A method and system for optimizing the scheduling of valet charging for electric vehicles

Abstract

This invention belongs to the field of electric vehicle charging scheduling technology, and provides an optimized scheduling method and system for valet charging of electric vehicles. Applied to a valet charging service platform, the method includes: acquiring electric vehicle valet charging service orders that include at least customer location and charging demand information; constructing a bi-objective mixed-integer linear programming model with the objective functions of minimizing total cost and maximizing revenue based on the acquired valet charging service orders, valet status, and charging station information; solving the objective function of the constructed bi-objective mixed-integer linear programming model to obtain a scheduling scheme for electric vehicle valet charging; and assigning valet personnel to pick up and charge the vehicle according to the customer location and the scheduling scheme, and then assigning valet personnel to retrieve and return the vehicle to the charging station after charging is completed, thus completing the optimized scheduling of electric vehicle valet charging.

Description

Technical Field

[0001] This invention belongs to the field of electric vehicle charging scheduling technology, specifically relating to an optimized scheduling method and system for valet charging of electric vehicles. Background Technology

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

[0003] Currently, carbon emissions from transportation account for 15% of the nation's total emissions, making it the third largest source of emissions after industry and construction. Driven by the "dual carbon" goals, the new energy vehicle industry has experienced rapid development, and the number of electric vehicles (EVs) on the road continues to grow.

[0004] The widespread adoption of electric vehicles has led to increasingly prominent issues of insufficient and unevenly distributed charging infrastructure, which has become a key bottleneck restricting daily use and the industry's sustainable development. On the one hand, due to limitations such as parking space ownership, grid capacity, or conditions in older urban areas, many users find it difficult to install private charging piles and have to rely on public charging facilities. On the other hand, existing public charging stations suffer from structural problems such as uneven distribution, long queues during peak hours, and low turnover rates of charging piles, making "charging difficulties" and "range anxiety" common pain points.

[0005] To overcome this predicament, valet charging services have emerged. These services allow users to book professional valet drivers through a platform, who will handle the entire process of picking up, charging, and returning the vehicle. This effectively reduces the time cost for users, making it particularly suitable for those without private charging stations, those who are time-sensitive, or those seeking ultimate convenience. It also demonstrates significant potential for extending into a one-stop automotive service ecosystem encompassing "charging + maintenance." However, existing valet charging services are mostly operated independently by automakers, with limited service areas and a generally static "car charging, driver waiting" model. This results in short effective service time for valet drivers, high operating costs, and inefficient resource allocation, making it difficult to support large-scale, sustainable platform operations.

[0006] Currently, existing research on valet charging mainly focuses on the static site selection and layout of charging facilities, or on increasing supply through asset-heavy models such as mobile charging vehicles. However, there is a lack of in-depth discussion on how to systematically improve the operational efficiency of existing fixed charging networks through service process reengineering and dynamic scheduling optimization.

[0007] Existing valet charging service models generally suffer from the following inherent defects, which severely limit their scalable and sustainable platform operation. Specifically:

[0008] (1) The inefficient model of “car charging and waiting”: The current mainstream model is “bundled” service, that is, after the agent delivers the vehicle to the charging station, he must wait on site to complete the charging before driving it back. This results in a large amount of idle waiting time being occupied by the agent, high labor costs, and extremely low number of orders that can be served per unit time (service efficiency).

[0009] (2) The scheduling decision is simple and crude: the existing scheduling logic is mostly based on simple proximity principle or experience rules, lacking systematic optimization; it fails to take a global perspective and coordinate the dynamic matching of multiple generations of customers, multiple orders, and multiple charging stations in both time and space, and cannot achieve the optimal balance between overall operating costs and service quality. Summary of the Invention

[0010] To address the aforementioned issues, this invention proposes an optimized scheduling method and system for valet charging of electric vehicles. Based on a valet charging platform, the system completes vehicle retrieval and return tasks through an independent two-stage service process, thereby overcoming the efficiency bottleneck of "vehicle waiting for charging." A bi-objective mixed integer linear programming model is constructed, with the objective functions of minimizing the total cost and maximizing the revenue of the valet charging platform. This model provides the platform with an optimized decision-making scheme that balances cost and revenue, thus achieving optimized scheduling of valet charging.

[0011] According to some embodiments, the first solution of the present invention provides an optimized scheduling method for valet charging of electric vehicles, which adopts the following technical solution:

[0012] A method for optimizing the scheduling of valet charging for electric vehicles, applied to a valet charging service platform, includes:

[0013] Obtain electric vehicle valet charging service orders that include at least the customer's location and charging needs.

