Charging path planning method and device, computer device and storage medium

Abstract

The application relates to a charging path planning method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining predicted driving resource transfer data of a vehicle reaching each charging station according to urban traffic data and meteorological data; determining road driving time, queuing waiting time and energy resource transfer data of the vehicle reaching each charging station according to the urban traffic data; and determining a path planning result according to the queuing waiting time, the predicted driving resource transfer data and the energy resource transfer data. The method can be used for real-time dynamic energy consumption charging path planning, which is more in line with the actual situation of user travel, and makes the charging path planning more reasonable.

Description

Technical Field

[0001] This application relates to the field of electric vehicle charging technology, and in particular to a charging path planning method, apparatus, computer equipment, and storage medium. Background Technology

[0002] Currently, the development of electric vehicles still faces some limitations, mainly in terms of insufficient driving range and a continuously widening gap between vehicles and charging stations. Furthermore, the discrepancy between the driving range displayed on the EV dashboard and the actual driving range is significant, and various charging platforms do not provide users with suggestions on the availability of charging stations. This makes it difficult for EV users to find a balance between charging time and location, resulting in inaccurate decisions about when and where to charge. Without proper charging guidance and planning, allowing vehicle owners to arbitrarily choose charging stations and routes will inevitably impact the operation of the power grid and the transportation network. Summary of the Invention

[0003] Therefore, it is necessary to provide a charging path planning method, device, computer equipment, and storage medium that can meet users' charging needs while effectively avoiding congestion and reducing charging time, in order to address the above-mentioned technical problems.

[0004] Firstly, this application provides a charging path planning method. The method includes:

[0005] Based on urban traffic data and meteorological data, predictive driving resource transfer data is obtained for vehicles to reach each charging station;

[0006] Based on urban traffic data, determine the road travel time, queuing time, and energy resource transfer data for vehicles to reach each charging station;

[0007] The route planning results are determined based on queuing time, predicted driving resource transfer data, and energy resource transfer data.

[0008] In one embodiment, urban traffic data includes travel traffic data and road traffic data;

[0009] Based on urban traffic data and meteorological data, predicted resource transfer data for vehicles reaching various charging stations is obtained, including:

[0010] The predicted travel time for each road is determined based on travel traffic data and road traffic data;

[0011] Predicted vehicle energy consumption is determined based on predicted driving time and meteorological data; among which, predicted vehicle energy consumption includes predicted driving energy consumption and predicted auxiliary energy consumption.

[0012] The predicted driving resource transfer data for each road is determined based on predicted driving energy consumption, predicted auxiliary energy consumption, and predicted driving time.

[0013] In one embodiment, urban traffic data also includes traffic network data;

[0014] The predicted travel time for each road is determined based on travel traffic data and road traffic data, including:

[0015] Traffic flow data for each road is determined based on travel data and road traffic data;

[0016] The average time occupancy rate of each road is determined based on the pre-set observation data and traffic flow data of the roads;

[0017] The average driving speed of each road is determined based on traffic flow data and average time occupancy.

[0018] Predicted travel time is determined based on traffic network data and average driving speed.

[0019] In one embodiment, determining the predicted vehicle energy consumption based on predicted driving time and weather data includes:

[0020] Obtain driving parameter data and average driving speed on various roads;

[0021] Determine the predicted driving resistance based on driving parameter data and average driving speed;

[0022] The predicted driving energy consumption in the predicted vehicle energy consumption is determined based on the predicted driving resistance, predicted vehicle speed, and transmission efficiency.

[0023] In one embodiment, before obtaining the predicted driving resource transfer data for vehicles reaching each charging station based on urban traffic data and meteorological data, the method further includes:

[0024] Acquire historical data on vehicle auxiliary energy consumption; where vehicle auxiliary energy consumption includes the actual auxiliary energy consumption of various types of vehicles under different ambient temperatures;

[0025] Based on the actual auxiliary energy consumption of various types of vehicles under different ambient temperatures, determine the actual auxiliary energy consumption corresponding to each ambient temperature.

[0026] A preset auxiliary energy consumption model is established based on the ambient temperature and its corresponding actual auxiliary energy consumption. The preset auxiliary energy consumption model is used to determine the predicted auxiliary energy consumption of the vehicle when it arrives at each charging station. The predicted auxiliary energy consumption is used to determine the predicted driving resource transfer data.

[0027] In one embodiment, the road travel time, queuing time, and energy resource transfer data of vehicles arriving at each charging station are determined based on urban traffic data, including:

[0028] Based on the vehicle's remaining energy data and vehicle location data when the charging request is initiated, the location data of the charging station at the vehicle's mileage is determined, and the road travel time of the vehicle to each charging station is determined based on the vehicle location data and the charging station location data.

