Highway vehicle energy supplement load prediction method and system based on traffic state

Abstract

The application provides a highway vehicle energy supplement load prediction method and system based on traffic states, relates to the technical field of intelligent traffic and multi-energy collaborative management, and aims at the problems that the prior art has the limitation of a single energy model, lacks traffic state dynamics, and path planning does not meet actual demands and the like.The method obtains energy consumption data of multi-energy type vehicles, constructs a vehicle specific power model, divides traffic states according to a public road local model, calibrates energy consumption factors of the multi-energy type vehicles under different traffic states, obtains an optimal path of vehicle driving through a multi-objective path planning algorithm based on road network topology information of a road traffic model, simulates a travel time, an initial energy state and a maximum energy capacity by using a Monte Carlo method, and predicts the space-time distribution of the energy supplement load of the multi-energy type vehicles.The application solves the problems in the prior art and realizes accurate prediction of the multi-energy type vehicles under different traffic states.

Description

Technical Field

[0001] This invention belongs to the field of intelligent transportation and multi-energy collaborative management technology, and particularly relates to a method and system for predicting the energy replenishment load of highway vehicles based on traffic conditions. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] With the rapid development of green and low-carbon transportation and the transformation of the energy structure, the scale of new energy vehicles, represented by electric vehicles (EVs) and hydrogen fuel cell vehicles (FCEVs), is constantly expanding, which is also driving the transformation of the energy supply system of road transportation systems. Therefore, the comprehensive integration of information on vehicles and roads of multiple energy types to achieve accurate prediction of the spatiotemporal distribution of refueling loads of vehicles of multiple energy types, such as fuel vehicles, electric vehicles, and hydrogen fuel cell vehicles, in highway scenarios has become a key requirement in the field of intelligent transportation and energy collaborative management.

[0004] However, existing energy load forecasting methods mostly target single energy types and fail to consider the interactive effects of energy consumption from vehicles with multiple energy types (gasoline vehicles, electric vehicles, hydrogen fuel cell vehicles, etc.), leading to significant prediction biases. Furthermore, traditional forecasting models often use average speed or predict under ideal traffic flow conditions, neglecting the nonlinear impact of smooth, slow, congested, and severely congested traffic conditions on energy consumption. Particularly under congested conditions, the idling fuel consumption of gasoline vehicles, the energy loss from frequent start-stop operations of electric vehicles, and the inefficient operation of hydrogen fuel cells are severely underestimated, making accurate predictions of energy load in various highway scenarios difficult. Simultaneously, existing path planning algorithms only use time or distance as a single optimization objective, without energy constraints. This can lead to vehicles choosing energy-intensive but short-time routes, only to be forced to detour midway due to energy depletion, exacerbating load fluctuations in service areas. Summary of the Invention

[0005] To overcome the shortcomings of the prior art, this invention provides a method and system for predicting highway vehicle energy replenishment load based on traffic conditions. By integrating real-time traffic condition perception, vehicle specific power energy consumption modeling, multi-objective path planning and Monte Carlo simulation technology, it can achieve accurate prediction of fuel consumption, electricity demand and hydrogen demand at highway service area nodes.

[0006] To achieve the above objectives, one or more embodiments of the present invention provide the following technical solutions:

[0007] The first aspect of the present invention provides a method for predicting highway vehicle energy replenishment load based on traffic conditions, comprising:

[0008] Acquire energy consumption data of vehicles with multiple energy types, traffic network operation data, and information on energy replenishment facilities in service areas;

[0009] A vehicle specific power model is constructed based on energy consumption data of vehicles with multiple energy types.

[0010] Traffic conditions are classified according to the public road bureau model, and the energy consumption factors of multi-energy vehicles under different traffic conditions are calibrated based on the vehicle power ratio.

[0011] Based on traffic network operation data, a road traffic model is constructed that includes information on road segment distance, traffic flow, maximum capacity, time, and energy consumption.

[0012] Based on the road network topology information of the road traffic model, the optimal path for vehicle travel is obtained through a multi-objective path planning algorithm;

[0013] Based on the optimal driving route of the vehicle and the information on the energy replenishment facilities in the service area, the Monte Carlo method is used to sample and simulate the probability model of related events such as the starting node, target node, travel time, initial energy state, and total energy capacity of vehicles of multiple energy types, and to predict the spatiotemporal distribution of energy replenishment load of vehicles of multiple energy types.

[0014] As one implementation method, the energy consumption data of multi-energy type vehicles includes the vehicle's position data, speed data, acceleration data, instantaneous fuel consumption rate, engine speed, battery voltage, battery current, hydrogen fuel cell voltage, and hydrogen fuel cell current.

[0015] Traffic network operation data includes static road network attribute data and dynamic road network attribute data. Static road network attribute data includes road segment length, number of lanes, road type, and maximum traffic capacity.

[0016] The information on service area energy replenishment facilities mainly includes the number of refueling piles, charging piles, and hydrogen refueling piles in the service area, the charging power of electric vehicles, the real-time number of refueling piles, charging piles, and hydrogen refueling piles in use, and the number of vehicles with multiple energy types queuing in the service area.

[0017] As one implementation method, the formula for calculating the vehicle power-to-weight ratio model is:

[0018] ;

[0019] in, For vehicle speed, The total mass of the vehicle. The angle of the road slope. The rolling quality coefficient, This is the rolling damping coefficient. air density, This is the drag coefficient. For the vehicle's windshield area, For the vehicle's windward speed, For acceleration, This is the acceleration due to gravity.

[0020] As one implementation method, traffic states are divided according to the public road authority model, and the energy consumption factors of multi-energy vehicles under different traffic states are calibrated. The specific process is as follows:

[0021] Speed ​​zones are defined based on the four traffic states identified by the public road authority model.

[0022] Based on the energy consumption data of vehicles with multiple energy types, the distribution of vehicle specific power ranges for each speed range under different traffic conditions is constructed.

[0023] Based on the distribution of vehicle specific power range, the average energy consumption power of each vehicle specific power range is calculated, and the average energy consumption power of each specific power range is fitted to obtain the mapping relationship between energy consumption power and specific power.

[0024] Based on the power distribution of each speed range and the mapping relationship between energy consumption power and power distribution range, the energy consumption factor of multi-energy type vehicles in each speed range under different traffic conditions is calculated.

