Charging station capacity determination method and device based on multi-dimensional features

Abstract

The present application relates to the technical field of charging station sizing, and discloses a charging station sizing method and device based on multi-dimensional features. The present application discloses obtaining a driving record table and a monthly feature record table of electric vehicles in a city, determining a hexagonal graph representing the service area of a charging station based on the driving record table, and dividing a district in the city according to the hexagonal graph; judging potential charging customers and charging demand of electric vehicles in the district, determining charging demand vehicles and charging power of each time period in the district; and determining a sizing scheme corresponding to the charging station based on the charging demand vehicles, the charging power and a future vehicle increment prediction value, so that the sizing scheme of the charging station can be determined in a time-space combined manner, the sizing process is more comprehensive and precise, and the sizing effect is improved.

Description

Technical Field

[0001] This invention relates to the field of charging station capacity grading technology, specifically to a charging station capacity grading method and apparatus based on multi-dimensional features. Background Technology

[0002] With the rapid growth of electric vehicle ownership, the demand for electric vehicle charging is also constantly increasing. Due to the unreasonable and imperfect layout of charging piles in the early stages of development, there are currently problems such as difficulty in charging electric vehicles and poor charging experience. To solve this problem, there are some methods for determining the capacity of charging piles based on sampling and simulation. However, these traditional methods for determining the capacity of charging stations are difficult to meet the market background of the large-scale growth of electric vehicles. They have problems such as incomplete and imprecise decision-making basis in the capacity determination process, and a better solution is needed. Summary of the Invention

[0003] In view of this, the present invention provides a charging station capacity determination method and apparatus based on multi-dimensional features to solve the problem of incomplete decision-making basis in the charging station capacity determination process, which leads to poor capacity determination effect.

[0004] This invention provides a method for determining the capacity of charging stations based on multi-dimensional features. The method includes acquiring driving record tables and monthly feature record tables of electric vehicles within a city; determining a hexagonal shape representing the service area of ​​a charging station based on the driving record tables; dividing the city into zones according to the hexagonal shape; identifying potential charging customers and charging needs for electric vehicles within the zones; determining the vehicles and electricity demand for charging in each time period within the zones; and determining the capacity allocation scheme for the charging station based on the vehicles, electricity demand, and predicted future vehicle growth.

[0005] In another aspect, the present invention provides a charging station capacity determination device based on multi-dimensional features. The device includes: a division module, used to acquire driving record tables and monthly feature record tables of electric vehicles in the city, and based on the driving record tables, determine a hexagonal shape representing the service area of ​​the charging station, and divide the city into areas according to the hexagonal shape; a demand judgment module, used to judge potential charging customers and charging demand of electric vehicles in the area, and determine the charging demand vehicles and charging power required for each time period in the area; and a capacity determination module, used to determine the capacity determination scheme corresponding to the charging station based on the charging demand vehicles, the charging power required, and the predicted value of future vehicle increment.

[0006] In another aspect, the present invention provides a computer device comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to implement the above-described charging station capacity determination method based on multi-dimensional features.

[0007] In another aspect, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to implement the above-described charging station capacity determination method based on multi-dimensional features.

[0008] In another aspect, the present invention provides a computer program product, including computer instructions for causing a computer to execute the charging station capacity determination method based on multidimensional features of the first aspect or any corresponding embodiment thereof.

[0009] In this process, the service area of ​​the charging station is determined based on the driving record table and monthly characteristic record table of electric vehicles. The city is divided into districts based on the service area, and the charging demand vehicles and charging power required at different times in each district, as well as the predicted value of future vehicle increase, are determined. The corresponding capacity setting scheme for the charging station in the district is determined. Combining the service area of ​​the charging station and the charging demand at different times in the service area, the capacity setting scheme of the charging station is determined in a time-space combination. This makes the capacity setting process more comprehensive and precise, improves the capacity setting effect, avoids the construction of too many or too few charging piles, and thus improves the utilization rate of charging piles. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the specific embodiments or related technologies of the present invention, the drawings used in the description of the specific embodiments or related technologies will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0011] Figure 1 This is a flowchart illustrating the charging station capacity determination method based on multi-dimensional features provided in an embodiment of the present invention.

[0012] Figure 2 This is a schematic diagram of the switching process of the charging station capacity grading method based on multi-dimensional features provided in the embodiments of the present invention;

[0013] Figure 3 This is a schematic diagram of the area and adjacent areas of the charging station capacity determination method based on multi-dimensional features provided in the embodiments of the invention;

[0014] Figure 4This is a schematic flowchart illustrating the charging station capacity determination method based on multi-dimensional features provided in this embodiment of the invention.

[0015] Figure 5 This is a schematic diagram of the structure of the charging station capacity stabilization device based on multi-dimensional features provided in an embodiment of the present invention;

[0016] Figure 6 This is another structural schematic diagram of the charging station capacity stabilization device based on multi-dimensional features provided in the embodiments of the present invention. Detailed Implementation

[0017] In recent years, the number of electric vehicles has grown rapidly, leading to a huge demand for charging. On the one hand, limited by the current development of power battery technology, the long charging process and inconvenience of electric vehicles have become major factors restricting their promotion and application and consumer purchases. On the other hand, some older residential communities were not developed with consideration for the need for electric vehicle charging due to transportation electrification, resulting in residents lacking the basic conditions to install private charging piles. In addition, the unreasonable and incomplete layout of charging piles in the early stages of development has led to a shortage of charging piles in most areas and idle charging piles in remote areas. The unreasonable layout of fast charging piles and slow charging piles and the insufficient utilization rate of charging piles have become the biggest problems in the industry. These problems have resulted in the current predicament of difficult charging for consumers, poor charging experience, and poor investment returns and profitability for operators, becoming a key obstacle to the healthy and rapid development of my country's new energy vehicle market.

[0018] To address the aforementioned problems, existing technologies often employ methods based on sampling, simulation, or traditional fuel vehicle data to replace methods for predicting charging demand and determining the capacity of charging stations.