[0014] Based on the obtained valet charging service orders, valet status, and charging station information, a bi-objective mixed integer linear programming model is constructed with the objective functions of minimizing total cost and maximizing revenue.

[0015] Solve the objective function of the constructed bi-objective mixed integer linear programming model to obtain the scheduling scheme for valet charging of electric vehicles;

[0016] Based on the customer's location and the scheduling plan, valet charging staff are assigned to pick up and charge the vehicle. Once charging is complete, valet charging staff are then assigned to retrieve and return the vehicle to the charging station, thus optimizing the scheduling of valet charging for electric vehicles.

[0017] As a further technical limitation, an improved Epsilon constraint algorithm based on interval constraints is used to solve the objective function of the constructed bi-objective mixed integer linear programming model, and the Pareto optimal solution set of the optimized scheduling scheme, including at least the protocol charging station site selection scheme and the valet task scheduling plan, is obtained.

[0018] Furthermore, the objective function includes a first objective function and a second objective function; wherein the first objective function is to minimize the total cost, and the second objective function is to maximize the revenue; in the process of solving the objective function, when transforming the second objective function into a constraint on the first objective function, an interval constraint form that allows the objective value to fluctuate within a certain tolerance range is adopted.

[0019] Furthermore, the steps of the improved Epsilon constraint algorithm based on interval constraints include:

[0020] Solve the first objective function and the second objective function respectively to obtain the minimum cost and its corresponding revenue, and the maximum revenue and its corresponding cost;

[0021] A number of constraint values ​​are evenly selected within the range from the minimum cost to the maximum cost.

[0022] The profit constraint is transformed into an interval constraint, and a feasible solution of the first objective function is found under each constraint interval.

[0023] Collect the feasible solutions obtained, compare them using Pareto dominance relations, filter and output all non-dominated solutions to form a Pareto optimal solution set.

[0024] As a further technical limitation, in the process of assigning valet parking attendants to pick up and charge vehicles, the valet parking attendants are assigned to pick up the vehicles at the customer locations, charging demand information, valet parking attendant status, and the obtained dispatch plan, based on the obtained customer location, charging demand information, valet parking attendant status, and the obtained dispatch plan. After charging is completed, the valet parking attendants are assigned to pick up the vehicles at the charging stations and return the vehicles to the customer locations, based on the valet parking attendant status and the dispatch plan.

[0025] As a further technical limitation, the constraints of the objective function include at least charging station constraints, state transfer constraints, charging service constraints, and charging time constraints.

[0026] According to some embodiments, the second aspect of the present invention provides an optimized scheduling system for valet charging of electric vehicles, employing the following technical solution:

[0027] A valet charging optimization scheduling system for electric vehicles includes:

[0028] The acquisition module is configured to acquire electric vehicle valet charging service orders that include at least customer location and charging demand information.

[0029] The building module is configured to construct a bi-objective mixed integer linear programming model with the objective functions of minimizing total cost and maximizing revenue, based on the acquired valet charging service orders, valet status, and charging station information.

[0030] The solver module is configured to solve the objective function of the constructed bi-objective mixed integer linear programming model to obtain the scheduling scheme for valet charging of electric vehicles.

[0031] The scheduling module is configured to assign valet charging staff to pick up and charge electric vehicles based on the customer's location and scheduling plan. After charging is completed, the valet charging staff will then be assigned to pick up and return the vehicles to the charging station, thus completing the optimized scheduling of valet charging for electric vehicles.

[0032] According to some embodiments, a third aspect of the present invention provides a computer-readable storage medium, employing the following technical solution:

[0033] A computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the valet charging optimization scheduling method for electric vehicles as described in the first aspect of the present invention.

[0034] According to some embodiments, the fourth aspect of the present invention provides an electronic device, which adopts the following technical solution:

[0035] An electronic device includes a memory, a processor, and a program stored in the memory and running on the processor, wherein the processor executes the program to implement the steps in the valet charging optimization scheduling method for electric vehicles as described in the first aspect of the present invention.

[0036] According to some embodiments, the fifth aspect of the present invention provides a computer program product, which adopts the following technical solution:

[0037] A computer program product includes software code, wherein the program in the software code performs the steps of the valet charging optimization scheduling method for electric vehicles as described in the first aspect of the present invention.