[0029] The predicted arrival time is determined based on the road travel time, and the predicted arrival time is input into a preset vehicle prediction model to determine the queuing time and predicted remaining energy data.

[0030] Based on the predicted remaining energy data and the predicted arrival time, determine the energy resource transfer data for vehicles arriving at each charging station.

[0031] In one embodiment, before obtaining predicted driving resource transfer data for vehicles reaching each charging station based on urban traffic data and meteorological data, the method further includes:

[0032] Acquire sample charging station data and its corresponding historical meteorological data, day type, maximum ambient temperature and minimum ambient temperature, and use the historical meteorological data, day type, maximum ambient temperature and minimum ambient temperature as input layer data;

[0033] The parameters of the initial prediction model are updated based on the input layer data to obtain the preset vehicle prediction model. The preset vehicle prediction model is used to predict and process urban traffic data to determine the queuing time of vehicles arriving at each charging station.

[0034] Secondly, this application also provides a charging path planning device. The device includes:

[0035] The driving loss module is used to obtain predicted driving resource transfer data for vehicles reaching various charging stations based on urban traffic data and meteorological data.

[0036] The charging prediction module is used to determine the road travel time, queuing time, and energy resource transfer data of vehicles to each charging station based on urban traffic data.

[0037] The route planning module is used to determine the route planning results based on queuing time, predicted driving resource transfer data, and energy resource transfer data.

[0038] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0039] Based on urban traffic data and meteorological data, predictive driving resource transfer data is obtained for vehicles to reach each charging station;

[0040] Based on urban traffic data, determine the road travel time, queuing time, and energy resource transfer data for vehicles to reach each charging station;

[0041] The route planning results are determined based on queuing time, predicted driving resource transfer data, and energy resource transfer data.

[0042] Fourthly, this application also provides a computer-readable storage medium. This computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0043] Based on urban traffic data and meteorological data, predictive driving resource transfer data is obtained for vehicles to reach each charging station;

[0044] Based on urban traffic data, determine the road travel time, queuing time, and energy resource transfer data for vehicles to reach each charging station;

[0045] The route planning results are determined based on queuing time, predicted driving resource transfer data, and energy resource transfer data.

[0046] Fifthly, this application also provides a computer program product. This computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0047] Based on urban traffic data and meteorological data, predictive driving resource transfer data is obtained for vehicles to reach each charging station;

[0048] Based on urban traffic data, determine the road travel time, queuing time, and energy resource transfer data for vehicles to reach each charging station;

[0049] The route planning results are determined based on queuing time, predicted driving resource transfer data, and energy resource transfer data.

[0050] The aforementioned charging route planning method, device, computer equipment, storage medium, and computer program product acquire the location information of charging stations within the range of the vehicle's remaining battery power when an electric vehicle needs to be charged. Then, it calculates the energy consumption (i.e., driving cost) of the vehicle traveling on each road segment in urban areas to the charging station using urban traffic data and meteorological data. Furthermore, it constructs a charging route planning model based on the queuing time and charging cost when the vehicle arrives at each charging station, as well as predicted driving resource transfer data and energy resource transfer data. The model then selects the most suitable charging stations and routes, which can meet the user's charging needs while avoiding road congestion and eliminating crowded charging stations, thereby reducing the time spent on charging during travel. Attached Figure Description

[0051] Figure 1This is a flowchart illustrating a charging path planning method in one embodiment;

[0052] Figure 2 This is a flowchart illustrating the process of determining vehicle energy consumption and predicting the transfer of driving resources in one embodiment;

[0053] Figure 3 This is a flowchart illustrating the process of determining the predicted travel time in one embodiment;

[0054] Figure 4 This is a schematic diagram of the process for determining vehicle energy consumption in one embodiment;

[0055] Figure 5 This is a schematic diagram of the process for constructing a preset auxiliary energy consumption model in one embodiment;

[0056] Figure 6 A schematic diagram of the vehicle charging process in one embodiment;

[0057] Figure 7 This is a schematic diagram illustrating the process of building a vehicle prediction model in one embodiment;

[0058] Figure 8 This is a structural block diagram of a charging path planning device in one embodiment;

[0059] Figure 9 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0061] In one embodiment, such as Figure 1 As shown, a charging path planning method is provided. This embodiment illustrates the application of this method to a terminal. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0062] S102 obtains predicted driving resource transfer data for vehicles reaching each charging station based on urban traffic data and meteorological data.

[0063] Specifically, after acquiring urban traffic network data, travel traffic data, and road traffic data, the system calculates the location information of charging stations within the vehicle's remaining mileage based on the traffic network data and the charging station data it includes. Then, based on the vehicle's location information and the location information within each charging station, the system calculates the predicted energy consumption for the distance the vehicle travels to each charging station under current urban road conditions, as well as the predicted auxiliary energy consumption calculated based on real-time meteorological data.

