A battery replacement demand prediction method and device, electronic equipment and storage medium

Abstract

The application discloses a battery replacement demand prediction method and device, electronic equipment and a storage medium. The method comprises the following steps: obtaining a battery replacement probability matrix of a vehicle in different environments and different vehicle states and driving configuration data of the vehicle on a road; obtaining prediction configuration information, calling the driving configuration data to perform road configuration through prediction time data in the prediction configuration information, and obtaining configuration data of each road section; simulating the configuration data of each road section through a pre-set vehicle dynamics model, obtaining prediction driving state data of the vehicle driving on the road section, determining prediction battery replacement information of the vehicle based on the prediction driving state data, prediction environment data in the prediction configuration information and the battery replacement probability matrix; and forming battery replacement demand distribution data based on the prediction battery replacement information of the vehicle on each road section. The scheme uses environment data, vehicle state and trajectory data to construct a battery replacement probability matrix, and combines a vehicle dynamics model to predict battery replacement information, thereby effectively alleviating the problem of concentrated battery replacement.

Description

Technical Field

[0001] This invention relates to the field of electric vehicle charging and swapping technology, and in particular to a method, apparatus, electronic device, and storage medium for predicting battery swapping demand. Background Technology

[0002] The development and popularization of pure electric vehicles is one of the important ways to solve the current environmental pollution and fossil energy crisis. In recent years, pure electric vehicles, represented by pure electric vehicles, have become the mainstream in the field of public transportation.

[0003] Pure electric vehicles can be categorized into charging and battery swapping types based on their energy replenishment methods. Compared to the former, battery swapping electric vehicles (battery swapping vehicles) offer advantages such as shorter charging times, convenient charging methods, and smaller space requirements. Consequently, the demand for battery swapping is increasing, leading to issues like long swapping times and insufficient battery reserves due to concentrated battery swapping activity. To improve the service quality of battery swapping stations, reduce their operating costs, and promote the development of electric vehicle battery swapping models, accurately predicting the battery swapping demand of electric vehicles has become a pressing issue. Current methods rely solely on setting a SOC (State of Charge) threshold, statistical learning methods, or neural networks for data prediction. These existing solutions, using overly simplistic data sets, result in inaccurate predictions. Summary of the Invention

[0004] This invention provides a method, apparatus, electronic device, and storage medium for predicting battery swapping demand, which aims to solve the problem of clustered battery swapping by predicting battery swapping demand.

[0005] According to one aspect of the present invention, a method for predicting battery swapping demand is provided, comprising:

[0006] Obtain the battery swapping probability matrix and vehicle driving configuration data under different environments and vehicle conditions;

[0007] Obtain the predicted configuration information, and use the predicted time data in the predicted configuration information to call the driving configuration data to perform road configuration, thereby obtaining the configuration data for each road segment;

[0008] By simulating the configuration data of each road segment through a pre-set vehicle dynamics model, the predicted driving state data of the vehicle in the road segment is obtained. Based on the predicted driving state data, the predicted environment data in the predicted configuration information and the battery swapping probability matrix, the predicted battery swapping information of the vehicle is determined.

[0009] Based on the predicted battery swapping information of vehicles on each road segment, data on the distribution of battery swapping demand is generated.

[0010] Obtain the battery swapping probability matrix and vehicle driving configuration data under different environments and vehicle states, including:

[0011] Acquire historical vehicle data and road topology data. Historical data includes environmental data and driving status data.

[0012] A battery swapping probability matrix is ​​generated based on environmental data and driving status data for vehicles in different environments and under different vehicle conditions.

[0013] Vehicle driving configuration data on the road is generated based on road topology data and driving status data.

[0014] Environmental data includes the date, time, and temperature of vehicle travel; driving status data includes the vehicle's location coordinates, speed data, and battery charge data during the driving process.

[0015] Based on environmental data and driving status data, a battery swapping probability matrix is ​​generated for vehicles in different environments and under different vehicle conditions, including:

[0016] The number of battery swaps was counted under different environmental data ranges and different vehicle conditions;

[0017] By using any environmental data range and the number of battery swaps and the total number of battery swaps under any vehicle condition, the battery swap probability under any environmental data range and any vehicle condition is obtained. The battery swap probability of each environmental data range and each vehicle condition forms a battery swap probability matrix.

[0018] Based on road topology data and driving status data, vehicle driving configuration data on the road is generated, including:

[0019] For any road segment in the road topology data, the average vehicle speed and traffic density at each time period on the road segment are statistically obtained based on the driving status data, which are used as the driving configuration data for the road segment.

[0020] Methods for obtaining road topology data include:

[0021] The road trajectory points of the vehicle at each time point are obtained, and the road trajectory points are merged based on the vehicle's driving status at each time point to obtain multiple trajectory segments, including driving trajectory segments and stationary trajectory segments.

[0022] Multiple trajectory segments are clustered according to their types to obtain trajectory segment sequences of each type.

[0023] By fusing the trajectory segment sequence with road data, road topology data is obtained.

[0024] Before fusing the trajectory segment sequence with road data, the method also includes:

[0025] A road buffer zone is set up, and road trajectory points in each trajectory segment are filtered based on road data in the road topology data and the road buffer zone.

[0026] By retrieving the driving configuration data from the predicted time data in the predicted configuration information, road configuration is performed to obtain the configuration data for each road segment, including:

[0027] Based on the predicted time data and the vehicle travel probability matrix, the vehicle distribution data is predicted.

[0028] Based on the average vehicle speed and traffic density in the driving configuration data, the vehicle distribution data is configured for each vehicle to obtain the vehicle configuration data for each road segment.

[0029] By using a pre-set vehicle dynamics model, the configuration data for each road segment is simulated to obtain predicted driving state data of the vehicle on the road segment, including:

[0030] For any vehicle in the vehicle distribution data, input the vehicle speed into the vehicle dynamics model to obtain the vehicle's power consumption data;

[0031] Based on power consumption data, predictive driving status data of the vehicle during driving is determined. The predictive driving status data includes battery charge data corresponding to each driving position during driving.