[0038] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0039] This invention, based on a valet charging platform, completes vehicle pickup and return tasks through a two-stage service process. This "pickup and return decoupling" model significantly improves the utilization rate of valet operators, freeing them from passive waiting and allowing them to handle different stages of multiple orders. This directly reduces the labor cost per order, laying the foundation for large-scale operation and breaking through the efficiency bottleneck of "vehicles waiting for charging." A dual-objective mixed-integer linear programming model is constructed, with the objective functions of minimizing total cost and maximizing revenue for the valet charging platform. This model comprehensively considers multiple practical constraints such as dynamic scheduling, charging station layout, and resource capacity, finding the optimal balance between operating costs and economic benefits. It avoids the risks of blind expansion or overly conservative decision-making, providing the platform with an optimized decision-making scheme that balances cost and revenue, and achieving optimized scheduling of valet charging. Attached Figure Description

[0040] The accompanying drawings, which form part of this embodiment, are used to provide a further understanding of this embodiment. The illustrative embodiments and their descriptions are used to explain this embodiment and do not constitute an improper limitation of this embodiment.

[0041] Figure 1 This is a flowchart of the valet charging optimization scheduling method for electric vehicles in Embodiment 1 of the present invention;

[0042] Figure 2 This is a schematic diagram of the valet charging service process for electric vehicles in Embodiment 1 of the present invention;

[0043] Figure 3 This is a flowchart of the improved Epsilon constraint algorithm based on interval constraints in Embodiment 1 of the present invention;

[0044] Figure 4 This is a schematic diagram of the node distribution of the 17-node test road network in Embodiment 1 of the present invention;

[0045] Figure 5 This is a schematic diagram of the Pareto front surface of the 17-node test road network in Embodiment 1 of the present invention;

[0046] Figure 6 This is a schematic diagram of the site selection and service allocation results of the Scheme E protocol charging station in Embodiment 1 of the present invention;

[0047] Figure 7 This is a schematic diagram of the site selection and service allocation results of the charging station according to Scheme F protocol in Embodiment 1 of the present invention;

[0048] Figure 8 This is a structural block diagram of the electric vehicle valet charging optimization scheduling system in Embodiment 2 of the present invention. Detailed Implementation

[0049] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0050] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0051] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0052] In this invention, terms such as "upper," "lower," "left," "right," "front," "back," "vertical," "horizontal," "side," and "bottom" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used only to facilitate the description of the structural relationships of the various components or elements of this invention and do not specifically refer to any component or element in this invention. They should not be construed as limiting the invention.

[0053] In this invention, terms such as "fixed connection," "connected," and "linked" should be interpreted broadly, indicating a fixed connection, an integral connection, or a detachable connection; a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can determine the specific meaning of these terms in this invention based on the specific circumstances, and they should not be construed as limitations on the invention.

[0054] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.

[0055] Example 1

[0056] Embodiment 1 of this invention introduces an optimized scheduling method for valet charging of electric vehicles.

[0057] Research on the site selection optimization of new energy vehicle charging stations is an extension of the basic site selection problem. For the site selection and capacity determination problem of charging stations, a genetic algorithm (GA) can be used to construct a charging station site selection model to optimize the operating cost under the constraints of depreciation cycle and unit power consumption. By improving the encoding (using charging schemes as genes) and decoding (determining the effective construction part) process of GA, it can be adapted to the site selection and capacity determination under the funding constraints of highways. An improved particle swarm optimization (PSO) algorithm can be used to optimize the layout of charging stations and improve the convergence speed. By combining differential evolution and PSO, the optimal planning of urban charging stations can be achieved. By using an improved PSO inertia weight and shrinkage factor to avoid premature convergence, it can be adapted to multi-objective site selection and capacity determination. A multi-objective simulated annealing (SA) algorithm can be used to solve the site selection problem under the multi-traveling salesman scenario to improve the slow convergence defect. An immune clonal selection algorithm (ICSA) can be used to improve the response of site selection and capacity determination to dynamic demand. Graph computation and cross-entropy optimization algorithms can be combined to solve the site selection problem under the uncertainty of charging demand.

