision-making process for battery swapping stations.

[0234] As an example, Figure 12 The overall flowchart of the battery swapping station site selection decision-making process is shown, such as... Figure 12 As shown, the process includes the following steps:

[0235] Step S1201: Obtain candidate addresses for battery swapping stations;

[0236] Step S1202: Establish business requirements and determine the number of battery swapping stations to be created;

[0237] Step S1203: Construct a decision model with profit as the optimization objective, and add decision variables and variable constraints;

[0238] Step S1204: Establish constraints for business rules and external restrictions;

[0239] Step S1205: Solve the multi-objective optimization problem of the decision model;

[0240] Step S1206: Determine the selection decision scheme based on the solution results.

[0241] This concludes the explanation of the methods provided in the embodiments of this application.

[0242] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0243] In one embodiment, Figure 13 A schematic diagram of the site selection device for the battery swapping station is shown. Figure 13It is known that the device 1300 includes: a data acquisition module 1301, a demand analysis module 1302, a cluster analysis module 1303, a cluster determination module 1304, and a location selection module 1305.

[0244] The data acquisition module 1301 is used to acquire target data for each of the multiple regional units contained in the first region. The target data includes factor data that can affect the battery swapping order data.

[0245] The demand analysis module 1302 is used to perform battery swapping demand analysis on the regional information of each regional unit using the target battery swapping demand analysis model, and to determine the battery swapping order demand data corresponding to each regional unit. The target battery swapping demand analysis model is used to characterize the relationship between regional information and battery swapping order demand data.

[0246] The clustering analysis module 1303 is used to cluster multiple regional units based on the battery swapping order demand data corresponding to each regional unit, so as to obtain at least one clustered region.

[0247] The cluster determination module 1304 is used to determine candidate cluster areas from at least one cluster area based on the battery swapping order demand data corresponding to each cluster area.

[0248] The location selection module 1305 is used to determine the candidate address of the battery swapping station based on the cluster center in the candidate cluster area.

[0249] In one embodiment, the clustering analysis module includes: a feature data acquisition module, a distance determination module, and a first clustering module. The feature data acquisition module acquires multidimensional feature data corresponding to each regional unit, wherein the multidimensional feature data for each regional unit includes the location information of the corresponding regional unit and the battery swapping order demand data corresponding to the corresponding regional unit. The distance determination module determines the distance between every two regional units based on the multidimensional feature data corresponding to multiple regional units, wherein the distance between every two regional units is used to characterize the differences between the multidimensional feature data of every two regional units. The first clustering module clusters the multiple regional units based on the distance between every two regional units to obtain at least one clustered region.

[0250] In one embodiment, the first clustering module includes a range determination module, a unit selection module, and a second clustering module. The range determination module is used to determine a clustering range centered on a first region unit and with a preset clustering radius as the search radius, wherein the first region unit is any one of a plurality of region units. The unit selection module is used to determine at least one second region unit from other region units within the clustering range whose distance is within a preset distance range, based on the distance between the first region unit and other region units within the clustering range. The second clustering module is used to determine the region composed of the first region unit and at least one second region unit as a cluster region when the number of at least one second region unit is greater than a preset number.

[0251] In one embodiment, the distance determination module is specifically used to normalize the multidimensional feature data corresponding to the third region unit and the multidimensional feature data corresponding to the fourth region unit respectively to obtain the first feature data and the second feature data, wherein the third region unit and the fourth region unit are any two of the multiple region units; and to calculate the distance between the first feature data and the second feature data.

[0252] In one embodiment, the site selection device for the battery swapping station further includes: a first model determination module, used to search for the target battery swapping demand analysis model associated with the first region from the association relationship between the regional unit and the battery swapping demand analysis model before performing battery swapping demand analysis on the regional information of each regional unit using the target battery swapping demand analysis model and determining the battery swapping order demand data corresponding to each regional unit.

[0253] In one embodiment, the site selection device for the battery swapping station further includes: a second model determination module, used to obtain a second region with a similarity greater than a preset similarity to the first region when there is no target battery swapping demand analysis model associated with the first region in the association relationship; and to determine the battery swapping demand analysis model associated with the second region as the target battery swapping demand analysis model.