[0064] S104 determines the road travel time, queuing time, and energy resource transfer data of vehicles to each charging station based on urban traffic data.

[0065] Among them, energy resource transfer refers to the charging cost calculated based on the time-of-use electricity price and the required charging amount when the vehicle arrives at each charging station.

[0066] Specifically, the system calculates the road travel time from vehicles to each charging station and the number of vehicles waiting to be charged at each charging station at the departure time based on urban traffic data. It then determines the number of vehicles that have completed charging at each charging station during the road travel time and the number of vehicles arriving at each charging station waiting to be charged, based on the road travel time. Finally, it calculates the queuing time for vehicles at each charging station based on the number of vehicles waiting to be charged at the departure time, the number of vehicles that have completed charging at each charging station during the road travel time, and the number of vehicles arriving at each charging station waiting to be charged.

[0067] Simultaneously, the time-of-use electricity price at the time the vehicle arrives at each charging station is determined, the remaining electricity at the time the vehicle arrives at each charging station is predicted, and the charging amount is calculated. Energy resource transfer data is then calculated based on the time-of-use electricity price and the charging amount.

[0068] S106 determines the route planning results based on queuing time, predicted driving resource transfer data, and energy resource transfer data.

[0069] Specifically, the calculated queuing time, predicted driving resource transfer data, and energy resource transfer data are input into the preset charging route planning model to select the most suitable charging route.

[0070] When selecting a suitable charging route, there are also constraints, namely, the current remaining energy data constraint, the route selection constraint, and the recommended number of charging stations constraint.

[0071] The current remaining energy data constraints are:

[0072]

[0073] in, The vehicle's initial energy, Vehicle minimum energy, This is a function for calculating travel distance. The distance from the vehicle to the charging station. The maximum driving distance with the current remaining energy.

[0074] The path selection constraint is as follows: when an electric vehicle passes through nodes i and j during its journey, if node i is the starting point, then only one path exists. If node i is an intermediate node, only one exists. , making ,exist , making If node i is the destination node, only exists Specifically:

[0075] .

[0076] The recommended number of charging stations is constrained as follows:

[0077]

[0078] in, This represents the number of nodes i and j in the vehicle's journey to the charging station.

[0079] By standardizing and eliminating the dimensional relationship between queuing time, predicted driving resource transfer data, and energy resource transfer data, the objective function for charging route planning is:

[0080]

[0081] in, These are coefficients, representing different planning needs of users during their travels, to meet... , These represent the predicted driving resource transfer data, queue waiting time, and energy resource transfer data selected by the user during their trip, respectively. These represent the minimum and maximum values ​​of predicted driving resource transfer data, queuing time, and energy resource transfer data for all paths, respectively.

[0082] In the aforementioned charging route planning method, when an electric vehicle needs to be charged, urban traffic data, meteorological data, and the location information of charging stations within the vehicle's remaining mileage are obtained through the vehicle's onboard system network. Then, the energy consumption, i.e., the driving cost, of the vehicle traveling on each segment of urban roads to the charging station is calculated using urban traffic data and meteorological data. Furthermore, the queuing time and charging cost when the vehicle arrives at each charging station are also considered. Based on the driving cost, queuing time, and charging cost, a charging route planning model is constructed, and the most suitable charging stations and routes are selected. This method can meet the user's charging needs while avoiding road congestion and eliminating crowded charging stations, thereby reducing the time spent on charging during the trip.

[0083] In one embodiment, such as Figure 2 As shown, based on urban traffic data and meteorological data, predicted resource transfer data for vehicles reaching each charging station is obtained, including:

[0084] S202 determines the predicted travel time for each road based on travel traffic data and road traffic data.

[0085] Urban traffic data includes travel data and road traffic data.

[0086] Specifically, traffic flow at different times on each road is calculated using travel data and road traffic data, and travel time is predicted based on the traffic flow.

[0087] S204 determines the predicted vehicle energy consumption based on predicted driving time and meteorological data.

[0088] Among them, predicted vehicle energy consumption includes predicted driving energy consumption and predicted auxiliary energy consumption.

[0089] Specifically, the predicted driving energy consumption is calculated based on the driving distance to each charging station and the predicted driving time, as well as the predicted auxiliary energy consumption required during the driving process based on weather conditions.

[0090] S206, determine the predicted driving resource transfer data for each road based on predicted driving energy consumption, predicted auxiliary energy consumption, and predicted driving time.

