New energy transport capacity task scheduling method and system based on energy complementation scene

Abstract

The invention provides a new energy transport capacity task scheduling method and system based on an energy complementation scene, and relates to the technical field of transport capacity task scheduling, and the scheduling method comprises the steps: collecting and preprocessing the real-time data of the energy, position, energy consumption and the like of a vehicle, carrying out the vehicle endurance evaluation and energy complementation judgment according to the real-time data, according to the endurance evaluation and energy complementation judgment result, screening energy complementation sites meeting preset conditions, carrying out scheme calculation and cost calculation on the screened energy complementation sites, comparing calculation results through an intelligent scheduling decision algorithm to obtain a final scheduling scheme, sending a scheduling instruction, carrying out cycle scheduling on newly added waybills or transport capacity tasks, and carrying out scheduling on the newly added waybills or transport capacity tasks. The scheduling scheme is dynamically adjusted and updated in real time according to actual conditions so as to adapt to efficient operation of a complex scene; the scheduling flexibility is enhanced, the scheduling efficiency and economic benefits of the new energy transport capacity in the energy complementing scene can be remarkably improved, and powerful support is provided for wide application of new energy automobiles in the logistics transportation field.

Description

Technical Field

[0001] The present application relates to the technical field of transport task scheduling, and specifically to a new energy transport task scheduling method and system based on energy replenishment scenarios. Background Art

[0002] In recent years, with the increasing attention paid to environmental protection and sustainable development and the adjustment of energy structure, the application and popularity of new energy vehicles as an important means to reduce carbon emissions and promote green travel have increased rapidly. However, a key challenge faced by new energy vehicles in actual operation is the energy supply problem, such as how to efficiently and economically manage the energy supply needs of vehicles in medium and long-distance transportation tasks, and the decision-making pressure of complex energy supply solutions on dispatchers when there are differences in prices at different energy supply stations at different times. These have become bottlenecks restricting the development of new energy transportation capacity and curbing the development of the industry.

[0003] Although there are many new energy vehicle dispatching systems on the market, most of them focus on basic functions such as vehicle allocation and route planning, and do not consider the refined management and optimized dispatching in the energy replenishment scenario. These systems often ignore the impact of key factors such as the real-time energy status of vehicles, the distribution of energy replenishment stations, and electricity price fluctuations on dispatching decisions, which may lead to energy waste, cost increase, or task delays in actual operations. Summary of the invention

[0004] In order to solve at least one of the technical defects in the above-mentioned technical problems, the present application provides a new energy capacity task scheduling method and system based on energy replenishment scenarios.

[0005] The embodiment of the present application provides a new energy capacity task scheduling method based on an energy replenishment scenario, comprising the following steps: Collect and pre-process real-time data on vehicle energy, location, and energy consumption; Carry out vehicle range assessment and energy replenishment judgment based on pre-processed real-time data; Based on the results of the battery life assessment and battery replenishment judgment, select the battery replenishment sites that meet the preset conditions; Carry out scheme calculation and cost calculation for the selected energy replenishment sites; The intelligent scheduling decision algorithm compares the results of the plan calculation and cost calculation to obtain the final scheduling plan and send the scheduling instructions; Cyclic scheduling of new transport capacity tasks, and dynamic adjustment and real-time update of scheduling plans based on actual conditions; Among them, the intelligent scheduling decision algorithm is based on the genetic algorithm to analyze the path combination solution with the lowest energy consumption. The application process of the genetic algorithm includes: Define parameters; Chromosome encoding; The fitness function calculates the total energy consumption of the chromosome; Iterate until a termination condition is reached (e.g. number of iterations T): Mathematical expressions summarize the path combination scheme that converges to the lowest energy consumption.

[0006] In an embodiment of the present application, the collection and preprocessing of real-time data includes: Obtain the current energy status and location information of new energy vehicles in real time; Model and dynamically calculate the average energy consumption per kilometer of the vehicle based on the energy consumption prediction model, combined with the vehicle's historical driving data and real-time road conditions information; Update the location information and electricity price list of energy replenishment sites in real time to ensure the timeliness and accuracy of data; Endurance assessment and energy replenishment judgment include: Based on the vehicle's current remaining power and average energy consumption per kilometer, combined with the distance to the task loading and unloading point, assess whether the vehicle can travel from its current location to the unloading point and retain 20% of the remaining power; If the evaluation result shows that the battery power is insufficient, the energy replenishment plan will be automatically started; The energy replenishment sites that meet the preset conditions include: Adopting the energy replenishment station screening algorithm, draw a circular area with the current position to the unloading point as the diameter, comprehensively consider the energy consumption (distance) and electricity price factors, and screen out multiple (such as three) energy replenishment stations closest to the vehicle and multiple (such as three) energy replenishment stations with the lowest electricity price in the circular area; Use geographic information systems (GIS) and data analysis algorithms to quickly locate and screen energy replenishment sites and integrate energy replenishment site information; Scheme calculation and cost calculation include: For the selected multiple (such as the three plus three) energy replenishment sites, the route navigation algorithm is used to calculate the route planning, path length and estimated energy consumption of each solution from the current location to the energy replenishment site and then to the unloading point; Combined with the electricity price information of each charging station, the total cost of multiple plans (such as the three plus three mentioned above) (including driving energy consumption cost and charging cost) is calculated to perform cost calculation; Intelligent scheduling decisions include: Compare the total costs of multiple plans, and select the plan with the lowest cost as the final scheduling plan through multi-plan comparison and optimization; The dispatch system sends dispatch instructions to the driver or the autonomous driving system according to the selected plan, including the charging station, driving route and estimated arrival time, etc., to realize intelligent charging judgment and plan generation; Round Robin scheduling includes: Every time a new waybill is added, the dispatch process is repeated, dynamic dispatch and real-time optimization are carried out to ensure the real-time and accuracy of the dispatch plan; Real-time updates include: The system continuously monitors vehicle status and changes in energy replenishment resources, dynamically optimizes the dispatch plan based on actual conditions, and supports efficient operations in complex scenarios such as cyclic dispatch through dynamic dispatch and real-time optimization. The multi-scenario comparison includes: Using the route navigation algorithm, calculate the path length and energy consumption of each energy replenishment scheme; Comprehensively consider energy consumption and electricity prices, intelligently screen, combine electricity price information, and calculate the total cost of each plan (including energy consumption cost and electricity price cost); Through the comparison algorithm, the plan with the lowest total cost is automatically selected as the final scheduling plan; Smart filtering includes: Through the screening algorithm, the two key factors of distance and electricity price are comprehensively considered to generate multiple alternative plans, and the optimal solution is selected through refined calculations to improve the scientificity and accuracy of scheduling decisions.

