Intelligent site selection method, device and equipment based on big data and optimization algorithm

Abstract

The invention relates to the technical field of new energy vehicles, and provides an intelligent site selection method, device and equipment based on big data and an optimization algorithm, and the method comprises the steps: obtaining multi-dimensional site selection data of a plurality of candidate land parcels, the multi-dimensional site selection data comprises parking quantity data, charging quantity demand data, traffic volume data and single-gun charging quantity data; performing correlation analysis and statistical operation on the multi-dimensional site selection data, and determining the plot score of the candidate plot; based on the plot score, screening out a target plot in the candidate plots; and carrying out optimization calculation on the target land parcel by using an operation planning optimization model, and determining a charging station site selection land parcel. According to the technical scheme provided by one or more embodiments of the invention, the optimized charging station site selection strategy can be formulated.

Description

Technical Field

[0001] The present disclosure relates to the technical field of new energy vehicles, and particularly to an intelligent site selection method, device and equipment based on big data and optimization algorithms. Background Art

[0002] New energy vehicles, especially electric vehicles, are becoming one of the mainstream means of transportation to replace traditional fuel vehicles due to their advantages of zero emissions and low noise. However, with the rapid increase in the ownership of new energy vehicles, the shortage of their supporting infrastructure, especially the insufficient quantity and layout of charging stations, has become one of the main bottlenecks restricting the further popularization and application of new energy vehicles. Summary of the Invention

[0003] In view of this, one or more embodiments of the present disclosure provide an intelligent site selection method, device and equipment based on big data and optimization algorithms, which can formulate an optimized site selection strategy for charging stations, improve the service effect of charging stations, and enhance the charging convenience of users.

[0004] On the one hand, the present disclosure provides an intelligent site selection method based on big data and optimization algorithms. The method includes: obtaining multi-dimensional site selection data of a plurality of candidate plots, where the multi-dimensional site selection data includes parking quantity data, charging quantity demand data, traffic volume data, and single-gun charging quantity data; performing correlation analysis and statistical operations on the multi-dimensional site selection data to determine the plot scores of the candidate plots; screening out target plots from the candidate plots based on the plot scores; and using an operations research optimization model to perform optimization calculations on the target plots to determine the site selection plots for charging stations.

[0005] On the other hand, the present disclosure also provides an intelligent site selection device based on big data and optimization algorithms. The device includes: a data acquisition unit for obtaining multi-dimensional site selection data of a plurality of candidate plots, where the multi-dimensional site selection data includes parking quantity data, charging quantity demand data, traffic volume data, and single-gun charging quantity data; a scoring unit for performing correlation analysis and statistical operations on the multi-dimensional site selection data to determine the plot scores of the candidate plots; a screening unit for screening out target plots from the candidate plots based on the plot scores; and a site selection unit for using an operations research optimization model to perform optimization calculations on the target plots to determine the site selection plots for charging stations.

[0006] On the other hand, the present disclosure also provides an electronic device. The electronic device includes a memory and a processor. The memory is used to store a computer program, and when the computer program is executed by the processor, the above-mentioned intelligent site selection method based on big data and optimization algorithms is implemented.

[0007] On the other hand, the present disclosure also provides a computer-readable storage medium for storing a computer program, which, when executed by a processor, implements the above-mentioned intelligent site selection method based on big data and optimization algorithms.

[0008] The technical solutions provided by one or more embodiments of the present disclosure comprehensively consider multi-dimensional data such as the number of parking spaces, charging demand, traffic volume, and single-gun charging volume. After data analysis, statistical operations, and optimization calculations, the site selection of charging stations can be determined. Compared with traditional site selection methods, this data-driven site selection method can more accurately depict the charging demand characteristics of different regions. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The features and advantages of the embodiments of the present disclosure will be more clearly understood by referring to the accompanying drawings. The drawings are schematic and should not be construed as limiting the present disclosure in any way. In the drawings:

[0010] Figure 1 A schematic diagram of the steps of the intelligent site selection method based on big data and optimization algorithms in one embodiment of the present disclosure is shown;

