Vehicle scheduling optimization method for new energy heavy truck charging and battery replacing station

Abstract

The invention provides a vehicle scheduling optimization method for a new energy heavy truck charging and swapping station, and relates to the field of vehicle scheduling optimization, and the method comprises the following steps: S1, a vehicle owner achieves the real-time communication with the swapping station through a charging and swapping reservation app, formulates a unified data exchange protocol, and clarifies the information content needing to be exchanged between the vehicle and the swapping station; s2, establishing a vehicle charging record database, and collecting charging time, charging amount, mileage and battery replacement frequency data of each vehicle; and using a data mining technology to analyze the use rules of the vehicle and the battery. According to the invention, through the real-time communication and data mining technology, scientific distribution of vehicle scheduling and charging power is realized, and the scheduling efficiency and accuracy are greatly improved; the scientific partition and dynamic vehicle distribution strategy of the charging and battery swapping station is combined with clear identification and guidance, so that the operation efficiency is improved, and the vehicle waiting time is shortened; meanwhile, the charging pile controls a dynamic power distribution and notification mechanism of the system.

Description

Technical Field

[0001] The present invention relates to the field of vehicle scheduling optimization, and in particular to a vehicle scheduling optimization method for a new energy heavy truck charging and swapping station. Background Art

[0002] With the widespread use of new energy heavy-duty trucks, the vehicle dispatching and charging power allocation issues of charging and swapping stations have become increasingly prominent. Traditional charging and swapping station management often relies on manual dispatching, which is inefficient and difficult to meet the charging needs of large-scale new energy heavy-duty trucks. At the same time, due to the urgency of heavy-duty truck transportation tasks and the diversity of vehicle types, how to reasonably allocate charging resources and power and improve charging efficiency has become an urgent problem to be solved. In the prior art, there is often a lack of scientific optimization methods for vehicle scheduling and charging power allocation at charging and swapping stations. After a vehicle arrives at a charging and swapping station, it may take a long time to wait, affecting the timely completion of the transportation task. In addition, the allocation of charging power is also unreasonable, which often causes some vehicles to charge too fast or too slow, affecting the battery life and the overall efficiency of the charging station. In order to solve these problems, a vehicle scheduling optimization method for new energy heavy-duty truck charging and swapping stations is needed; this method needs to be able to achieve real-time communication between vehicles and swapping stations, collect and analyze the usage patterns of vehicles and batteries, and reasonably allocate charging resources and power according to the owner's reservation needs and the actual situation of the vehicle; at the same time, it is also necessary to consider the layout and capacity conditions of the charging and swapping stations, as well as the type of vehicle, power status, urgency of the transportation task and other factors to ensure that the vehicle can complete the charging task quickly and efficiently.

[0003] Therefore, we made improvements to this and proposed a vehicle scheduling optimization method for new energy heavy-duty truck charging and swapping stations. Summary of the invention

[0004] Technical issues to be solved The present invention is aimed at the above-mentioned defects existing in the prior art, and specifically proposes a vehicle scheduling optimization method for new energy heavy-duty truck charging and swapping stations. It aims to address the problem that vehicles may need to wait for a long time after arriving at the charging and swapping stations, affecting the timely completion of the transportation tasks; in addition, the allocation of charging power is also unreasonable, which often leads to some vehicles charging too fast or too slow, affecting the battery life and the overall efficiency of the charging station.

[0005] Technical Solution In order to solve the above technical problems, the present invention provides a vehicle dispatch optimization method for a new energy heavy truck charging and swapping station, comprising the following steps: S1: The car owner uses the charging and swapping reservation app to achieve real-time communication with the battery swap station. At this time, a unified data exchange protocol is formulated to clarify the information that needs to be exchanged between the vehicle and the battery swap station; S2: Establish a vehicle charging record database to collect data on each vehicle’s charging time, charging amount, mileage, and battery replacement frequency; use data mining technology to analyze the usage patterns of vehicles and batteries; S3: The user enters vehicle information through the charging and swapping reservation app, including license plate number, vehicle model, battery size, reservation time and expected charging capacity. After the system verifies that the information is correct, it confirms the reservation and generates a reservation order; S4: According to the charging needs of heavy truck drivers, the layout and capacity of the battery swap station, determine the number and type of partitions and divide the battery swap station into overnight charging area, temporary charging area and emergency charging area; clearly divide the location and scope of each area in the charging station, set up clear signs and guide signs to help drivers quickly find the charging position; S5: Automatically identify the brand and type of the vehicle through license plate recognition and RFID technology; judge the vehicle's operating status based on the vehicle's battery health and mileage; and allocate adjacent charging positions for vehicles of the same brand and type for management and maintenance; S6: Calculate the allocable charging power based on the actual power limit of the charging station and the charging demand of each vehicle, where the charging demand includes the expected charging amount and the remaining power; assign different power weights to each vehicle based on whether the vehicle has a transportation mission, the remaining battery power, and the vehicle type; S7: According to the needs of vehicle scheduling and charging power allocation, select genetic algorithm, simulated annealing algorithm and dynamic programming optimization algorithm; build an optimization model for vehicle scheduling and charging power allocation based on vehicle information and battery swap station resource status conditions; use the optimization algorithm to solve the model and obtain the optimal vehicle scheduling plan and charging power allocation plan.