[0007] In the embodiment of the present application, the parameters are defined, including: Population (P), used to represent a set of possible solutions; Chromosome (C), used to represent a potential solution; Gene (G), a unit in a chromosome used to represent a component of a solution; Fitness function (f), a function used to evaluate the quality of chromosomes; Selection operator (S), used for the process of selecting chromosomes for the next generation; The crossover operator (X) is used to combine two chromosomes to produce a new chromosome; The mutation operator (M) is used to randomly change some genes of the chromosome to introduce diversity; The number of iterations (T) is used to represent the total number of generations run by the genetic algorithm; Chromosome encoding, including: Gene 1, used to represent the energy replenishment site number G1∈{1, 2, …, 6}; Gene 2, used to represent the loading point G2=L, where L represents the set of loading points; Gene 3, used to represent the unloading point G3=U, where U represents the set of unloading points; Gene 4, used to represent the energy replenishment site number G4∈{1, 2, …, 6} or empty ( ); Fitness function, including: The fitness function f(C) is used to calculate the total energy consumption of chromosome C. The fitness f(C) of chromosome C is calculated by the following formula: If G1= (without charging station): f(C)=d0L+dLU; If G4= (Without charging station): f(C)=d0iL+dUi; Otherwise (there is a charging station): f(C)=min(d0iL+dUi, d0i+dLiU); in: d0L represents the distance from the current location to the loading point; dLU represents the distance from the loading point to the unloading point; d0iL represents the distance from the current position to the loading point via the recharging station i; dUi represents the distance from the unloading point to the recharging station i; d0i represents the distance from the current location to the energy replenishment site i; dLiU represents the distance from the loading point to the unloading point via the recharging station i.

[0008] In an embodiment of the present application, the iteration process includes several steps until a termination condition (such as the number of iterations T) is reached, including: Step 1: Initialize the initial population P(0); Step 2: For each generation t from 1 to T: Calculate fitness: Calculate the fitness f(C) for each chromosome C in the population P(t-1) after the t-1th iteration; Selection: Use the selection operator S to select parent chromosomes from the current population; Crossover: Use the crossover operator X to generate offspring chromosomes; Mutation: Use mutation operator M to introduce new mutations; Update the population: add the offspring to the population P(t) after the tth iteration; Step 3: Termination condition: when the number of iterations T is reached, the chromosome with the highest fitness is selected as the optimal solution.

[0009] In the embodiments of the present application, the mathematical expressions are summarized, including: The initial population P(0) is a randomly generated set of chromosomes; During the iteration, the selection operator S uses the roulette wheel selection method, in which the probability of each chromosome being selected is proportional to its fitness; The crossover operator X uses a single-point crossover or a two-point crossover to randomly select a crossover point and exchange the corresponding parts of the two chromosomes; The mutation operator M is implemented by randomly changing a gene in the chromosome; Converge to a path combination solution with lower energy consumption.

[0010] In an embodiment of the present application, the energy consumption prediction model includes: Use regression models and machine learning algorithms (such as regression models, neural networks, etc.) combined with historical vehicle driving data, real-time road conditions and vehicle performance parameters to establish an accurate energy consumption prediction model; The energy replenishment site screening algorithm includes: Utilize the spatial query and data analysis functions of GIS, combined with customized distance and electricity price weights, to achieve rapid screening and sorting of energy replenishment sites; Route planning and cost calculation algorithms include: Using classic path planning algorithms such as Dijkstra and A*, combined with vehicle energy consumption models and electricity price information, the optimal path and total cost of each solution are calculated; Real-time data collection and modeling include: Obtain the energy status (such as remaining power) and positioning information of new energy vehicles in real time; Build a mathematical model of the average energy consumption per kilometer of the vehicle through historical data or real-time data to ensure the accuracy of energy consumption prediction; Energy replenishment site information integration includes: Real-time integration of location information and electricity price tables of energy replenishment sites to provide comprehensive data support for dispatching decisions; Energy replenishment judgment includes intelligent energy replenishment judgment and solution generation, including: Based on the vehicle's current remaining power, mission distance, and energy consumption model, determine whether recharging is needed and determine the amount of recharging when recharging is needed; Through intelligent screening algorithms, the three nearest energy replenishment sites and the three energy replenishment sites with the lowest electricity prices are selected by taking into account distance and electricity price factors. These sites must be located within a circle with the diameter from the current location to the unloading point. Dynamic optimization of the loop scheduling process, including: Realize the dynamic response of the dispatch system, recalculate the optimal dispatch plan every time a new waybill is added to adapt to the changing transportation needs and environmental conditions; Comprehensive consideration of energy consumption and electricity prices includes: Incorporate the real-time energy consumption of new energy vehicles, electricity prices at charging stations, and transportation task requirements into a unified dispatching framework to achieve the optimal balance between economic benefits and operational efficiency; Realize dynamic response and real-time optimization of the dispatching system to ensure efficient and economical dispatching in a complex and changing transportation environment; Algorithm integration and application: It integrates a variety of advanced algorithms (such as energy consumption prediction models, path planning algorithms, multi-scheme comparison algorithms, etc.), and realizes the automation and intelligence of the entire process from data collection to decision output through the collaborative work between algorithms.