[0058] With the development of the electric vehicle industry, the limitations of user-independent charging models (such as the lack of private charging piles and long waiting times for public charging) are becoming increasingly prominent. Valet charging has become a research hotspot. Specifically: On-demand battery delivery service models can be adopted for mobility-as-a-service scenarios (such as electric taxis and ride-hailing services). Service vehicles can be dispatched to provide battery delivery services for electric taxis, achieving high efficiency in vehicle battery swapping and mobility services in a short time. However, this requires dedicated equipment and has high operating costs. Mobile charging service models can be adopted, using reservation mechanisms and intelligent system decision-making to achieve accurate prediction and dynamic matching of charging demand, improving service response speed. However, users still need to participate in the reservation process, not fully releasing time costs. Electric vehicle mutual charging services can be adopted, allowing two electric vehicles to provide power together while driving to solve emergency charging needs. However, the charging effect is only good when the electric vehicle penetration rate is low, making it difficult to adapt to large-scale applications. Electric vehicle sharing service scheduling based on multi-time-dimensional multi-task optimization models can be adopted to improve system efficiency by minimizing delivery time and charging costs. However, this does not involve the fully managed characteristics of "valet charging".

[0059] like Figure 1 The method for optimizing the scheduling of valet charging for electric vehicles, as shown, is applied to a valet charging service platform and includes:

[0060] Obtain electric vehicle valet charging service orders that include at least the customer's location and charging needs.

[0061] Based on the obtained valet charging service orders, valet status, and charging station information, a bi-objective mixed integer linear programming model is constructed with the objective functions of minimizing total cost and maximizing revenue.

[0062] Solve the objective function of the constructed bi-objective mixed integer linear programming model to obtain the scheduling scheme for valet charging of electric vehicles;

[0063] Based on the customer's location and the scheduling plan, valet charging staff are assigned to pick up and charge the vehicle. Once charging is complete, valet charging staff are then assigned to retrieve and return the vehicle to the charging station, thus optimizing the scheduling of valet charging for electric vehicles.

[0064] like Figure 2 As shown in this embodiment, after a user places an order through the valet platform, the system assigns a valet to pick up the vehicle at the user's designated location. The valet then drives the vehicle to a charging station assigned by the platform to complete charging. During charging, the valet can return to a rest area before performing other tasks. When the vehicle is almost fully charged, the system again assigns a valet (which may be the same person or different people) to pick up the vehicle from the charging station and return it to the user's location. This process decouples the traditional "car charging, person waiting" bundled model into two independent sub-tasks: "picking up the car" and "returning the car," thereby significantly improving the valet's time utilization efficiency and the overall system scheduling flexibility.

[0065] It should be noted that the charging stations used by the valet charging service platform in this embodiment are social charging stations built by the government power supply department. The platform cooperates with the government unit through agreement leasing and revenue sharing, and obtains a fixed proportion of charging piles to serve customers.

[0066] To more accurately represent the operation process of the valet charging service, this embodiment makes the following assumptions about some basic conditions:

[0067] (1) All valet operators depart from known fixed rest points and are equipped with folding electric vehicles for short-distance shuttles;

[0068] (2) The location information of the charging station and the customer point is known, and the current remaining battery power of the vehicle is sufficient to support driving to the designated charging station; after each sub-task (picking up or returning the vehicle) is completed, the valet must return to the rest point from which it started before it can accept the next task.

[0069] (3) During vehicle charging, the key is stored in the smart key cabinet managed by the platform, and the customer service representative can retrieve the vehicle by authorizing a one-time password.

[0070] This embodiment addresses the operational characteristics of valet charging services by constructing a dual-objective mixed-integer linear programming model for optimizing the selection of designated charging stations and the scheduling of valet services. The aim is to provide a theoretical basis and decision support for the scalability and feasibility of valet charging services. The various parameters and key decision variables required during the model construction process are defined as follows:

[0071] (1) Set

[0072] I is the meeting point for valet rest areas. ;

[0073] K represents a collection of charging stations. ;

[0074] J represents the set of customer points, j ;

[0075] E represents the gathering of customers. ;

[0076] T represents the total duration of the valet charging activity, where any single moment is represented as t.

[0077] This represents the actual travel time between nodes.

[0078] (2) Model parameters

[0079] Cost1 is the unit time driving cost of the valet driving the folding tram;

[0080] Cost2 is the unit time driving cost of a valet driving a customer's vehicle;

[0081] For the initial time (t=0), substitute the guest Located at rest point i, ,otherwise 0;

[0082] Cap represents the number of charging piles in social charging stations;

[0083] The proportion of charging piles allocated from social charging stations to valet platforms;

[0084] M is a large positive integer;

[0085] D represents the total number of orders received by the system;

[0086] V represents the charging speed of the charging station;

[0087] For customers The demand for vehicle charging.