[0006] As the preferred technical solution of the present application, step S4 also includes dynamic vehicle allocation: dynamically allocate the vehicle to the most suitable charging area according to the vehicle type, power status, and urgency of the transportation task; set the priority order of each area to determine the expedited charging area>temporary charging area>overnight charging area to ensure that emergency charging needs are met first; dynamically adjust the priority order of each area according to the real-time situation of vehicle arrival; monitor the vehicle charging status and resource status of each area in real time, and display them to operators and drivers through a visual interface; and establish a feedback mechanism to collect user opinions and suggestions and continuously optimize the zoning processing strategy.

[0007] As the preferred technical solution of the present application, step S6 also includes realizing dynamic allocation and adjustment of charging power through the charging pile control system; the charging pile can receive and execute the power adjustment instruction sent by the battery swap station; set the upper and lower limits of the charging power to prevent overcharging and undercharging; at the same time, monitor the battery temperature and charging current parameters to ensure the safety and stability of the charging process; when the charging power is adjusted, the system notifies the user of the change in charging power through SMS, email and APP push; collects user opinions and suggestions on charging power allocation, and continuously optimizes the allocation strategy.

[0008] As the preferred technical solution of the present application, step S7 also includes real-time display of vehicle information, charging station resource status and charging power distribution; providing operation functions for operators to manually adjust vehicle scheduling plans and charging power distribution; and setting user authority management functions to ensure that only authorized users can access and operate the visualization interface; according to the user's role and responsibilities, different operation permissions and data access permissions are assigned, and the model is weighted, and the allocation standard is; vehicle power demand: urgency: vehicle type: battery inventory at battery swap station: idle charging positions: reservation status: weather and road conditions factors = 0.3: 0.2: 0.1: 0.15: 0.1: 0.05: 0.1.

[0009] As a preferred technical solution of the present application, the data mining technology in step S2 specifically adopts association rule mining and cluster analysis to build an analysis model to analyze the usage patterns of vehicles and batteries. The specific expression of the analysis model is as follows: Time Series Analysis Model: The historical charging demand data is {x1,x2,…,xn}, and the demand at the next m time points is analyzed as {xn+1,xn+2,…,xn+m}; The model can be expressed as: φ(B)(xt-μ)=θ(B)εt; Where φ(B) and θ(B) are the autoregressive and moving average polynomials, μ is the mean, and εt is the white noise sequence; Random Forest Model: The feature vector is x, the target variable is y, and the random forest model can be expressed as: y=B∑ b=1 1 BTb(x); Where B is the number of trees and Tb(x) is the prediction result of the bth tree.

[0010] As a preferred technical solution of the present application, the license plate recognition in step S5 specifically adopts a surveillance camera in combination with image recognition technology to identify vehicle information, and the surveillance cameras are respectively installed at the entry and exit gates of the battery swap station, as well as the charging area.

[0011] As the preferred technical solution of the present application, the information content in step S1 includes vehicle location, battery power, battery health status, vehicle estimated arrival time, vehicle type, urgency of transportation task, vehicle brand and model. The charging and swapping appointment app actively sends vehicle information to the battery swap station every 5 minutes and when the vehicle enters within three kilometers of the battery swap station. The battery swap station receives and processes this information in real time.