[0011] The embodiment of the present application further provides a new energy transportation capacity task scheduling system based on energy replenishment scenario, which adopts the above-mentioned new energy transportation capacity task scheduling method based on energy replenishment scenario, and the system includes: Data acquisition module, used to collect and pre-process the real-time data of the vehicle's energy, location, and energy consumption; A judgment module is used to evaluate vehicle range and make energy replenishment judgments based on pre-processed real-time data; The site screening module is used to screen the energy replenishment sites that meet the preset conditions based on the results of the battery life evaluation and energy replenishment judgment; A calculation module is used to calculate the scheme and cost of the selected energy replenishment sites; The plan formation module is used to compare the results of plan calculation and cost calculation through the intelligent scheduling decision algorithm to obtain the final scheduling plan and send scheduling instructions; The cyclic scheduling module is used to cyclically schedule the newly added transport tasks and dynamically adjust and update the scheduling plan in real time according to the actual situation; Among them, the intelligent scheduling decision algorithm analyzes the path combination solution with the lowest energy consumption based on the genetic algorithm. The application process of the genetic algorithm includes: Define parameters; Chromosome encoding; The fitness function calculates the total energy consumption of the chromosome; Iterate until the termination condition is reached: Mathematical expressions summarize the path combination scheme that converges to the lowest energy consumption.

[0012] The solution provides a new energy transportation task scheduling method and system based on the energy replenishment scenario. By calculating the matching degree between the remaining power of new energy vehicles and the task requirements in real time, it can predict in advance whether energy replenishment is needed, thereby avoiding midway stagnation or return due to insufficient power, significantly improving the execution efficiency and punctuality of transportation tasks, and improving operational efficiency; in the energy replenishment plan selection stage, the two key factors of the distance and electricity price of the energy replenishment site are comprehensively considered, and the algorithm is used to select the energy replenishment sites that are both close and economical, which effectively reduces the energy replenishment cost of new energy vehicles, thereby reducing the overall transportation cost and reducing the operating cost; it supports dynamic scheduling and real-time optimization. Whenever a new transportation task is added, the system can immediately re-evaluate and adjust the scheduling plan to ensure a high degree of flexibility and responsiveness in the changing market demand and transportation environment, and enhance scheduling flexibility; automated and intelligent response system The workload of manual query and evaluation is reduced, and the labor cost is reduced; at the same time, the characteristics of instant response also shorten the decision-making cycle, reduce time cost, and reduce labor cost and time cost; based on precise mathematical models and advanced algorithm support, such as energy consumption prediction models, path planning algorithms and multi-scheme comparison algorithms, the scheduling method of this application can make more scientific and reasonable decisions, reduce the uncertainty caused by human judgment, improve scheduling accuracy, and improve the scientific nature of decision-making; focus on the capacity scheduling of new energy vehicles, by optimizing the energy replenishment path and reducing unnecessary mileage, it reduces energy consumption and carbon emissions, which is in line with the current green and low-carbon sustainable development concept, has positive significance for environmental protection and promotes green development, and can also significantly improve the scheduling efficiency and economic benefits of new energy capacity in the energy replenishment scenario, and provide strong support for the widespread application of new energy vehicles in the field of logistics and transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings: Figure 1 A schematic diagram of the steps of a new energy transport capacity task scheduling method based on a refueling scenario provided in an embodiment of the present application. DETAILED DESCRIPTION

[0014] In order to make the technical solutions and advantages in the embodiments of the present application more clearly understood, the exemplary embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than an exhaustive list of all the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0015] In the process of realizing this application, the applicant found that a key challenge faced by new energy vehicles in actual operation is the energy supply problem, such as: how to be efficient in medium and long-distance transportation tasks, the price differences at different refueling stations at different times, the decision-making pressure of complex refueling schemes on dispatchers, and the economical management of vehicle refueling needs, etc. These have become bottlenecks restricting the development of new energy transportation capacity and curbed the development of the industry.

[0016] Although there are many new energy vehicle dispatching systems on the market, most of them focus on basic functions such as vehicle allocation and route planning, and do not consider the refined management and optimized dispatching in the energy replenishment scenario. These systems or methods often ignore the impact of key factors such as the real-time energy status of vehicles, the distribution of energy replenishment sites, and electricity price fluctuations on dispatching decisions, which may lead to energy waste, cost increase, or task delays in actual operations.