[0011] Figure 2 A schematic diagram of the process of the intelligent site selection method based on big data and optimization algorithms in one embodiment of the present disclosure is shown;

[0012] Figure 3 A schematic diagram of the functional modules of the intelligent site selection device based on big data and optimization algorithms in one embodiment of the present disclosure is shown;

[0013] Figure 4 A schematic diagram of the structure of an electronic device in one embodiment of the present disclosure is shown. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0014] To make the objectives, technical solutions, and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present disclosure. Apparently, the described embodiments are some, but not all, of the embodiments of the present disclosure. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present disclosure without creative efforts shall fall within the scope of protection of the present disclosure.

[0015] In the related art, in the existing charging station location selection methods, there is often a lack of full utilization of multi-dimensional data such as the spatial distribution of charging demand, traffic flow, and user behavior characteristics, resulting in unreasonable location selection results. For example, some charging stations are built in areas with few electric vehicles, with low charging demand and utilization rate, causing waste of resources; while in areas with dense electric vehicles, the number of charging stations is insufficient or the location is unreasonable, resulting in problems such as inconvenient charging for users and long charging queue times. These unreasonable layouts not only affect the user experience but also restrict the promotion and application of new energy vehicles.

[0016] In addition, most traditional charging station location selection models are based on simple geographical and economic factors, ignoring the complexity of new energy vehicle charging behavior. For example, users' charging behavior is affected by various factors such as distance, charging cost, waiting time, and the availability of charging facilities. At the same time, factors such as the service radius of the charging station, the maximum service capacity per unit time, investment cost, and operating cost also need to be comprehensively considered in the location selection decision.

[0017] In view of this, an intelligent location selection method based on big data and optimization algorithms provided by an embodiment of the present disclosure can formulate an optimized charging station location selection strategy, improve the service effect of the charging station, and enhance the charging convenience of users.

[0018] Please refer to Figure 1 , an intelligent location selection method based on big data and optimization algorithms provided by an embodiment of the present disclosure may include the following multiple steps.

[0019] S1: Obtain multi-dimensional location selection data of multiple candidate plots, where the multi-dimensional location selection data includes parking quantity data, charging quantity demand data, traffic volume data, and single-gun charging quantity data.

[0020] In this embodiment, some preparation and preprocessing work need to be carried out on the multi-dimensional data required for the location selection of new energy vehicle charging stations.

[0021] Specifically, the parking quantity data of the candidate plot can be the statistics of the parking quantity within the candidate plot. The parking quantity reflects the activity of electric vehicles within the plot and is an important indicator for measuring charging demand.

[0022] The charging quantity demand data of the candidate plot can be the calculation of the charging quantity demand for each candidate plot. The calculation method of the charging quantity demand can be: among all the vehicles parked in the plot, select those vehicles whose current SOC (state of charge of the battery) is lower than the average value of their historical charging SOC, calculate the charging quantity demand of these vehicles, and then subtract the charging quantity that the plot can provide. This data can reflect the actual charging quantity required by electric vehicles in a specific plot.

[0023] The traffic volume data of the candidate plots can be the number of vehicles passing through each candidate plot. The traffic volume data can reflect the vehicle flow of a plot and has important reference value for predicting the charging demand.

[0024] The single-gun charging volume data of the candidate plots can be the daily average charging volume of each single charging gun of the charging piles within each candidate plot. If there is no charging pile in a certain candidate plot, the value is recorded as 0. This data can reflect the utilization of the existing charging facilities in the current plot.

[0025] In some embodiments, the obtaining of the multi-dimensional site selection data of multiple candidate plots includes: using a geospatial indexing system to divide the charging site selection area into grids to determine the candidate plots; for each of the candidate plots, obtaining the corresponding multi-dimensional site selection data.