[0091] Specifically, in the process of calculating the energy consumption and travel time of the vehicle to each charging station, the predicted travel energy consumption of each road during the travel process is estimated by predicting the travel energy consumption and the predicted travel time. Based on the travel energy consumption of each road and the predicted auxiliary energy consumption during the travel process, the predicted travel resource transfer data during the travel process is calculated.

[0092] The specific expression for predicting driving energy consumption is:

[0093]

[0094] in, , , , , These are respectively represented as the electric vehicle's motor conversion efficiency, transmission system conversion efficiency, predicted driving energy consumption, predicted auxiliary energy consumption, and predicted driving energy consumption.

[0095] The specific expression for predicting the transfer of driving resources is as follows:

[0096]

[0097] in, , , , These represent unit time cost, predicted driving time, average daily charging price, and predicted driving resource transfer data, respectively.

[0098] In this embodiment, by estimating the predicted driving energy consumption of the vehicle on various roads during the driving process, and estimating the predicted auxiliary energy consumption required based on the weather conditions during the driving process, and then calculating the predicted driving resource transfer data (i.e. driving cost) of the entire driving process based on the predicted driving energy consumption and the predicted auxiliary energy consumption, data support is provided for selecting suitable charging routes, which can reduce the time and extra mileage consumed by users during their travels.

[0099] In one embodiment, such as Figure 3 As shown, the predicted travel time for each road is determined based on travel traffic data and road traffic data, including:

[0100] S302 determines the traffic flow data for each road based on travel traffic data and road traffic data.

[0101] Urban traffic data also includes traffic network data.

[0102] Specifically, after acquiring travel traffic data and road traffic data, the traffic flow for the travel distance is calculated. Based on traffic flow assignment theory, the traffic flow for the travel distance is transformed into the traffic flow for each road at different times, and the average speed of each road is represented by its traffic flow. The relationship between traffic flow and average speed is expressed as follows:

[0103]

[0104] in, This represents the average speed of the road at time t. This represents the traffic flow on the road at time t. Indicates road density.

[0105] S304 determines the average time occupancy rate of each road based on preset observation data and traffic flow data.

[0106] Specifically, since road density is difficult to obtain, the average time occupancy rate of roads is used to calculate road density. Pre-observation data is obtained by conducting preliminary observations of each road. This data is then combined with traffic flow data to calculate the average time occupancy rate. The specific expression is:

[0107]

[0108]

[0109]

[0110] in, , , , Let represent the total observation time, the total number of electric vehicles, the distance between the i-th electric vehicle and the vehicle in front, and the average inter-vehicle distance, respectively. Indicates average time occupancy; , Let these represent the length of the i-th vehicle and the length of the detector, respectively. , Let represent the time and speed at which the i-th car passes the tester.

[0111] S306 determines the average driving speed of each road based on traffic flow data and average time occupancy.

[0112] Specifically, assuming that the length of vehicles on each road is 1000 mm. The specific expression for the relationship between average driving speed and average time occupancy is as follows:

[0113]

[0114] .

[0115] S308 determines the predicted travel time based on traffic network data and average driving speed.

[0116] Specifically, the travel time on each road is calculated using the average speed and distance of each road, and then the predicted travel time is estimated. The specific expression is:

[0117]

[0118] in, , , ··· These represent the distances of each road. , , ··· These represent the vehicle's speed on each road. This indicates the predicted travel time.

[0119] In this embodiment, by dividing the driving route into various roads and observing each road in advance, the average time occupancy of each road is estimated using traffic flow data and preset observation data, and then the average driving speed is estimated. Combined with the distance of each road, the driving time of each road is estimated, and thus the predicted driving time is obtained. This reduces the estimation error of the predicted driving time of the vehicle to each charging station and improves the rationality of the selection of charging routes.

[0120] In one embodiment, such as Figure 4 As shown, the predicted vehicle energy consumption is determined based on predicted driving time and meteorological data, including:

[0121] S402, obtains driving parameter data and average driving speed on each road.

[0122] The driving parameter data includes parameters related to air resistance, slope resistance, road friction, and vehicle mass.

[0123] S404 determines the predicted driving resistance based on driving parameter data and average driving speed.

[0124] Specifically, air resistance, slope resistance, road friction, and acceleration resistance are estimated based on the acquired form parameter data, and the sum of air resistance, slope resistance, road friction, and acceleration resistance is the predicted driving resistance.

[0125] The air resistance during driving is:

[0126]

[0127] in, , , , These represent air density, air drag coefficient, vehicle frontal area, and vehicle speed, respectively.

[0128] The slope resistance during driving is:

[0129]

[0130] in, , g and g represent the mass of the electric vehicle, the road inclination angle, and the acceleration due to gravity, respectively.