[0017] Example 1 In view of the above problems, this embodiment provides a new energy capacity task scheduling method based on the energy replenishment scenario, such as Figure 1 As shown, the following steps are included: S101: Collect and pre-process real-time data on energy, location, and energy consumption of vehicles; S102: Evaluate vehicle range and determine energy replenishment based on pre-processed real-time data; S103: According to the results of the battery life evaluation and the energy replenishment judgment, select energy replenishment sites that meet the preset conditions; S104: performing scheme calculation and cost calculation on the selected energy replenishment sites; S105: Compare the results of the scheme calculation and cost calculation through the intelligent scheduling decision algorithm to obtain the final scheduling scheme, and send a scheduling instruction; S106: cyclically dispatching the newly added transport capacity tasks, and dynamically adjusting and updating the dispatching plan in real time according to the actual situation; Among them, the intelligent scheduling decision algorithm is based on the genetic algorithm to analyze the path combination solution with the lowest energy consumption. The application process of the genetic algorithm includes: Define parameters; Chromosome encoding; The fitness function calculates the total energy consumption of the chromosome; Iterate until a termination condition is reached (e.g. number of iterations T): Mathematical expressions summarize the path combination scheme that converges to the lowest energy consumption.

[0018] In this embodiment, the collection and preprocessing of real-time data includes: Obtain the current energy status and location information of new energy vehicles in real time; Model and dynamically calculate the average energy consumption per kilometer of the vehicle based on the energy consumption prediction model, combined with the vehicle's historical driving data and real-time road conditions information; update the location information and electricity price list of the energy replenishment station in real time to ensure the timeliness and accuracy of the data; The battery life assessment and recharging judgment include: based on the vehicle's current remaining power and average energy consumption per kilometer, combined with the distance to the task loading and unloading point, assess whether the vehicle can travel from the current location to the unloading point and retain 20% of the power remaining; if the assessment result shows that the power is insufficient, the recharging plan will be automatically started; Screening the energy replenishment sites that meet the preset conditions includes: using the energy replenishment site screening algorithm, drawing a circular area with the current position to the unloading point as the diameter, comprehensively considering the distance and electricity price factors, and screening the three nearest energy replenishment sites and the three energy replenishment sites with the lowest electricity prices in the area; using the geographic information system (GIS) and data analysis algorithm to achieve rapid positioning and screening of energy replenishment sites, and integrate energy replenishment site information; The scheme calculation and cost calculation include: for the six selected charging stations, the route navigation algorithm is used to calculate the route planning, path length and estimated energy consumption of each scheme from the current location to the charging station and then to the unloading point; combined with the electricity price information of each charging station, the total cost of each scheme (including driving energy consumption cost and charging cost) is calculated for cost calculation; Intelligent dispatching decision-making includes: comparing the total costs of six options, and selecting the option with the lowest cost as the final dispatching option through multi-option comparison and optimization; the dispatching system sends dispatching instructions to the driver or the autonomous driving system based on the selected option, including the charging station, driving route and estimated arrival time, etc., to realize intelligent charging judgment and solution generation; Cyclic scheduling includes: each time a new waybill is added, the scheduling process is repeated to ensure the timeliness and accuracy of the scheduling plan; Real-time updates include: the system continuously monitors vehicle status and changes in energy replenishment resources, dynamically optimizes scheduling plans based on actual conditions, and supports efficient operations in complex scenarios such as cyclic dispatch. The comparison of multiple plans includes: using the route navigation algorithm to calculate the path length and energy consumption of each energy replenishment plan; comprehensively considering energy consumption and electricity prices, and intelligently screening; combining electricity price information to calculate the total cost of each plan (including energy consumption cost and electricity price cost); through the comparison algorithm, automatically selecting the plan with the lowest total cost as the final scheduling plan; Intelligent screening and comparison of multiple options: Through the screening algorithm, the two key factors of distance and electricity price are comprehensively considered to generate multiple alternative options, and the optimal solution is selected through refined calculation, which significantly improves the scientificity and accuracy of scheduling decisions.

[0019] In this embodiment, the parameters are defined, including: Population (P), used to represent a set of possible solutions; Chromosome (C), used to represent a potential solution; Gene (G), a unit in a chromosome used to represent a component of a solution; Fitness function (f), a function used to evaluate the quality of chromosomes; Selection operator (S), used for the process of selecting chromosomes for the next generation; The crossover operator (X) is used to combine two chromosomes to produce a new chromosome; The mutation operator (M) is used to randomly change some genes of the chromosome to introduce diversity; The number of iterations (T) is used to represent the total number of generations that the genetic algorithm runs.

[0020] Chromosome encoding, including: Gene 1, used to represent the energy replenishment site number G1∈{1, 2, …, 6}; Gene 2, used to represent the loading point G2=L; Gene 3, used to represent the unloading point G3=U; Gene 4, used to represent the energy replenishment site number G4∈{1, 2, ..., 6} or empty ( ); Fitness function, including: The fitness function f(C) is used to calculate the total energy consumption of chromosome C. The fitness f(C) of chromosome C is calculated by the following formula: If G1= (without charging station): f(C)=d0L+dLU; If G4= (Without charging station): f(C)=d0iL+dUi; Otherwise (there is a charging station): f(C)=min(d0iL+dUi, d0i+dLiU); in: d0L represents the distance from the current location to the loading point; dLU represents the distance from the loading point to the unloading point; d0iL represents the distance from the current position to the loading point via the recharging station i; dUi represents the distance from the unloading point to the recharging station i; d0i represents the distance from the current location to the energy replenishment site i; dLiU represents the distance from the loading point to the unloading point via the recharging station i.