[0026] In a practical application example, H3 is a geospatial indexing system used to divide the Earth's surface into a series of hexagonal grids (some pentagonal grids are also supported). The H3 indexing system numbers and manages these grids in a hierarchical structure, and each grid has a unique index code. The H3 indexing system balances the uniformity of area division and computational efficiency by using the geometric shape of hexagons. The H3 indexing system has 16 levels (from 0 to 15), and the higher the level, the smaller the hexagonal grid. The side length of the hexagon at each level is about 1 / 7 of the side length of the previous level. For example: The H3 level 8 index is a medium-grained grid, covering an area of about 5 square kilometers, suitable for geospatial analysis and data processing at the urban level.

[0027] According to the scale of the charging site selection area, different levels of the H3 indexing system can be used for grid division to obtain candidate plots.

[0028] S2: Perform correlation analysis and statistical operations on the multi-dimensional site selection data to determine the plot scores of the candidate plots.

[0029] In this embodiment, through the fusion and analysis of multi-dimensional data, the charging demand of each plot can be accurately predicted, and the charging demand of each candidate plot is quantified in the form of plot scores.

[0030] In some embodiments, the performing of correlation analysis and statistical operations on the multi-dimensional site selection data to determine the plot scores of the candidate plots includes: calculating the feature correlation between each feature data and the single-gun charging volume data, where the feature data includes at least one of the parking quantity data, the charging volume demand data, and the traffic volume data; normalizing the feature correlation to obtain the feature weight of each feature data; and determining the plot scores of the candidate plots based on the feature weight and the data value of the feature data.

[0031] By performing correlation analysis and weighted summation calculations on multi-dimensional data such as parking quantity, traffic volume, and charging demand, the plot score of each candidate plot can be determined, thereby identifying candidate plots with higher charging demands.

[0032] In a practical application example, multi-dimensional data such as parking quantity data, traffic volume data, charging demand data, and single-gun charging quantity data can be integrated to form a feature dataset. Each data record can include the following features: parking quantity, traffic volume, charging demand, year and month (time feature), H3 index (spatial feature), the city where the plot is located, etc.

[0033] Subsequently, the correlation between each feature (parking quantity, traffic volume, charging demand, etc.) and the single-gun charging quantity can be calculated. The correlation can be calculated through statistical methods (such as the Pearson correlation coefficient) to quantify the influence degree of each feature on the single-gun charging quantity.

[0034] The correlation values of all features are scaled proportionally to a scale where the sum of all correlations is 1. That is, by normalizing the correlation of each feature, the weight of each feature can be obtained. The weight reflects the importance of each feature in evaluating the charging demand of the plot. Let the correlation of each feature be R i After normalization, the weight value W of the feature can be obtained i . The weight calculation formula can be as follows:

[0035]

[0036] Where W i is the weight value of the i-th feature, R i is the Pearson correlation of the i-th feature, n is the total number of features, |R i | represents the absolute value of R i , ensuring that all weight values are non-negative.

[0037] The normalized weight W i satisfies the following conditions:

[0038]

[0039] According to the weight of each feature, weighted summation can be performed on all feature data. Specifically, for the data record of each plot, the feature values such as parking quantity, traffic volume, and charging demand are multiplied by the corresponding weights respectively, and then summed. The summation calculation result is the score of the plot.

[0040] Based on the calculated scores, the priority of the charging demand for each plot can be evaluated. The higher the score of the plot, the greater its comprehensive charging demand, and it is more suitable as an alternative plot for charging station construction.

[0041] S3: Based on the scores of the plots, select the target plots from the candidate plots.

[0042] In this embodiment, based on the plot scores, plots with scores greater than a certain threshold m (for example, m = 0.7, i.e., 70%) can be selected as the target plots. The selected target plots will be used as the input of the operations research optimization model for site selection optimization calculation.

[0043] S4: Use the operations research optimization model to perform optimization calculations on the target plots to determine the site for the charging station.

[0044] In this embodiment, by comprehensively considering multiple factors (such as charging demand, traffic flow, service radius, construction cost, operation cost, etc.), the operations research optimization model can adopt an optimization algorithm (such as a linear integer programming algorithm) to perform optimization calculations on the target plots to determine the site for the charging station.