[0019] However, the above technology may have the following problems:

[0020] 1. The decision-making basis considered during the capacity determination process is not comprehensive enough, resulting in poor capacity determination effect of charging piles, thus leading to low utilization rate of charging piles;

[0021] 2. The user experience when recharging a car was not considered during the capacity setting process, resulting in a poor user experience;

[0022] 3. The future increase in the number of vehicles was not considered during the capacity determination process, resulting in the capacity determination results of charging piles not conforming to the market background of a large increase in electric vehicles, which affects the service life of charging stations.

[0023] To address at least one of the aforementioned problems, various embodiments of the present invention provide a charging station capacity determination method based on multi-dimensional features, comprising: acquiring driving record tables and monthly feature record tables of electric vehicles in the city; determining a hexagonal shape representing the service area of ​​the charging station based on the driving record tables; dividing the city into zones according to the hexagonal shape; judging potential charging customers and charging demand for electric vehicles in the zones; determining the charging demand vehicles and charging power required for each time period in the zones; and determining the capacity determination scheme corresponding to the charging station based on the charging demand vehicles, charging power required, and future vehicle increment predictions.

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] According to embodiments of the present invention, a method for determining the capacity of charging stations based on multi-dimensional features is provided. Figure 1 This is a flowchart illustrating the charging station capacity grading method based on multi-dimensional features provided in an embodiment of the present invention, as shown below. Figure 1 As shown, the process includes the following steps:

[0026] Step S101: Obtain the driving record table and monthly feature record table of electric vehicles in the city. Based on the driving record table, determine the hexagonal shape representing the service area of ​​the charging station. Divide the city into areas according to the hexagonal shape.

[0027] Step S102: Identify potential charging customers and charging demand for electric vehicles in the area, and determine the vehicles and charging power required for each time period in the area.

[0028] Step S103: Based on the vehicles requiring charging, the amount of electricity needed for charging, and the predicted increase in future vehicles, determine the capacity allocation scheme for the charging station.

[0029] In one possible implementation, the record table can be a data structure with a fixed structure. The record table can include, but is not limited to, a table name, fields, and records. The table name can be a unique name for the record table, the fields can be the data type of each column in the record table, and the records can be the specific data corresponding to each row in the record table.

[0030] Specifically, the driving record table can be used to characterize the driving characteristics of each electric vehicle (hereinafter referred to as vehicle) in the city, and the monthly characteristic record table can be used to characterize the charging characteristics of each vehicle in the city in each month.

[0031] For example, the driving record sheet may include, but is not limited to: vehicle identification number, trip start time, trip end time, trip start location, trip end location, and average trip speed. The monthly feature record sheet may include, but is not limited to: vehicle identification number, month, total number of charging times this month, and average charging time this month.

[0032] In one possible implementation, a hexagonal shape representing the service area of ​​the charging station is determined based on the driving record table. The city is then divided into zones according to this hexagonal shape, and this is achieved through the following steps:

[0033] Obtain driving data from the vehicle's driving record table and the geographical coordinates of the charging station. Based on the driving data and geographical coordinates, determine the vehicles that can be reached within the coverage area of ​​each charging station and classify the vehicles into the hexagonal area of ​​the charging station.

[0034] Among them, a charging station refers to a facility or place that provides charging services for electric vehicles, including multiple charging piles and supporting power infrastructure; the geographical coordinates can refer to the latitude and longitude coordinates of the charging station.

[0035] Here, using hexagonal grids with uniform adjacency to divide the service area of ​​the charging stations can ensure that the area division has close coverage.

[0036] In one possible implementation, potential charging customers for electric vehicles within the area are identified, and the charging demand for vehicles in the area at different times is determined, based on at least one of the following steps:

[0037] Determine whether a vehicle needs charging based on its State of Charge (SOC).

[0038] Determine whether a vehicle needs charging based on its trajectory.

[0039] Determine whether a vehicle needs charging based on its charging habits and historical charging data.

[0040] Specifically, if a vehicle's SOC is lower than a preset battery threshold, it indicates that the vehicle needs to be charged and can be considered a vehicle with charging demand. If the vehicle's starting point and ending point are frequently within the area, it indicates that the vehicle's activity range belongs to the area and can be considered a vehicle with charging demand in that area. Analyzing the vehicle's historical charging behavior, if the vehicle's historical data indicates that it is frequently charged at night, it indicates that the vehicle can be considered a vehicle with charging demand in that area during nighttime hours.

[0041] Among them, potential charging customers can refer to electric vehicle users who may need to charge within the area.

[0042] In one possible implementation, the charging demand of electric vehicles within the area is determined, and the corresponding charging demand for each time period within the area is determined, based on at least one of the following steps:

[0043] Based on historical charging data for the area, peak and off-peak charging times are identified within the area. Combined with vehicle type records and charging habits, the number of vehicles that need charging during a certain period is predicted.

[0044] Based on the SOC and battery capacity of each vehicle, estimate the charging demand of each vehicle at a certain time period.

[0045] Among them, charging demand refers to the amount of charging required by vehicles within the area during a specific time period.

[0046] In one possible implementation, based on the number of vehicles requiring charging, the amount of electricity needed for charging, and the projected increase in future vehicles, the capacity allocation scheme for the charging station is determined, including:

[0047] Based on the analyzed data, the projected increase in future vehicles is determined. Based on the vehicles requiring charging, the amount of electricity needed for charging, and the projected increase in future vehicles, the number of charging piles and the power demand capacity corresponding to the charging station are determined. The number of charging piles can refer to the number of charging piles that the charging station needs to be equipped with, and the power demand capacity can refer to the power supply obtained by the charging station from the electricity consumption.

[0048] Specifically, based on market growth forecasts, vehicle sales data, and policy support, the growth trend of the number of electric vehicles in the area will be predicted, and the future vehicle increment forecast will be determined.

[0049] Using the methods described above, the capacity design of charging stations can be determined by combining time and space, and the scale and capacity of charging stations can be rationally planned to meet the continuously growing demand for electric vehicle charging.

[0050] In one specific embodiment, the driving record table and monthly feature record table of electric vehicles in the city are obtained based on the following steps:

[0051] Based on the vehicle network data of electric vehicles, the corresponding vehicle operation data of electric vehicles is determined. The vehicle operation data includes: driving data, parking data and charging data.