[0088] The service fee per unit time for a valet driver to drive a customer's vehicle;

[0089] The service fee per unit time for a valet to drive a folding vehicle to the customer's location;

[0090] The basic service fee charged per charge for charging customers;

[0091] For charging stations The cost of the agreement;

[0092] Penalty cost per unit for incomplete orders

[0093] This refers to the percentage of revenue that the platform takes from the client's earnings.

[0094] (3) Decision variables

[0095] = ;

[0096] = ;

[0097] = ;

[0098] = ;

[0099] Let t represent the number of available charging stations in charging station k during time period t.

[0100] The charging time of customer j's vehicle at the charging station;

[0101] The departure time for valet e to serve customer j in picking up their car;

[0102] The departure time for valet e to serve customer j in returning the car.

[0103] The prerequisite for scaling up valet charging services is to reasonably control various costs. During the valet service, there will be electricity consumption costs and vehicle wear and tear costs for the folding electric vehicle. In this embodiment, these are unified as cost1, the unit travel time cost of driving the folding electric vehicle. During the process of driving the user's vehicle to and from the charging station, the valet driver will face the risk of unexpected events. This part of the risk cost needs to be borne by the valet platform and is represented as cost2, the unit time driving cost of driving the customer's vehicle.

[0104] Assuming the valet charging platform selects a contracted charging station from existing alternative social charging stations and pays a five-year contract fee, this embodiment calculates the daily cost into the objective function to obtain the charging station contract cost. To ensure the system maximizes service availability for user orders, this embodiment sets a penalty cost for incomplete orders, which is the total number of orders D minus the number of orders that are returned within the specified time, multiplied by... Finally, based on the valet's service process, the travel cost is obtained. The first objective function, i.e., the total operating cost, can be expressed as:

[0105]

[0106] The second objective function, maximizing total revenue, reflects the fundamental requirement for the sustainable development of valet charging services as a commercial service. This embodiment references existing valet charging service prices on the market and establishes a pricing model that is the sum of a service fee per unit time and a basic fee for a single service. In this embodiment, the service fee for the valet driver to transport the folding electric vehicle to the customer's location is... The service fee for a valet driver to take the user's vehicle to the charging station is... The entire valet service process includes two segments: the customer's journey to and from the charging station. Therefore, it is represented by twice the pick-up fee, plus the base fee for a single service. Therefore, the second objective function is expressed as:

[0107]

[0108] The constraints on the objective function in this embodiment include:

[0109] 1) Charging station constraints

[0110] In the operation of valet charging services, the size of each social charging station is uniform, and valet operators can only go to charging stations with which agreements have been signed; secondly, it should be ensured that the number of vehicles charging at the agreed charging stations will not exceed their capacity. The constraints thus established are as follows:

[0111]

[0112] Formulas (3) and (4) indicate that any vehicle pick-up and return service must be performed at the selected protocol charging station; Formula (5) restricts the use of charging stations upon construction; Formula (6) indicates that for any protocol charging station at any time, the number of charging vehicles allocated by the system is less than or equal to the charging station capacity.

[0113] 2) State Transmission Constraints

[0114] Valet service, as an additional service to enhance the service capacity of charging stations, considers allocating a certain percentage of charging piles from social charging stations to valet platforms. Therefore, the calculation is the number of charging piles in the social charging stations multiplied by a fixed percentage. The initial capacity of the charging station is represented by a state transit constraint. Since this embodiment considers a dynamic scheduling scheme under a real-world service scenario, state transit constraints are used to represent the capacity of the charging station at each moment. The valet's state also follows a dynamic transit process; its location distribution and task execution status change over time, with specific constraints as follows:

[0115]

[0116] Formula (7) represents the number of available charging piles in the charging station at time t=0; Formula (8) represents the number of charging piles available in the charging station during time period t. The number of available charging piles is related to the number of vehicles entering and leaving the charging station during the t-1 time period; Formula (9) represents the number of vehicles leaving the station at t=0 time. The valet's dwelling state depends on the valet's dwelling location at the initial time and the task allocation for the initial time period; Formula (10) represents the valet at rest point i at time t. The number is calculated by subtracting the number of agents who left at the current moment from the number of agents who returned at the current moment, and then adding the number of agents who returned at the current moment.