[0032] The vehicle's predicted battery swapping information is determined based on predicted driving status data, predicted environment data from the predicted configuration information, and the battery swapping probability matrix, including:

[0033] The battery charge data and predicted environmental data corresponding to each driving location are matched in the battery swapping probability matrix to determine the battery swapping probability corresponding to each driving location.

[0034] Determine the range of driving locations where the probability of battery swapping meets the battery swapping threshold, and determine the time range corresponding to the driving location range. Use the driving location range and / or time range as the vehicle's predicted battery swapping information.

[0035] According to another aspect of the present invention, a battery swapping demand prediction device is provided, comprising:

[0036] The data acquisition module is used to acquire the battery swapping probability matrix of the vehicle under different environments and different vehicle states, as well as the vehicle's driving configuration data on the road.

[0037] The configuration data acquisition module is used to acquire the predicted configuration information, and to call the driving configuration data through the predicted time data in the predicted configuration information to perform road configuration and obtain the configuration data of each road segment.

[0038] The predictive battery swapping information determination module is used to simulate the configuration data of each road segment through a pre-set vehicle dynamics model to obtain the predicted driving state data of the vehicle on the road segment. Based on the predicted driving state data, the predicted environment data in the predicted configuration information and the battery swapping probability matrix, the predicted battery swapping information of the vehicle is determined.

[0039] The battery swapping demand distribution data determination module is used to generate battery swapping demand distribution data based on the predicted battery swapping information of vehicles on each road segment.

[0040] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0041] At least one processor; and

[0042] A memory that is communicatively connected to at least one processor; wherein,

[0043] The memory stores a computer program that can be executed by at least one processor, such that the at least one processor is able to perform the battery swapping demand prediction method according to any embodiment of the present invention.

[0044] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the battery swapping demand prediction method of any embodiment of the present invention.

[0045] The technical solution of this invention constructs a battery swapping probability matrix using vehicle status, vehicle trajectory information, and environmental information collected by the vehicle. It then uses a vehicle dynamics model and configuration data from various road segments for joint simulation to determine the predicted battery swapping information for the vehicle. Based on this predicted information, it generates battery swapping demand distribution data, achieving full utilization and in-depth mining of battery swapping vehicle big data. The obtained vehicle battery swapping demand distribution data can determine peak battery swapping periods and road segments, improving the accuracy and efficiency of battery swapping demand prediction. Furthermore, it allows for proactive measures based on the predicted peak battery swapping periods and road segments, helping to alleviate peak battery swapping times and address battery swapping anxiety. The prediction results also provide important references for specifying battery swapping scheduling strategies and selecting battery swapping station locations.

[0046] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 This is a flowchart of a battery swapping demand forecasting method provided in Embodiment 1 of the present invention;

[0049] Figure 2 This is a schematic diagram of SOC-battery swapping distribution under different environments provided by embodiments of the present invention;

[0050] Figure 3 This is a flowchart of a battery swapping demand prediction method provided in Embodiment 2 of the present invention;

[0051] Figure 4 This is a schematic diagram of the distribution of battery swapping vehicles in a certain city to which this embodiment of the invention applies;

[0052] Figure 5 This is a schematic diagram of the urban road topology applicable to embodiments of the present invention;

[0053] Figure 6 This is a schematic diagram showing the distribution of battery swapping vehicles in the road network, applicable to embodiments of the present invention;

[0054] Figure 7 This is a schematic diagram of the structure of a battery swapping demand prediction device provided in Embodiment 3 of the present invention;

[0055] Figure 8 This is a schematic diagram of the structure of an electronic device that implements the battery swapping demand prediction method of this invention. Detailed Implementation

[0056] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0057] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0058] Example 1

[0059] Figure 1 This is a flowchart of a battery swapping demand forecasting method provided in Embodiment 1 of the present invention. This embodiment is applicable to the forecasting of battery swapping demand for electric vehicles. The method can be executed by a battery swapping demand forecasting device, which can be implemented in hardware and / or software and can be configured in electronic devices such as computers. Figure 1 As shown, the method includes:

[0060] S110. Obtain the battery swapping probability matrix and vehicle driving configuration data under different environments and vehicle states.

[0061] Specifically, the battery swapping probability matrix can be understood as the SOC-temperature-battery swapping probability matrix, which is the probability matrix of how the SOC battery swapping distribution changes with temperature. This matrix can be constructed by statistically analyzing the historical battery swapping behavior over time periods based on SOC, and combining this with the ambient temperature during battery swapping to statistically analyze the SOC battery swapping distribution across different temperature ranges. The driving configuration data can be understood as the average speed and traffic density of vehicles on each road. This can be calculated by obtaining the road length, number of vehicles, and vehicle speed for each road.

[0062] Specifically, by reading historical battery data from a big data platform, the State of Charge (SOC) distribution of a vehicle before and after a battery swap can be obtained, for example... Figure 2The diagram illustrates the battery swapping distribution of vehicles under different environmental conditions on a given day. It shows that nearly 74% of vehicles swap batteries when their SOC (State of Charge) is below 50%. It's important to note that the power and capacity of pure electric vehicle batteries are temperature-dependent, generally decreasing with decreasing temperature. Therefore, drivers tend to choose to swap batteries at higher SOC levels in cold weather, while in situations of concentrated battery swapping, the proportion of swaps at lower SOC levels increases. Thus, a SOC-temperature-battery swapping probability matrix is ​​constructed based on the SOC-battery swapping probability distribution. The SOC-battery swapping probability distribution is determined by statistically analyzing data to determine the battery swapping probability of vehicles in different time periods. Furthermore, the ambient temperature parameter is introduced to statistically analyze the SOC battery swapping distribution across different temperature ranges, thus constructing the SOC-temperature-battery swapping probability matrix. Vehicle driving data is obtained from a big data platform. Based on the road length, vehicle speed, and number of vehicles in each time period, the average vehicle speed and traffic density for that time period are calculated, yielding vehicle driving configuration data on the road.