[0052] Based on the annual average monthly temperature, the 12 months are divided into at least one monthly temperature range, and each monthly temperature range includes at least one month; the annual average monthly temperature is related to the energy consumption of electric vehicles.

[0053] Based on vehicle operation data, user profiles of electric vehicles are created to determine the charging usage characteristics of electric vehicles corresponding to temperature ranges in each month.

[0054] Based on charging usage characteristics, determine the driving record sheet and monthly characteristic record sheet for electric vehicles.

[0055] In one possible implementation, based on the vehicle-to-everything (V2X) data of the electric vehicle, the corresponding vehicle operation data of the electric vehicle is determined. The vehicle operation data includes driving data, parking data, and charging data, and is achieved based on the following steps:

[0056] Based on the vehicle's vehicle network data, obtain the vehicle's annual charging data segments, which include, but are not limited to: driving time, driving speed, cumulative mileage, latitude and longitude, voltage, and current;

[0057] Vehicle driving data, parking data, and charging data are determined based on charging data segments.

[0058] In one possible implementation, based on the annual average monthly temperature, the 12 months are divided into at least one monthly temperature interval, each interval including at least one month, including:

[0059] Based on the characteristics of vehicle energy consumption changing with temperature and the average monthly temperature of the year, the months are divided into intervals based on a 5-degree Celsius difference in the average monthly temperature, thus dividing the months into at least one temperature interval.

[0060] Specifically, the monthly temperature ranges are shown in Table 1:

[0061]

[0062] Table 1

[0063] Each monthly temperature range includes at least one month, and the temperature difference between monthly temperature ranges is 5 degrees Celsius.

[0064] In one possible implementation, user profiles for electric vehicles are created based on vehicle operation data to determine the charging usage characteristics of electric vehicles corresponding to temperature ranges for each month, including:

[0065] Using a monthly temperature range as the statistical period, monthly vehicle usage characteristics are determined based on vehicle operation data. These monthly usage characteristics are then used to create a user profile based on vehicle charging and driving behavior. This user profile is used to characterize the vehicle owner's behavior patterns, usage preferences, and charging needs, in order to identify different types of vehicle user groups.

[0066] Specifically, monthly usage characteristic data includes, but is not limited to: parking area, charging area, average parking duration, average charging amount per charge, and average initial SOC of charging.

[0067] Among them, the parking area can refer to the geographical area where the vehicle frequently stops or stays during daily use, the charging area can refer to the area where the vehicle is frequently charged, the average parking time can refer to the average parking time of the vehicle each time it stops, the average charging amount can refer to the average amount of electricity that the vehicle replenishes each time it is charged, and the average charging start SOC in the monthly usage data characteristics can refer to the ratio of the average remaining battery capacity at the start of charging to the end of charging.

[0068] For example, creating a user profile based on monthly usage characteristic data may include:

[0069] When the parking area is mainly concentrated in residential and work areas, the charging area is slow charging at home or work, the average parking time is relatively long, the average charging amount is medium or small, the average starting SOC is relatively high, and the preference for fast or slow charging is towards slow charging, the vehicle owner can be a daily short-distance commuter.

[0070] In one possible implementation, based on charging usage characteristics, a driving record table and a monthly characteristic record table for the electric vehicle are determined, including:

[0071] On a per-vehicle basis, analyze the charging usage characteristics of the vehicle in different monthly temperature ranges and determine the monthly temperature range charging characteristic record table.

[0072] Based on vehicle operation data, a trip chain record table and a monthly feature record table are determined.

[0073] Specifically, the monthly temperature range charging characteristic record table includes, but is not limited to: vehicle identification number, month and temperature range, number of charging times, charging amount and SOC starting value; the trip chain record table includes, but is not limited to: vehicle identification number, departure location, arrival location, driving time, driving distance; the monthly characteristic record table includes, but is not limited to: vehicle identification number, month, number of charging times, charging amount.

[0074] Using the methods described above, based on the characteristics of vehicle energy consumption changing with temperature, we determine monthly temperature range charging characteristic record tables, trip chain record tables, and monthly characteristic record tables. By performing feature mining and statistical analysis according to different levels, time dimensions, and regions, we can better predict charging demand under different months and temperatures, thereby optimizing the layout of charging stations and power dispatch. Determining the monthly characteristic record tables makes it easier to predict future electric vehicle growth trends and corresponding charging demand.

[0075] In one specific embodiment, based on the driving record table, a hexagonal shape representing the service area of ​​the charging station is determined. The city is then divided into zones according to this hexagonal shape, which is achieved through the following steps:

[0076] Based on the driving record table, the maximum flow rate of vehicles in the city and the median driving time were determined; the driving time was used to characterize the time required for vehicles in the city to reach the charging station.

[0077] The side length of the hexagon is determined by the product of the maximum vehicle flow rate and the median driving time. The convex hull algorithm is then used to construct the hexagon based on the boundary determined by the side length.

[0078] Using a pre-defined parallel line matching method, the hexagonal shape to which the parking point belongs is determined based on the coordinate position of the electric vehicle's parking point. The city is then divided into zones based on the hexagonal shape. Each zone includes, but is not limited to, charging stations and electric vehicles.

[0079] In one possible implementation, based on driving record tables, the maximum vehicle flow speed and median driving time within the city are determined, including:

[0080] To obtain the distribution of traffic flow speeds within the city, based on the average vehicle speed V during time period t. veh,t The urban traffic flow velocity V during time period t is determined using the following formula. tra,t :

[0081] V tra,t =sum(V veh,t )

[0082] The maximum flow velocity V of the vehicle is calculated using the following formula. max :

[0083] V max =max(V tra,t )

[0084] Get T last,cha The median driving time T is calculated using the following formula. mid :

[0085] T mid =mid(T last,cha )

[0086] Among them, T last,cha It is used to indicate the last time a vehicle traveled before arriving at a charging station.

[0087] Among them, the maximum vehicle flow rate can represent the vehicle speed under ideal traffic conditions, and the median driving time can represent the driving time required for a vehicle to reach a charging station.