[0131] The road friction force during driving is:

[0132]

[0133] in, This represents the coefficient of sliding friction of the road.

[0134] The acceleration resistance during driving is .

[0135] The predicted driving resistance is:

[0136] .

[0137] S406, the predicted driving energy consumption in the predicted vehicle energy consumption is determined based on the predicted driving resistance, the predicted vehicle speed and the transmission efficiency.

[0138] Specifically, the driving energy consumption of different roads is calculated based on the predicted driving resistance of different roads. Therefore, the sum of the driving energy consumption of all roads is the predicted driving energy consumption for the entire driving process. Specifically:

[0139] .

[0140] In this embodiment, the driving resistance is estimated and predicted by considering the air resistance, slope resistance, road friction, and acceleration resistance of each road. Then, the driving energy consumption of each road is calculated based on the estimated driving resistance, and the predicted driving energy consumption of the entire driving process is integrated to achieve segmented energy consumption estimation. By accurately estimating the energy consumption of each road, the estimation error of the predicted driving energy consumption of the entire driving process is reduced, and the accuracy of charging route planning is improved.

[0141] In one embodiment, such as Figure 5 As shown, before obtaining the predicted resource transfer data for vehicles reaching each charging station based on urban traffic data and meteorological data, the method also includes:

[0142] S502, acquire historical data on vehicle auxiliary energy consumption; where vehicle auxiliary energy consumption includes the actual auxiliary energy consumption of various types of vehicles under different ambient temperatures.

[0143] Specifically, data is collected from various vehicles to obtain the actual auxiliary energy consumption under different ambient temperatures and driving conditions.

[0144] S504 determines the actual auxiliary energy consumption corresponding to each ambient temperature based on the real auxiliary energy consumption of various types of vehicles under different ambient temperatures.

[0145] Specifically, the historical data of vehicle auxiliary energy consumption collected is classified and processed, and the ambient temperature is matched one-to-one with the actual auxiliary energy consumption corresponding to that ambient temperature.

[0146] S506, establish a preset auxiliary energy consumption model based on the ambient temperature and its corresponding actual auxiliary energy consumption.

[0147] Among them, the preset auxiliary energy consumption model is used to determine the predicted auxiliary energy consumption of the vehicle when it arrives at each charging station, and the predicted auxiliary energy consumption is used to determine the predicted driving resource transfer data.

[0148] Specifically, based on the actual auxiliary energy consumption of various vehicles under different ambient temperatures and driving conditions, a relationship between ambient temperature and auxiliary energy consumption is established, i.e., a preset auxiliary energy consumption model. This model is then fitted using the least squares method, and the preset auxiliary energy consumption is... The specific relation is as follows:

[0149]

[0150] in, These are the fitting coefficients. For actual auxiliary energy consumption, To predict auxiliary energy consumption.

[0151] In this embodiment, by fitting the expression that best approximates the actual auxiliary energy consumption based on the relationship between ambient temperature and auxiliary energy consumption in historical data, a preset auxiliary energy consumption model is obtained, and the predicted auxiliary energy consumption during driving is estimated in this way, thereby reducing the estimation error of the predicted auxiliary energy consumption during the entire driving process and improving the accuracy of charging route planning.

[0152] In one embodiment, such as Figure 6 As shown, based on urban traffic data, the road travel time, queuing time, and energy resource transfer data for vehicles arriving at each charging station are determined, including:

[0153] S602 determines the location data of charging stations at the vehicle's mileage based on the vehicle's remaining energy data and vehicle location data when the charging request is initiated, and determines the road travel time for the vehicle to reach each charging station based on the vehicle location data and charging station location data.

[0154] Specifically, when the onboard system detects that the vehicle's remaining battery power is below the preset alarm threshold, the system issues a warning and obtains the current remaining energy data and vehicle location data. Using the vehicle location data as a starting point, it filters for charging station locations within the mileage range of the current remaining energy data. It then obtains the distance data between the vehicle and each charging station using urban traffic data, and calculates the road travel time and the corresponding predicted arrival time based on this distance data.

[0155] S604 determines the predicted arrival time based on road travel time and inputs the predicted arrival time into a preset vehicle prediction model to determine queuing time and predicted remaining energy data.

[0156] Specifically, obtain the number of vehicles waiting to be charged at the charging station at the current moment. Estimate the number of vehicles that complete charging and leave the charging station upon arrival. The number of vehicles that arrive at charging stations during the journey and are waiting to be charged This is to determine the number of vehicles in each charging station when the vehicle arrives, and then calculate the estimated queuing time after arrival.

[0157] The number of vehicles N in each charging station when the vehicles arrive is:

[0158] .