[0063] In this embodiment, the acquisition of the battery swapping probability matrix and vehicle driving configuration data on the road provides a data foundation for subsequent prediction of vehicle battery swapping demand, which helps to quickly determine the distribution of vehicle battery swapping demand.

[0064] S120. Obtain the predicted configuration information, and use the predicted time data in the predicted configuration information to call the driving configuration data to perform road configuration, thereby obtaining the configuration data for each road segment.

[0065] Specifically, the predicted configuration information can be understood as initialization data generated for vehicle simulation. This initialization data can be automatically generated randomly by simulation software, such as the open-source traffic simulation software SUMO. Initialization parameters include the initial date D. t and initial time T ini Initial location P ini and initial charge state of charge (SOC) ini The ambient temperature of the day (Temp) D and destination P end It should be noted that the initial date is represented using a seven-day week, such as Monday, Tuesday, Sunday, etc. Before automatically generating the predicted configuration information, the parameter value range needs to be pre-set. The configuration data for a road segment can be understood as configuration data obtained through a path planning algorithm, including the path destination, total travel time, and stop time. For example, the Dijkstra algorithm can be used to determine the path set Paths, and the path with the shortest distance in the path set can be selected based on the shortest path principle, thereby determining the configuration data for the shortest path. This configuration data includes the destination P. end and stop time.

[0066] Specifically, in the simulation software SUMO, the predicted configuration data is automatically generated by the simulation software, based on the predicted time data D in the predicted configuration information. t and T ini For each road, the average speed and traffic density are calculated using methods that calculate average speed and traffic density. Then, a path planning algorithm is used to determine a set of paths. The shortest path in this set is selected as the vehicle's travel route, and the destination is determined based on the chosen route. The total travel time T is calculated based on the road length and average road speed. cost The stopping time T is obtained. end =T ini +T cost .

[0067] Optionally, the driving configuration data can be called from the prediction time data in the prediction configuration information to perform road configuration, thereby obtaining the configuration data for each road segment. This includes: predicting vehicle distribution data based on the prediction time data and the vehicle travel probability matrix; and configuring the vehicles in the vehicle distribution data based on the average vehicle speed and traffic density in the driving configuration data to obtain the vehicle configuration data for each road segment.

[0068] The vehicle trip probability matrix can be understood as a matrix representing user travel characteristics. It can be used to characterize the travel features of various electric vehicles in the road network. It should be noted that the trip matrix, or OD matrix, refers to the traffic volume from all origins to destinations in the traffic network. The rows of the OD matrix represent the traffic generation at each origin, and the columns represent the traffic absorption at each destination. The corresponding OD matrix can be obtained by obtaining the traffic flow of electric vehicles on each road segment. In this embodiment, an unbalanced OD back-calculation model is used, as follows:

[0069]

[0070] Among them, Q k Let T be the traffic flow rate for road segment k. i,j This represents the element in the OD matrix to be determined. Let represent the probability that a vehicle travels from node i to node j via road segment k, where n represents the number of traffic nodes and l represents the number of road segments in the region. The probability matrix of vehicle travel from node i to node j within time period t can be obtained by statistically analyzing historical big data. Travel probability matrix The calculation formula is as follows:

[0071]

[0072] in, Let T represent the traffic volume from node i to node j in the traffic network at time t. Iterate through all origin and destination nodes to obtain the probability-based traffic volume T. i,j , Traffic flow Q k The total error is minimized. By statistically analyzing historical big data, the OD (Original Departure-Destination) travel probability matrix for vehicles traveling from node i to node j within time period t can be obtained.

[0073] It should be noted that vehicle distribution data can be specifically understood as distribution data that characterizes the density of vehicles in the road network. It can include vehicle temporal distribution data and vehicle spatial distribution data. Among them, vehicle temporal distribution data includes the distribution status of vehicles in various time periods, which can intuitively observe which time periods have more dense vehicles and which time periods have more sparse vehicles. Vehicle spatial distribution data includes the distribution status of vehicles in various time periods, which can intuitively observe which road segments have more dense vehicles and which road segments have more sparse vehicles.

[0074] Specifically, in the SUMO simulation software, the initial date (within one week) of the battery swapping vehicle is randomly generated. t and time T ini Initial location P ini and initial charge state of charge (SOC) ini The ambient temperature of the day (Temp) ini and destination P end , where P end Based on T ini The OD probability travel matrix is ​​generated at each time point. Based on the predicted time data and the vehicle travel probability matrix, the temporal and spatial distribution of vehicles is obtained, making the simulated vehicle distribution close to the actual situation. It should be noted that for the randomly generated initialization parameters, the range of each parameter value should be set before random generation. For example, the initial date can be set to a range of Monday to Tuesday, and the initial battery level can be set to 30% to 50%, etc. The specific setting range can be set according to actual needs, so that the obtained prediction results cover as many road segments and time periods as possible. According to D... t and T ini The average speed and traffic density of each road in the road network are set. Path planning is performed using simulation software based on the initial parameters, and Dijkstra's shortest path algorithm is used to determine the travel path. If the shortest path passes through road segment k, then... The value is 1 if the distance is less than 1, and 0 otherwise. The vehicle travels to its destination along the shortest path; the total travel time T can be calculated based on the road length and average road speed. cost The stopping time T can be obtained. end =T ini +T costIterate through all origin and destination nodes to obtain the traffic T. i,j , Traffic flow Q k The total error is minimized.

[0075] In this embodiment, the vehicle distribution is obtained by determining the prediction time data and the vehicle travel probability matrix. Then, the driving path is configured according to the average vehicle speed and traffic density, so that the constructed vehicle distribution is closer to the actual vehicle distribution on the road, which helps to improve the accuracy of battery swapping demand prediction.

[0076] S130. By using a pre-set vehicle dynamics model, the configuration data of each road segment is simulated to obtain the predicted driving state data of the vehicle on the road segment. Based on the predicted driving state data, the predicted environment data in the predicted configuration information, and the battery swapping probability matrix, the predicted battery swapping information of the vehicle is determined.