[0025] As one implementation method, the road traffic model uses graph theory modeling, and the road network topology is represented as follows:

[0026] ;

[0027] in, This represents the set of all endpoints of road segments in a highway network. This represents the set of road segments in a highway network. This represents a length matrix for each segment of a highway network. This represents the traffic flow matrix for each segment of the highway network. This represents a matrix representing the maximum capacity of each segment in a highway network. The time matrix of vehicles traveling on different segments of the highway network. This represents the energy consumption matrix for predicting driving conditions on each section of the highway network.

[0028] As one implementation method, the formula for the mapping relationship between energy consumption and specific power is:

[0029] ;

[0030] in, The energy type is The functional mapping relationship between the energy consumed by a vehicle and its specific power range. The system is in a smooth state. In a slow-moving state, The traffic is congested. The traffic is severely congested.

[0031] As one implementation method, based on the road network topology information of the road traffic model, the optimal path for vehicle travel is obtained through a multi-objective path planning algorithm. The specific process is as follows:

[0032] Initialize the weight matrix and path matrix, where the weight matrix includes weighted values ​​for road segment distance, time, and energy consumption;

[0033] In the road network topology of the road traffic model, all nodes are traversed through three nested loops to update the weight matrix and path matrix, thereby obtaining the optimal set of path nodes.

[0034] By adjusting the weighting coefficients of road segment distance, time, and energy consumption, the optimal path with the shortest road segment distance, shortest time, and lowest energy consumption can be obtained.

[0035] As one implementation method, based on the optimal travel path of the vehicle and the information on service area energy replenishment facilities, a Monte Carlo method is used to sample and simulate a probability model of events related to the starting node, destination node, travel time, initial energy state, and total energy capacity of vehicles of multiple energy types, predicting the spatiotemporal distribution of energy replenishment load for vehicles of multiple energy types. The specific process is as follows:

[0036] Set the total number of vehicles of various energy types and obtain the energy consumption factors of these vehicles under different traffic conditions;

[0037] Construct a probability model of events related to the starting node, target node, initial travel time, initial energy state, and total energy capacity of vehicles with multiple energy types. Use Monte Carlo sampling to generate the starting node, target node, initial travel time, initial energy state, and total energy capacity of vehicles with multiple energy types.

[0038] Determine travel routes for vehicles with multiple energy types using a multi-objective path planning algorithm;

[0039] For each route segment, calculate the vehicle's speed, travel time, and energy consumption on that segment, and update the vehicle's remaining energy state.

[0040] Based on the set energy replenishment conditions, it is determined whether energy replenishment is needed, the energy replenishment load of vehicles of multiple energy types at each service area node is calculated, and the spatiotemporal distribution prediction results of energy replenishment load are generated.

[0041] A second aspect of the present invention provides a highway vehicle energy replenishment load prediction system based on traffic conditions, comprising:

[0042] The information acquisition module is used to acquire energy consumption data of vehicles with multiple energy types, traffic network operation data, and information on energy replenishment facilities in service areas;

[0043] The vehicle power ratio building module is used to build a vehicle power ratio model based on energy consumption data of vehicles of multiple energy types.

[0044] The energy consumption factor calibration module is used to classify traffic states according to the public road bureau model and calibrate the energy consumption factors of multi-energy vehicles under different traffic states based on the vehicle power ratio.

[0045] The road network traffic module is used to construct a road traffic model based on traffic network operation data, which includes information on road segment distance, traffic flow, maximum capacity, time, and energy consumption.

[0046] The path planning module is used to obtain the optimal path for vehicles based on the road network topology information of the road traffic model and through a multi-objective path planning algorithm.

[0047] The multi-energy vehicle refueling load prediction module is used to predict the spatiotemporal distribution of multi-energy vehicle refueling load by sampling and simulating the probability model of related events such as the starting node, target node, travel time, initial energy state, and total energy capacity of multi-energy vehicles based on the optimal travel path of the vehicle and the refueling facility information of the service area.

[0048] A third aspect of the present invention provides a computer device including a memory, a processor, and a program stored in the memory and executable on the processor, wherein the processor executes the program to perform the steps of the method described in the first aspect of the present invention.

[0049] The above one or more technical solutions have the following beneficial effects:

[0050] This embodiment collects energy consumption data from vehicles of multiple energy types, and for the first time integrates energy consumption predictions for fuel vehicles, electric vehicles, and hydrogen fuel cell vehicles, overcoming the limitations of traditional single-energy models. By fusing real-time traffic condition perception, vehicle specific power energy consumption modeling, and refined traffic condition modeling, it can meet the energy load prediction needs of highways under multiple scenarios and conditions, improving prediction accuracy. A multi-objective path planning algorithm with the shortest time, shortest distance, and lowest energy consumption is proposed, overcoming the shortcomings of existing path planning algorithms while satisfying different user preferences. The highway vehicle refueling load prediction method based on traffic conditions has advantages such as high accuracy, wide scenario coverage, and ease of implementation, achieving accurate prediction of fuel consumption, electricity demand, and hydrogen demand at highway service area nodes. It can be applied to intelligent highway energy management platforms, in-vehicle navigation energy refueling decision support systems, and integrated energy service station planning.

[0051] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0052] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0053] Figure 1 This is a flowchart of the highway vehicle energy replenishment load prediction method based on traffic conditions according to Embodiment 1 of the present invention.

[0054] Figure 2 This is a vehicle power-to-weight ratio diagram according to Embodiment 1 of the present invention;

[0055] Figure 3 This is a characteristic diagram of the relationship between instantaneous energy consumption power and specific power of a vehicle according to Embodiment 1 of the present invention;

[0056] Figure 4 This is a power distribution diagram under various traffic conditions according to Embodiment 1 of the present invention;

[0057] Figure 5 This is a simplified highway network topology diagram according to Embodiment 1 of the present invention;

[0058] Figure 6 This is a flowchart of the multi-objective optimal path algorithm of Embodiment 1 of the present invention;

[0059] Figure 7 Spatiotemporal distribution prediction of refueling load for vehicles with multiple energy types in Embodiment 1 of the present invention. Detailed Implementation

[0060] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0061] It should be noted that the terminology used herein is for the purpose of describing particular implementations only and is not intended to limit the exemplary implementations of the present invention.

[0062] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0063] Example 1

[0064] This embodiment discloses a method for predicting highway vehicle energy replenishment load based on traffic conditions.

[0065] To more clearly illustrate this embodiment, the process of predicting highway vehicle energy replenishment load based on traffic conditions can be specifically described as follows:

[0066] A traffic-state-based method for predicting highway vehicle energy replenishment load includes:

[0067] S1. Obtain energy consumption data of vehicles with multiple energy types, traffic network operation data, and information on energy replenishment facilities in service areas;

[0068] S2. Based on the energy consumption data of vehicles with multiple energy types, construct a vehicle specific power model;

[0069] S3. Traffic conditions are divided according to the public road bureau model, and the energy consumption factors of multi-energy vehicles under different traffic conditions are calibrated based on the vehicle power ratio.