[0045] In some embodiments, the step of using the operations research optimization model to perform optimization calculations on the target plots to determine the site for the charging station includes: determining the objective function and constraints of the operations research optimization model according to the plot information of the target plots; using the operations research optimization model to perform optimization calculations on the target plots to generate the site for the charging station.

[0046] Specifically, the objective function can be set to maximize the coverage range of the charging station, can be set to maximize the utilization efficiency of the charging station, or can also be set to minimize the construction and operation costs of the charging station. The constraints can include but are not limited to: restricting the service radius of the charging station (for example, 3 kilometers), restricting the maximum service capacity of the charging piles, and restricting the maximum waiting time of the vehicles.

[0047] In some embodiments, the step of determining the objective function and constraints of the operations research optimization model according to the plot information of the target plots includes: determining a first coefficient based on the charging volume demand data of the target plots, the traffic volume data of the target plots, and a first decision variable, where the first decision variable represents whether to establish a target charging station on the target plot; determining a second coefficient based on the distance between the target plot and the site for the charging station, and a second decision variable, where the second decision variable represents the coverage relationship between the target plot and the site for the charging station; determining a third coefficient based on the second decision variable and a preset constant; determining the objective function based on the first coefficient, the second coefficient, and the third coefficient.

[0048] In some embodiments, determining the objective function based on the first coefficient, the second coefficient, and the third coefficient includes: determining the first coefficient as the numerator term; determining the difference between the second coefficient and the third coefficient as the denominator term; and determining the objective function according to the numerator term and the denominator term.

[0049] In some embodiments, determining the objective function and the constraint conditions of the operational research optimization model according to the plot information of the target plot includes at least one of the following: determining a first constraint condition according to the distance between the target plot and the plot for charging station location selection, and the charging service radius corresponding to each target plot; determining a second constraint condition according to the summation result of the first decision variable, where the first decision variable represents whether to establish a target charging station at the target plot; determining a third constraint condition according to the summation result of the second decision variable, where the second decision variable represents the coverage relationship between the target plot and the plot for charging station location selection; determining a fourth constraint condition according to the value range of the first decision variable; and determining a fifth constraint condition according to the value range of the second decision variable.

[0050] In a practical application example, the objective function can be as follows:

[0051]

[0052] The first constraint condition is d(i,j) ≤ r i , r i ∈R;

[0053] The second constraint condition is ∑ i∈N δ i = m;

[0054] The third constraint condition is

[0055] The fourth constraint condition is

[0056] The fifth constraint condition is

[0057] The formula symbols in the objective function and each constraint condition can refer to the explanations in the following table.

[0058]

[0059]

[0060] It should be noted that the objective function formula in this application example aims to obtain the charging station locations that contain many trajectory points and have a large traffic attraction within the service radius constraint, that is, to maximize the coverage range of the charging stations. According to the actual application scenario, to maximize the utilization efficiency of the charging stations or minimize the construction and operation costs of the charging stations, other objective function formulas can be established to achieve this.

[0061] In this application example, the numerator part of the objective function formula can represent the weighted sum of the charging amount requirements and traffic impact factors of all selected charging stations. Specifically, it is obtained by multiplying the demand di of all target plots i by the traffic impact factor ai, and only those target plots that are actually selected to build charging stations are counted (i.e., δ i = 1).

[0062] In this application example, the first part of the denominator of the objective function formula is a double summation expression, which can calculate the weighted sum of the distances d(i, j) between all target plots i and their corresponding other charging station location plots j within the service radius. For each target plot i, the distance d(i, j) to all j in the pre-location set Mi within its service radius r is calculated. Then, this distance multiplied by the decision variable Zij is a binary variable. If the pre-location j is within the service radius of the pre-location i, then Zij = 1; otherwise, it is 0.

[0063] The first part of the denominator, that is, the double summation can play the following roles.

[0064] Average the coverage distance: It calculates the total sum of the distances between all selected charging stations and the pre-locations within their service areas. Through this summation, the model not only considers how many pre-locations in the service area are covered, but also takes into account the distances between each pre-location and the charging stations, thereby reflecting the service efficiency of the charging stations to the surrounding areas.