[0077] The pre-set vehicle dynamics model is as follows:

[0078]

[0079] In the above formula, F d F is the driving force provided by the powertrain to the vehicle. r F represents the total resistance of the vehicle. w For air resistance; F f F represents rolling resistance. i It is a ramp resistance; F a To accelerate resistance; C D ρ is the air drag coefficient; A is the frontal area; ρ is the air density; v r dv / dt is the relative velocity of the vehicle in the absence of wind; m is the mass of the vehicle; f is the rolling resistance coefficient; δ is the conversion factor for the rotating mass of the vehicle, δ>1; dv / dt is the acceleration.

[0080] Specifically, based on the vehicle dynamics model, the vehicle is simulated. When the vehicle is in operation, the predicted vehicle speed and the road information are fed back into the vehicle dynamics model. Through processing, the predicted driving state data of the vehicle on the road segment is obtained, namely the vehicle's location information and the vehicle's SOC value. The current battery swapping probability data of the vehicle is predicted by predicting environmental data and the battery swapping probability matrix, where the predicted environmental data is the ambient temperature value.

[0081] Optionally, the configuration data of each road segment is simulated using a pre-set vehicle dynamics model to obtain the predicted driving state data of the vehicle on the road segment. This includes: for any vehicle in the vehicle distribution data, inputting the vehicle speed into the vehicle dynamics model to obtain the vehicle's power consumption data; and determining the predicted driving state data of the vehicle during the driving process based on the power consumption data. The predicted driving state data includes the battery charge data corresponding to each driving position during the driving process.

[0082] Specifically, power consumption data can be understood as the SOC value consumed by the vehicle, which can be calculated through the vehicle dynamics model.

[0083] Specifically, vehicle speed and road information are acquired and input into the vehicle dynamics model to calculate the vehicle's driving force. This calculated driving force serves as the vehicle's required power, and the vehicle battery provides the corresponding power based on this demand. It should be noted that the battery output power equals the required power, where battery power = U (battery voltage) × I (current), and required power = F (required power) × V (vehicle speed). The vehicle's current battery SOC is obtained by subtracting the vehicle's consumed SOC from its total battery charge. Therefore, the formula for calculating battery SOC is as follows:

[0084]

[0085] Where t represents time, V OC (V) is the battery open-circuit voltage; R int (Ω) is the battery's internal resistance; C(Ah) is the battery's nominal capacity; P B (KW) represents the power supplied by the battery. The battery charge at each driving position is calculated using the formula above, based on the vehicle's speed at each driving position.

[0086] Optionally, the predicted battery swapping information of the vehicle is determined based on the predicted driving state data, the predicted environment data in the predicted configuration information, and the battery swapping probability matrix. This includes: matching the battery charge data and predicted environment data corresponding to each driving position in the battery swapping probability matrix to determine the battery swapping probability corresponding to each driving position; determining the range of driving positions where the battery swapping probability meets the battery swapping threshold, and determining the time range corresponding to the driving position range; and determining the driving position range and / or time range as the predicted battery swapping information of the vehicle.

[0087] Specifically, the battery charge data calculated through the vehicle dynamics model and the ambient temperature data of the road environment where the vehicle is located are used as input parameters. The battery swapping probability matrix is ​​traversed to obtain the battery swapping probability value that matches the input parameters. This can be represented by F. SOC-T This is represented. A battery swapping probability threshold F is set. thIt can be determined by judging the battery swapping probability F SOC-T With F th The magnitude of the probability F determines whether a vehicle will undergo battery swapping. SOC-T Greater than or equal to F th If the battery swapping is successful, the vehicle is considered to be swapping its battery; otherwise, it is not, and the current vehicle position P is recorded. end and time T end The process continues to analyze vehicles at other driving positions to obtain the battery swapping probability for each driving position at each time step.

[0088] In this embodiment, the SOC value of the vehicle at each driving position is determined by the vehicle kinematics model. Then, the battery swapping probability matrix is ​​matched according to the ambient temperature to determine the predicted battery swapping information of the vehicle at each driving position, providing a data foundation for the subsequent determination of battery swapping demand distribution data.

[0089] S140. Based on the predicted battery swapping information of vehicles on each road segment, battery swapping demand distribution data is generated.

[0090] Specifically, the battery swapping demand distribution data can be understood as data generated from the predicted battery swapping information of vehicles on each road segment, including but not limited to vehicle location information, time information, battery swapping probability, road ID, SOC value, etc.

[0091] Specifically, based on the predicted battery swapping information of vehicles on each road segment, a battery swapping demand distribution map can be drawn, including temporal and spatial distribution data of battery swapping demand. This data can also be displayed in the form of a statistical table. The specific display format is not limited and can be set according to actual needs.

[0092] In this embodiment, by drawing a battery swapping demand distribution map or generating a data statistics table based on the predicted battery swapping information of vehicles on each road segment, the battery swapping demand prediction result is obtained. The prediction result allows for a direct observation of the time and road segments where clustered battery swapping phenomena occur, which helps to alleviate battery swapping peaks and battery swapping anxiety.

[0093] The technical solution of this embodiment obtains vehicle status data, environmental data, and vehicle trajectory data from a big data platform, processes the acquired data, maps the vehicle trajectory data to the road network, and then calculates the travel probability matrix for each road at different times within a week. Combined with the ambient temperature during battery swapping, it calculates the SOC-temperature-battery swapping probability matrix for different temperature ranges, constructs a battery swapping dynamics model, and obtains the predicted battery swapping information for vehicles at each driving position on each road segment using the SOC-temperature-battery swapping probability matrix, thus achieving spatiotemporal battery swapping demand prediction. This solves the problem of predicting vehicle battery swapping demand under different environments and vehicle states, enabling the determination of corresponding spatiotemporal battery swapping demand predictions based on given environmental conditions using a vehicle dynamics model and battery swapping probability matrix. This improves the accuracy of battery swapping demand prediction results, allows for proactive mitigation measures based on the prediction results, effectively alleviating battery swapping anxiety. The prediction results also provide important references for specifying battery swapping scheduling strategies and selecting battery swapping station locations.