[0012] As the preferred technical solution of the present application, step S3 also includes the system notifying the user of the reservation result and the detailed location of the charging station and the charging equipment number information through SMS, email and APP push. After receiving the reservation request, the charging and swapping station records the vehicle information and reservation time, checks the resource status of the swapping station, and confirms whether the reservation requirements are met; then prioritizes the reservation requests according to the reservation time, vehicle type, and urgency of the transportation task; reserves charging resources and charging positions for the reserved vehicles to ensure charging on time.

[0013] As a preferred technical solution of the present application, step S5 also includes using an adjacent position allocation algorithm to automatically calculate and allocate adjacent charging positions based on vehicle identification results and charging station layout; displaying the vehicle position and charging position allocation on a visual interface, and providing an operation function for the operator to manually adjust the charging position allocation.

[0014] As a preferred technical solution of this application, the specific algorithm for solving the vehicle scheduling solution and the charging power allocation solution is as follows: Objective function: Minimize∑ i=1 N (WaitingTime i ); Among them, WaitingTime i Indicates waiting time; Constraints: WaitingTimei≥0; ∑ i=1 N (ChargingTimei·1Chargingi)≤M·T; ∑ i=1 N (SwappingTimei·1Swappingi)≤K·T; Among them, 1Chargingi and 1Swappingi are indicator functions, indicating whether the i-th vehicle chooses to charge or swap batteries; Solution: Optimize vehicle scheduling using genetic algorithms; Initialize the population: randomly generate a set of possible vehicle scheduling solutions; Selection: Select excellent individuals for reproduction according to the fitness function; Crossover: exchange genes of selected individuals to generate new individuals; Mutation: Perform random mutations on new individuals with a small probability to increase population diversity; Iteration: Repeat the selection, crossover, and mutation steps until the termination condition is reached; Use ARIMA model for demand forecasting; yt=φ1yt-1+φ2yt-2+...+φpyt-p+εt+θ1εt-1+θ2εt-2+...+θqεt-q; Among them, yt is the time series data, φ and θ are model parameters, and εt is the error term; Processing reservation requests through a greedy algorithm; Apply dynamic programming for regional management and scheduling; f(n)=mink{Cost(k)+f(nk)}; Where k is a decision or choice, and Cost(k) is the cost or expense of choosing k; Design a heuristic algorithm for neighbor position assignment. Beneficial Effects

[0015] Compared with the existing technology, the present invention realizes the scientific allocation of vehicle scheduling and charging power through real-time communication and data mining technology, greatly improving the scheduling efficiency and accuracy; the scientific zoning and dynamic vehicle allocation strategy of the charging and swapping station, combined with clear identification and guidance, improves operational efficiency and reduces vehicle waiting time; at the same time, the dynamic power allocation and notification mechanism of the charging pile control system enhances user experience and satisfaction. DETAILED DESCRIPTION

[0016] The following examples are used to illustrate the present invention, but they are not intended to limit the scope of the present invention.

[0017] As described in the background technology, after a vehicle arrives at a charging and swapping station, it may need to wait for a long time, affecting the timely completion of the transportation task; in addition, the distribution of charging power is also unreasonable, which often causes some vehicles to charge too fast or too slow, affecting the battery life and the overall efficiency of the charging station.

[0018] In order to solve this technical problem, the present invention provides a vehicle scheduling optimization method for a new energy heavy-duty truck charging and swapping station, which is applied to automated vehicle scheduling.