[0065] Optimize the service quality: The denominator part optimizes the service quality by minimizing the average distance. A shorter d(i, j) means that the charging station is closer to the pre-locations within the service area, which may imply a faster arrival time and higher user satisfaction.

[0066] Prevent over-concentration: This part helps prevent over-concentration of charging stations. If many charging stations are concentrated in a certain area, then the will be very high, which will increase the value of the denominator and thus reduce the value of the objective function. This prompts the model to disperse the locations of the charging stations throughout the area.

[0067] Improve the flexibility of the model: This setting allows the model to have a certain degree of flexibility while meeting other constraints, such as deploying more charging stations in areas with higher demand.

[0068] In this application example, the second part of the denominator of the objective function formula is a penalty term part. The min function is used to compare with 1 and take the smaller value of the two. This means that if is at least 1 (i.e., at least one selected site is within the service radius of i), the result of this expression is 1. If is 0 (i.e., no selected site is within the service radius of i), the result of this expression is 0.

[0069] Then, the difference between this minimum value and 1 is calculated. If is at least 1, the difference is 0; otherwise, the difference is -1.

[0070] This difference can be multiplied by the large constant C. Since C is a very large positive number, if is at least 1, the product is 0; if is 0, the product is a large negative number, thus having a great negative impact on the objective function as a penalty.

[0071] In this way, the negative penalty term in the denominator effectively penalizes any pre-selected site that is not within the service radius of any selected charging station. The purpose is to encourage the selection of charging stations to cover as many pre-selected sites as possible and reduce unserved areas. Therefore, this objective function encourages the selection of charging stations that can cover multiple pre-selected sites and meet the demand volume and traffic impact factor.

[0072] In this application example, to avoid waste of power resources caused by uneven layout of electric taxi charging stations, the service radii of different regions can be used as the distance constraint between charging stations, that is, the first constraint condition is determined. The second constraint condition indicates that the number of finally selected charging stations is m. The third constraint condition indicates that each pre-selected site can only be covered by one finally selected site. The fourth constraint condition and the fifth constraint condition both indicate that the numerical value range is 0 or 1.

[0073] In the related art, traditional charging station site selection methods often cannot fully consider the spatial and temporal distribution characteristics of the charging demand of new energy vehicles, resulting in unreasonable charging station layout. For example, some charging stations are located in areas with relatively low charging demand, while there are problems of insufficient charging stations or inconvenient locations in high-demand areas. This mismatch between charging demand and supply will lead to low utilization rate of charging stations, serious waste of resources, and affect the return on investment.

[0074] The technical solution provided by one or more embodiments of the present disclosure can accurately depict the charging demand distribution in different regions, optimize the charging station site selection strategy, and maximize the utilization rate and service effect of charging stations by introducing a method based on big data analysis and prediction models.

[0075] In the related art, existing charging station location models usually only focus on a single location factor, such as geographical location, land price, etc., lacking comprehensive consideration of multiple important factors. However, the location of new energy vehicle charging stations should be a multi-objective and multi-constraint optimization problem, which needs to consider factors in multiple dimensions such as charging demand, traffic flow, construction cost, operation cost, service radius, user behavior, etc.

[0076] The technical solutions provided by one or more embodiments of the present disclosure, through the combination of an operations research optimization model and a multi-objective optimization algorithm, can balance and optimize among multi-dimensional factors, and achieve the global optimal solution of the charging station layout.

[0077] In the related art, the location and layout of charging stations not only affect the coverage area of their services, but also directly relate to the charging experience of users. If the location of the charging station is unreasonable, it may cause users to wait in line for a long time to charge, or need to travel a long distance to reach the charging station, thereby reducing the acceptance and usage frequency of new energy vehicles by users.

[0078] The technical solutions provided by one or more embodiments of the present disclosure, by considering factors such as the service radius, service capacity, and maximum waiting time of the charging station, propose a location scheme that can be dynamically adjusted and optimized to improve the charging convenience and satisfaction of users.

