Charging pile site selection method and system based on GIS spatial analysis

Abstract

The invention discloses a charging pile site selection method and system based on a geographic information system (GIS) space analysis function. The method comprises the steps that on the basis of correlation analysis and collinearity removal of influence factors influencing the number of electric vehicles, the number of charging piles and layout, a space-time geographic weighted regression model is constructed based on selected principal components, and the number of the charging piles needing to be arranged in each grid is determined; and a comprehensive score model of the POI points of each grid is constructed in combination with the traffic flow and the correlation coefficients, the positions of the charging piles needing to be planned are determined in the H-meter buffer area of the POI points in combination with the land use property according to the scores, and prediction of the number of the charging piles and accurate positioning of each charging pile needing to be planned are achieved.

Description

Technical Field

[0001] The present invention relates to the field of transportation and energy integration technology, and in particular to a charging pile site selection method and system based on GIS spatial analysis. Background Art

[0002] The booming development of electric vehicles has put forward higher demands on charging facilities, and the specific site selection of charging piles is the focus of future urban planning.

[0003] Many scholars have conducted research on charging pile site selection based on planning data, statistical data, floating car data, etc., based on improved particle swarm algorithm, genetic algorithm, BWM's improved interval VIKOR model, topological theory and anomaly algorithm, queuing theory, multi-objective optimization and other different methods. The research on site selection is more focused on further optimizing the site selection in the selected points. This patent focuses on using the spatial analysis function of GIS to solve the problems of predicting the number of charging piles in different regions and how to accurately locate the location of each planned charging pile. Summary of the invention

[0004] In order to solve the deficiencies of the prior art, the present invention provides a charging pile site selection method and system based on the spatial analysis function of the geographic information system (GIS). Based on the correlation analysis and collinearity removal of the factors affecting the number of electric vehicles, the number of charging piles and the layout, a spatiotemporal geographic weighted regression model is constructed based on the selected principal components to determine the number of charging piles that need to be laid out for each grid; a comprehensive scoring model for each grid POI point is constructed in combination with traffic flow and correlation coefficients, and the location of the charging piles that need to be planned is determined within the H-meter buffer zone of the POI point based on the score and the nature of the land use, so as to realize the prediction of the number of charging piles and the precise positioning of each charging pile that needs to be planned.

[0005] Terminology explanation:

[0006] Principal component analysis: It is a classic statistical method for extracting the main characteristic components from data. It is often used for dimensionality reduction of high-dimensional data. It can convert multiple related indicators into a few unrelated comprehensive indicators while minimizing information loss. The first principal component P1 contains the maximum information in the data, so its contribution rate is the highest. If the cumulative contribution rate reaches 85% or above, it can be considered that the first m principal components can well preserve the information of the original sample.

[0007] Spatiotemporal geographically weighted regression model: Based on the traditional geographically weighted regression model, the temporal and spatial characteristics of the data are embedded into the regression model, which can be used to explain spatial and temporal phenomena.

[0008] In a first aspect, the present invention provides a charging pile site selection method based on GIS spatial analysis;

[0009] A charging pile site selection method based on GIS spatial analysis, including:

[0010] Obtain data on factors that have a significant impact on the number of electric vehicles, the number of charging piles, and their layout, such as GDP, population density, roads, and POI points in the study area at different times, and import the data into the GIS spatial database;

[0011] Use GIS software to pre-process the influencing factor data and unify the coordinate system and resolution of the data; count the values ​​of influencing factors such as GDP and POI in each grid and make associations;

[0012] Statistical software was used to analyze the correlation of influencing factors, and principal component analysis was used to remove the collinearity between influencing factors;

[0013] Based on the selected principal components, a spatiotemporal geographic weighted regression model is constructed to Predict the number of charging piles required within the area;

[0014] Construct a comprehensive scoring model for the POI points of each grid, and determine the location of the charging piles that need to be planned based on the score and the nature of the land use.

[0015] Secondly, a charging pile site selection system based on GIS spatial analysis is provided;

[0016] Charging pile site selection system based on GIS spatial analysis, including:

[0017] The data acquisition module is configured to: obtain the data of factors that have a great impact on the number of electric vehicles, the number of charging piles and their layout, such as GDP, population density, roads, and POI points in the study area at different periods, and import the data into the GIS spatial database;

[0018] The data preprocessing module is configured to: preprocess the influencing factor data using GIS software, unify the coordinate system and resolution of the data; count the values ​​of influencing factors such as GDP and POI in each grid, and associate them;

[0019] The data analysis module is configured to: analyze the correlation of influencing factors using statistical software and remove the collinearity between influencing factors using the principal component analysis method;

[0020] The model building module is configured to: build a spatiotemporal geographic weighted regression model based on the selected principal components, Predict the number of charging piles required within the area;

[0021] Site selection and positioning module: Build a comprehensive scoring model for the POI points in each grid, and determine the location of the charging piles that need to be planned based on the score and the nature of the land use.