[0088] In one possible implementation, the side length of the hexagon is determined based on the product of the maximum vehicle flow rate and the median driving time. Then, using a convex hull algorithm, the hexagon is constructed based on the boundary determined by the side length, including:

[0089] The side length L of a hexagon is calculated using the following formula:

[0090] L = V max ×T mid

[0091] The latitude and longitude coordinates in the vehicle's charging data segment are fitted with the hexagonal image region using the convex hull algorithm to determine whether the vehicle's charging location is within the region of the hexagonal image.

[0092] Specifically, by using the convex hull algorithm and dividing the area into regular hexagonal regions, the charging location of the vehicle is fitted to the corresponding hexagonal region to determine the region where the vehicle charging behavior occurs. The fitting process of the convex hull algorithm includes: drawing a parallel line between the charging location and the hexagon, and checking whether the line coincides with the three intersection points of the hexagon. If they coincide, the charging location belongs to the region.

[0093] For example, a hexagonal graphic representing the service area of ​​a charging station is as follows: Figure 2 As shown, Figure 2 This is a schematic diagram of a charging station capacity determination method based on multi-dimensional features provided in an embodiment of the present invention. The side length of the hexagonal shape is determined based on the product of the maximum vehicle flow rate and the median driving time, and the boundary of the hexagonal image is determined based on the convex hull algorithm.

[0094] By using the above methods and dividing the area into regular hexagonal zones, the service area of ​​charging stations can be evenly covered, reducing service blind spots and improving the convenience for vehicle owners to find charging stations. By setting and calculating the boundary length based on the flow rate changes in the region, the time taken to reach the charging station during peak congestion periods can be effectively controlled, improving the user charging experience. Dividing the area based on the vehicle's driving speed and median driving time ensures that most vehicles can reach the nearest charging station within a reasonable time.

[0095] In one specific embodiment, potential charging customers and charging demand are assessed for electric vehicles within the designated area to determine the vehicles and electricity consumption required for charging at different times within the area, including:

[0096] Based on preset permanent assessment standards and preset charging habit standards, determine at least one permanent and non-permanent area within a region, and determine the ownership of private charging piles within the permanent area.

[0097] Based on the availability of private charging stations in the area where the resident is stationed, potential customers and non-potential customers are identified at different times within the area.

[0098] Based on the real-time charging status of potential customers' monthly characteristic records, determine the vehicles with charging demand in each time period within the area.

[0099] Based on the average charging status in the monthly characteristic record table of potential customers, the charging power required for each time period in the area is determined.

[0100] In one possible implementation, based on preset permanent location assessment criteria and preset charging habit criteria, at least one permanent and non-permanent area within a designated zone is identified, along with the ownership status of private charging stations within the permanent area, including:

[0101] When the parking time and frequency of a vehicle in a designated area meet the preset permanent parking assessment criteria, the area is determined as the permanent parking area for that vehicle.

[0102] When the parking time and frequency of a vehicle in a designated area do not meet the preset permanent parking assessment criteria, the area is determined to be a non-permanent parking area for that vehicle.

[0103] When a vehicle has a private charging device, it is considered to have a private charging device when the charging frequency at a point of interest within its permanent area is greater than the preset frequency, the charging power is less than or equal to the preset power, and there is no charging record in the charging facility operator's database.

[0104] When a vehicle charges at a point of interest within its permanent location more frequently than a preset frequency, and the charging facility operator's database contains a charging record for that point of interest, it indicates that the vehicle does not have a private charging device and has a preferred charging station.

[0105] Specifically, the preset permanent stationing assessment criteria may include: a stationing frequency greater than 33% and a stationing time greater than the average charging time; permanent stationing areas may refer to areas where vehicles have long stationing times and high frequencies, and permanent stationing areas may include, but are not limited to, residences and workplaces, while non-permanent stationing areas may refer to areas where vehicles occasionally stop; wherein, permanent stationing areas and non-permanent stationing areas are determined based on stationing areas in monthly usage characteristic data.

[0106] Point of Interest (POI) can refer to a way of expressing a specific geographical location in a geographic information system.

[0107] Furthermore, "no habitual charging station" refers to a situation that does not meet the criteria for either having private charging equipment or having a habitual charging station but no private charging equipment. The car owner does not have private charging equipment, nor does he / she have a habitual public charging location.

[0108] In one possible implementation, based on the availability of private charging stations within the designated area, potential and non-potential customers are identified for different time periods within the designated area, including:

[0109] When a vehicle is parked in a designated area, has no private charging facilities in the area, and has been charged at least once in the area, the vehicle is identified as a potential customer in the area.

[0110] When a vehicle is parked in a designated area and there are no private charging facilities within the area, the vehicle is identified as a potential customer within the area.

[0111] When a vehicle is parked in a designated area and has a private charging facility within that area, or when a vehicle is parked in a non-designated area, the vehicle is identified as a non-potential customer within that area.

[0112] Among them, potential customers can refer to vehicles that rely on public charging stations for charging, suspected potential customers can refer to vehicles that may use public charging stations for charging in the future, and non-potential customers can refer to vehicles that do not need to use public charging stations for charging or do not rely on public charging stations in a specific area for charging.

[0113] Here, by accurately identifying potential customers with charging needs as one of the bases for determining capacity, it is possible to avoid over-constructing unnecessary charging piles.

[0114] In one possible implementation, based on the real-time charging status in the monthly characteristic record table of potential customers, the charging demand vehicles corresponding to each time period in the area are determined, which is achieved based on the following steps:

[0115] Obtain the number of vehicles with a real-time SOC less than the average starting SOC of N months among potential customers and suspected potential customers for each time period, and use this number of vehicles as the corresponding charging demand vehicles for that time period.

[0116] Among them, real-time SOC can refer to the real-time charging status of the vehicle, that is, the current remaining charge of the battery; average charging start SOC can refer to the battery charging status at the average start of charging over N months, where N can be set according to specific needs.

[0117] In one possible implementation, the charging demand for each time period within a given area is determined based on the average charging status recorded in the monthly characteristic log of potential customers. This can be achieved through the following steps:

[0118] Obtain the historical average SOC change of the vehicle in each month, and the average SOC consumption per trip per day of the vehicle over N months;

[0119] The minimum value between the historical average SOC change and the range-average SOC consumption is determined as the corresponding charging power requirement for the vehicle.