[0070] S4. Based on traffic network operation data, construct a road traffic model that includes information on road segment distance, traffic flow, maximum capacity, time, and energy consumption.

[0071] S5. Based on the road network topology information of the road traffic model, the optimal path for vehicle travel is obtained through a multi-objective path planning algorithm;

[0072] S6. Based on the optimal route of vehicle travel and the information on energy replenishment facilities in service areas, the Monte Carlo method is used to sample and simulate the probability model of related events such as the starting node, target node, travel time, initial energy state, and total energy capacity of vehicles of multiple energy types, and to predict the spatiotemporal distribution of energy replenishment load of vehicles of multiple energy types.

[0073] like Figure 1 As shown, in step S1, energy consumption data of vehicles with multiple energy types, traffic network operation data, and information on energy replenishment facilities in service areas are obtained.

[0074] In this embodiment, energy consumption data of gasoline vehicles, electric vehicles, and hydrogen fuel cell vehicles, traffic network operation data, and information on service area refueling facilities are collected.

[0075] (1) The energy consumption data of multi-energy vehicles includes the vehicle's position data, speed data, acceleration data, instantaneous fuel consumption rate, engine speed, battery voltage, battery current, hydrogen fuel cell voltage, and hydrogen fuel cell current. The engine power, battery power, and hydrogen fuel cell power are obtained through calculation and processing.

[0076] (2) Traffic network operation data includes static road network attribute data and dynamic road network attribute data. Static road network attribute data includes road segment length, number of lanes, road type, and maximum traffic capacity.

[0077] Multiple traffic checkpoints are set up on highways to acquire dynamic road network data. Each checkpoint collects information on vehicles of various energy types, such as the time taken to pass through the checkpoint. This data is then processed to obtain information such as traffic flow, vehicle type, total energy capacity, initial energy state, and travel time for the final road segment.

[0078] (3) Service area energy replenishment facilities information mainly includes the number of refueling piles, charging piles and hydrogen refueling piles in the service area, electric vehicle charging power, real-time number of refueling piles, charging piles and hydrogen refueling piles in use, and the number of vehicles with multiple energy types queuing in the service area.

[0079] like Figure 1 As shown, in step S2, a vehicle specific power model is constructed based on the energy consumption data of vehicles with multiple energy types.

[0080] Vehicle specific power (VSP) refers to the power output per unit mass of a moving vehicle, and is a key parameter for quantifying the energy consumption of a vehicle under dynamic operating conditions. VSP comprehensively reflects the impact of speed, acceleration, gradient, and air resistance on energy consumption, overcoming the shortcomings of traditional energy consumption testing methods that struggle to statistically measure vehicle mass.

[0081] In this embodiment, the specific process is as follows:

[0082] (1) Vehicle specific power VSP is understood from a physical point of view as the power required by the vehicle engine to overcome various frictions and resistances and increase its own kinetic energy and gravitational potential energy.

[0083] The formula for calculating the vehicle's power-to-weight ratio (VSP) is:

[0084] (1)

[0085] in, , These are the vehicle's total mass and speed, respectively. , These are the vehicle's kinetic energy and gravitational potential energy, respectively. , These are air resistance and rolling friction, respectively, experienced by the car.

[0086] (2) The VSP model is simplified based on the calculation formulas for the vehicle's kinetic energy, gravitational potential energy, air resistance and rolling friction.

[0087] The formulas are as follows:

[0088] ,

[0089] ,

[0090] (2)

[0091]

[0092] in, The rolling quality coefficient, The vehicle's height. air density, This is the drag coefficient. For the vehicle's windshield area, For the vehicle's windward speed, This is the rolling damping coefficient. This is the acceleration due to gravity.

[0093] Substituting formula (2) into formula (1), we obtain the new... The calculation formula is:

[0094] (3)

[0095] in, To accelerate the vehicle, The angle between the road slopes.

[0096] Generally, the rolling quality coefficient is taken. Road slope angle drag coefficient Vehicle headwind speed , The specific power of the vehicle was obtained. The simplest calculation formula is:

[0097] (4)

[0098] like Figure 2 As shown in the vehicle power-to-weight ratio diagram, it can be concluded that although the vehicle speed and acceleration values ​​are different, the same result may still be obtained. value.

[0099] Following the steps outlined above, introducing vehicle specific power as a core evaluation indicator in the energy consumption modeling and analysis process allows for the comprehensive quantification of key operating parameters such as vehicle speed, acceleration, and road gradient, thereby more accurately reflecting the energy consumption level of vehicles under different conditions. By employing specific power calculation, not only can energy consumption estimation biases caused by relying solely on speed or acceleration be avoided, but the energy consumption comparison and evaluation of vehicles with multiple energy types can also be achieved within a unified framework. Compared to traditional energy consumption estimation methods based on experience or single parameters, this method can meticulously characterize the vehicle's operating characteristics at the micro-level, improving the accuracy of energy consumption prediction; it is applicable to the unified modeling of vehicles with multiple energy types, enhancing the model's adaptability and universality; and it provides highly reliable input parameters for subsequent route optimization, energy consumption control, and energy replenishment scheduling, thus effectively supporting the optimized operation of multi-energy transportation systems.

[0100] like Figure 1 As shown, in step S3, traffic states are divided according to the public road bureau model, and the energy consumption factors of multi-energy type vehicles under different traffic states are calibrated based on the vehicle power ratio.

[0101] Based on energy consumption data and specific power models of vehicles with multiple energy types, a characteristic map of the relationship between instantaneous energy consumption and specific power of vehicles during operation is established. For example... Figure 3 As shown, taking a hydrogen fuel cell vehicle as an example, the characteristic diagram of the relationship between instantaneous energy consumption power and specific power shows that the vehicle's instantaneous energy consumption power... The values ​​exhibit strong dispersion, with significant differences in energy consumption among vehicles under various traffic conditions, including smooth flow, slow traffic, congestion, and severe congestion. Even under different speed and acceleration conditions, the same energy consumption may still be achieved. Therefore, a traffic state differentiation mechanism should be introduced into energy consumption modeling, incorporating different traffic states such as smooth flow, slow traffic, congestion, and severe congestion into the analysis framework. In this way, the actual energy consumption level of vehicles under multi-mode traffic conditions can be more accurately reflected, providing a more reliable basis for energy consumption prediction and route optimization.