[0159] The estimated waiting time is:

[0160]

[0161] in, , , These are the charging time required for the electric vehicle currently being charged, the charging time of vehicles that arrived before this vehicle, and the estimated queuing time.

[0162] S606 determines the energy resource transfer data for vehicles arriving at each charging station based on predicted remaining energy data and predicted arrival time.

[0163] Specifically, by acquiring the vehicle's state of charge (SOC) when the vehicle issues the warning, the remaining energy data is calculated based on the predicted driving energy consumption. Specifically:

[0164]

[0165] in, , These represent the initial SOC and maximum energy data of the electric vehicle, respectively.

[0166] Energy resource transfer data Specifically:

[0167]

[0168] in, , These represent the state of charge of the electric vehicle and the charging station, respectively, when charging is complete. Time-of-use electricity pricing.

[0169] In this embodiment, by calculating the data of each charging station within the vehicle's remaining mileage when the vehicle issues a charging reminder, the system estimates the number of vehicles that complete charging and the number of vehicles that need charging during the journey to each charging station. This allows for the calculation of queuing time, the predicted remaining energy data upon reaching the charging station, and the estimation of energy resource transfer data upon completion of charging. This enables the selection of economically suitable charging sites, reduces additional travel time and expenses, provides data support for charging route planning, and improves the accuracy of charging route planning.

[0170] In one embodiment, such as Figure 7 As shown, before obtaining predicted driving resource transfer data for vehicles reaching each charging station based on urban traffic data and meteorological data, the method also includes:

[0171] S702 acquires sample charging station data and its corresponding historical meteorological data, day type, maximum ambient temperature and minimum ambient temperature, and uses the historical meteorological data, day type, maximum ambient temperature and minimum ambient temperature as input layer data.

[0172] S704, update the parameters of the initial prediction model based on the input layer data to obtain the preset vehicle prediction model.

[0173] Among them, the preset vehicle prediction model is used to predict and process urban traffic data to determine the queuing time for vehicles to arrive at each charging station.

[0174] Specifically, in the unsupervised training phase, multi-layer Boltzmann machines (RBMs) are stacked, so the parameters between the levels of the n RBMs are... The model is initialized as follows:

[0175]

[0176] Among them, parameters , Weights on the visible layer, Weights on the hidden layer This is the connection matrix between the visible layer and the hidden layer; This is the visible layer, i.e., the input data after normalization; It is a hidden layer.

[0177] If the parameters are known Based on the input visual layer Hidden layer for:

[0178]

[0179] in, Let be the activation function, and be the output value of the i-th node in the hidden layer h. Let be the i-th column of the weight matrix W. Let be the i-th component in the hidden layer weight b.

[0180] Similarly, if the hidden layers are known, then the layers can be viewed as:

[0181] .

[0182] The initial vehicle prediction model is trained using the maximum likelihood estimation method on the training data, thereby obtaining the parameter optimization objective function under ideal conditions:

[0183]

[0184] in, As training samples, .

[0185] Then, the parameters were optimized using the contrastive divergence method. Find the parameters The optimal solution is obtained and assigned to the connection weight matrix and weights. The weights and values ​​of each layer of the RBM are then calculated to complete the pre-training process of parameter initialization.

[0186] To minimize the prediction error, the structural parameters of the RBM model are updated, and the optimization objective function is constructed based on the energy loss criterion as follows:

[0187]

[0188] in, For loss function, , For learning rate, , This is a regularization constraint.

[0189] In this embodiment, by constructing a vehicle prediction model and optimizing and updating it, the number of vehicles leaving the charging station and the number of vehicles arriving at the charging station during the journey can be estimated relatively accurately. This provides data support for estimating and predicting queuing time and reduces the estimation error of queuing time.

[0190] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0191] Based on the same inventive concept, this application also provides a charging path planning device for implementing the charging path planning method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more charging path planning device embodiments provided below can be found in the limitations of the charging path planning method described above, and will not be repeated here.

[0192] In one embodiment, such as Figure 8As shown, a charging route planning device is provided, including: a driving loss module 802, a charging prediction module 804, and a route planning module 806, wherein:

[0193] The driving loss module 802 is used to obtain predicted driving resource transfer data for vehicles reaching various charging stations based on urban traffic data and meteorological data.

[0194] The charging prediction module 804 is used to determine the road travel time, queuing time, and energy resource transfer data of vehicles arriving at each charging station based on urban traffic data.

[0195] The route planning module 806 is used to determine the route planning results based on queuing time, predicted driving resource transfer data, and energy resource transfer data.