[0254] In one embodiment, the target battery swapping demand analysis model is constructed as follows: an initial demand analysis model and sample data are obtained, wherein the sample data includes sample data of a sample area and sample battery swapping order demand data of the corresponding sample area; the sample data of the sample area is input into the initial demand analysis model; the demand analysis results output by the initial demand analysis model are obtained; based on the demand analysis results and the sample battery swapping order demand data of the corresponding sample area, the model parameters of the initial demand analysis model are adjusted to obtain the target battery swapping demand analysis model.

[0255] In one embodiment, the site selection device for the battery swapping station further includes: a regional demand determination module, which is used to perform weighted calculation on the battery swapping order demand data of the regional units contained in each cluster region before determining the candidate cluster region from at least one cluster region based on the battery swapping order demand data corresponding to each cluster region, so as to obtain the battery swapping order demand data corresponding to each cluster region.

[0256] In one embodiment, the cluster determination module is specifically used to sort the cluster regions according to the order of battery swapping order demand data corresponding to the cluster regions from largest to smallest to obtain a cluster region sequence; from the cluster region sequence, select the cluster regions ranked in the top N positions to obtain candidate cluster regions, where N is a positive integer.

[0257] In one embodiment, the site selection device for the battery swapping station further includes: a site selection decision module, used to input the battery swapping order demand data corresponding to the candidate cluster area into the decision model to obtain the target cluster area and the scale of the target battery swapping station.

[0258] In one embodiment, the decision model is constructed as follows: a battery swapping profit function corresponding to the decision model is constructed based on the revenue data and cost data of the battery swapping station; multiple constraints of the decision model are constructed based on the battery swapping order supply data, battery swapping order demand data, and the power supply of the target cluster area, wherein the battery swapping order supply data is the order data for providing battery swapping services to the target battery swapping station; and the decision model is constructed based on the battery swapping profit function and multiple constraints.

[0259] In one embodiment, multiple constraints include: the supply data of battery swapping orders is less than the demand data of battery swapping orders; the ratio between the supply data of battery swapping orders and the demand data of battery swapping orders is greater than a preset ratio; the supply data of battery swapping orders at a battery swapping station is less than the supply data of battery swapping orders at the corresponding battery swapping scale; the power demand data of a battery swapping station is less than the power supply of the target cluster area; and the number of battery swapping stations in the target cluster area is less than or equal to a preset number.

[0260] In one embodiment, revenue data includes battery swapping revenue for each battery swapping order, and cost data includes land occupation cost for the target cluster area, battery swapping cost of the target battery swapping station, and distance cost of the target battery swapping station. The battery swapping station site selection device further includes a profit determination module, used to construct a cost function based on the land occupation cost for the target cluster area, the battery swapping cost of the battery swapping station, and the distance cost of the battery swapping station; construct a revenue function based on the battery swapping revenue for each battery swapping order and the battery swapping supply of the battery swapping stations in the target cluster area; and construct a battery swapping profit function based on the cost function and the revenue function.

[0261] In one embodiment, the decision model is constructed as follows: a cost function corresponding to the decision model is constructed based on the cost data of the battery swapping station; a battery swapping profit function corresponding to the decision model is constructed based on the revenue data and cost data of the battery swapping station; multiple constraints of the decision model are constructed based on the battery swapping order supply data, the battery swapping order demand data, and the power supply of the target cluster area, wherein the battery swapping order supply data is the order data for providing battery swapping services to the target battery swapping station; and the decision model is constructed based on the battery swapping profit function, the cost function corresponding to the battery swapping station, and the multiple constraints.

[0262] In one embodiment, this application also provides a readable storage medium storing computer program instructions that, when executed by a processor, implement the above-described method for selecting the location of a battery swapping station.

[0263] In one embodiment, this application also provides a computer program product in which the instructions, when executed by the processor of an electronic device, cause the electronic device to perform the above-described method for selecting the location of a battery swapping station.