[0102] S3-1. Divide traffic conditions and speed ranges according to the public road bureau model.

[0103] According to common traffic engineering standards, highway traffic conditions are classified by saturation. To more intuitively study the relationship between saturation and speed, the Bureau of Public Roads Model (BPR model) is introduced. The BPR model is a very classic and commonly used speed-flow relationship model in traffic engineering, mainly used to describe the relationship between traffic delay and traffic flow.

[0104] The Public Roads Authority (BPR) model is expressed as follows:

[0105] (5)

[0106] in, Indicates the travel time under the current conditions. This represents the travel time when the saturation is 0, i.e., under free-flow conditions. This indicates the actual traffic flow on that road section. This indicates the maximum traffic capacity of this road section. , This is a parameter related to impedance and is associated with road grade. This represents saturation.

[0107] The formulas for calculating saturation and velocity are:

[0108] ,

[0109] ,

[0110] (6)

[0111] in, For the length of the road segment, The vehicle speed is the speed under free-flow conditions where the saturation is 0. This refers to the vehicle's speed under the current saturation conditions.

[0112] From formulas (5) and (6), the formula relating velocity and saturation is derived as follows:

[0113] (7)

[0114] According to common traffic engineering standards, traffic conditions are typically classified into four categories: free-flowing, slow-moving, congested, and severely congested. Free-flowing traffic refers to a state where traffic flow is free, vehicles move smoothly with minimal delays, occasionally accompanied by slight accelerations and decelerations, with accelerations approaching zero. Slow-moving traffic refers to a situation where traffic flow is stabilizing, but vehicles begin to experience slight delays, requiring them to reduce speed to adapt to the traffic density. This is accompanied by periodic acceleration and deceleration, with a moderate acceleration variance. Traffic congestion refers to a state where traffic flow approaches or reaches its capacity limit, vehicle delays increase significantly, localized congestion may occur, vehicles frequently brake or accelerate suddenly, and the acceleration variance is high. Severe traffic congestion refers to a situation where traffic demand exceeds capacity, traffic flow is unstable, resulting in queues and continuous congestion, vehicle speeds approach zero, and more frequent starts and stops cause higher acceleration variance, generating more additional energy consumption compared to other traffic conditions. This directly increases the complexity of vehicle energy consumption models. .

[0115] According to the traffic state classification criteria, respectively , , and Substituting into formula (7) yields , , and The final speed ranges and saturation ranges corresponding to the traffic conditions are shown in Table 1.

[0116] Table 1. Speed ​​and saturation ranges for four traffic conditions.

[0117]

[0118] S3-2. Based on the energy consumption data of vehicles with multiple energy types, construct the vehicle power ratio range distribution of vehicles with multiple energy types in different traffic conditions and at different speed ranges.

[0119] (1) Calculate the specific power value of the vehicle every second based on the energy consumption data of vehicles of each energy type, and divide it into intervals at equal intervals.

[0120] In this embodiment, the specific process is as follows:

[0121] 1) Based on the multi-energy vehicle energy consumption data obtained in step S1, calculate the second-by-second energy consumption of fuel vehicles, electric vehicles, and hydrogen fuel cell vehicles. value.

[0122] 2) Regarding the specific power of vehicles ( Divide the intervals into equal intervals.

[0123] Vehicle specific power ( Divided into many interval units Typically, the step size is 1kW / t. The interval is divided into equal intervals, using the following formula:

[0124] (8)

[0125] in, express Number of intervals.

[0126] By performing the above steps and dividing the vehicle power distribution into equal intervals, the vehicle power distribution modeling algorithm can be simplified, and the computational efficiency can be improved for subsequent model building.

[0127] (2) Calculate the probability density distribution of vehicle power ratio in different speed ranges for vehicles with multiple energy types under different traffic conditions.

[0128] Based on the calculated second-by-second Values, statistics on the performance of vehicles of various energy types under different traffic conditions. The percentage of operating time within a given interval yields the performance of multi-energy type vehicles under different traffic conditions. Interval distribution, the formula is:

[0129] (9)

[0130] in, Traffic status Next indivual Distribution values ​​of the interval, Traffic status Next indivual Sample size of the interval Traffic status The total sample size is as follows. Indicates smooth traffic flow. Indicates slow-moving traffic. Indicates traffic congestion. This indicates a state of severe traffic congestion.

[0131] This embodiment uses a hydrogen fuel cell vehicle as an example to construct hydrogen fuel cell vehicles under four traffic conditions. The distribution of. For example... Figure 4 As shown, it can be concluded that although vehicle energy consumption varies under different traffic conditions, The values ​​may be the same.

[0132] Speed ​​ranges under four traffic conditions were divided using a step size of 3.6 km / h, and statistics were obtained for vehicles of multiple energy types. The interval distribution has the following probability density function:

[0133] (10)

[0134] in, In traffic conditions and average speed range Under the conditions, the first indivual The distribution value of the interval; Traffic conditions and average speed range Under the conditions, the first indivual Sample size for the interval; Traffic status The average speed range below Total sample size.

[0135] By dividing the speed range into equal intervals, the probability density distribution of vehicle specific power in each speed range under different traffic conditions for vehicles of multiple energy types can be simplified, thus improving computational efficiency.

[0136] S3-3. Based on the distribution of vehicle specific power intervals, calculate the average energy consumption power of each vehicle specific power interval, and fit the average energy consumption power of each specific power interval to obtain the mapping relationship between energy consumption power and specific power.

[0137] Different energy vehicles have different Energy Consumption Rates (ECRs). The power source of gasoline vehicles is only the chemical energy produced by burning gasoline or diesel in the engine. The energy consumption of electric vehicles is the output power of the battery. The energy consumption of hydrogen fuel cell electric vehicles consists of both the power of the fuel cell and the power of the battery.

[0138] Based on the collected and calculated energy consumption dataset, for vehicles of different energy types, each... The average energy consumption per second within a given interval is taken as the energy consumption power within that interval. Energy consumption power of the vehicle during actual driving is then established relative to the energy consumption power within that interval. Mapping relationship between vehicle energy consumption and power consumption The different mapping relationships reflect, to some extent, the differences in energy control strategies and powertrain structures of vehicles with different energy types.

[0139] (1) Based on the vehicle power ratio range distribution, calculate the average energy consumption power of each vehicle power ratio range.