[0019] Specifically, the vehicle dispatch optimization method for new energy heavy truck charging and swapping stations specifically includes the following steps: S1: Car owners can use the charging and swapping reservation app to achieve real-time communication with the swapping station. At this time, a unified data exchange protocol is formulated to clarify the information that needs to be exchanged between the vehicle and the swapping station. The information includes vehicle location, battery power, battery health status, vehicle estimated arrival time, vehicle type, transportation mission urgency, vehicle brand and model. The charging and swapping reservation app actively sends vehicle information to the swapping station every 5 minutes and when the vehicle enters within 3 kilometers of the swapping station. The swapping station receives and processes this information in real time; Real-time communication between vehicles and battery swap stations is achieved through the charging and swapping reservation app, ensuring accurate and timely information transmission, reducing errors and delays in manual scheduling; a unified data exchange protocol is formulated to clarify the information content that needs to be exchanged between vehicles and battery swap stations, providing an accurate data basis for subsequent vehicle scheduling and charging power allocation; S2: Establish a vehicle charging record database to collect data on charging time, charging capacity, mileage, and battery replacement frequency for each vehicle; use data mining technology to analyze the usage patterns of vehicles and batteries, including charging time distribution, the relationship between mileage and power consumption, and the relationship between battery life and charging times; apply the analysis results to vehicle scheduling and battery management; Establish a vehicle charging record database, use data mining technology to analyze the usage patterns of vehicles and batteries, and provide a scientific basis for vehicle scheduling and battery management; according to the owner's reservation needs and the actual situation of the vehicle, optimize the algorithm to reasonably allocate vehicle scheduling and charging power, reduce the waiting time of the vehicle, and improve the charging efficiency; dynamically adjust the charging power of each vehicle, give priority to meeting the charging needs of vehicles with emergency transportation tasks and vehicles with low power, and ensure the effective use of charging resources; S3: The user enters vehicle information through the charging and swapping reservation app, including license plate number, vehicle model, battery size, reservation time and expected charging amount. After the system verifies that the information is correct, it confirms the reservation and generates a reservation order. Then the system notifies the user of the reservation result and the detailed location of the charging station and the charging equipment number information through SMS, email and APP push. After receiving the reservation request, the charging and swapping station records the vehicle information and reservation time, checks the resource status of the swapping station, and confirms whether the reservation requirements are met. Then, the reservation request is prioritized according to the reservation time, vehicle type, and urgency of the transportation task. Charging resources and charging positions are reserved for the reserved vehicle to ensure charging on time. According to the charging needs of heavy truck drivers, the layout and capacity of the battery swap stations, the charging stations are scientifically zoned, with clear signs and guide signs to help drivers quickly find charging positions. The dynamic vehicle allocation strategy ensures that emergency charging needs are met first, and dynamically adjusts the priority order of each area according to the real-time arrival of vehicles, improving the flexibility of the charging and swap stations. S4: According to the charging needs of heavy truck drivers, the layout and capacity conditions of the battery swap station, determine the number and type of zones and divide the battery swap station into overnight charging zone, temporary charging zone and emergency charging zone; clearly divide the location and scope of each zone in the charging station, set up clear signs and guide signs for drivers to quickly find the charging position; configure charging equipment, number of charging piles and battery inventory according to the needs of each zone; dynamically adjust the resource allocation of each zone according to the real-time situation of vehicle arrival; The charging and swapping reservation app provides a convenient reservation service. The system notifies users of reservation results and charging station information via SMS, email, and APP push, which improves the user experience. The charging pile control system realizes the dynamic allocation and adjustment of charging power, and notifies users of changes in charging power, which increases transparency and user participation. S5: Automatically identify the brand and type of the vehicle through license plate recognition and RFID technology; judge the vehicle's operating status based on the vehicle's battery health and mileage; allocate adjacent charging positions to vehicles of the same brand and type for management and maintenance; at the same time, consider the vehicle's operating status and allocate vehicles with similar status together; then use the adjacent position allocation algorithm to automatically calculate and allocate adjacent charging positions based on the vehicle identification results and charging station layout; display the vehicle position and charging position allocation on the visual interface, and provide operation functions for operators to manually adjust the charging position allocation; S6: Calculate the allocable charging power based on the actual power limit of the charging station and the charging needs of each vehicle, including the expected charging amount and the remaining power. Allocate different power weights to each vehicle based on whether the vehicle has a transportation mission, the remaining battery power, and the vehicle type. Prioritize the charging needs of vehicles with urgent transportation missions and vehicles with low power. Dynamically adjust the charging power of each vehicle based on the real-time charging situation of the vehicle and the changes in the resources of the battery swap station. Using genetic algorithms, simulated annealing algorithms and dynamic programming optimization algorithms, we build an optimization model for vehicle scheduling and charging power allocation to find the best solution. We use data mining technology to deeply analyze the usage patterns of vehicles and batteries to provide support for decision-making. S7: According to the requirements of vehicle scheduling and charging power allocation, select genetic algorithm, simulated annealing algorithm and dynamic programming optimization algorithm; build an optimization model for vehicle scheduling and charging power allocation based on vehicle information and resource status conditions of battery swap stations; use the optimization algorithm to solve the model and obtain the optimal vehicle scheduling plan and charging power allocation plan; The method takes into account multiple factors such as vehicle type, power status, and urgency of the transportation task. It has strong adaptability and can cope with vehicle scheduling and charging power allocation problems in different scenarios. With the continuous development of the new energy heavy-duty truck market, this method can be further expanded and optimized to meet larger-scale charging needs in the future.