[0022] In a third aspect, the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in the first aspect when executing the program.

[0023] In a fourth aspect, the present invention further provides a storage medium that non-temporarily stores computer-readable instructions, wherein when the non-temporary computer-readable instructions are executed by a computer, the instructions of the method described in the first aspect are executed.

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] The present invention provides a charging pile site selection method and system based on GIS spatial analysis; based on the spatial analysis of the factors that have a great impact on the number and layout of charging piles, a spatiotemporal geographic enhanced regression model is constructed, which fully considers the spatiotemporal characteristics of each influencing factor, and can realize the determination of the number and location of charging piles that need to be planned in different regions, thereby improving the accuracy of the number and site selection of planned charging piles;

[0026] The present invention constructs a comprehensive scoring model for POI points in a grid that combines traffic flow and correlation coefficients, determines the location of charging piles based on the scores and takes into account the nature of the land use, and solves the problem of how to accurately locate charging piles;

[0027] The present invention combines the classic principal component analysis method for removing multi-factor correlation and achieving data dimensionality reduction with a spatiotemporal geographic weighted regression model that considers spatial and temporal heterogeneity, that is, it takes into account the spatiotemporal variability of many influencing factors that affect the number and layout of charging piles, and reduces the complexity of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0029] Figure 1 is a flow chart of the method of embodiment 1;

[0030] Figure 2 This is a data schematic diagram of Example 1. DETAILED DESCRIPTION

[0031] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0032] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0033] In this embodiment, all data is obtained in compliance with laws and regulations and based on the user's consent, and is used legally.

[0034] Embodiment 1

[0035] This embodiment provides a charging pile site selection method based on GIS spatial analysis, including:

[0036] S101: Obtain data on factors that have a significant impact on the number of electric vehicles, the number of charging piles, and their layout, such as GDP, population density, roads, and POI points in the study area at different times, and import the data into the GIS spatial database;

[0037] S102: Use GIS software to pre-process the influencing factor data, unify the coordinate system and resolution of the data; count the values ​​of influencing factors such as GDP and POI in each grid, and associate them;

[0038] S103: Analyze the correlation of influencing factors using statistical software and remove the collinearity between influencing factors using principal component analysis method;

[0039] S104: Based on the selected principal components, a spatiotemporal geographic weighted regression model is constructed to Predict the number of charging piles required within the area;

[0040] S105: Build each mesh The comprehensive scoring model of POI points within the system determines the locations of charging piles that need to be planned based on the scores and the nature of the land use.

[0041] Furthermore, the step S101: obtaining data on factors that have a significant impact on the number of electric vehicles, the number of charging piles and their layout, such as GDP, population density, roads, and POI points in the study area at different periods, and importing the data into a GIS spatial database, specifically includes:

[0042] S101-1: Obtain data on factors that have a significant impact on the number of electric vehicles, the number of charging piles, and their layout, such as GDP, population density, land use type, roads, transportation POI points, residential POI points, commercial POI points, medical POI points, educational POI points, and existing charging pile distribution in the study area at different times;

[0043] S101-2: Sort and convert the data, import data such as GDP, population density, and land use type into the GIS spatial database as surface layers; import data such as road networks and rivers into the GIS spatial database as line layers; import traffic POI points, residential POI points, commercial POI points, medical POI points, educational POI points, and existing charging pile distribution into the GIS spatial database as point layers, such as Figure 2 ;

[0044] Furthermore, the S102: using GIS software to pre-process the influencing factor data, unify the coordinate system and resolution of the data; count the values ​​of influencing factors such as GDP and POI in each grid, and associate them, specifically includes:

[0045] S102-1: Use the projection function of GIS software to project the coordinate system of all data into the same projection coordinate system; use the clipping function to keep the area range of the surface, line, and point layers consistent;

[0046] S102-2: Take the lowest resolution of the surface layer data (GDP, population density, land use type) as the standard, and use the resampling function of the GIS software to obtain a gridded layer with a uniform resolution; obtain the surface layer data corresponding to each grid, such as GDP, population density, land use type, etc.;

[0047] S102-3: Use the geometric statistics function of GIS software to calculate the road length; because the traffic flow of roads of different levels varies greatly, it is necessary to convert the roads into standard roads for comparison. The conversion formula is as follows:

[0048]

[0049] In the formula, For Grid Total number of types of inner roads; For Grid The road number in; For Grid middle road the number of For Type of road number The length of the road in km; Conversion factors for standard lengths of different roads.