[0094] Example 2

[0095] Figure 3 This is a flowchart of a battery swapping demand prediction method provided in Embodiment 2 of the present invention. This embodiment is an optimization of the method in the above embodiments. Optionally, it involves acquiring historical vehicle data and road topology data, whereby the historical data includes environmental data and driving status data; generating a battery swapping probability matrix for the vehicle under different environments and vehicle states based on the environmental data and driving status data; and generating driving configuration data for the vehicle on the road based on the road topology data and driving status data. Figure 3 As shown, the method includes:

[0096] S210. Obtain historical vehicle data and road topology data. Historical data includes environmental data and driving status data.

[0097] Specifically, vehicle historical data refers to the data generated by the battery-swapping vehicle during its operation. This historical data includes environmental data and driving status data. It can be collected and stored using vehicle-to-everything (V2X) technology. Therefore, vehicle historical data can be obtained from a V2X big data platform or read from a vehicle data management system. It should be noted that environmental data includes the date, time, and temperature of the vehicle's operation; driving status data includes the vehicle's position coordinates, speed data, and battery charge data during operation; position coordinates refer to the longitude and latitude of the vehicle's location during operation. The data attributes of historical data are shown in Table 1. Road topology data can be understood as road network data that integrates vehicle trajectory data. It can be obtained by mapping vehicle trajectory data to road network data. Optionally, methods for obtaining road topology data include: acquiring road trajectory points of the vehicle at various time points; merging road trajectory points based on the vehicle's driving status at each time point to obtain multiple trajectory segments, including driving trajectory segments and stationary trajectory segments; clustering multiple trajectory segments according to their type to obtain trajectory segment sequences of various types; and fusing the trajectory segment sequences with road data to obtain road topology data. Specifically, trajectory points can be understood as vehicle location information, obtained through GPS and BeiDou positioning, primarily containing the latitude and longitude data corresponding to the vehicle's location. Trajectory points and related data for each time point can be obtained from the data management platform. Merging road trajectory points specifically refers to linearly connecting trajectory points belonging to the same road to form trajectory segments. Clustering can be understood as a linear stitching method, which can stitch together based on speed and trajectory status. Road data can be understood as road network data, which can be obtained first through the open-source OpenStreetMap platform, such as... Figure 4 The diagram shows the distribution of electric vehicle swapping services in a certain city.

[0098] Table 1 Historical Data Attribute Table

[0099]

[0100] Specifically, the entire road network is first obtained through the open-source OpenStreetMap platform. Then, the latitude and longitude selection function is used to export the road network data required for the study. Finally, QGI software and Python are used to draw the road network and process the administrative region correspondence to form a schematic diagram of the road topology of a certain city, such as... Figure 5 As shown.

[0101] It should be noted that since it is impossible to intuitively determine the vehicle's driving status by obtaining road trajectory data at various time points, a speed threshold can be set to determine whether the vehicle is in a moving or stationary state, and thus determine whether the trajectory segment belongs to a moving trajectory segment or a stationary trajectory segment.

[0102] Specifically, let the coordinates of trajectory point i be (x... i ,y i ), timestamp t i The coordinates of the trajectory point i+1 are (x i+1 ,y i+1 ), timestamp t i+1 If two coordinate points are on the same road, then the velocity v of trajectory point i is... i The following formula can be used to calculate:

[0103]

[0104] Set the speed threshold v t To determine whether the vehicle is moving or stationary, if v i >v t If v i ≤v t If , then the trajectory point i is marked as "stopped".

[0105] It should be noted that the steps for determining the trajectory state of a trajectory point are as follows:

[0106] Step 1: Starting from the first trajectory point in the trajectory point sequence, determine the state flag of each trajectory point in turn.

[0107] Step 2: If the state of the current trajectory point is the same as the state of the previous trajectory point, then add the current trajectory point to the current trajectory segment;

[0108] Step 3: If the state of the current trajectory point is different from the state of the previous trajectory point, store the current trajectory segment in the trajectory segment result, and create a new trajectory segment with the current trajectory point as the starting point; Step 4: Repeat steps 2 and 3 until all trajectory points have been processed.

[0109] For example, suppose the sequence of trajectory points is P = p1,,p2,p3,,……,p n The state label sequence is S = s1, s2, s3, ..., s n The trajectory segment result sequence is T = t1, t2, t3, ..., t m When the state of the current point is the same as the state of the previous point, t k =t k ∪p i , where k is the number of the current trajectory segment. When the state of the current point differs from the state of the previous point, t k =t k ∪p i , t k+1 =pi , where k is the number of the current trajectory segment.

[0110] After completing the trajectory state determination process for the above trajectory points, multiple trajectory segments are clustered according to their types. Specifically, velocity sequences are used as clustering features to perform linear clustering of the trajectory segment sequences. For each trajectory segment, it is concatenated with all adjacent trajectory segments that share the same state label to form a new sub-trajectory segment. The specific steps are as follows:

[0111] Step 1: Assume the trajectory segment sequence T = t1,,t2,t3 3, ,……,t m The state identifier label sequence is L = l1, l2, l3, ..., l m The new sub-trajectory segment sequence is S = s1, s2, s3, ..., s n ,

[0112] Step 2: For each trajectory segment t i If l i =l i+1 , then s j =s j ∪t i , where j is the number of the new sub-trajectory segment;

[0113] For example, if the trajectory segment sequence T = t1,,t2,t3,,t4,,t5 and L = 1,2,1,2,1, then the new sub-trajectory segment sequence S = t1∪t3∪t5,t2∪t4.

[0114] Optionally, before fusing the trajectory segment sequence with the road data, the method further includes: setting a road buffer area and filtering the road trajectory points in each trajectory segment based on the road data in the road topology data and the road buffer area.

[0115] It should be noted that vehicle trajectory points are obtained based on GPS and BeiDou positioning and have spatiotemporal characteristics. However, due to factors such as signal strength, signal interference, or object obstruction, trajectory points may drift to some extent. Therefore, it is necessary to clean the vehicle trajectory points and vehicle trajectory data. Noisy trajectory points that may be caused by positioning drift can be filtered by constructing a buffer area.