[0020] The vehicle dispatch optimization method for new energy heavy-duty truck charging and swapping stations provided by the present invention realizes the scientific allocation of vehicle dispatch and charging power through real-time communication and data mining technology, greatly improving the dispatch efficiency and accuracy. The scientific zoning and dynamic vehicle allocation strategy of the charging and swapping station, combined with clear identification and guidance, improves operational efficiency and reduces vehicle waiting time. At the same time, the dynamic power allocation and notification mechanism of the charging pile control system enhances user experience and satisfaction.

[0021] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features and technical solutions in the embodiments may be combined with each other.

[0022] Embodiment 1, a vehicle dispatch optimization method for new energy heavy-duty truck charging and swapping stations, wherein step S4 also includes dynamic vehicle allocation: dynamically allocate vehicles to the most suitable charging areas according to vehicle type, power status, and transportation mission urgency conditions; set the priority order of each area to determine the expedited charging area>temporary charging area>overnight charging area to ensure that emergency charging needs are met first; dynamically adjust the priority order of each area according to the real-time situation of vehicle arrival; monitor the vehicle charging status and resource status of each area in real time, and display them to operators and drivers through a visual interface; and establish a feedback mechanism to collect user opinions and suggestions and continuously optimize the zoning processing strategy.

[0023] Furthermore, step S6 also includes realizing dynamic allocation and adjustment of charging power through the charging pile control system; the charging pile can receive and execute the power adjustment command sent by the battery swap station; setting the upper and lower limits of the charging power to prevent overcharging and undercharging; at the same time, monitoring the battery temperature and charging current parameters to ensure the safety and stability of the charging process; when the charging power is adjusted, the system notifies the user of the change in charging power through SMS, email and APP push; collects user opinions and suggestions on charging power allocation, and continuously optimizes the allocation strategy.

[0024] Furthermore, step S7 also includes real-time display of vehicle information, charging station resource status and charging power distribution; providing operation functions for operators to manually adjust vehicle scheduling plans and charging power distribution; and setting user authority management functions to ensure that only authorized users can access and operate the visualization interface; according to the user's role and responsibilities, different operation permissions and data access rights are assigned, and the model is weighted, and the allocation standard is; vehicle power demand: urgency: vehicle type: battery inventory of battery swap station: idle charging positions: reservation status: weather and road conditions factors = 0.3: 0.2: 0.1: 0.15: 0.1: 0.05: 0.1.

[0025] Embodiment 2 further optimizes the vehicle dispatch optimization method for the new energy heavy truck charging and swapping station provided in Embodiment 1. Specifically, the data mining technology in step S2 specifically adopts association rule mining and cluster analysis to build an analysis model to analyze the usage rules of vehicles and batteries. The specific expression of the analysis model is as follows: Time Series Analysis Model: The historical charging demand data is {x1,x2,…,xn}, and the demand at the next m time points is analyzed as {xn+1,xn+2,…,xn+m}; The model can be expressed as: φ(B)(xt-μ)=θ(B)εt; Where φ(B) and θ(B) are the autoregressive and moving average polynomials, μ is the mean, and εt is the white noise sequence; Random Forest Model: The feature vector is x, the target variable is y, and the random forest model can be expressed as: y=B∑ b=1 1 BTb(x); Where B is the number of trees and Tb(x) is the prediction result of the bth tree.

[0026] Furthermore, the specific algorithm for solving the vehicle dispatching scheme and the charging power allocation scheme is as follows: Objective function: Minimize∑ i=1 N (WaitingTime i ); Among them, WaitingTime i Indicates waiting time; Constraints: WaitingTimei≥0; ∑ i=1 N(ChargingTimei·1Chargingi)≤M·T; ∑ i=1 N (SwappingTimei·1Swappingi)≤K·T; Among them, 1Chargingi and 1Swappingi are indicator functions, indicating whether the i-th vehicle chooses to charge or swap batteries; Solution: Optimize vehicle scheduling using genetic algorithms; Initialize the population: randomly generate a set of possible vehicle scheduling solutions; Selection: Select excellent individuals for reproduction according to the fitness function; Crossover: exchange genes of selected individuals to generate new individuals; Mutation: Perform random mutations on new individuals with a small probability to increase population diversity; Iteration: Repeat the selection, crossover, and mutation steps until the termination condition is reached; Use ARIMA model for demand forecasting; yt=φ1yt-1+φ2yt-2+...+φpyt-p+εt+θ1εt-1+θ2εt-2+...+θqεt-q; Among them, yt is the time series data, φ and θ are model parameters, and εt is the error term; Processing reservation requests through a greedy algorithm; Apply dynamic programming for regional management and scheduling; f(n)=mink{Cost(k)+f(nk)}; Where k is a decision or choice, and Cost(k) is the cost or expense of choosing k; Design a heuristic algorithm for neighbor position assignment.