[0021] In this embodiment, the iteration process includes several steps until a termination condition (such as the number of iterations T) is reached, including: Step 1: Initialize the initial population P(0); Step 2: For each generation t from 1 to T: Calculate fitness: Calculate the fitness f(C) for each chromosome C in the population P(t-1) after the t-1th iteration; Selection: Use the selection operator S to select parent chromosomes from the current population; Crossover: Use the crossover operator X to generate offspring chromosomes; Mutation: Use mutation operator M to introduce new mutations; Update the population: add the offspring to the population P(t) after the tth iteration; Step 3: Termination condition: when the number of iterations T is reached, the chromosome with the highest fitness is selected as the optimal solution.

[0022] In this embodiment, the mathematical expression is summarized as follows: The initial population P(0) is a randomly generated set of chromosomes; During the iteration, the selection operator S uses the roulette wheel selection method, in which the probability of each chromosome being selected is proportional to its fitness; The crossover operator X uses a single-point crossover or a two-point crossover to randomly select a crossover point and exchange the corresponding parts of the two chromosomes; The mutation operator M is implemented by randomly changing a gene in the chromosome; Converge to a path combination solution with lower energy consumption.

[0023] In this embodiment, the energy consumption prediction model includes: using a regression model, a machine learning algorithm (such as a regression model, a neural network, etc.), combining the vehicle's historical driving data, real-time road condition information and vehicle performance parameters to establish an accurate energy consumption prediction model; The energy replenishment site screening algorithm includes: using the spatial query and data analysis functions of GIS, combined with customized distance and electricity price weights, to achieve rapid screening and sorting of energy replenishment sites; Route planning and cost calculation algorithms include: using classic path planning algorithms such as Dijkstra and A*, combined with vehicle energy consumption models and electricity price information, to calculate the optimal path and total cost of each solution; Real-time data collection and modeling include: obtaining the energy status (such as remaining power) and positioning information of new energy vehicles in real time, and building a mathematical model of the average energy consumption per kilometer of the vehicle through historical data or real-time data to ensure the accuracy of energy consumption prediction; Energy replenishment site information integration includes: real-time integration of energy replenishment site location information and electricity price lists to provide comprehensive data support for dispatching decisions; Intelligent energy replenishment judgment and solution generation include: judging whether energy replenishment is needed and determining the amount of energy replenishment when it is needed based on the vehicle's current remaining power, mission distance and energy consumption model; using an intelligent screening algorithm, taking into account both distance and electricity price factors, selecting the three nearest energy replenishment sites and the three energy replenishment sites with the lowest electricity prices, and these sites must be located within a circle with a diameter from the current location to the unloading point; Cyclic scheduling and dynamic optimization include: achieving dynamic response of the scheduling system, recalculating the optimal scheduling plan every time a new waybill is added to adapt to the changing transportation demand and environmental conditions; Comprehensive consideration of energy consumption and electricity prices includes: incorporating the real-time energy consumption of new energy vehicles, electricity prices at energy replenishment sites, and transportation task requirements into a unified scheduling framework to achieve the optimal balance between economic benefits and operational efficiency; Dynamic scheduling and real-time optimization: Supports cyclic dispatch scenarios, realizes dynamic response and real-time optimization of the dispatch system, and ensures efficient and economical dispatch in complex and changing transportation environments; Algorithm integration and application: Integrate multiple advanced algorithms (such as energy consumption prediction models, path planning algorithms, multi-scheme comparison algorithms, etc.), and through the collaborative work between algorithms, realize the automation and intelligence of the entire process from data collection to decision output.

[0024] The new energy capacity task scheduling method based on the energy replenishment scenario of this embodiment can form a real-time online new energy vehicle capacity task network operation or scheduling system based on the energy replenishment scenario by using ITC technologies such as network, electronics, Internet of Things, and Internet of Vehicles, thereby giving play to the implementation and application of the method of this embodiment. The specific implementation steps and processes will not be repeated here, and will be elaborated in detail through Example 2.

[0025] Example 2 The new energy transportation capacity task scheduling system based on the energy replenishment scenario of this embodiment adopts the above-mentioned new energy transportation capacity task scheduling method based on the energy replenishment scenario, and can form a real-time online new energy vehicle network operation or scheduling system based on the energy replenishment scenario through ITC technologies such as network, electronics, Internet of Things, and Internet of Vehicles, and then be applied to specific scenarios. The system includes: Data acquisition module, used to collect and pre-process the real-time data of the vehicle's energy, location, and energy consumption; A judgment module is used to evaluate vehicle range and make energy replenishment judgments based on pre-processed real-time data; The site screening module is used to screen the energy replenishment sites that meet the preset conditions based on the results of the battery life evaluation and energy replenishment judgment; A calculation module is used to calculate the scheme and cost of the selected energy replenishment sites; The plan formation module is used to compare the results of plan calculation and cost calculation through the intelligent scheduling decision algorithm to obtain the final scheduling plan and send scheduling instructions; The cyclic scheduling module is used to cyclically schedule the newly added transport tasks and dynamically adjust and update the scheduling plan in real time according to the actual situation; Among them, the intelligent scheduling decision algorithm analyzes the path combination solution with the lowest energy consumption based on the genetic algorithm. The application process of the genetic algorithm includes: Define parameters; Chromosome encoding; The fitness function calculates the total energy consumption of the chromosome; Iterate until the termination condition is reached: Mathematical expressions summarize the path combination scheme that converges to the lowest energy consumption.