[0079] In the related art, the new energy vehicle market and users' charging behaviors are constantly changing, and traditional location methods lack flexibility and are difficult to adapt to future changing needs. With the increase in the ownership of new energy vehicles and the evolution of users' charging behaviors, the location strategy of charging stations needs to have dynamic adaptability to cope with diverse future demands.

[0080] The technical solutions provided by one or more embodiments of the present disclosure, through data-driven location models and algorithms, can dynamically adjust the location scheme according to real-time data to ensure the long-term effectiveness and sustainability of the charging station network layout.

[0081] In summary, the technical solutions provided by one or more embodiments of the present disclosure, by integrating big data analysis, intelligent optimization algorithms, and machine learning technologies, provide an innovative solution for the scientific planning and efficient construction of new energy vehicle charging infrastructure.

[0082] Please refer to Figure 2 , the intelligent location method based on big data and optimization algorithms provided by one embodiment of the present disclosure may include main processes such as location data preparation, scoring of alternative plots for charging stations, screening plots with scores greater than m, and optimizing the location.

[0083] The technical solutions provided by one or more embodiments of the present disclosure propose a method for locating charging stations based on multi-dimensional data fusion, comprehensively considering various data sources such as the number of parked vehicles, charging demand, traffic volume, and single-gun charging volume. Compared with traditional location methods, this data-driven location method can more accurately characterize the charging demand characteristics of different regions.

[0084] The technical solutions provided by one or more embodiments of the present disclosure propose a method for analyzing the correlation between features and single-gun charging volume, which can calculate the correlation between multi-dimensional data such as the number of parked vehicles, traffic volume, and charging demand and single-gun charging volume, and quantify the impact of each feature on charging demand. Different from traditional simple index analysis methods, this method comprehensively considers the complex relationships of multiple factors, which helps to more accurately evaluate the charging demand of plots.

[0085] By normalizing the feature correlation, the weight of each feature is determined so that the sum of the weights of all features is 1. This dynamic adjustment method of weights can be adaptively optimized according to the changes of data features, ensuring the scientificity and rationality of the score calculation results.

[0086] The method of weighted summation is used to calculate the comprehensive score of each plot. This method can integrate the influence of multi-dimensional data into a unified index, so as to more accurately identify plots with higher charging demand and provide decision support for the location of charging stations. Compared with traditional charging station location methods, this data-driven scoring method is more flexible and accurate.

[0087] The technical solutions provided by one or more embodiments of the present disclosure make full use of multi-dimensional data such as the number of parked vehicles, traffic volume, and charging demand, and combine features such as time and space to provide a comprehensive method for calculating the plot score. By integrating multiple data sources, the accuracy and reliability of charging station location are improved.

[0088] The technical solutions provided by one or more embodiments of the present disclosure combine operations research optimization technology to propose an optimization model for optimizing the location of charging stations. The model comprehensively considers multiple factors, including charging demand, traffic flow, service radius, and the number of parked vehicles, to maximize the service coverage and benefits of charging stations, while controlling the construction and operation costs of charging stations.

[0089] Please refer to Figure 3 , the present disclosure also provides an intelligent location device based on big data and optimization algorithms, and the device includes:

[0090] A data acquisition unit 100, configured to acquire multi-dimensional location data of multiple candidate plots, where the multi-dimensional location data includes parked vehicle number data, charging demand data, traffic volume data, and single-gun charging volume data;

[0091] A scoring unit 200 is configured to perform correlation analysis and statistical operations on the multi-dimensional site selection data to determine the site score of the candidate plot.

[0092] A screening unit 300 is configured to screen out target plots from the candidate plots based on the site scores.

[0093] A site selection unit 400 is configured to perform optimization calculations on the target plots using an operations research optimization model to determine the site for the charging station.

[0094] In one embodiment, the data acquisition unit 100 is specifically configured to use a geospatial indexing system to divide the charging site selection area into grids to determine the candidate plots; for each candidate plot, obtain the corresponding multi-dimensional site selection data.