[0116] Specifically, the transverse centerline of the road can be used as a baseline, and buffer zones can be set on the left and right sides of this baseline. Based on the road data and the buffer zones, trajectory points that are not in the buffer zones can be filtered out. For example, the buffer zone width threshold can be set to 50m. For each vehicle trajectory point, it can be determined whether it is within the buffer zone. If the vehicle trajectory point is within the buffer zone, the point is retained; if the vehicle trajectory point is not within the buffer zone, the point is deleted.

[0117] For example, let the road topology be P, the buffer zone be B, and the vehicle trajectory point sequence be D = d1, d2, d3, ..., d n The sequence of vehicle trajectory points after deletion is D′=d 1′ ,d 2′ ,d 3′ ,…,d m′ The method for determining whether a vehicle's trajectory point is within the buffer zone is as follows: d i ∈B if(d i ∈P)or(distance(d i ,P)≤50m), where d i Let P be the coordinates of the vehicle trajectory point, P be the road topology, and B be the buffer zone.

[0118] Specifically, based on the vehicle trajectory data determined by the above method, the corresponding vehicles can be matched according to the vehicle's VIN. Then, the vehicle trajectory segments are matched to the road network using the road ID, and the trajectory points are mapped to the road network to obtain road topology data, i.e., a schematic diagram of the distribution of the battery-swapping vehicles in the road network, such as... Figure 6 As shown.

[0119] In this embodiment, vehicle trajectory data is obtained from a big data platform, and the vehicle trajectory data is cleaned to achieve trajectory correction. The cleaned trajectory points are then used to determine the vehicle trajectory segments on each road. The trajectory segments and corresponding vehicle information are then mapped onto the road network to obtain road topology data. This provides a basis for subsequently determining the average vehicle speed and traffic density on each road in the road network, thereby improving the accuracy of determining the average vehicle speed and traffic density on each road.

[0120] 220. Generate a battery swapping probability matrix for vehicles in different environments and under different vehicle conditions based on environmental data and driving status data.

[0121] It should be noted that the method for generating a battery swapping probability matrix for a vehicle in different environments and different vehicle states based on environmental data and driving status data includes: counting the number of battery swaps in different environmental data ranges and different vehicle states; obtaining the battery swapping probability for any environmental data range and any vehicle state by using the number of battery swaps and the total number of battery swaps in any environmental data range and any vehicle state; and forming a battery swapping probability matrix for each environmental data range and each vehicle state.

[0122] Specifically, by setting environmental data conditions, vehicle driving status data that meets these conditions is obtained from a big data platform. The number of battery swaps and the total number of battery swaps are statistically analyzed for different environmental data ranges and vehicle states. The ratio of the number of battery swaps to the total number of battery swaps is determined, yielding the battery swap probability for any environmental data range and any vehicle state. All obtained battery swap probabilities are then used to form a battery swap probability matrix. The specific calculation formula for the battery swap probability matrix is ​​as follows:

[0123]

[0124] Where: P(SOC∈[x,y],T∈[a,b]) is the probability of battery swapping when SOC is between x and y, and temperature T is between a and b. C [x,y],[a,b] It represents the number of battery swaps when the State of Charge (SOC) is between x and y, and the Time Limit (T) is between a and b. N is the total number of battery swaps.

[0125] S230: Generate vehicle driving configuration data on the road based on road topology data and driving status data.

[0126] Specifically, the process iterates through each road in the road network, obtaining its ID, length, number of vehicles, and vehicle speed. It also iterates through each time period, obtaining the number of vehicles and their speeds for that period, calculating the average speed for that period, and calculating the traffic density for each road during that period. Optionally, it generates vehicle driving configuration data based on road topology data and driving status data, including: for any road segment in the road topology data, statistically obtaining the average speed and traffic density for each time period on that segment based on driving status data, using this as the segment's driving configuration data.

[0127] Specifically, the acquired road network topology data is imported using the open-source traffic simulation software SUMO. The average vehicle speed and traffic density of each road are calculated. The driving configuration data of the calculated average vehicle speed and traffic density road segments are then used to configure the road network in SUMO. The calculation and statistical steps for average vehicle speed and traffic density are as follows:

[0128] Step 1: Define the variables road_id (road number), length (road length), vehicle_count (number of vehicles), speed (vehicle speed), time_period (time period), and density (vehicle density);

[0129] Step 2: Traverse each road in the road network, obtain the number of vehicles and vehicle speed on each road in the current time period, and traverse each time period:

[0130] Calculate the average vehicle speed on the road during the current time period: speed / vehicle_count;

[0131] Calculate the traffic density of the road in the current time period: vehicle_count / length;

[0132] Step 3: Output the average vehicle speed and traffic density for each road in each time period.

[0133] S240. By using a pre-set vehicle dynamics model, the configuration data of each road segment is simulated to obtain the predicted driving state data of the vehicle on the road segment. Based on the predicted driving state data, the predicted environment data in the predicted configuration information, and the battery swapping probability matrix, the predicted battery swapping information of the vehicle is determined.

[0134] S250: Based on the predicted battery swapping information of vehicles on each road segment, data on the distribution of battery swapping demand is generated.

[0135] The technical solution of this embodiment acquires environmental data, vehicle status data, and vehicle trajectory data based on a big data platform and completes data processing; constructs a specific urban road network topology through an open-source map platform; obtains vehicle trajectory segments based on the number of vehicle trajectories through linear clustering, maps the vehicle trajectory segments to the road network, and calculates the travel probability matrix of each road at different times within a week, and calculates the traffic density at different times; calculates the time distribution of historical battery swapping behavior based on battery state of charge (SOC), and constructs a SOC-temperature-battery swapping probability matrix by combining the ambient temperature at the time of battery swapping and calculating the SOC battery swapping distribution in different temperature ranges; then introduces a vehicle dynamics model to complete the prediction of vehicle spatiotemporal battery swapping demand under given environmental conditions, improving the accuracy of vehicle trajectory data determination. At the same time, the joint implementation of the SOC-temperature-battery swapping probability matrix and the vehicle dynamics model to achieve spatiotemporal battery swapping demand prediction improves the accuracy of the battery swapping demand prediction results.