[0264] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0265] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be, for example, electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0266] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0267] The above flowcharts and / or block diagrams describing the site selection method, apparatus, storage medium, and computer program product for a battery swapping station according to embodiments of this application have described various aspects of this application. It should be understood that each block in the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowcharts and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by dedicated hardware performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

[0268] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and not to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and they should all be covered within the scope of the claims and specification of this application. In particular, as long as there is no structural conflict, the various technical features mentioned in the embodiments can be combined in any way. This application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method for site selection of a battery swap station, characterized in that, include: Obtain target data for each of the multiple regional units contained in the first region, wherein the target data includes factor data that can affect the station change order data; The target battery swapping demand analysis model is used to analyze the regional information of each regional unit to determine the battery swapping order demand data corresponding to each regional unit. The target battery swapping demand analysis model is used to characterize the correlation between regional information and battery swapping order demand data. Based on the battery swapping order demand data corresponding to each regional unit, the multiple regional units are clustered to obtain at least one clustered region. Based on the battery swapping order demand data corresponding to each cluster region, candidate cluster regions are determined from the at least one cluster region; The candidate addresses of the battery swapping stations are determined based on the cluster centers in the candidate cluster regions.

2. The method of claim 1, wherein, The step of clustering the multiple regional units based on the battery swapping order demand data corresponding to each regional unit to obtain at least one clustered region includes: Obtain multi-dimensional feature data corresponding to each regional unit, wherein the multi-dimensional feature data corresponding to each regional unit includes the location information of the corresponding regional unit and the battery swapping order demand data of the corresponding regional unit; Based on the multidimensional feature data corresponding to the plurality of regional units, the distance between every two regional units is determined, wherein the distance between every two regional units is used to characterize the difference between the multidimensional feature data between every two regional units; Based on the distance between every two regional units, the multiple regional units are clustered to obtain at least one clustered region.

3. The method of claim 2, wherein, The step of clustering the multiple regional units based on the distance between every two regional units to obtain the at least one clustered region includes: The clustering range is determined by taking the first region unit as the center and using the preset clustering radius as the search radius, wherein the first region unit is any one of the plurality of region units; Based on the distance between the first region unit and other region units within the cluster range, at least one second region unit is determined from the other region units within the cluster range whose distance is within a preset distance range; If the number of at least one second region unit is greater than a preset number, the region composed of the first region unit and the at least one second region unit is determined as a cluster region.

4. The method according to claim 2 or 3, characterized in that, The step of determining the distance between any two regional units based on the multidimensional feature data corresponding to the multiple regional units includes: The multidimensional feature data corresponding to the third region unit and the multidimensional feature data corresponding to the fourth region unit are normalized respectively to obtain the first feature data and the second feature data, wherein the third region unit and the fourth region unit are any two of the plurality of region units; Calculate the distance between the first feature data and the second feature data.

5. The method according to claim 1, characterized in that, Before performing battery swapping demand analysis on the regional information of each regional unit using the target battery swapping demand analysis model to determine the battery swapping order demand data corresponding to each regional unit, the method further includes: From the association between regional units and battery swapping demand analysis models, find the target battery swapping demand analysis model associated with the first region.

6. The method according to claim 5, characterized in that, The method further includes: If there is no target battery swapping demand analysis model associated with the first region in the association relationship, a second region with a similarity greater than a preset similarity to the first region is obtained; The battery swapping demand analysis model associated with the second region is determined as the target battery swapping demand analysis model.

7. The method according to claim 5 or 6, characterized in that, The target battery swapping demand analysis model is constructed in the following manner: Obtain an initial demand analysis model and sample data, wherein the sample data includes sample data of a sample area and sample battery swapping order demand data of the corresponding sample area; Input the sample data of the sample area into the initial demand analysis model; Obtain the requirements analysis results output by the initial requirements analysis model; Based on the demand analysis results and the battery swapping order demand data samples corresponding to the sample area, the model parameters of the initial demand analysis model are adjusted to obtain the target battery swapping demand analysis model.

8. The method according to any one of claims 1 to 7, characterized in that, Before determining candidate cluster regions from the at least one cluster region based on the battery swapping order demand data corresponding to each cluster region, the method further includes: The battery swapping order demand data of the regional units contained in each cluster region are weighted and calculated to obtain the battery swapping order demand data corresponding to each cluster region.