[0120] Specifically, the historical average SOC change can refer to the overall trend of a vehicle's charging and energy consumption over a one-month period, while the single-trip average SOC consumption can refer to the amount of battery energy consumed during a single trip. The historical average SOC change is used to characterize the vehicle's energy change trend over a month, while the single-trip average SOC consumption is used to characterize the vehicle's daily energy consumption.

[0121] Here, the minimum value between the historical average SOC change and the single-trip average SOC consumption is taken. When the historical average SOC change is large and the single-trip average SOC consumption is small, it can be indicated that the vehicle's recent usage is relatively light. Therefore, using the smaller consumption as an estimate of the minimum charging demand is a more conservative approach. When the historical average SOC change is small and the single-trip average SOC consumption is large, the smaller change is still used as the basis for estimating the charging demand.

[0122] In one possible implementation, a data table is used to determine the potential charging data of vehicles based on date type, charging demand of vehicles in different time periods, and charging power requirements, as shown in Table 2 below:

[0123]

[0124]

[0125] Table 2

[0126] The system includes: Area ID (for station construction); Center Point Coordinates (for station construction); Geographic Fence (for station construction); City Name (for recording and classifying data from different cities); Date Type (for identifying whether the period is a holiday); Time Segment (can be 15 minutes per segment); Maximum Potential Customers Starting Charging During This Time Segment; Maximum Suspected Potential Customers Starting This Time Segment; Maximum Total Charging During This Time Segment (including potential and suspected potential customers); Average Charging Amount of Potential Customers Starting This Time Segment; and Standard Deviation of Charging Amount of Potential Customers Starting This Time Segment, reflecting the differences in charging amounts between different vehicles.

[0127] By using the above methods to determine the vehicles and electricity required for charging in each time period, areas and time periods with high charging demand can be identified, thus enabling more effective allocation of charging resources. By predicting charging demand and rationally allocating resources, waiting time for users at charging stations can be reduced, improving the user charging experience. Ensuring sufficient charging piles during high-demand periods can enhance user satisfaction and encourage more users to choose public charging facilities.

[0128] In one specific embodiment, the capacity allocation scheme for the charging station is determined based on the number of vehicles requiring charging, the amount of electricity needed for charging, and the predicted increase in future vehicles, including:

[0129] The system obtains traffic flow data for each time period within the area, determines the number of electric vehicles in the traffic flow based on a preset ratio, and determines the expected charging pile demand for each time period within the area based on the number of electric vehicles. The expected charging pile demand is used to characterize the charging pile demand gap in the area during the corresponding time period.

[0130] When the expected demand for charging piles in the area during the first time period exceeds the gap threshold, determine the average number of charging vehicles of potential customers in the first time period and the adjacent second time period.

[0131] Determine the difference between the average number of charging vehicles in the area and the number of adjacent preset public charging piles in the area, and use the difference as the number of charging piles corresponding to the charging station.

[0132] Obtain the minimum charging power and the optimal charging power for the charging piles within the area, and determine the rated power of the charging piles based on the minimum charging power and the optimal charging power for the charging experience.

[0133] Based on the number of charging piles and their rated power, determine the corresponding capacity scheme for the charging station.

[0134] In one possible implementation, traffic flow data for each time period within the area is obtained, the number of electric vehicles in the traffic flow is determined according to a preset ratio, and the estimated charging pile demand for each time period within the area is determined based on the number of electric vehicles, including:

[0135] Based on the data on the number of motor vehicles and electric vehicles in the city, the traffic flow corresponding to each time period in the area is determined.

[0136] The conversion between gasoline vehicles and electric vehicles is performed using a preset ratio of A:1 to determine the number of electric vehicles in each time period, thereby determining the expected demand for charging stations in each time period; where A can be specifically determined based on actual data.

[0137] In one possible implementation, when the projected demand for charging stations in the area during the first time period exceeds the shortage threshold, the average number of charging vehicles of potential customers during the first time period and the adjacent second time period is determined, including:

[0138] Determine the average number of charging vehicles for potential customers and suspected potential customers in the first time period and the adjacent second time period within the area.

[0139] Furthermore, the difference between the average number of charging vehicles in the area and the number of adjacent preset public charging piles in the area is determined, and this difference is used as the number of charging piles corresponding to the charging station, including:

[0140] Determine the average number of charging vehicles in the area and the difference in the number of public charging piles in the six adjacent areas. The difference is then used to determine the number of charging piles corresponding to the charging station.

[0141] Here, the number of charging piles can be used to characterize the recommended number of charging piles to be installed at the charging station.

[0142] For example, the number of charging stations can be calculated using the following formula:

[0143]

[0144] Where, N all It can represent the average number of charging vehicles in the area. It can represent the number of charging piles in charging stations in six adjacent areas.

[0145] Furthermore, the area can interact with the six adjacent areas as follows: Figure 3 As shown, Figure 3 This is a schematic diagram of a region and adjacent regions for a charging station capacity determination method based on multi-dimensional features provided in the embodiments of the invention. The target charging station refers to the charging station to be determined, and stations 1-4 can refer to charging stations in 6 adjacent regions.

[0146] In one possible implementation, the minimum charging power can characterize the minimum charging power that the charging station can provide at any time, and the optimal charging experience power can characterize the power required to provide users with the fastest and most comfortable charging experience.

[0147] By using the above method, and by obtaining the traffic flow in the area at different times, and determining the number of electric vehicles in the area according to a preset ratio, the charging demand of electric vehicles at each time period can be accurately predicted, ensuring that the charging piles after calibration can meet the charging needs of electric vehicles. The rated power of the charging piles is determined based on the minimum charging power and the optimal experience charging power, which can meet the user's fast charging needs while ensuring that the cost of the equipment and the grid load are controlled within a reasonable range.

[0148] In one specific embodiment, the minimum charging power and the optimal charging experience power of charging piles within the area are obtained based on the following steps:

[0149] The number of potential customers in the area during each time period is obtained. When the number of potential customers is equal to the maximum number of charging piles that can be built at the charging station, the corresponding time period is determined to be the peak period.