[0026] Specifically, this embodiment can also be applied and implemented in detail through the following steps: Step 1: Parameter setting, data collection and preprocessing 1. Basic vehicle data: New energy vehicles are first entered into the system through a unique number, and then the vehicle's power, mileage data, and positioning information are obtained in real time through Tbox.

[0027] 2. Basic data of charging stations: Charging stations are entered into the system through unique numbers. At the same time, the location data of the charging stations, the tiered electricity price schedule, and the number of charging piles included are also obtained.

[0028] 3. Data reprocessing: For the vehicle data obtained in real time, it is first classified according to the waybill table dimension, and combined with the waybill route length, energy consumption summary during the period and other data, the linear regression model is used to predict the comprehensive average energy consumption per kilometer of a single vehicle. A simple model can be established as follows: 1) The arrival time T1 and T2 of the waybill at the loading point and the unloading point; 2) According to T1 and T2, find the matching timestamp in the formal record table in the time series database to determine the starting point power E1 and the ending point power E2, the starting point mileage value L1 and the ending point mileage value L2; 3) Cumulative mileage value L0=L2-L1; Cumulative energy consumption value E0=E2-E1; Average energy consumption per kilometer = α = L0 / E0 Step 2: Create task data 1. Confirm the task loading and unloading points: When the user creates a new task, he can confirm the loading and unloading point addresses, that is, the longitude and latitude information of the two points.

[0029] 2. Confirm the vehicles to be dispatched: The user selects the vehicles to be included in the dispatch analysis.

[0030] Step 3: Task Scheduling Analysis 1. The first step: Get the current vehicle location information (i.e. longitude and latitude data), call the third-party map software interface, and input the route planning: current location - loading point - unloading point. The total length β of the entire journey can be obtained through the interface.

[0031] 2. Step 2: Get the remaining power γ and total current δ of the current vehicle, calculate β / α-γ, if the value is less than 0.2δ (that is, the remaining power is less than 20% of the total power), go to step 3; otherwise, exit the program and directly execute the normal transportation task.

[0032] 3. The third step: Enter the energy replenishment scheduling link. First, connect the current position and the unloading position with a straight line, and use the straight line as the diameter to draw a circle. You can confirm a regional circle λ range and a circle center coordinate. Through the center and radius length, as well as the energy replenishment site location data, confirm all the energy replenishment site data within the regional circle.

[0033] 4. Step 4: Among all the charging stations within the circle λ, select the three charging stations with the lowest current tiered electricity prices; then select the three charging stations closest to the current coordinates of the vehicle within λ. So far, 6 charging stations have been selected.

[0034] 5. Step 5: Call the route planning API of the third-party map software and add the route. The route planning is: 1) Current location - charging station - loading point - unloading point; 2) Current location - loading point - charging station - unloading point. The route combination with the lowest energy consumption is analyzed based on the genetic algorithm. The algorithm settings are as follows: ①Define parameters: Population (P): a set of possible solutions; Chromosome (C): represents a potential solution; Gene (G): A unit in a chromosome that represents a component of a solution; Fitness function (f): function used to evaluate chromosome quality; Selection operator (S): the process used to select chromosomes for the next generation; Crossover operator (X): The process used to combine two chromosomes to produce a new chromosome; Mutation operator (M): used to randomly change some genes of chromosomes to introduce diversity; Iteration number (T): The total number of generations that the genetic algorithm runs.

[0035] ②Chromosome coding: Gene 1: Energy replenishment site number G1∈{1,2,…,6} Gene 2: Loading point G2=L Gene 3: Unloading point G3=U Gene 4: Energy replenishment site number G4∈{1,2,…,6} or empty ( ) ③Fitness function: The fitness function f(C) calculates the total energy consumption of chromosome C. For each chromosome C, its fitness f(C) is given by the following formula: If G1= (No charging station): f(C)=d0L+dLU If G4= (No charging station): f(C)=d0iL+dUi Otherwise (there is a charging station): f(C)=min(d0iL+dUi,d0i+dLiU) in: d0L is the distance from the current location to the loading point; dLU is the distance from the loading point to the unloading point; d0iL is the distance from the current location to the loading point via the recharging station i; dUi is the distance from the unloading point to the recharging station i; d0i is the distance from the current location to the energy replenishment site i; dLiU is the distance from the loading point to the unloading point via the recharging station i.

[0036] ④Iteration process: The iterative process of a genetic algorithm can be represented as a series of steps until a termination condition (such as the number of iterations T) is reached: 1. Initialize the initial population P(0).

[0037] 2. For each generation t from 1 to T: Calculate fitness: Calculate the fitness f(C) for each chromosome C in the population P(t-1) after the t-1th iteration; Selection: Use the selection operator S to select parent chromosomes from the current population; Crossover: Use the crossover operator X to generate offspring chromosomes; Mutation: Use mutation operator M to introduce new mutations; Update the population: add the offspring to the population P(t) after the tth iteration.

[0038] 3. Termination condition: When the number of iterations T is reached, the chromosome with the highest fitness is selected as the optimal solution.

[0039] ⑤Summary of mathematical expressions: 1. The initial population P(0) is a randomly generated set of chromosomes.

[0040] 2. During the iteration process, the selection operator S can use the roulette wheel selection method, in which the probability of each chromosome being selected is proportional to its fitness.