[0140] To more intuitively illustrate the energy consumption and power of multi-energy vehicles under different traffic conditions... The functional relationship between intervals is calculated for each energy type of vehicle under traffic conditions of smooth flow, slow flow, congestion, and severe congestion. The average energy consumption within the interval is given by the formula:

[0141] (11)

[0142] in, The energy type is Cars in traffic conditions Next, the indivual Average power consumption in the range; Energy type Cars in traffic conditions Next, the indivual The total number of vehicles in the section; The energy type is Cars in traffic conditions Next, the indivual The first in the interval The instantaneous power consumption of a vehicle.

[0143] (2) Fit the average energy consumption power for each specific power range to obtain the energy consumption power and The mapping relationship.

[0144] Linear functions were used to fit the energy consumption power of vehicles of various energy types under different traffic conditions. The mathematical relationship, i.e., energy consumption and power:

[0145] (12)

[0146] in, The energy type is The functional mapping relationship between the energy consumed by a vehicle and its specific power range. The system is in a smooth state. In a slow-moving state, The traffic is congested. The traffic is severely congested.

[0147] Following the steps outlined above, by fitting the average energy consumption power across different power ratio ranges, a mapping relationship between energy consumption power and vehicle power ratio is established. This method can quantitatively express the energy consumption characteristics of vehicles under different traffic conditions in the form of a mathematical model. Employing linear function fitting not only simplifies the energy consumption calculation process for vehicles with multiple energy types in complex traffic environments but also effectively captures the energy consumption differences under various conditions such as smooth traffic, slow traffic, congestion, and severe congestion.

[0148] S3-4. Based on the power distribution of each speed range and combined with the mapping relationship between energy consumption power and power distribution range, calculate the energy consumption factor of multi-energy type vehicles in each speed range under different traffic conditions.

[0149] (1) According to formulas (10) and (12), the speed range of vehicles with multiple energy types can be obtained. The corresponding energy consumption power is given by the formula:

[0150] (13)

[0151] in, The energy type is Cars in traffic conditions Below, speed range Corresponding power consumption; The energy type is Cars in traffic conditions Below, the energy consumption power corresponding to the specific power range.

[0152] (2) Based on the energy consumption power of vehicles of multiple energy types in different traffic conditions, the energy consumption factor is predicted for each speed range, and the energy consumption factor of vehicles of multiple energy types in different traffic conditions is obtained.

[0153] The energy consumption factor is generally defined as the energy consumed by a specific vehicle model per unit distance or unit time at a specific speed. The speed energy consumption factor is generally defined as the energy consumed by a vehicle per unit distance within a specific speed range.

[0154] (14)

[0155] Formula (13), formula (14), and work calculation formula With the speed calculation formula By combining these equations, the final formula for calculating the energy consumption factor can be obtained as follows:

[0156] (15)

[0157] After the above steps, the energy consumption factors of multi-energy vehicles under different traffic conditions are obtained, which can more accurately predict the energy consumption of multi-energy vehicles during driving, and thus provide a data basis for accurately obtaining the spatiotemporal distribution of vehicle energy replenishment load in the actual traffic network.

[0158] like Figure 1 As shown, in step S4, a road traffic model containing information on road segment distance, traffic flow, maximum capacity, time, and energy consumption is constructed based on traffic network operation data.

[0159] The highway network structure directly influences vehicle route selection and mileage, which in turn affects the choice of refueling service areas and refueling duration. Furthermore, the maximum capacity of the road design and actual traffic flow jointly affect vehicle speed, thus influencing the timing of refueling demand. Therefore, analyzing the highway network topology, maximum road capacity, and actual traffic flow is a crucial prerequisite for accurately predicting the spatiotemporal distribution of refueling loads for vehicles of various energy types on highways.

[0160] The highway network model is modeled using graph theory, and the topological structure of the network is represented as follows:

[0161] (16)

[0162] in, This represents the set of all endpoints of road segments in a highway network. This represents the set of road segments in a highway network. This represents a length matrix for each segment of a highway network. This represents the traffic flow matrix for each segment of the highway network. This represents a matrix representing the maximum capacity of each segment in a highway network. The time matrix of vehicles traveling on different segments of the highway network. This represents the energy consumption matrix for predicting driving conditions on each section of the highway network.

[0163] Specifically, assuming all road segments are two-way streets, and highway service area nodes are the endpoints of road segments, the length matrix of each road segment in the highway network is... for:

[0164] (17)

[0165] in, This indicates that the two nodes are not connected by any road in the actual road network. Represents a node To the node The length of the road segment.

[0166] Traffic flow matrix of each segment in the highway network for:

[0167] (18)

[0168] in, Represents a node To the node Traffic flow on the road section.

[0169] Maximum capacity matrix of each segment in the highway network for:

[0170] (19)

[0171] in, Represents a node To the node The maximum traffic capacity of the road section.

[0172] Based on the Public Roads Authority (BPR) model in step S3, the time matrix of the vehicle for each segment of travel can be obtained. Assuming from node To the node The travel time on zero-traffic sections is The actual travel time on the road segment is The calculation formula is as follows:

[0173] (20)

[0174] Assuming from node To the node The driving speed on zero-traffic sections is The actual driving speed on the road section is The calculation formula is as follows:

[0175] (twenty one)

[0176] Based on the calculated road segment speed Then you can find its corresponding speed energy consumption factor. Multiplying the energy consumption by the road segment length yields the predicted energy consumption matrix for each driving segment. , from node To the node The predicted energy consumption is The calculation formula is as follows:

[0177] (twenty two)

[0178] like Figure 1 As shown, in step S5, based on the road network topology information of the road traffic model, the optimal path for vehicle travel is obtained through a multi-objective path planning algorithm.

[0179] The starting point for multi-energy vehicles and the finish line Determined by the OD matrix, in general, the starting point and the finish line Since there is more than one driving path between them, this embodiment proposes a multi-objective optimal path planning algorithm that enables vehicles powered by different energy sources to always choose the path with the shortest distance, shortest time, and lowest energy consumption during the driving process. This algorithm can quickly and accurately determine the starting point. and the finish line The optimal driving path node set between .

[0180] like Figure 6 As shown, the starting point is solved using a multi-objective optimal path algorithm. and the finish line The optimal path between them, the specific process is as follows:

[0181] (1) Initialize the weight matrix and path matrix, wherein the weight matrix includes the weighted values ​​of road segment distance, time and energy consumption.