[0150] The duration between two peak periods is determined as the uncongested charging time. The average charging power required for the uncongested charging time is obtained. Based on the average charging power required and the uncongested charging time, the minimum charging power of the charging pile is determined.

[0151] Obtain the shortest charging time for vehicles within a preset number of months of non-congested charging time, and determine the optimal charging power based on the average charging power required and the shortest charging time for vehicles.

[0152] In one possible implementation, the number of potential customers and suspected potential customers for each time period is obtained. When the sum of potential customers and suspected potential customers equals the maximum number of charging piles that can be built, the corresponding time period is determined to be the peak time period.

[0153] Here, the maximum number of charging piles that can be built is used to characterize the default maximum number of charging piles that can be built when the charging station is initially built. When the sum of potential customers and suspected potential customers equals the maximum number of charging piles that can be built, it indicates that the charging demand of the charging station during that period has reached the maximum capacity of the charging facilities.

[0154] In one possible implementation, the duration between two peak periods is defined as the uncongested charging time. The average charging power required during this uncongested charging time is obtained. Based on the average charging power required and the uncongested charging time, the minimum charging power of the charging pile is determined, including:

[0155] Based on the number of vehicles in the area during the peak hours of the day and the corresponding charging electricity demand, the time interval between the arrival of the next peak hour is determined, and this time interval is used as the congestion charging time.

[0156] The minimum charging power of a charging station is calculated using the following formula:

[0157] P ide =Q need / T allo

[0158] Among them, Q need T is the average amount of electricity expected to be needed for charging during the congested charging period. allo The charging time is for congestion; the minimum charging power of the charging station is used to characterize the minimum power of the charging station required to reduce congestion and waiting time at charging stations.

[0159] In one possible implementation, the shortest charging time for a vehicle within a preset number of months of uncongested charging time is obtained. Based on the average charging energy requirement and the shortest charging time, the optimal charging power for the charging experience is determined, including:

[0160] The optimal charging power for the best charging experience is calculated using the following formula:

[0161] P idu =Q need / T min

[0162] Among them, T min Find the shortest charging time for the vehicle during this period within N months.

[0163] Here, the shortest charging time T for a vehicle min The optimal charging power is used to characterize the ideal charging time and the optimal charging experience. It is used to characterize the optimal charging power required to ensure that potential customers can complete charging within the best experience time.

[0164] The above methods can optimize the power configuration of charging stations when setting their capacity, thereby maximizing charging efficiency, improving user experience, and reducing resource waste between peak and off-peak hours.

[0165] In one specific embodiment, based on the vehicle-to-everything (V2X) data of the electric vehicle, the corresponding vehicle operation data of the electric vehicle is determined. The vehicle operation data includes: driving data, parking data, and charging data, including:

[0166] Acquire vehicle speed and current data from the vehicle-to-everything (V2X) data;

[0167] When the vehicle speed is greater than 0 or the vehicle speed is equal to 0 and the current data is greater than 0, it is determined that the electric vehicle is in a driving state, and the driving data corresponding to the driving state is obtained.

[0168] When the vehicle speed is 0 and the current data is 0, it is determined that the electric vehicle is in a parked and off state, and the parking data corresponding to the parked and off state is obtained.

[0169] When the vehicle speed is 0 and the current data is less than 0, it is determined that the electric vehicle is in a parking charging state, and the charging data corresponding to the parking charging state is obtained.

[0170] Specifically, the acquisition of vehicle network data includes, but is not limited to: time data, speed data, cumulative mileage data, latitude and longitude data, voltage data, and current data; driving data includes, but is not limited to: start time, end time, driving duration, start location, and end location; parking data includes, but is not limited to: start time, end time, parking duration, and parking location; and charging data includes, but is not limited to: start time, end time, charging duration, charging location, initial SOC, ending SOC, average charging power, and charging amount.

[0171] For example, the vehicle operation data is divided according to the following criteria:

[0172]

[0173] By using the above method, the corresponding operating data for different operating states of the vehicle are determined based on the vehicle's vehicle network data, providing a data basis for the capacity determination of charging stations, so that the capacity determination results are more in line with the vehicle's motion characteristics.

[0174] For example, Figure 4 This is a schematic diagram of the specific process of the charging station capacity determination method based on multi-dimensional features provided in the embodiments of the present invention, as shown below. Figure 4 As shown in the figure, the following steps are included:

[0175] Step S401: Multi-source data fusion;

[0176] Here, vehicle network data and annual monthly average temperature data are integrated to determine the driving record sheet and the monthly feature record sheet;

[0177] Step S402: Determine the station service area;

[0178] Here, the side length of the hexagonal shape is calculated, the boundary of the hexagonal shape is determined by the convex hull algorithm, the hexagonal shape is used as the service area of ​​the charging station, and the city is divided into areas based on the hexagonal shape.

[0179] Step S403: Vehicle user profile generation;

[0180] Here, user profiles for electric vehicles are created based on vehicle operation data to determine the charging usage characteristics of electric vehicles corresponding to temperature ranges in each month.

[0181] Step S404: Determine charging requirements;

[0182] Here, we identify potential customers and suspected potential customers;

[0183] Step S405: Predict the increase in demand;

[0184] Here, the expected demand for charging stations in the area at different times is determined;

[0185] Step S406: Assess the required charging station;

[0186] Here, the difference between the average number of charging vehicles in the area and the number of adjacent preset number of public charging piles in the area is determined, and the difference is used as the number of charging piles corresponding to the charging station.

[0187] Step S407: Assess charging demand;

[0188] Here, the minimum charging power and the optimal charging power for the charging piles in the area are obtained, and the rated power of the charging piles is determined based on the minimum charging power and the optimal charging power for the charging experience.

[0189] Figure 5 This is a schematic diagram of the structure of the charging station capacity stabilization device based on multi-dimensional features provided in an embodiment of the present invention, as shown below. Figure 5 As shown, the device can be applied to intelligent electronic devices such as servers and computers; the device includes: a partitioning module 501, a demand judgment module 502, and a capacity determination module 503;

[0190] Among them, the segmentation module 501 is used to obtain the driving record table and monthly feature record table of electric vehicles in the city, and based on the driving record table, determine the hexagonal shape representing the service area of ​​the charging station, and divide the city into areas according to the hexagonal shape.