[0041] 3. The crossover operator X can use single-point crossover or two-point crossover to randomly select crossover points and exchange the corresponding parts of the two chromosomes.

[0042] 4. The mutation operator M can be realized by randomly changing a gene in the chromosome.

[0043] Eventually, the genetic algorithm will converge to a path combination solution with lower energy consumption.

[0044] Step 6: For cyclic tasks, each time a waybill is completed, the system will automatically dispatch the same task order to the vehicle. At this time, before the waybill is generated, the refueling scheduling plan will be judged again to close the loop of the transportation business. The new energy transportation capacity task scheduling method and system based on the refueling scenario provided in the above-mentioned embodiments 1 and 2 calculates the matching degree between the remaining power of the new energy vehicle and the task requirements in real time, and predicts in advance whether refueling is needed, thereby avoiding midway stagnation or return due to insufficient power, significantly improving the execution efficiency and punctuality of transportation tasks, and improving operational efficiency; in the stage of selecting the refueling plan, the two key factors of the distance and electricity price of the refueling site are comprehensively considered, and the algorithm is used to select the refueling sites that are both close and economical, which effectively reduces the refueling cost of new energy vehicles, thereby reducing the overall transportation cost and reducing the operating cost; it supports dynamic scheduling and real-time optimization. Whenever a new transportation task is added, the system can immediately re-evaluate and adjust the scheduling plan to ensure that in the changing market demand Maintain a high degree of flexibility and response speed in the transportation environment, and enhance scheduling flexibility; the automated and intelligent response system reduces the workload of manual query and evaluation, and reduces labor costs; at the same time, the characteristics of instant response also shorten the decision-making cycle, reduce time costs, and reduce labor costs and time costs; based on precise mathematical models and advanced algorithm support, such as energy consumption prediction models, path planning algorithms, and multi-scheme comparison algorithms, the scheduling method of this scheme can make more scientific and reasonable decisions, reduce the uncertainty caused by human judgment, improve scheduling accuracy, and improve the scientific nature of decision-making; focus on the capacity scheduling of new energy vehicles, by optimizing the energy replenishment path and reducing unnecessary mileage, reduce energy consumption and carbon emissions, in line with the current green, low-carbon sustainable development concept.

[0045] In this application, unless otherwise clearly specified and limited, the terms "connected", "connected", "including", etc. should be understood in a broad sense, for example, it can be an electrical connection or can communicate with each other; it can be directly connected or indirectly connected through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0046] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0047] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A new energy transportation task scheduling method based on energy replenishment scenario, characterized in that: The following steps are involved: Collect and pre-process real-time data on vehicle energy, location, and energy consumption; Carry out vehicle range evaluation and energy replenishment judgment based on the pre-processed real-time data; According to the results of the battery life evaluation and the energy replenishment judgment, selecting energy replenishment sites that meet preset conditions; Carry out scheme calculation and cost calculation for the selected energy replenishment sites; Comparing the results of the solution calculation and the cost calculation through an intelligent scheduling decision algorithm to obtain a final scheduling solution, and sending a scheduling instruction; Cyclic scheduling of new transport capacity tasks, and dynamic adjustment and real-time update of scheduling plans based on actual conditions; The intelligent scheduling decision algorithm analyzes the path combination scheme with the lowest energy consumption based on the genetic algorithm, and the application process of the genetic algorithm includes: Define parameters; Chromosome encoding; The fitness function calculates the total energy consumption of the chromosome; Iterate until the termination condition is reached: Mathematical expressions summarize the path combination scheme that converges to the lowest energy consumption.

2. The method for scheduling new energy transportation tasks based on energy replenishment scenarios according to claim 1, characterized in that: The real-time data collection and preprocessing include: Obtain the vehicle's current energy status and location information in real time; Model and dynamically calculate the average energy consumption per kilometer of the vehicle based on the energy consumption prediction model, combined with the vehicle's historical driving data and real-time road conditions information; Update the location information and electricity price list of energy replenishment sites in real time; The endurance evaluation and the energy replenishment judgment include: Based on the vehicle's current remaining power and average energy consumption per kilometer, combined with the distance to the task loading and unloading points, evaluate whether the vehicle can travel from its current location to the unloading point; If the evaluation result shows that the battery power is insufficient, the energy replenishment plan will be automatically started; The energy replenishment sites selected to meet the preset conditions include: Adopting the energy replenishment site screening algorithm, a circular area is drawn with the current position to the unloading point as the diameter, and the energy consumption and electricity price factors are comprehensively considered to screen out multiple energy replenishment sites closest to the vehicle and multiple energy replenishment sites with the lowest electricity price within the circular area; Use geographic information systems and data analysis algorithms to locate and screen energy replenishment sites and integrate energy replenishment site information; The solution calculation and the cost calculation include: For the selected multiple energy replenishment sites, the route navigation algorithm is used to calculate the route planning, path length and estimated energy consumption of each plan from the current location to the energy replenishment site and then to the unloading point; Combine the electricity price information of each energy replenishment site to calculate the total cost of multiple plans and perform cost calculation; The intelligent scheduling decision algorithm includes: Comparing the total costs of the multiple plans, and selecting the plan with the lowest cost as the final scheduling plan through comparison and optimization of multiple plans; Sending a dispatch instruction to the driver or the automatic driving system according to the selected final dispatch plan; The dispatch instruction includes: charging station, driving route and estimated arrival time; The cyclic scheduling includes: Every time a new waybill is added, the dispatch process is repeated, with dynamic dispatch and real-time optimization; The real-time update includes: Continuously monitor vehicle status and energy resource changes, and dynamically optimize scheduling plans based on actual conditions.