[0182] In this embodiment, the starting point is set as The endpoint is and transit points are , storage nodes With nodes The weights between them storage nodes To the node The first transit point of the shortest path If the starting point To the finish line If the optimal path has no intermediate nodes, then Initialize the weight matrices respectively. and path matrix All elements in and ,in The calculation formula is:

[0183] (twenty three)

[0184] in, These are the weighting coefficients for road segment distance, travel time, and energy consumption, respectively. Changing the magnitude of these weighting coefficients may result in different optimal routes in the final planning.

[0185] (2) In the road network topology of the road traffic model, all nodes are traversed by three nested loops to update the weight matrix and path matrix, and the optimal path node set is obtained.

[0186] In this embodiment, an intermediate node is introduced. As a pathway bridge, global path optimization is performed using three nested loops: the outer loop iterates through all possible transit points. The middle loop enumerates the set of starting points. The inner loop iterates through the final set. Each iteration compares the existing paths. transit route The value of , if it satisfies Then update the weight matrix. Update the path matrix Repeat this process until completion, ultimately obtaining the weight matrix for all nodes. and path matrix .

[0187] like , then it represents a node With nodes The optimal path weight between them is 6. Similarly, if , then it represents a node With nodes The first relay node with the optimal distance between them is Next, search... , ,until If the optimal path between two nodes no longer has intermediate nodes, then the nodes can be determined. With nodes The set of nodes for the optimal path is .

[0188] (3) Adjust the weighting coefficients of road segment distance, time and energy consumption to obtain the optimal path with the shortest road segment distance, the shortest time and the lowest energy consumption.

[0189] In this embodiment, an optimal path planning algorithm is designed with the overall objectives of minimizing the path length, time, and energy consumption. The optimal path planning algorithm is then used to obtain the optimal route for the vehicle.

[0190] Through the above steps, an optimal travel plan is provided for vehicles of multiple energy types while satisfying the comprehensive objectives of shortest path, least time, and lowest energy consumption. This algorithm fully considers the reality that multiple candidate paths exist between the origin and destination, and can quickly and accurately output the optimal path node set while ensuring computational efficiency. Specifically, firstly, it can achieve comprehensive optimization from multiple dimensions by taking into account the operating characteristics of vehicles of multiple energy types, considering travel distance, travel time, and energy consumption; secondly, by dynamically balancing distance, time, and energy consumption factors, it effectively avoids the local optimum problem caused by single-objective planning, thereby improving the overall operational efficiency of the transportation system; finally, this method provides an efficient and feasible solution for route scheduling of large-scale multi-energy vehicles, which helps to achieve coordinated optimization of the transportation and energy systems, reduce overall energy consumption levels, and improve road traffic efficiency.

[0191] like Figure 1 , Figure 7 As shown, in step S6, based on the optimal route of the vehicle and the information on the energy replenishment facilities in the service area, the Monte Carlo method is used to sample and simulate the probability model of related events such as the starting node, target node, travel time, initial energy state, and total energy capacity of vehicles of multiple energy types, and to predict the spatiotemporal distribution of the energy replenishment load of vehicles of multiple energy types.

[0192] The Monte Carlo method is a mathematical method for simulating random number solutions. The solution process is as follows: construct a relevant probability model of related events, sample a large number of random numbers from the probability distribution of the probability model, and use these random numbers to establish an estimate of the random event as the solution of the random event.

[0193] In this embodiment, the specific process for predicting the spatiotemporal distribution of refueling load for vehicles with multiple energy types is as follows:

[0194] (1) Set the total number of vehicles and obtain the energy consumption factors of vehicles with multiple energy types under different traffic conditions.

[0195] (2) Construct a probability model of related events for the starting node, target node, initial travel time, initial energy state, and total energy capacity of vehicles of multiple energy types. The Monte Carlo sampling method is used to generate the starting node, target node, initial travel time, initial energy state, and total energy capacity of vehicles of multiple energy types. The constructed probability model of related events is shown below.

[0196] 1) Travel probability matrix.

[0197] To more accurately simulate the travel characteristics of vehicles of three different energy types, an OD (Original Departure / Origin) matrix method is introduced for analysis. Traffic flow data for each energy type of vehicle at various road segments, measured by transportation authorities, can be used to obtain the OD matrix for each time of day. The following formula can then be used to obtain the OD travel probability matrix for each energy type of vehicle at each time point. .

[0198] (twenty four)

[0199] in, The energy type is Cars from road network nodes Departure to reach road network node The probability of travel, The energy type is Cars from road network nodes Departure to reach road network node Total quantity The energy type is Cars from road network nodes Total number of departures This represents the total number of nodes in the road network topology.

[0200] 2) Probability density function of travel time.

[0201] The time when vehicles enter the highway determines the temporal distribution of highway vehicle energy replenishment load. The initial travel times of vehicles entering the highway exhibit a saddle-shaped temporal distribution, with peak traffic accounting for over 40% of the total daily traffic. The energy type measured by the transportation department is... The probability density function of the initial departure time of the vehicle is .

[0202] 3) Probability density function of total energy capacity of vehicles.

[0203] The maximum usable energy that a vehicle's energy storage device can store under standard operating conditions is defined as the Total Energy Capacity (TEC), and its unit is the energy standard unit. The maximum energy storage capacity varies among vehicles of the same energy type; based on statistical data, the maximum energy storage capacity can be determined by the energy type. The probability density function of the total energy capacity of the vehicle is .

[0204] 4) Probability density function of the vehicle's initial energy state.

[0205] The remaining energy percentage of a vehicle is defined as its energy state (ES), with a value ranging from 0 to 1. During highway driving, exiting the highway at will is prohibited, and reverse driving is forbidden; therefore, vehicles ensure their remaining energy is at a relatively high level before entering the highway. Furthermore, considering the distance between the vehicle's departure and entry onto the highway, we assume the initial energy state of the vehicle before entering the highway. It follows a uniform distribution of [50%, 90%].

[0206] , (25)

[0207] (3) Determine the travel route of the vehicle through a multi-objective path planning algorithm.

[0208] (4) For each route segment, calculate the vehicle’s speed, travel time and energy consumption on that route segment, and update the vehicle’s remaining energy state accordingly.

[0209] The derivation of the formula for calculating the remaining energy state of vehicles with multiple energy types is shown below: Assuming there are... Vehicle energy type The vehicles have a total of [number] routes in the optimal driving path. The nth node. Then the nth Vehicle energy type The vehicle arrived at the node time for:

[0210] (26)

[0211] in, The energy-complement discriminant function has values ​​of 0 and 1. , indicating the first The car in Each node does not replenish energy. , indicating the first The car in Each node is recharged.