[0191] The demand judgment module 502 is used to judge potential charging customers and charging demand of electric vehicles in the area, and to determine the charging demand vehicles and charging power required for each time period in the area.

[0192] The capacity calibrator 503 is used to determine the capacity calibrator scheme corresponding to the charging station based on the number of vehicles requiring charging, the amount of electricity required for charging, and the predicted increase in future vehicles.

[0193] In one specific embodiment, the segmentation module 501 is used to determine the vehicle operation data corresponding to the electric vehicle based on the vehicle network data of the electric vehicle. The vehicle operation data includes: driving data, parking data and charging data.

[0194] Based on the annual average monthly temperature, the 12 months are divided into at least one monthly temperature range, and each monthly temperature range includes at least one month; the annual average monthly temperature is related to the energy consumption of electric vehicles.

[0195] Based on vehicle operation data, user profiles of electric vehicles are created to determine the charging usage characteristics of electric vehicles corresponding to temperature ranges in each month.

[0196] Based on charging usage characteristics, determine the driving record sheet and monthly characteristic record sheet for electric vehicles.

[0197] In one specific embodiment, the segmentation module 501 is used to determine the maximum flow rate of vehicles in the city and the median driving time based on the driving record table; the driving time is used to characterize the time required for vehicles in the city to reach the charging station.

[0198] The side length of the hexagon is determined by the product of the maximum vehicle flow rate and the median driving time. The convex hull algorithm is then used to construct the hexagon based on the boundary determined by the side length.

[0199] Using a pre-defined parallel line matching method, the hexagonal shape to which the parking point belongs is determined based on the coordinate position of the electric vehicle's parking point. The city is then divided into zones based on the hexagonal shape. Each zone includes, but is not limited to, charging stations and electric vehicles.

[0200] In one specific embodiment, the demand judgment module 502 is used to determine at least one permanent area and non-permanent area within a region based on a preset permanent assessment standard and a preset charging habit standard, and to determine the ownership status of private charging piles within the permanent area.

[0201] Based on the availability of private charging stations in the area where the resident is stationed, potential customers and non-potential customers are identified at different times within the area.

[0202] Based on the real-time charging status of potential customers' monthly characteristic records, determine the vehicles with charging demand in each time period within the area.

[0203] Based on the average charging status in the monthly characteristic record table of potential customers, the charging power required for each time period in the area is determined.

[0204] In one specific embodiment, the capacity quantification module 503 is used to obtain the traffic flow in the area at different times, determine the number of electric vehicles in the traffic flow according to a preset ratio, and determine the expected charging pile demand in the area at different times based on the number of electric vehicles; the expected charging pile demand is used to characterize the charging pile demand gap in the area at the corresponding time period.

[0205] When the expected demand for charging piles in the area during the first time period exceeds the gap threshold, determine the average number of charging vehicles of potential customers in the first time period and the adjacent second time period.

[0206] Determine the difference between the average number of charging vehicles in the area and the number of adjacent preset public charging piles in the area, and use the difference as the number of charging piles corresponding to the charging station.

[0207] Obtain the minimum charging power and the optimal charging power for the charging piles within the area, and determine the rated power of the charging piles based on the minimum charging power and the optimal charging power for the charging experience.

[0208] Based on the number of charging piles and their rated power, determine the corresponding capacity scheme for the charging station.

[0209] In one specific embodiment, the capacity determination module 503 is used to obtain the number of potential customers in each time period within the area. When the number of potential customers is equal to the maximum number of charging piles that can be built at the charging station, the corresponding time period is determined to be the peak period.

[0210] The duration between two peak periods is determined as the uncongested charging time. The average charging power required for the uncongested charging time is obtained. Based on the average charging power required and the uncongested charging time, the minimum charging power of the charging pile is determined.

[0211] Obtain the shortest charging time for vehicles within a preset number of months of non-congested charging time, and determine the optimal charging power based on the average charging power required and the shortest charging time for vehicles.

[0212] In one specific embodiment, the segmentation module 501 is used to acquire vehicle speed and current data from the vehicle network data;

[0213] When the vehicle speed is greater than 0 or the vehicle speed is equal to 0 and the current data is greater than 0, it is determined that the electric vehicle is in a driving state, and the driving data corresponding to the driving state is obtained.

[0214] When the vehicle speed is 0 and the current data is 0, it is determined that the electric vehicle is in a parked and off state, and the parking data corresponding to the parked and off state is obtained.

[0215] When the vehicle speed is 0 and the current data is less than 0, it is determined that the electric vehicle is in a parking charging state, and the charging data corresponding to the parking charging state is obtained.

[0216] It should be noted that the charging station capacity calibrating device based on multi-dimensional features provided in the above embodiments, when implementing the corresponding charging station capacity calibrating method based on multi-dimensional features, is only illustrated by the division of the above-described program modules. In practical applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. Furthermore, the device provided in the above embodiments and the corresponding... Figure 1 The embodiments of the methods shown belong to the same concept, and their specific implementation process can be found in the method embodiments, which will not be repeated here.

[0217] This invention also provides a computer device having the above-described features. Figure 5 The charging station capacity stabilization device shown is based on multi-dimensional features.

[0218] Please see Figure 6 , Figure 6 This is another structural schematic diagram of the charging station capacity stabilization device based on multi-dimensional features provided in the embodiments of the present invention, as shown below. Figure 6As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 Take a processor 10 as an example.

[0219] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0220] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0221] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0222] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0223] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 20 can be connected via a bus or other means. Figure 6 Taking the example of a connection between China and Israel via a bus.

[0224] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0225] The computer device also includes a communication interface 30 for communicating with other devices or communication networks.