[0027] The above are only preferred embodiments of the present invention. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present invention. These improvements and modifications should also be regarded as within the scope of protection of the present invention.

Claims

1. A vehicle dispatch optimization method for a new energy heavy truck charging and swapping station, characterized in that: The steps include: S1: The car owner uses the charging and swapping reservation app to achieve real-time communication with the battery swap station. At this time, a unified data exchange protocol is formulated to clarify the information that needs to be exchanged between the vehicle and the battery swap station; S2: Establish a vehicle charging record database to collect data on each vehicle’s charging time, charging amount, mileage, and battery replacement frequency; use data mining technology to analyze the usage patterns of vehicles and batteries; S3: The user enters vehicle information through the charging and swapping reservation app, including license plate number, vehicle model, battery size, reservation time and expected charging capacity. After the system verifies that the information is correct, it confirms the reservation and generates a reservation order; S4: According to the charging needs of heavy truck drivers, the layout and capacity of the battery swap station, determine the number and type of partitions and divide the battery swap station into overnight charging area, temporary charging area and emergency charging area; clearly divide the location and scope of each area in the charging station, set up clear signs and guide signs to help drivers quickly find the charging position; S5: Automatically identify the brand and type of the vehicle through license plate recognition and RFID technology; judge the vehicle's operating status based on the vehicle's battery health and mileage; and allocate adjacent charging positions for vehicles of the same brand and type for management and maintenance; S6: Calculate the allocable charging power based on the actual power limit of the charging station and the charging demand of each vehicle, where the charging demand includes the expected charging amount and the remaining power; assign different power weights to each vehicle based on whether the vehicle has a transportation mission, the remaining battery power, and the vehicle type; S7: Select genetic algorithm, simulated annealing algorithm and dynamic programming optimization algorithm according to the requirements of vehicle scheduling and charging power allocation; Based on vehicle information and battery swap station resource status conditions, an optimization model for vehicle scheduling and charging power allocation is constructed; the optimization algorithm is used to solve the model to obtain the optimal vehicle scheduling plan and charging power allocation plan.

2. A vehicle dispatch optimization method for a new energy heavy truck charging and swapping station according to claim 1, characterized in that: The step S4 also includes dynamic vehicle allocation: dynamically allocating vehicles to the most suitable charging area according to the type of vehicle, power status, and urgency of the transportation task; setting the priority order of each area to determine the expedited charging area>temporary charging area>overnight charging area to ensure that emergency charging needs are met first; dynamically adjusting the priority order of each area according to the real-time situation of vehicle arrival; real-time monitoring of vehicle charging status and resource status in each area, and displaying them to operators and drivers through a visual interface; and establishing a feedback mechanism to collect user opinions and suggestions and continuously optimize the zoning processing strategy.

3. The vehicle dispatch optimization method for a new energy heavy truck charging and swapping station according to claim 1 is characterized in that: The step S6 also includes realizing dynamic allocation and adjustment of charging power through the charging pile control system; the charging pile can receive and execute the power adjustment command sent by the battery swap station; setting the upper and lower limits of the charging power to prevent overcharging and undercharging; at the same time, monitoring the battery temperature and charging current parameters to ensure the safety and stability of the charging process; when the charging power is adjusted, the system notifies the user of the change in charging power through SMS, email and APP push; collects users' opinions and suggestions on charging power allocation, and continuously optimizes the allocation strategy.

4. The vehicle dispatch optimization method for a new energy heavy truck charging and swapping station according to claim 1 is characterized in that: The step S7 also includes real-time display of vehicle information, charging station resource status and charging power allocation; providing an operation function for operators to manually adjust the vehicle scheduling plan and charging power allocation; and setting a user authority management function to ensure that only authorized users can access and operate the visualization interface; according to the user's role and responsibilities, different operation permissions and data access permissions are allocated, and at the same time, the model is weighted, and the allocation standard is; Vehicle power demand: Urgency: Vehicle type: Battery inventory at battery swap station: Available charging slots: Reservation status: Weather and road conditions = 0.3: 0.2: 0.1: 0.15: 0.1: 0.05: 0.