[0196] In one embodiment, the driving loss module 802 further includes a driving resource transfer module, which is used to determine the predicted driving time of each road based on travel traffic data and road traffic data; determine the predicted vehicle energy consumption based on the predicted driving time and meteorological data; wherein the predicted vehicle energy consumption includes predicted driving energy consumption and predicted auxiliary energy consumption; and determine the predicted driving resource transfer data of each road based on the predicted driving energy consumption, predicted auxiliary energy consumption and predicted driving time.

[0197] In one embodiment, the driving loss module 802 further includes a driving time prediction module, which is used to determine the traffic flow data of each road based on travel traffic data and road traffic data; determine the average time occupancy of each road based on preset observation data and traffic flow data; determine the average driving speed of each road based on traffic flow data and average time occupancy; and determine the predicted driving time based on traffic network data and average driving speed.

[0198] In one embodiment, the driving loss module 802 further includes an energy consumption prediction module, which is used to acquire driving parameter data and the average driving speed of each road; determine the predicted driving resistance based on the driving parameter data and the average driving speed; and determine the predicted driving energy consumption in the predicted vehicle energy consumption based on the predicted driving resistance, the predicted vehicle driving speed, and the transmission operating efficiency.

[0199] In one embodiment, the device further includes:

[0200] The auxiliary energy consumption acquisition module is used to acquire historical data on vehicle auxiliary energy consumption.

[0201] The data processing module is used to determine the actual auxiliary energy consumption corresponding to each ambient temperature based on the actual auxiliary energy consumption of various types of vehicles under different ambient temperatures.

[0202] The fitting model module is used to establish a preset auxiliary energy consumption model based on the ambient temperature and its corresponding actual auxiliary energy consumption.

[0203] In one embodiment, the charging prediction module 804 further includes an energy resource transfer module, which is used to determine the location data of the charging station at the vehicle's mileage based on the vehicle's remaining energy data and vehicle location data when the charging request is initiated, and to determine the road travel time of the vehicle to each charging station based on the vehicle location data and charging station location data; to determine the predicted arrival time based on the road travel time, and to input the predicted arrival time into a preset vehicle prediction model to determine the queuing time and predicted remaining energy data; and to determine the energy resource transfer data of the vehicle to each charging station based on the predicted remaining energy data and the predicted arrival time.

[0204] In one embodiment, the device further includes:

[0205] The training data acquisition module is used to acquire sample charging station data and its corresponding historical meteorological data, day type, maximum ambient temperature and minimum ambient temperature, and uses the historical meteorological data, day type, maximum ambient temperature and minimum ambient temperature as input layer data.

[0206] The model optimization module is used to update the parameters of the initial prediction model based on the input layer data to obtain the preset vehicle prediction model.

[0207] Each module in the aforementioned charging path planning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0208] In one embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 9As shown, the computer device includes a processor, memory, input / output interfaces, a communication interface, a display unit, and an input device. The processor, memory, and input / output interfaces are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interfaces. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a charging path planning method. The display unit is used to form a visually visible image and can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0209] Those skilled in the art will understand that Figure 9 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0210] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps in the above method embodiments.

[0211] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0212] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0213] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0214] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0215] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A charging path planning method, characterized in that, The method includes: Predicted driving resource transfer data for vehicles reaching each charging station is obtained based on urban traffic data and meteorological data. The urban traffic data includes travel traffic data and road traffic data. Obtaining the predicted driving resource transfer data for vehicles reaching each charging station based on the urban traffic data and meteorological data includes: determining the predicted travel time for each road based on the travel traffic data and road traffic data; determining the predicted vehicle energy consumption based on the predicted travel time and meteorological data; wherein the predicted vehicle energy consumption includes predicted driving energy consumption and predicted auxiliary energy consumption. Determining the predicted vehicle energy consumption based on the predicted travel time and meteorological data includes: acquiring driving parameter data and the average driving speed for each road; determining the predicted driving resistance based on the driving parameter data and the average driving speed; determining the predicted driving energy consumption in the predicted vehicle energy consumption based on the predicted driving resistance, the predicted vehicle driving speed, and transmission efficiency; wherein air resistance, slope resistance, road friction, and acceleration resistance are estimated based on the acquired driving parameter data, and the predicted driving resistance is determined to include the sum of air resistance, slope resistance, road friction, and acceleration resistance; and the driving energy consumption for each road is calculated based on the predicted driving resistance for different roads. Based on the urban traffic data, the road travel time, queuing time, and energy resource transfer data for each vehicle to reach each charging station are determined. Based on the vehicle's remaining energy data and vehicle location data when the charging request is initiated, the location data of the charging station at the vehicle's mileage is determined, and the road travel time for each vehicle to reach each charging station is determined based on the vehicle location data and the charging station location data. The predicted arrival time is determined based on the road travel time, and the predicted arrival time is input into a preset vehicle prediction model to determine the queuing time and predicted remaining energy data. Based on the predicted remaining energy data and the predicted arrival time, the energy resource transfer data for each vehicle to reach each charging station is determined. Here, energy resource transfer refers to the charging cost calculated based on the time-of-use electricity price and the required charging amount at the time the vehicle arrives at each charging station. The path planning result is determined based on the queue waiting time, the predicted driving resource transfer data, and the energy resource transfer data.