9. The method according to any one of claims 1 to 8, characterized in that, The step of determining candidate cluster regions from the at least one cluster region based on the battery swapping order demand data corresponding to each cluster region includes: The cluster regions are sorted in descending order of battery swapping order demand data corresponding to each cluster region to obtain a cluster region sequence. From the cluster region sequence, select the cluster regions that rank in the top N positions to obtain the candidate cluster regions, where N is a positive integer.

10. The method according to any one of claims 1 to 9, characterized in that, The method further includes: Input the battery swapping order demand data corresponding to the candidate cluster area into the decision model to obtain the target cluster area and the scale of the target battery swapping station.

11. The method according to claim 10, characterized in that, The decision model is constructed in the following manner: The battery swapping profit function corresponding to the decision model is constructed based on the revenue data and cost data of the battery swapping station. Based on the battery swapping order supply data, the battery swapping order demand data, and the power supply of the target cluster area, multiple constraints are constructed for the decision model, wherein the battery swapping order supply data is the order data for providing battery swapping services to the target battery swapping station; The decision model is constructed based on the battery swapping profit function and the various constraints.

12. The method according to claim 11, characterized in that, The constraints include: The supply data for battery swapping orders is less than the demand data for battery swapping orders. The ratio between the battery swapping order supply data and the battery swapping order demand data is greater than a preset ratio. The battery swapping order supply data of the battery swapping station is less than the battery swapping order supply data of the battery swapping station under the corresponding battery swapping scale. The power demand data of the battery swapping station is less than the power supply of the target cluster area. The number of battery swapping stations within the target cluster area is less than or equal to a preset number.

13. The method according to claim 11, characterized in that, The revenue data includes the battery swapping revenue corresponding to each battery swapping order, and the cost data includes the land occupation cost corresponding to the target cluster area, the battery swapping cost of the target battery swapping station, and the distance cost corresponding to the target battery swapping station. The step of constructing the battery swapping profit function corresponding to the decision model based on the revenue data and cost data of the battery swapping stations includes: A cost function is constructed based on the land occupation cost corresponding to the target cluster area, the battery swapping cost of the battery swapping station, and the distance cost corresponding to the battery swapping station; A revenue function is constructed based on the battery swapping revenue corresponding to each battery swapping order and the battery swapping supply of the battery swapping stations in the target cluster area; The battery swapping profit function is constructed based on the cost function and the revenue function.

14. The method according to claim 10, characterized in that, The decision model is constructed in the following manner: The cost function corresponding to the decision model is constructed based on the cost data of the battery swapping station. The battery swapping profit function corresponding to the decision model is constructed based on the revenue data and cost data of the battery swapping station. Based on the battery swapping order supply data, the battery swapping order demand data, and the power supply of the target cluster area, multiple constraints are constructed for the decision model, wherein the battery swapping order supply data is the order data for providing battery swapping services to the target battery swapping station; The decision model is constructed based on the battery swapping profit function, the cost function corresponding to the battery swapping station, and multiple constraints.

15. A site selection device for a battery swapping station, characterized in that, include: The data acquisition module is used to acquire target data for each of the multiple regional units contained in the first region, wherein the target data includes factor data that can affect the battery swapping order data; The demand analysis module is used to perform battery swapping demand analysis on the regional information of each regional unit using the target battery swapping demand analysis model, and to determine the battery swapping order demand data corresponding to each regional unit. The target battery swapping demand analysis model is used to characterize the correlation between regional information and battery swapping order demand data. The clustering analysis module is used to cluster the multiple regional units based on the battery swapping order demand data corresponding to each regional unit, so as to obtain at least one clustered region. The cluster determination module is used to determine candidate cluster regions from the at least one cluster region based on the battery swapping order demand data corresponding to each cluster region. The site selection module is used to determine the candidate address of the battery swapping station based on the cluster centers in the candidate cluster area.

16. A readable storage medium, characterized in that, The readable storage medium stores computer program instructions that, when executed by a processor, implement the site selection method for a battery swapping station as described in any one of claims 1-14.

17. A computer program product, characterized in that, When the instructions in the computer program product are executed by the processor of the electronic device, the electronic device causes the electronic device to perform the site selection method for the battery swapping station as described in any one of claims 1-14.

Images