1.

5. The vehicle dispatch optimization method for a new energy heavy truck charging and swapping station according to claim 1 is characterized in that: The data mining technology in step S2 specifically adopts association rule mining and cluster analysis to build an analysis model to analyze the usage patterns of vehicles and batteries. The specific expression of the analysis model is as follows: Time Series Analysis Model: The historical charging demand data is {x1,x2,…,xn}, and the demand at the next m time points is analyzed as {xn+1,xn+2,…,xn+m}; The model can be expressed as: φ(B)(xt-μ)=θ(B)εt; Where φ(B) and θ(B) are the autoregressive and moving average polynomials, μ is the mean, and εt is the white noise sequence; Random Forest Model: The feature vector is x, the target variable is y, and the random forest model can be expressed as: y=B∑ b=1 1 BTb(x); Where B is the number of trees and Tb(x) is the prediction result of the bth tree.

6. The vehicle dispatch optimization method for a new energy heavy truck charging and swapping station according to claim 1 is characterized in that: The license plate recognition in step S5 specifically uses a surveillance camera in conjunction with image recognition technology to identify vehicle information. The surveillance cameras are respectively installed at the entrance and exit gates of the battery swap station, as well as the charging area.

7. The vehicle dispatch optimization method for a new energy heavy truck charging and swapping station according to claim 1 is characterized in that: The information content in step S1 includes vehicle location, battery power, battery health status, vehicle estimated arrival time, vehicle type, urgency of transportation task, vehicle brand and model. The charging and swapping appointment app actively sends vehicle information to the battery swapping station every 5 minutes and when the vehicle enters within three kilometers of the battery swapping station. The battery swapping station receives and processes this information in real time.

8. The vehicle dispatch optimization method for a new energy heavy truck charging and swapping station according to claim 1 is characterized in that: The step S3 also includes the system notifying the user of the reservation result and the detailed location of the charging station and the charging equipment number information through SMS, email and APP push. After receiving the reservation request, the charging and swapping station records the vehicle information and reservation time, checks the resource status of the swapping station, and confirms whether the reservation requirements are met; then prioritizes the reservation requests according to the reservation time, vehicle type, and urgency of the transportation task; reserves charging resources and charging positions for the reserved vehicles to ensure charging on time.

9. The vehicle dispatch optimization method for a new energy heavy truck charging and swapping station according to claim 1 is characterized in that: The step S5 also includes using an adjacent position allocation algorithm to automatically calculate and allocate adjacent charging positions according to the vehicle identification result and the charging station layout; displaying the vehicle position and charging position allocation on a visual interface, and providing an operation function for the operator to manually adjust the charging position allocation.

10. The vehicle dispatch optimization method for a new energy heavy truck charging and swapping station according to claim 1 is characterized in that: The specific algorithm for solving the vehicle dispatching scheme and charging power allocation scheme is as follows: Objective function: Minimize∑ i=1 N (WaitingTime i ); Among them, WaitingTime i Indicates waiting time; Constraints: WaitingTimei≥0; ∑ i=1 N (ChargingTimei·1Chargingi)≤M·T; ∑ i=1 N (SwappingTimei·1Swappingi)≤K·T; Among them, 1Chargingi and 1Swappingi are indicator functions, indicating whether the i-th vehicle chooses to charge or swap batteries; Solution: Optimize vehicle scheduling using genetic algorithms; Initialize the population: randomly generate a set of possible vehicle scheduling solutions; Selection: Select excellent individuals for reproduction according to the fitness function; Crossover: exchange genes of selected individuals to generate new individuals; Mutation: Perform random mutations on new individuals with a small probability to increase population diversity; Iteration: Repeat the selection, crossover, and mutation steps until the termination condition is reached; Use ARIMA model for demand forecasting; yt=φ1yt-1+φ2yt-2+...+φpyt-p+εt+θ1εt-1+θ2εt-2+...+θqεt-q; Among them, yt is the time series data, φ and θ are model parameters, and εt is the error term; Processing reservation requests through a greedy algorithm; Apply dynamic programming for regional management and scheduling; f(n)=mink{Cost(k)+f(nk)}; Where k is a decision or choice, and Cost(k) is the cost or expense of choosing k; Design a heuristic algorithm for neighbor position assignment.