[0136] Example 3

[0137] Figure 7 This is a schematic diagram of the structure of a battery swapping demand prediction device provided in Embodiment 3 of the present invention.

[0138] like Figure 7 As shown, the device includes:

[0139] The data acquisition module 310 is used to acquire the battery swapping probability matrix of the vehicle under different environments and different vehicle states, as well as the vehicle's driving configuration data on the road.

[0140] The configuration data acquisition module 320 is used to acquire the predicted configuration information, and to call the driving configuration data through the predicted time data in the predicted configuration information to perform road configuration and obtain the configuration data of each road segment.

[0141] The predictive battery swapping information determination module 330 is used to simulate the configuration data of each road segment through a pre-set vehicle dynamics model to obtain the predicted driving state data of the vehicle driving on the road segment, and determine the predicted battery swapping information of the vehicle based on the predicted driving state data, the predicted environment data in the predicted configuration information and the battery swapping probability matrix.

[0142] The battery swapping demand distribution data determination module 340 is used to generate battery swapping demand distribution data based on the predicted battery swapping information of vehicles on each road segment.

[0143] Optionally, the data acquisition module 310 is specifically used for:

[0144] Obtain the battery swapping probability matrix and vehicle driving configuration data under different environments and vehicle states, including:

[0145] Acquire historical vehicle data and road topology data. Historical data includes environmental data and driving status data.

[0146] A battery swapping probability matrix is ​​generated based on environmental data and driving status data for vehicles in different environments and under different vehicle conditions.

[0147] Vehicle driving configuration data on the road is generated based on road topology data and driving status data.

[0148] Environmental data includes the date, time, and temperature of vehicle travel; driving status data includes the vehicle's location coordinates, speed data, and battery charge data during the driving process.

[0149] Based on environmental data and driving status data, a battery swapping probability matrix is ​​generated for vehicles in different environments and under different vehicle conditions, including:

[0150] The number of battery swaps was counted under different environmental data ranges and different vehicle conditions;

[0151] By using any environmental data range and the number of battery swaps and the total number of battery swaps under any vehicle condition, the battery swap probability under any environmental data range and any vehicle condition is obtained. The battery swap probability of each environmental data range and each vehicle condition forms a battery swap probability matrix.

[0152] Based on road topology data and driving status data, vehicle driving configuration data on the road is generated, including:

[0153] For any road segment in the road topology data, the average vehicle speed and traffic density at each time period on the road segment are statistically obtained based on the driving status data, which are used as the driving configuration data for the road segment.

[0154] Methods for obtaining road topology data include:

[0155] The road trajectory points of the vehicle at each time point are obtained, and the road trajectory points are merged based on the vehicle's driving status at each time point to obtain multiple trajectory segments, including driving trajectory segments and stationary trajectory segments.

[0156] Multiple trajectory segments are clustered according to their types to obtain trajectory segment sequences of each type.

[0157] By fusing the trajectory segment sequence with road data, road topology data is obtained.

[0158] Before fusing the trajectory segment sequence with road data, the method also includes:

[0159] A road buffer zone is set up, and road trajectory points in each trajectory segment are filtered based on road data in the road topology data and the road buffer zone.

[0160] Optionally, the data acquisition module 320 is configured for:

[0161] By retrieving the driving configuration data from the predicted time data in the predicted configuration information, road configuration is performed to obtain the configuration data for each road segment, including:

[0162] Based on the predicted time data and the vehicle travel probability matrix, the vehicle distribution data is predicted.

[0163] Based on the average vehicle speed and traffic density in the driving configuration data, the vehicle distribution data is configured for each vehicle to obtain the vehicle configuration data for each road segment.

[0164] By using a pre-set vehicle dynamics model, the configuration data for each road segment is simulated to obtain predicted driving state data of the vehicle on the road segment, including:

[0165] For any vehicle in the vehicle distribution data, input the vehicle speed into the vehicle dynamics model to obtain the vehicle's power consumption data;

[0166] Based on power consumption data, predictive driving status data of the vehicle during driving is determined. The predictive driving status data includes battery charge data corresponding to each driving position during driving.

[0167] The vehicle's predicted battery swapping information is determined based on predicted driving status data, predicted environment data from the predicted configuration information, and the battery swapping probability matrix, including:

[0168] The battery charge data and predicted environmental data corresponding to each driving location are matched in the battery swapping probability matrix to determine the battery swapping probability corresponding to each driving location.

[0169] Determine the range of driving locations where the probability of battery swapping meets the battery swapping threshold, and determine the time range corresponding to the driving location range. Use the driving location range and / or time range as the vehicle's predicted battery swapping information.

[0170] The battery swapping demand prediction device provided in this embodiment of the invention can execute the battery swapping demand prediction method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0171] Example 4

[0172] Figure 8 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0173] like Figure 8 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0174] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0175] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as battery swapping demand forecasting methods.

[0176] In some embodiments, the battery swapping demand forecasting method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded into and / or installed on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the battery swapping demand forecasting method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the battery swapping demand forecasting method by any other suitable means (e.g., by means of firmware).

[0177] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0178] Computer programs used to implement the battery swapping demand forecasting method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0179] Example 5

[0180] Embodiment 5 of the present invention also provides a computer-readable storage medium storing computer instructions for causing a processor to execute a battery swapping demand prediction method, the method comprising:

[0181] Obtain the battery swapping probability matrix and vehicle driving configuration data under different environments and vehicle conditions;

[0182] Obtain the predicted configuration information, and use the predicted time data in the predicted configuration information to call the driving configuration data to perform road configuration, thereby obtaining the configuration data for each road segment;

[0183] By simulating the configuration data of each road segment through a pre-set vehicle dynamics model, the predicted driving state data of the vehicle in the road segment is obtained. Based on the predicted driving state data, the predicted environment data in the predicted configuration information and the battery swapping probability matrix, the predicted battery swapping information of the vehicle is determined.