[0050] For example, roads can be divided into five levels: expressway, first-class, second-class, third-class, and fourth-class highways. In Jinan, the second-class roads are the most densely populated. =1. According to the Highway Engineering Technical Standard, the design flow rate of a secondary highway is 5,000-15,000 vehicles. Taking 10,000 vehicles as the flow rate of a standard road, the middle values ​​of the design flow rates of four-lane, six-lane, and eight-lane highways, i.e., 40,000, 62,500, and 80,000 vehicles, are used for conversion, that is, The design flow rates of first-class highway, third-class highway and fourth-class highway are 32,500, 4,000 and 1,200 vehicles respectively. They are 3.25, 0.4 and 0.12 respectively; urban roads are divided into four levels: expressways, trunk roads, secondary trunk roads and branch roads, which can be divided into the same level as first-class highways, second-class highways, third-class highways and fourth-class highways respectively;

[0051] Convert all types of roads in each grid into standard road lengths, and count the standard lengths of roads in each grid;

[0052] S102-4: Use the statistical function of GIS software to count the number of various POI points in each grid, such as transportation, residential, commercial, medical, educational, and existing charging pile distribution;

[0053] S102-5: Using the association function of GIS software, the GDP, population density, land use type, standard road length, number of POIs of various types and other data at different times and on each grid are associated one by one in the attribute table; illustratively, the associated attribute table is shown in Table 1;

[0054] Table 1 Example of attribute table after association Grid Label <![CDATA[x1 GDP (in ten thousand yuan)]]> <![CDATA[Population density of x2 (persons)]]> <![CDATA[x3 Land use type]]> <![CDATA[x4 Standard Road Length (km)]]> <![CDATA[x5 Transportation-related POI]]> <![CDATA[x6 Resident POI]]> <![CDATA[x7 Commercial POI]]> <![CDATA[x8 Medical POI]]> <![CDATA[x9 Educational POI]]> <![CDATA[x 10 Existing charging pile POI]]> … <![CDATA[x n ]]> 2000.0 1000.0 Commercial land 15.6 8 5 15 2 0 0 2 300.0 2500.0 Residential land 10.0 10 20 5 8 5 4 …

[0055] Further, S103: using statistical software to analyze the correlation of the influencing factors, using the principal component analysis method, selecting the first m principal components with a cumulative contribution rate greater than 85%, and removing the collinearity between the influencing factors, specifically including:

[0056] S103-1: Export the corresponding data from the GIS software and use statistical analysis software to analyze the correlation coefficient R between GDP, population density, land use type, standard road length, and various types of POI points;

[0057] S103-2: Based on the results of the correlation analysis, check the value, Yes (1-R 2 ), if VIF >7.5, it means that there is collinearity problem in the data and the collinearity between the data needs to be removed;

[0058] S103-3: Standardize the data to eliminate the differences between different variables due to different units. The standardization formula is:

[0059] (2)

[0060] in: =

[0061] Where Z i For x i After normalization, x i is the data of a single sample of a certain feature, is the mean of the sample data of the feature. is the standard deviation of the overall sample data of the variable, and N is the total number of samples;

[0062] S103-4: Factors with larger VIF can be transformed and principal components extracted using the principal component analysis method in the statistical analysis software SPSS; select the cumulative contribution rate ( … ) More than 85% of the m principal components P1…Pm, among which …is calculated as follows:

[0063] ……… (3)

[0064] In the formula, … is the contribution coefficient of the first m principal components to the first principal component after the transformation, … is the contribution coefficient of the first m principal components to the mth principal component;

[0065] Further, S104: Based on the selected principal components, a spatiotemporal geographic weighted regression model is constructed to The number of charging piles required within the project is predicted; specifically including:

[0066] S104-1: importing the m principal components extracted from the principal components into the GIS software, and using the association function of the GIS software to associate the m principal components with the grid;

[0067] S104-2: Based on the selected m principal components, a spatiotemporal geographic weighted regression model is constructed;

[0068]

[0069] In the formula, is the number of charging piles that need to be planned in grid i, is the regional sample point Space-time geographic coordinates, It is The regression coefficient of the independent variable is a function of the spatial and temporal position. is the error term of the sample point;

[0070] Further, S105: construct each grid The comprehensive scoring model of POI points in the system determines the location of charging piles that need to be planned based on the score and the nature of the land use, including:

[0071] S105-1: normalize the traffic flow O near various POI points (x) in the grid i. The normalization formula is shown in Formula 2.