[0212] (5) Based on the set energy replenishment conditions, determine whether to replenish energy, calculate the vehicle energy replenishment load of each service area node, and generate the spatiotemporal distribution prediction results of the energy replenishment load.

[0213] Firstly, considering practical implications, when a multi-energy type vehicle arrives at a service area node that does not contain a refueling facility for that energy type, the refueling probability... When a car cannot reach a refueling facility of the same energy type in the next service area, the probability of refueling is... .

[0214] If none of the above conditions are met, i.e., the multi-energy type vehicle can reach the next service area node and the service area node contains refueling facilities of the same energy type, then considering only the remaining energy ratio, the probability density function formula for refueling multi-energy type vehicles is:

[0215] (27)

[0216] (6) After the vehicle completes its refueling, it updates its current remaining energy status and cumulative driving time, and dynamically updates the refueling load and real-time operating status of the node it is located at.

[0217] 1) Node of The total energy replenishment load is:

[0218] (28)

[0219] 2) The vehicle's cumulative driving time includes not only the driving time on each road segment, but also the queuing time during the refueling process and the actual time spent refueling.

[0220] Assume that the time interval between vehicle arrivals at the service area and the refueling time at the service area's refueling facilities both follow an exponential distribution. Using a step size of 1 hour, the number of multi-energy type vehicles traveling to the refueling node per hour for refueling services is used as a parameter. The waiting time for vehicles of multiple energy types for:

[0221] ,

[0222] ,

[0223] (29)

[0224] in, The number of energy replenishment facilities within the service area nodes; The total number of vehicles of various energy types that can be recharged per unit time for each recharge facility is the reciprocal of the vehicle recharge time. For the service intensity of energy replenishment facilities, if The closer the value is to 1, the busier the refueling facilities at the service area. Currently, the refueling time for both traditional gasoline and hydrogen fuel cell vehicles is generally 3-5 minutes, far less than the travel time on highways, and can be ignored. Therefore, we only need to study the refueling time of electric vehicles. We assume that electric vehicles use only fast charging with constant power when refueling on highways, and the fast charging power is... Charging efficiency is And it is fully charged every time it is charged, that is Then the electric vehicle in the first The formula for calculating the charging time of each node is:

[0225] (30)

[0226] Through the above steps, a refined travel modeling of vehicles of multiple energy types in actual road networks is achieved, integrating multiple key aspects such as path planning, energy consumption evolution, node load feedback, and refueling behavior. By introducing multi-energy coupled energy consumption factors, a dynamic update mechanism for remaining energy state, and a refueling node load management mechanism, the model can effectively simulate the energy consumption and refueling decision-making processes of vehicles of multiple energy types, such as electric vehicles, fuel vehicles, and hydrogen fuel cell vehicles, under complex traffic conditions.

[0227] This process has significant technical advantages: First, by setting differentiated energy consumption factors and refueling strategies for vehicles of different energy types, it enables unified modeling and refined management of multi-energy transportation systems. Second, by introducing a dynamic refueling judgment mechanism, it makes real-time decisions based on the vehicle's remaining energy status and the refueling load at nodes, improving energy utilization efficiency and effectively mitigating the congestion risk of refueling facilities. Third, by continuously updating energy consumption and time during the journey, combined with the spatiotemporal status feedback of refueling nodes, it achieves the co-evolution of traffic behavior and energy behavior. In addition, this process has good versatility and scalability, and can be flexibly embedded into various traffic simulation platforms or intelligent traffic management systems, providing reliable support for multi-energy vehicle route optimization and energy consumption control.

[0228] Example 2

[0229] The purpose of this embodiment is to provide a highway vehicle energy replenishment load prediction system based on traffic conditions, including:

[0230] The information acquisition module is used to acquire energy consumption data of vehicles with multiple energy types, traffic network operation data, and information on energy replenishment facilities in service areas;

[0231] The vehicle power-to-energy ratio building module is used to build a vehicle power-to-energy ratio model based on the energy consumption data of vehicles of multiple energy types.

[0232] The energy consumption factor calibration module is used to classify traffic states according to the public road bureau model and calibrate the energy consumption factors of multi-energy type vehicles under different traffic states based on the vehicle power ratio.

[0233] The road network traffic module is used to construct a road traffic model based on traffic network operation data, which includes information on road segment distance, traffic flow, maximum capacity, time, and energy consumption.

[0234] The path planning module is used to obtain the optimal path for vehicles based on the road network topology information of the road traffic model and through a multi-objective path planning algorithm.

[0235] The multi-energy vehicle refueling load prediction module is used to predict the spatiotemporal distribution of multi-energy vehicle load by sampling and simulating the probability model of related events such as the starting node, target node, travel time, initial energy state, and total energy capacity of multi-energy vehicles based on the optimal travel path of the vehicle and the refueling facility information of the service area.

[0236] The highway vehicle energy replenishment load prediction system based on traffic conditions implements the method steps in Example 1.

[0237] Example 3

[0238] The purpose of this embodiment is to provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of the above-described method.

[0239] The steps and methods involved in the apparatus of the above embodiments correspond to those in Embodiment 1. For specific implementation details, please refer to the relevant description section of Embodiment 1.

[0240] Those skilled in the art will understand that the modules or steps of the present invention described above can be implemented using general-purpose computer devices. Optionally, they can be implemented using computer-executable program code, thereby allowing them to be stored in a storage device for execution by a computer device, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. The present invention is not limited to any particular combination of hardware and software.