[0095] In one embodiment, the scoring unit 200 is specifically configured to calculate the feature correlation between each feature data and the single-gun charging volume data, where the feature data includes at least one of the parking quantity data, the charging volume demand data, and the traffic volume data; normalize the feature correlation to obtain the feature weight of each feature data; based on the feature weight and the data value of the feature data, determine the site score of the candidate plot.

[0096] In one embodiment, the site selection unit 400 is specifically configured to determine the objective function and constraints of the operations research optimization model according to the plot information of the target plot; use the operations research optimization model to perform optimization calculations on the target plot to generate the site for the charging station.

[0097] In one embodiment, the site selection unit 400 includes a function subunit 401. The function subunit 401 is specifically configured to determine a first coefficient based on the charging volume demand data of the target plot, the traffic volume data of the target plot, and a first decision variable, where the first decision variable represents whether to establish a target charging station at the target plot; determine a second coefficient based on the distance between the target plot and the site for the charging station and a second decision variable, where the second decision variable represents the coverage relationship between the target plot and the site for the charging station; determine a third coefficient based on the second decision variable and a preset constant; determine the objective function based on the first coefficient, the second coefficient, and the third coefficient.

[0098] In one embodiment, the function subunit 401 is further configured to determine the first coefficient as the numerator term; determine the difference between the second coefficient and the third coefficient as the denominator term; determine the objective function according to the numerator term and the denominator term.

[0099] In one embodiment, the site selection unit 400 includes a condition sub-unit 402. The condition sub-unit 402 is specifically configured to determine a first constraint condition according to the distance between the target plot and the site selection plot of the charging station, and the charging service radius corresponding to each target plot; determine a second constraint condition according to the summation result of the first decision variables, where the first decision variables represent whether to establish a target charging station on the target plot; determine a third constraint condition according to the summation result of the second decision variables, where the second decision variables represent the coverage relationship between the target plot and the site selection plot of the charging station; determine a fourth constraint condition according to the value range of the first decision variables; and determine a fifth constraint condition according to the value range of the second decision variables.

[0100] Each unit illustrated in the above embodiment can be specifically implemented by a computer chip or by a product with a certain function. A typical implementation device is a computer. Specifically, the computer can be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0101] For convenience of description, the above devices are described by function as various units separately. Of course, when implementing the present application, the functions of each unit can be implemented in one or more software and / or hardware.

[0102] Please refer to Figure 4 , the present disclosure also provides an electronic device, where the electronic device includes a memory and a processor, the memory is used to store a computer program, and when the computer program is executed by the processor, the intelligent site selection method based on big data and optimization algorithm described above is implemented.

[0103] The present disclosure also provides a computer-readable storage medium, where the computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the intelligent site selection method based on big data and optimization algorithm described above is implemented.

[0104] Among them, the processor may be a Central Processing Unit (CPU). The processor may also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. chips, or a combination of the above types of chips.

[0105] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the methods in the embodiments of the present disclosure. The processor executes various functional applications and data processing of the processor by running the non-transitory software programs, instructions, and modules stored in the memory, that is, implements the methods in the above method embodiments.

[0106] The memory may include a program storage area and a data storage area. Among them, the program storage area can store an operating system and application programs required for at least one function; the data storage area can store data created by the processor, etc. In addition, the memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely set relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above networks include, but are not limited to, the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0107] Those skilled in the art can understand that to implement all or part of the processes in the methods of the above embodiments, it can be completed by instructing relevant hardware through a computer program. The program can be stored in a computer-readable storage medium. When the program is executed, it may include the processes of the embodiments of the above methods. Among them, the storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a Flash Memory, a Hard Disk Drive (abbreviation: HDD), or a Solid-State Drive (SSD), etc.; the storage medium may also include a combination of the above types of memories.

[0108] Each embodiment in this specification is described in a progressive manner. For the identical or similar parts among the embodiments, reference can be made to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the embodiments of the device, equipment, and storage medium, since they are basically similar to the method embodiments, the description is relatively simple, and reference can be made to the relevant parts of the method embodiments for the relevant content.