[0072] S105-2: Calculate the comprehensive score of various POI points in grid i ;

[0073] (5)

[0074] In the formula, yes POI point The comprehensive score of points, yes The regression coefficient of POI-like points, yes POI point The AC flow after standardization of each point;

[0075] S105-2: Grids predicted by spatiotemporal geographically weighted regression models The number of charging piles required Subtract the number of existing charging stations , which is the grid The number of charging piles that need to be planned , according to the comprehensive score of POI points Select the locations of the charging piles to be planned; if the distance between the two travel points is less than L meters, delete the points with lower scores until the selected points are Points;

[0076] S105-3: Use the selected S POIs as the midpoint and H meters as the radius to create a buffer zone (H is less than 1 / 2 of the minimum resolution), and give priority to public facilities or open spaces for the layout of charging piles.

[0077] Embodiment 2

[0078] This embodiment provides a charging pile site selection system based on GIS spatial analysis;

[0079] Charging pile site selection system based on GIS spatial analysis, including:

[0080] The data acquisition module is configured to: obtain the data of factors that have a great impact on the number of electric vehicles, the number of charging piles and their layout, such as GDP, population density, roads, and POI points in the study area at different periods, and import the data into the GIS spatial database;

[0081] The data preprocessing module is configured to: preprocess the influencing factor data using GIS software, unify the coordinate system and resolution of the data; count the values ​​of influencing factors such as GDP and POI in each grid, and associate them;

[0082] The data analysis module is configured to: analyze the correlation of influencing factors using statistical software and remove the collinearity between influencing factors using the principal component analysis method;

[0083] The model building module is configured to: build a spatiotemporal geographic weighted regression model based on the selected principal components, Predict the number of charging piles required within the area;

[0084] Site selection and positioning module: Build a comprehensive scoring model for POI points in each grid i, and determine the location of the charging piles that need to be planned based on the score and the nature of the land use.

[0085] It should be noted that the above data acquisition module, data preprocessing module, quantity analysis module, model building module and site selection and positioning module correspond to steps S101 to S105 in Embodiment 1, and the examples and application scenarios implemented by the above modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above Embodiment 1. It should be noted that the above modules, as part of the system, can be executed in a computer system such as a set of computer executable instructions.

[0086] The proposed system can be implemented in other ways. For example, the system embodiment described above is only illustrative, and the division of the modules is only a logical function division. In actual implementation, there may be other division methods, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed.

[0087] Embodiment 3

[0088] This embodiment also provides an electronic device, including: one or more processors, one or more memories, and one or more computer programs; wherein the processor is connected to the memory, and the one or more computer programs are stored in the memory. When the electronic device is running, the processor executes the one or more computer programs stored in the memory so that the electronic device executes the method described in the above embodiment one.

[0089] The method in the first embodiment can be performed by combining hardware and software modules in the processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0090] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0091] Embodiment 4

[0092] This embodiment further provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, the charging pile site selection method based on GIS spatial analysis described in Embodiment 1 is completed.

[0093] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A charging pile site selection method and system based on GIS spatial analysis, characterized by including: Obtain data on factors that have a significant impact on the number of electric vehicles, the number of charging piles, and their layout, such as GDP, roads, population density, and POI points in the study area at different times, and import the data into the GIS spatial database; Use GIS software to pre-process the influencing factor data, unify the coordinate system and resolution of the data; count the values ​​of influencing factors such as GDP and POI in each grid and make associations; Statistical software was used to analyze the correlation of influencing factors, and principal component analysis was used to remove the collinearity between influencing factors; Based on the selected principal components, a spatiotemporal geographic weighted regression model is constructed to Predict the number of charging piles required within the area; Build each mesh The comprehensive scoring model of POI points is used to determine the location of charging piles that need to be planned near the POI points based on the scores and the nature of the land use.

2. The charging pile site selection method and system based on GIS spatial analysis as claimed in claim 1 is characterized in that: include: Obtain data on factors that have a significant impact on the number of electric vehicles, the number of charging piles, and their layout, such as GDP, road network, population density, land use type, transportation POI points, residential POI points, commercial POI points, medical POI points, educational POI points, and existing charging pile distribution in the study area at different times; The data is sorted and formatted, and data such as GDP, population density, and land use type are imported into the GIS spatial database as surface layers; data such as road networks and rivers are imported into the GIS spatial database as line layers; traffic POI points, residential POI points, commercial POI points, medical POI points, educational POI points, and the distribution of existing charging piles are imported into the GIS spatial database as point layers.