[0241] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A method for predicting highway vehicle energy replenishment load based on traffic conditions, characterized in that, include: Acquire energy consumption data of vehicles with multiple energy types, traffic network operation data, and information on energy replenishment facilities in service areas; A vehicle specific power model is constructed based on energy consumption data of vehicles with multiple energy types. Traffic states are classified according to the Public Roads Authority model, and the energy consumption factors of multi-energy vehicles under different traffic states are calibrated based on vehicle power-to-weight ratio; the formula for calculating the energy consumption factor is: ； in, , , and These represent the vehicle speeds under saturation conditions of 0, 0.6, 0.8, and 1, respectively. Indicates the energy type as Cars in smooth traffic conditions and average speed range Conditions, No. indivual The distribution value of the interval; Indicates the energy type as Cars in slow traffic conditions and average speed range Conditions, No. indivual The distribution value of the interval; Indicates the energy type as Cars in congested traffic and average speed range Conditions, No. indivual The distribution value of the interval; Indicates the energy type as Cars in severely congested traffic conditions and average speed range Conditions, No. indivual The distribution value of the interval; The energy type is The energy consumption power of a car in a smooth traffic condition, corresponding to the power range; The energy type is The energy consumption power of a car in slow traffic conditions, corresponding to the power range; The energy type is The energy consumption power of a car in congested traffic conditions, corresponding to the power range. The energy type is The energy consumption power of a car in a severely congested traffic situation, corresponding to the power range; Based on traffic network operation data, a road traffic model is constructed that includes information on road segment distance, traffic flow, maximum capacity, time, and energy consumption. Based on the road network topology information of the road traffic model, the optimal path for vehicle travel is obtained through a multi-objective path planning algorithm; the specific process is as follows: Initialize the weight matrix and path matrix, where the weight matrix includes weighted values ​​for road segment distance, time, and energy consumption; In the road network topology of the road traffic model, all nodes are traversed through three nested loops to update the weight matrix and path matrix, thereby obtaining the optimal set of path nodes. By adjusting the weighting coefficients of road segment distance, time, and energy consumption, the optimal path with the shortest road segment distance, shortest time, and lowest energy consumption can be obtained. Based on the optimal travel route of vehicles and information on service area energy replenishment facilities, a Monte Carlo method is used to sample and simulate a probability model of events related to the starting node, destination node, travel time, initial energy state, and total energy capacity of vehicles of various energy types, predicting the spatiotemporal distribution of energy replenishment load for these vehicles. The specific process is as follows: Set the total number of vehicles of various energy types and obtain the energy consumption factors of these vehicles under different traffic conditions; Construct a probability model of events related to the starting node, target node, initial travel time, initial energy state, and total energy capacity of vehicles with multiple energy types. Use Monte Carlo sampling to generate the starting node, target node, initial travel time, initial energy state, and total energy capacity of vehicles with multiple energy types. Determine travel routes for vehicles with multiple energy types using a multi-objective path planning algorithm; For each route segment, calculate the vehicle's speed, travel time, and energy consumption on that segment, and update the vehicle's remaining energy state. Based on the set energy replenishment conditions, it is determined whether energy replenishment is needed, the energy replenishment load of vehicles of multiple energy types at each service area node is calculated, and the spatiotemporal distribution prediction results of energy replenishment load are generated.

2. The method for predicting highway vehicle energy replenishment load based on traffic conditions as described in claim 1, characterized in that, The energy consumption data of the multi-energy type vehicles includes the vehicle's position data, speed data, acceleration data, instantaneous fuel consumption rate, engine speed, battery voltage, battery current, hydrogen fuel cell voltage, and hydrogen fuel cell current. The traffic network operation data includes static road network attribute data and dynamic road network attribute data, wherein the static road network attribute data includes road segment length, number of lanes, road type, and maximum traffic capacity; The information on energy replenishment facilities in the service area mainly includes the number of gas stations, charging stations, and hydrogen refueling stations in the service area, the charging power of electric vehicles, the real-time number of gas stations, charging stations, and hydrogen refueling stations in use, and the number of vehicles with multiple energy types queuing in the service area.

3. The method for predicting highway vehicle energy replenishment load based on traffic conditions as described in claim 1, characterized in that, The calculation formula for the vehicle power-to-weight ratio model is as follows: ； in, For vehicle speed, The total mass of the vehicle. The angle of the road slope. The rolling quality coefficient, This is the rolling damping coefficient. air density, This is the drag coefficient. For the vehicle's windshield area, For the vehicle's windward speed, For acceleration, This is the acceleration due to gravity.

4. The method for predicting highway vehicle energy replenishment load based on traffic conditions as described in claim 1, characterized in that, Traffic states are classified according to the public road authority model, and the energy consumption factors of multi-energy vehicles under different traffic states are calibrated. The specific process is as follows: Speed ​​zones are defined based on the four traffic states identified by the public road authority model. Based on the energy consumption data of vehicles with multiple energy types, the distribution of vehicle specific power ranges for each speed range under different traffic conditions is constructed. Based on the distribution of vehicle specific power range, the average energy consumption power of each vehicle specific power range is calculated, and the average energy consumption power of each specific power range is fitted to obtain the mapping relationship between energy consumption power and specific power. Based on the power distribution of each speed range and the mapping relationship between energy consumption power and power distribution range, the energy consumption factor of multi-energy type vehicles in each speed range under different traffic conditions is calculated.

5. The method for predicting highway vehicle energy replenishment load based on traffic conditions as described in claim 4, characterized in that, The formula for the mapping relationship between energy consumption and specific power is: ； in, The energy type is The functional mapping relationship between the energy consumed by a vehicle and its specific power range. The system is in a smooth state. In a slow-moving state, The traffic is congested. The traffic is severely congested.

6. The method for predicting highway vehicle energy replenishment load based on traffic conditions as described in claim 1, characterized in that, The road traffic model is modeled using graph theory, and the road network topology is represented as follows: ； in, This represents the set of all endpoints of road segments in a highway network. This represents the set of road segments in a highway network. This represents a length matrix for each segment of a highway network. This represents the traffic flow matrix for each segment of the highway network. This represents a matrix representing the maximum capacity of each segment in a highway network. The time matrix of vehicles traveling on different segments of the highway network. This represents the energy consumption matrix for predicting driving conditions on each section of the highway network.

7. A highway vehicle energy replenishment load prediction system based on traffic conditions, characterized in that, Implementing the highway vehicle energy replenishment load prediction method based on traffic conditions as described in any one of claims 1-6, comprising: The information acquisition module is used to acquire energy consumption data of vehicles with multiple energy types, traffic network operation data, and information on energy replenishment facilities in service areas; The vehicle power ratio construction module is used to build a vehicle power ratio model based on energy consumption data of vehicles of multiple energy types. The energy consumption factor calibration module is used to classify traffic states according to the public road bureau model and calibrate the energy consumption factors of multi-energy type vehicles under different traffic states based on the vehicle power ratio. The road network traffic module is used to construct a road traffic model based on traffic network operation data, which includes information on road segment distance, traffic flow, maximum capacity, time, and energy consumption. The path planning module is used to obtain the optimal path for vehicles based on the road network topology information of the road traffic model and through a multi-objective path planning algorithm. The multi-energy vehicle refueling load prediction module is used to predict the spatiotemporal distribution of multi-energy vehicle refueling load by sampling and simulating the probability model of related events such as the starting node, target node, travel time, initial energy state, and total energy capacity of multi-energy vehicles based on the optimal travel path of the vehicle and the refueling facility information of the service area.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps of the method described in any one of claims 1-6.

Images