2. The method according to claim 1, characterized in that, The step of obtaining predicted driving resource transfer data for vehicles reaching each charging station based on the urban traffic data and the meteorological data includes: The predicted driving resource transfer data for each road is determined based on the predicted driving energy consumption, the predicted auxiliary energy consumption, and the predicted driving time.

3. The method according to claim 2, characterized in that, The urban traffic data also includes traffic network data; The step of determining the predicted travel time for each road based on the travel traffic data and the road traffic data includes: Traffic flow data for each road is determined based on the travel traffic data and the road traffic data; The average time occupancy rate of each road is determined based on the preset observation data of the road and the traffic flow data. The average driving speed of each road is determined based on the traffic flow data and the average time occupancy rate. The predicted travel time is determined based on the traffic network data and the average driving speed.

4. The method according to claim 2, characterized in that, Before obtaining the predicted driving resource transfer data for vehicles reaching each charging station based on the urban traffic data and the meteorological data, the method further includes: Acquire historical data on vehicle auxiliary energy consumption; wherein, the vehicle auxiliary energy consumption includes the actual auxiliary energy consumption of various types of vehicles under different ambient temperatures; Based on the actual auxiliary energy consumption of each type of vehicle under different ambient temperatures, the actual auxiliary energy consumption corresponding to each ambient temperature is determined. A preset auxiliary energy consumption model is established based on the ambient temperature and the corresponding actual auxiliary energy consumption; the preset auxiliary energy consumption model is used to determine the predicted auxiliary energy consumption of the vehicle when it arrives at each charging station, and the predicted auxiliary energy consumption is used to determine the predicted driving resource transfer data.

5. The method according to claim 1, characterized in that, Before obtaining the predicted driving resource transfer data for vehicles reaching each charging station based on urban traffic data and meteorological data, the method further includes: Acquire sample charging station data and its corresponding historical meteorological data, day type, maximum ambient temperature and minimum ambient temperature, and use the historical meteorological data, day type, maximum ambient temperature and minimum ambient temperature as input layer data; The parameters of the initial prediction model are updated based on the input layer data to obtain a preset vehicle prediction model; the preset vehicle prediction model is used to predict the urban traffic data and determine the queuing time for vehicles to arrive at each charging station.

6. A charging path planning device, characterized in that, The device includes: The driving loss module is used to obtain predicted driving resource transfer data for vehicles reaching various charging stations based on urban traffic data and meteorological data; the urban traffic data includes travel traffic data and road traffic data; it is also used to determine the predicted driving time for each road based on the travel traffic data and the road traffic data; and to determine the predicted vehicle energy consumption based on the predicted driving time and the meteorological data; wherein the predicted vehicle energy consumption includes predicted driving energy consumption and predicted auxiliary energy consumption; it is also used to acquire driving parameter data and the average driving speed of each road; to determine the predicted driving resistance based on the driving parameter data and the average driving speed; to determine the predicted driving energy consumption in the predicted vehicle energy consumption based on the predicted driving resistance, the predicted vehicle driving speed, and the transmission efficiency; and to estimate air resistance, slope resistance, road friction, and acceleration resistance based on the acquired driving parameter data, and to determine that the predicted driving resistance includes the sum of air resistance, slope resistance, road friction, and acceleration resistance, and to calculate the driving energy consumption for each road based on the predicted driving resistance of different roads; The charging prediction module is used to determine the road travel time, queuing time, and energy resource transfer data of a vehicle arriving at each charging station based on the urban traffic data; it is also used to determine the location data of the charging station at the vehicle's mileage based on the vehicle's remaining energy data and vehicle location data when the charging request is initiated, and to determine the road travel time of the vehicle arriving at each charging station based on the vehicle location data and the charging station location data; to determine the predicted arrival time based on the road travel time, and to input the predicted arrival time into a preset vehicle prediction model to determine the queuing time and predicted remaining energy data; and to determine the energy resource transfer data of the vehicle arriving at each charging station based on the predicted remaining energy data and the predicted arrival time; wherein, energy resource transfer refers to the charging cost calculated based on the time-of-use electricity price and the required charging amount at the time the vehicle arrives at each charging station. The route planning module is used to determine the route planning result based on the queuing waiting time, the predicted driving resource transfer data, and the energy resource transfer data.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

Images