3. The charging pile site selection method and system based on GIS spatial analysis as claimed in claim 1 is characterized in that: include: Use the projection function of GIS software to project the coordinate system of all data into the same projection coordinate system; Use the clipping function to keep the area range of the surface, line, and point layers consistent; Taking the lowest resolution of the surface layer data (GDP, population density, land use type) as the standard, use the resampling function of the GIS software to obtain a gridded layer with uniform resolution; obtain the surface layer data corresponding to each grid, such as GDP, population density, land use type, etc.; The geometric statistics function of GIS software is used to calculate the road length; because the traffic flow of roads of different grades varies greatly, it is necessary to convert the roads into standard roads for comparison; Use the statistical function of GIS software to count the number of various POI points in each grid, such as transportation, residential, commercial, medical, educational, and existing charging pile distribution; By using the association function of GIS software, data such as GDP, population density, land use type, standard road length, number of POIs of various types, etc. at different times and on each grid are associated one by one in the attribute table.

4. The charging pile site selection method and system based on GIS spatial analysis as claimed in claim 1 is characterized in that: include: Export the corresponding data from the GIS software and use statistical analysis software to analyze the correlation coefficient R between GDP, population density, land use type, standard road length, and various types of POI points; According to the results of correlation analysis, check the If VIF>7.5, it means that there is collinearity problem in the data and the collinearity between the data needs to be removed; The data were standardized to eliminate the differences between different variables due to different units; Factors with larger VIF can be transformed and principal components extracted using the principal component analysis method in the statistical analysis software SPSS; Select the cumulative contribution rate ( … ) are greater than 85% of the m principal components P1…Pm.

5. The method and system for selecting a charging pile site based on GIS spatial analysis as claimed in claim 1, characterized in that: include: Import the m principal components extracted from the principal components into the GIS software, and use the association function of the GIS software to associate the m principal components with the grid; Based on the selected m principal components, a spatiotemporal geographic weighted regression model is constructed.

6. The charging pile site selection method and system based on GIS spatial analysis as claimed in claim 1 is characterized in that: include: Standardize the traffic flow O around various POI points (x) in grid i; Calculate the comprehensive score of various POI points in grid i ; 。 In the formula, yes POI point The comprehensive score of points, yes The regression coefficient of POI-like points, yes POI point The AC flow after standardization of each point; Grids for spatiotemporal geographically weighted regression model predictions The number of charging piles required Subtract the number of existing charging stations , which is the grid The number of charging piles that need to be planned , according to the comprehensive score of POI points Select the locations of the charging piles to be planned; if the distance between two travel points is less than L meters among the selected points, delete the points with lower scores until S points are selected; A buffer zone is made with the selected S POIs as the midpoint and H meters as the radius, and charging piles are laid out in places with public facilities or vacant land as priority.

7. The charging pile site selection system based on GIS spatial analysis is characterized by including: The data acquisition module is configured to import the data of factors that have a great impact on the distribution of the magnitude of charging piles, such as GDP, roads, population density, land use type, transportation POI points, residential POI points, commercial POI points, medical POI points, educational POI points, and existing charging pile distribution, into the GIS spatial database; The data preprocessing module is configured to: preprocess the influencing factor data using GIS software, unify the coordinate system and resolution of the data; count the values ​​of influencing factors such as GDP and POI in each grid, and associate them; The data analysis module is configured to: analyze the correlation of influencing factors using statistical software and remove the collinearity between influencing factors using the principal component analysis method; The model building module is configured to: build a spatiotemporal geographic weighted regression model based on the selected principal components, Predict the number of charging piles required within the area; Site selection module: build each grid The comprehensive scoring model of POI points is used to determine the location of charging piles that need to be planned near the POI points based on the scores and the nature of the land use.

8. An electronic device, characterized in that: include: a memory for non-transitory storage of computer readable instructions; A computer program stored on a processor and executable on the processor; Wherein, when the computer-readable instructions and computer programs are executed by the processor, the method described in any one of claims 1 to 7 is executed.

9. A storage medium, characterized in that: Non-temporarily storing data and a computer program, which, when executed by a processor, executes the instructions of the method according to any one of claims 1 to 7.

Images