[0184] Based on the predicted battery swapping information of vehicles on each road segment, data on the distribution of battery swapping demand is generated.

[0185] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0186] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0187] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0188] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0189] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0190] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for predicting battery swapping demand, characterized in that, include: Obtain the battery swapping probability matrix and vehicle driving configuration data under different environments and vehicle conditions; Obtain the predicted configuration information, and use the predicted time data in the predicted configuration information to call the driving configuration data to perform road configuration, thereby obtaining the configuration data for each road segment; By using a pre-set vehicle dynamics model, the configuration data of each road segment is simulated to obtain the predicted driving state data of the vehicle on the road segment. Based on the predicted driving state data, the predicted environment data in the predicted configuration information, and the battery swapping probability matrix, the predicted battery swapping information of the vehicle is determined. Based on the predicted battery swapping information of vehicles on each of the aforementioned road segments, battery swapping demand distribution data is generated. The acquisition of the battery swapping probability matrix and vehicle driving configuration data under different environments and vehicle states includes: Acquire historical vehicle data and road topology data, wherein the historical data includes environmental data and driving status data; Based on the environmental data and driving status data, a battery swapping probability matrix for the vehicle under different environments and different vehicle states is generated. Based on the road topology data and the driving status data, vehicle driving configuration data on the road is generated; The environmental data includes the date, time, and temperature of the vehicle's operation; the driving status data includes the vehicle's position coordinates, speed data, and battery charge data during the driving process. The generation of the battery swapping probability matrix for the vehicle under different environments and vehicle states based on the environmental data and driving status data includes: The number of battery swaps was counted under different environmental data ranges and different vehicle conditions; The battery swapping probability for any environmental data range and any vehicle state is obtained by using the number of battery swaps and the total number of battery swaps for any environmental data range and any vehicle state. The battery swapping probability of each environmental data range and each vehicle state forms a battery swapping probability matrix.

2. The method according to claim 1, characterized in that, The process of generating vehicle driving configuration data on the road based on the road topology data and the driving status data includes: For any road segment in the road topology data, the average vehicle speed and traffic density at each time period on the road segment are statistically obtained based on the driving status data, and used as the driving configuration data for the road segment.

3. The method according to claim 1, characterized in that, The method for obtaining the road topology data includes: The road trajectory points of the vehicle at each time point are obtained, and the road trajectory points are merged based on the vehicle's driving status at each time point to obtain multiple trajectory segments, including driving trajectory segments and stationary trajectory segments. The multiple trajectory segments are clustered according to their types to obtain trajectory segment sequences of each type. The trajectory segment sequence is fused with road data to obtain road topology data.

4. The method according to claim 3, characterized in that, Before fusing the trajectory segment sequence with road data, the method further includes: A road buffer zone is set up, and road trajectory points in each trajectory segment are filtered based on the road data in the road topology data and the road buffer zone.

5. The method according to claim 1, characterized in that, The process of calling the driving configuration data from the predicted time data in the predicted configuration information to perform road configuration, and obtaining the configuration data for each road segment, includes: Based on the predicted time data and the vehicle travel probability matrix, the vehicle distribution data is predicted. Based on the average vehicle speed and traffic density in the driving configuration data, the vehicle distribution data is configured for each vehicle to obtain the vehicle configuration data for each road segment.

6. The method according to claim 5, characterized in that, The process involves simulating the configuration data of each road segment using a pre-set vehicle dynamics model to obtain predicted driving state data for the vehicle on the road segment, including: For any vehicle in the vehicle distribution data, the vehicle's speed is input into the vehicle dynamics model to obtain the vehicle's power consumption data; Based on the power consumption data, the predicted driving status data of the vehicle during driving is determined, wherein the predicted driving status data includes battery charge data corresponding to each driving position during driving.

7. The method according to claim 6, characterized in that, The step of determining the vehicle's predicted battery swapping information based on the predicted driving state data, the predicted environment data in the predicted configuration information, and the battery swapping probability matrix includes: The battery charge data corresponding to each driving location and the predicted environment data are matched in the battery swapping probability matrix to determine the battery swapping probability corresponding to each driving location. Determine the driving location range where the battery swap probability meets the battery swap threshold, and determine the time range corresponding to the driving location range. Then, determine the driving location range and / or the time range as the vehicle's predicted battery swap information.

8. A battery swapping demand forecasting device, characterized in that, include: The data acquisition module is used to acquire the battery swapping probability matrix of the vehicle under different environments and different vehicle states, as well as the vehicle's driving configuration data on the road. The configuration data acquisition module is used to acquire the predicted configuration information, and to call the driving configuration data through the predicted time data in the predicted configuration information to perform road configuration and obtain the configuration data of each road segment. The predictive battery swapping information determination module is used to simulate the configuration data of each road segment using a pre-set vehicle dynamics model to obtain the predicted driving state data of the vehicle driving on the road segment, and determine the predicted battery swapping information of the vehicle based on the predicted driving state data, the predicted environment data in the predicted configuration information, and the battery swapping probability matrix. The battery swapping demand distribution data determination module is used to generate battery swapping demand distribution data based on the predicted battery swapping information of vehicles on each of the road segments. Specifically, the data acquisition module is used to acquire historical vehicle data and road topology data, wherein the historical data includes environmental data and driving status data; generate a battery swapping probability matrix for the vehicle under different environments and different vehicle states based on the environmental data and driving status data; and generate driving configuration data for the vehicle on the road based on the road topology data and the driving status data. The environmental data includes the date, time, and temperature of the vehicle's operation; the driving status data includes the vehicle's position coordinates, speed data, and battery charge data during the driving process. The data acquisition module is also specifically used to count the number of battery swaps under different environmental data ranges and different vehicle states; by using the number of battery swaps and the total number of battery swaps under any environmental data range and any vehicle state, the battery swap probability under any environmental data range and any vehicle state is obtained, and the battery swap probabilities under each environmental data range and each vehicle state form a battery swap probability matrix.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the battery swapping demand forecasting method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the battery swapping demand prediction method according to any one of claims 1-7.

Images