[0226] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0227] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0228] Although embodiments of the invention 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 invention, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for determining the capacity of charging stations based on multi-dimensional features, characterized in that, The method includes: The system obtains driving record tables and monthly feature record tables for electric vehicles within the city. Based on the driving record tables, it determines a hexagonal shape representing the service area of ​​charging stations and divides the city into zones according to the hexagonal shape. The driving record tables include: vehicle identification number, trip start time, trip end time, trip start position, trip end position, and average trip speed. The monthly feature record tables include: vehicle identification number, month, total number of charging times this month, and average charging time this month. The potential charging customers and charging demand of electric vehicles in the area are identified, and the charging demand vehicles and charging power required for each time period in the area are determined. Based on the vehicles with charging needs, the amount of electricity required for charging, and the predicted increase in future vehicles, the capacity allocation scheme for the charging station is determined. The process of determining the capacity allocation scheme for the charging station based on the vehicles with charging demand, the amount of electricity required for charging, and the predicted increase in future vehicles includes: The system obtains traffic flow data for each time period within the area, determines the number of electric vehicles in the traffic flow based on a preset ratio, and determines the expected charging pile demand for each time period within the area based on the number of electric vehicles. The expected charging pile demand is used to characterize the charging pile demand gap in the area during the corresponding time period. When the expected demand for charging piles in the area during the first time period is greater than the shortage threshold, the average number of charging vehicles of potential customers in the first time period and the adjacent second time period is determined. Determine the difference between the average number of charging vehicles in the area and the number of adjacent preset number of public charging piles in the area, and use the difference as the number of charging piles corresponding to the charging station; Obtain the minimum charging power and the optimal charging experience charging power of the charging piles in the area, and determine the rated power of the charging piles based on the minimum charging power and the optimal charging experience charging power. Based on the number of charging piles and the rated power of the charging piles, determine the capacity scheme corresponding to the charging station; The minimum charging power and optimal charging experience power of charging piles within the area are obtained based on the following steps: The number of potential customers in the area during each time period is obtained. When the number of potential customers is equal to the maximum number of charging piles that can be built at the charging station, the corresponding time period is determined to be the peak time period. The duration between two peak periods is determined as the uncongested charging duration. The average charging power required corresponding to the uncongested charging duration is obtained. Based on the average charging power required and the uncongested charging duration, the minimum charging power of the charging pile is determined. Obtain the shortest charging time for a vehicle within the non-congested charging time of a preset number of months, and determine the optimal charging power based on the average charging power required and the shortest charging time for the vehicle.

2. The method according to claim 1, characterized in that, To obtain the driving record table and monthly feature record table of electric vehicles in the city, the following steps are required: Based on the vehicle network data of electric vehicles, the vehicle operation data corresponding to the electric vehicle is determined, and the vehicle operation data includes: driving data, parking data and charging data; Based on the annual average monthly temperature, the 12 months are divided into at least one monthly temperature range, and the monthly temperature range includes at least one month; the annual average monthly temperature is related to the energy consumption of the electric vehicle. Based on the vehicle operation data, a user profile is created for the electric vehicle to determine the charging usage characteristics of the electric vehicle corresponding to the temperature range of each month. Based on the charging usage characteristics, the driving record table and the monthly characteristic record table of the electric vehicle are determined.

3. The method according to claim 2, characterized in that, Based on the driving record table, a hexagonal shape representing the service area of ​​the charging station is determined. The city is then divided into zones according to this hexagonal shape, achieved through the following steps: Based on the driving record table, the maximum flow rate of vehicles in the city and the median driving time are determined; the driving time is used to characterize the time required for vehicles in the city to reach the charging station. The side length of the hexagon is determined based on the product of the maximum flow rate of the vehicle and the median driving time. The convex hull algorithm is then used to construct the hexagon based on the boundary determined by the side length. Using a pre-defined parallel line matching method, the hexagonal shape to which the electric vehicle stops belong is determined based on the coordinate position of the electric vehicle's stop. The city is then divided into zones based on the hexagonal shape. Each zone includes: charging stations and electric vehicles.

4. The method according to claim 3, characterized in that, The system identifies potential charging customers and determines charging demand for electric vehicles within the designated area, identifying the vehicles and required charging capacity for each time period within the area. Based on preset permanent assessment criteria and preset charging habit criteria, at least one permanent and non-permanent area is identified, and the ownership of private charging piles in the permanent area is determined. Based on the availability of private charging stations in the designated residential area, potential and non-potential customers are identified for each time period within the designated residential area. Based on the real-time charging status in the monthly characteristic record table of the potential customers, determine the vehicles with charging demand in each time period within the area. Based on the average charging status in the monthly characteristic record table of the potential customers, the charging power required for each time period in the area is determined.

5. The method according to claim 2, characterized in that, The vehicle network data based on electric vehicles determines the vehicle operation data corresponding to the electric vehicle. The vehicle operation data includes: driving data, parking data, and charging data, including: Acquire vehicle speed and current data from the vehicle-to-everything (V2X) data; When the vehicle speed is greater than 0 or the vehicle speed is equal to 0 and the current data is greater than 0, it is determined that the electric vehicle is in a driving state, and the driving data corresponding to the driving state is obtained. When the vehicle speed is equal to 0 and the current data is equal to 0, it is determined that the electric vehicle is in a parked and off state, and the parking data corresponding to the parked and off state is obtained. When the vehicle speed is equal to 0 and the current data is less than 0, it is determined that the electric vehicle is in a parking charging state, and the charging data corresponding to the parking charging state is obtained.

6. An apparatus for implementing the charging station capacity stabilization method based on multi-dimensional features as described in claim 1, characterized in that, The device includes: The segmentation module is used to obtain the driving record table and monthly feature record table of electric vehicles in the city, and based on the driving record table, determine the hexagonal shape representing the service area of ​​the charging station, and divide the city into areas according to the hexagonal shape. The demand judgment module is used to judge potential charging customers and charging demand of electric vehicles in the area, and determine the charging demand vehicles and charging electricity required for each time period in the area. The capacity determination module is used to determine the capacity determination scheme corresponding to the charging station based on the vehicles with charging demand, the amount of electricity required for charging, and the predicted increase in future vehicles.

7. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the charging station capacity determination method based on multi-dimensional features as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the charging station capacity determination method based on multi-dimensional features as described in any one of claims 1 to 5.

Images