3. The method for dispatching new energy transportation tasks based on energy replenishment scenarios according to claim 2, characterized in that: The definition parameters include: The population P is used to represent a set of possible solutions; Chromosome C, used to represent a potential solution; Gene G, a unit in a chromosome, is used to represent a component of the solution; Fitness function f, a function used to evaluate the quality of chromosomes; Selection operator S is used to select the next generation chromosome process; The crossover operator X is used to combine two chromosomes to generate a new chromosome; The mutation operator M is used to randomly change some genes of the chromosome to introduce diversity; The number of iterations T is used to represent the total number of generations of genetic algorithm operations; The chromosome encoding includes: Gene 1, used to represent the energy replenishment site number G1∈{1,2,…,6}; Gene 2, used to represent the loading point G2=L, where L represents the set of loading points; Gene 3, used to represent the unloading point G3=U, where U represents the set of unloading points; Gene 4, used to represent the energy replenishment site number G4∈{1,2,…,6} or empty; The fitness function comprises: The fitness function f is used to calculate the total energy consumption of chromosome C. The fitness f(C) of chromosome C is calculated by the following formula: If G1= , then f(C)=d0L+dLU; If G4= , then f(C)=d0iL+dUi; Otherwise: f(C)=min(d0iL+dUi,d0i+dLiU); in: represents an empty set; d0L represents the distance from the current position to the loading point; dLU represents the distance from the loading point to the unloading point; d0iL represents the distance from the current position through the charging station i to the loading point; dUi represents the distance from the unloading point to the charging station i; d0i represents the distance from the current position to the charging station i; dLiU represents the distance from the loading point through the charging station i to the unloading point; min() represents the minimum value.

4. The method for scheduling new energy transportation tasks based on energy replenishment scenarios according to claim 3 is characterized in that: The iterative process includes the following steps: Step 1: Initialize the initial population P(0); Step 2: For each generation t from 1 to T: Calculate fitness: Calculate the fitness f(C) for each chromosome C in the population P(t-1) after the t-1th iteration; Selection: Use the selection operator S to select parent chromosomes from the current population; Crossover: Use the crossover operator X to generate offspring chromosomes; Mutation: Use mutation operator M to introduce new mutations; Update the population: add the offspring to the population P(t) after the tth iteration; Step 3: When the number of iterations reaches T, the chromosome with the highest fitness is selected as the optimal solution.

5. The method for dispatching new energy transportation tasks based on energy replenishment scenarios according to claim 4 is characterized in that: The mathematical expression is summarized as follows: The initial population P(0) is a randomly generated set of chromosomes; During the iteration, the selection operator S uses the roulette wheel selection method, in which the probability of each chromosome being selected is proportional to its fitness; The crossover operator X uses a single-point crossover or a two-point crossover method to randomly select a crossover point and exchange the corresponding parts of the two chromosomes; The mutation operator M is implemented by randomly changing a gene in the chromosome; Converge to a path combination solution with low energy consumption.

6. The method for scheduling new energy transportation tasks based on energy replenishment scenarios according to claim 2, characterized in that: The energy consumption prediction model includes: Using regression models and machine learning algorithms, combined with historical vehicle driving data, real-time road conditions and vehicle performance parameters, an energy consumption prediction model is established; The energy replenishment site screening algorithm includes: Utilize the spatial query and data analysis functions of GIS, combined with customized distance and electricity price weights, to achieve the screening and sorting of energy replenishment sites; The route planning and cost calculation algorithm includes: The Dijkstra path planning algorithm is used to combine the vehicle energy consumption model and electricity price information to calculate the optimal path and total cost of each solution; The energy replenishment judgment includes: Based on the vehicle's current remaining power, mission distance, and energy consumption model, determine whether recharging is needed and determine the amount of recharging when recharging is needed; Through an intelligent screening algorithm, taking into account distance and electricity price factors, the three nearest energy replenishment sites and the three energy replenishment sites with the lowest electricity prices are selected, and these sites must be located within a circle with a diameter from the current location to the unloading point.

7. A new energy transportation task scheduling system based on energy replenishment scenarios, characterized in that: The method for scheduling new energy transportation tasks based on energy replenishment scenarios according to any one of claims 1 to 6 is adopted, and the system comprises: Data acquisition module, used to collect and pre-process the real-time data of the vehicle's energy, location, and energy consumption; A judgment module, used to evaluate vehicle range and make energy replenishment judgment based on the pre-processed real-time data; A site screening module, used to screen energy replenishment sites that meet preset conditions according to the results of the battery life evaluation and the energy replenishment judgment; A calculation module is used to calculate the scheme and cost of the selected energy replenishment sites; A scheme forming module, used to compare the results of the scheme calculation and the cost calculation through an intelligent scheduling decision algorithm to obtain a final scheduling scheme and send a scheduling instruction; The cyclic scheduling module is used to cyclically schedule the newly added transport tasks and dynamically adjust and update the scheduling plan in real time according to the actual situation; The intelligent scheduling decision algorithm analyzes the path combination scheme with the lowest energy consumption based on the genetic algorithm, and the application process of the genetic algorithm includes: Define parameters; Chromosome encoding; The fitness function calculates the total energy consumption of the chromosome; Iterate until the termination condition is reached: Mathematical expressions summarize the path combination scheme that converges to the lowest energy consumption.

Images