[0109] The above description is only for the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

[0110] Although the embodiments of the present disclosure have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present disclosure, and such modifications and variations fall within the scope defined by the appended claims.

Claims

1. An intelligent site selection method based on big data and optimization algorithm, characterized in that: The method comprises: Acquire multi-dimensional site selection data of multiple candidate plots, wherein the multi-dimensional site selection data includes parking quantity data, charging quantity demand data, traffic volume data, and single-gun charging quantity data; Performing correlation analysis and statistical operations on the multi-dimensional site selection data to determine the site scores of the candidate sites; Based on the plot scores, screening out target plots from the candidate plots; The operations research optimization model is used to optimize the target plot and determine the site selection plot for the charging station.

2. The method according to claim 1, characterized in that The step of obtaining multi-dimensional site selection data of a plurality of candidate plots includes: Using a geospatial indexing system, gridding the charging site selection area to determine the candidate plots; For each of the candidate plots, the corresponding multi-dimensional site selection data is obtained.

3. The method according to claim 1, characterized in that The performing correlation analysis and statistical operation on the multi-dimensional site selection data to determine the plot score of the candidate plot includes: Calculating the characteristic correlation between each characteristic data and the single-gun charging amount data, wherein the characteristic data includes at least one of the parking quantity data, the charging amount demand data and the traffic volume data; Normalizing the feature correlation to obtain a feature weight for each feature data; The parcel score of the candidate parcel is determined based on the feature weight and the data value of the feature data.

4. The method according to claim 1, characterized in that: The method of using the operations research optimization model to optimize the target plot and determine the site selection plot for the charging station includes: Determining the objective function and constraint conditions of the operations optimization model according to the plot information of the target plot; The operations research optimization model is used to optimize the target plot and generate the charging station site selection plot.

5. The method according to claim 4, characterized in that Determining the objective function and constraint conditions of the operations optimization model according to the plot information of the target plot includes: Determining a first coefficient based on the charging demand data of the target plot, the traffic volume data of the target plot, and a first decision variable, wherein the first decision variable represents whether to establish a target charging station in the target plot; Determining a second coefficient based on the distance between the target plot and the charging station site selection plot and a second decision variable, wherein the second decision variable represents the coverage relationship between the target plot and the charging station site selection plot; Determine a third coefficient based on the second decision variable and a preset constant; The objective function is determined based on the first coefficient, the second coefficient, and the third coefficient.

6. The method according to claim 5, characterized in that The determining the objective function based on the first coefficient, the second coefficient and the third coefficient comprises: Determine the first coefficient as a numerator term; Determine the difference between the second coefficient and the third coefficient as the denominator; The objective function is determined according to the numerator term and the denominator term.

7. The method according to claim 4, characterized in that Determining the objective function and constraint conditions of the operations optimization model according to the plot information of the target plot includes at least one of the following: Determine a first constraint condition according to the distance between the target plot and the charging station site selection plot, and the charging service radius corresponding to each of the target plots; Determining a second constraint condition according to a summation result of a first decision variable, wherein the first decision variable represents whether to establish a target charging station in the target plot; Determining a third constraint condition according to a summation result of a second decision variable, wherein the second decision variable represents an overlay relationship between the target plot and the charging station site selection plot; Determining a fourth constraint condition according to the value range of the first decision variable; A fifth constraint condition is determined according to the value range of the second decision variable.

8. An intelligent site selection device based on big data and optimization algorithm, characterized in that: The device comprises: A data acquisition unit, used to acquire multi-dimensional site selection data of multiple candidate plots, wherein the multi-dimensional site selection data includes parking quantity data, charging quantity demand data, traffic volume data and single-gun charging quantity data; A scoring unit, used to perform correlation analysis and statistical operations on the multi-dimensional site selection data to determine the site scores of the candidate sites; A screening unit, configured to screen out a target plot from the candidate plots based on the plot scores; The site selection unit is used to optimize the target plot by using an operations research optimization model to determine the site selection plot for the charging station.

9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory is used to store a computer program, and when the computer program is executed by the processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium is used to store a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images