[0117] 3) Charging service constraints

[0118] The core of valet charging service lies in the service process. For any valet, multiple services cannot be performed simultaneously, and for each customer's order, the pick-up and return of the vehicle only require one service. The charging time at the charging station is expressed as the required electricity divided by the charging speed of the charging pile. This embodiment decouples the pick-up and return tasks of valet charging, allowing different valeters to complete the pick-up and return of the same customer's vehicle. Therefore, detailed coordination of the valet's services is required, which leads to the establishment of constraints:

[0119]

[0120] Formula (11) restricts the valet service personnel The service is unique; formulas (12) and (13) represent any customer The vehicle pick-up and return tasks can be served at most once; Formula (14) not only limits the flow conservation of entering and leaving the charging station, but also stipulates that the customer's vehicle pick-up and return services are at the same charging station; Formula (15) is the formula for calculating the charging time; Formula (16) connects the vehicle pick-up task and the vehicle return task, that is, it ensures that customer j's vehicle can only be picked up by the valet after it is fully charged.

[0121] 4) Charging time constraints

[0122] This model can provide specific service scheduling for valet tasks, which requires detailed time nodes to ensure that the service is consistent and reasonable. The following are the relevant time constraints:

[0123]

[0124] Formulas (17) and (18) are expressions for the departure time of valet e serving customer j in the car pick-up task; Formulas (19) and (20) are expressions for the departure time of valet e serving customer j in the car return task; Formula (21) represents the latest time limit for vehicle delivery to customer for the car return task; Formula (22) is the value constraint of the variable.

[0125] This embodiment constructs a bi-objective mixed-integer linear programming model. Its structural characteristics make it difficult to find an optimal solution that optimizes both objective functions. Therefore, this embodiment employs the Epsilon constraint algorithm for solving the problem. By setting one objective function as the primary objective and transforming it into a constraint on the other objective function, the original problem is transformed into a single-objective optimization problem with Epsilon constraints, allowing the determination of the Pareto front of the model.

[0126] like Figure 3 As shown, the specific solution steps of the Epsilon constraint method are as follows:

[0127] a. Initialize model parameters and structure. Set up a bi-objective optimization model: and ;

[0128] b. Solve for the two extreme points. Solve without considering the potential gains or losses. The solution is obtained. and corresponding benefits Solve the problem without considering costs. The solution is obtained. and the corresponding costs ;

[0129] c. Determine the profit constraint range. As the upper limit, with Set a profit constraint range as the lower limit: ;

[0130] d. Set the ε value and step size. Select evenly within the profit range. There are several ε values, and the step size is: ;

[0131] e. Algorithm improvement based on payoff constraint intervals. Based on the model characteristics, this embodiment transforms the payoff constraint into an interval constraint for each ε value: in The tolerance level represents the allowable fluctuation of returns within a certain range. For each value of ε, a feasible solution is found that minimizes cost while constraining returns.

[0132] f. Collecting and filtering Pareto solutions. For each solution obtained for each ε value, a dominance check is performed: if the new solution is not dominated by any existing solution, it is added to the Pareto solution set; if the new solution dominates some old solutions, the old solutions are removed; if the cost of the new solution is lower than the minimum cost point, it is considered abnormal and discarded. The algorithm terminates when all ε values ​​have been calculated, and the Pareto front is obtained.

[0133] This embodiment uses a 17-node test road network to conduct experimental analysis on the model and algorithm to verify the model's effectiveness. The test road network includes 2 valet rest points (for a total of 6 valet passengers), 5 alternative charging stations, and 10 customer points. The node locations are as follows: Figure 4 As shown.

[0134] Considering the large-scale computational power of the Epsilon constraint algorithm, this embodiment takes the midday peak charging demand period of 12:00-15:00 as an example, setting the total duration of the valet charging service activity to T=3 hours, with any one time period being t=0.2 hours. Based on the types of new energy vehicles in daily life, the user charging demand is set to a random distribution between (20, 100) kWh; assuming a large social charging station contains 20 charging piles, the government allocates a dedicated charging pile ratio of 0.3 (6 charging piles) to the valet platform, and the valet platform needs to pay an agreement cost of 50,000 yuan / five years for each cooperating charging station; to improve the utilization efficiency of charging piles and increase the capacity of the valet charging service, it is assumed that the charging piles are 120 kWh DC charging piles. To encourage the system to complete user charging orders as quickly as possible, it is assumed that the penalty for uncompleted orders is 20 yuan / order; the platform takes 80% of the total revenue, i.e., μ=0.8, with the remainder going to the government as a partner. Referring to the unit price of valet charging services already launched by car companies such as NIO and Nezha, Table 1 shows the specific values ​​of the valet charging service fee and the valet driver's unit time driving cost in this embodiment.

[0135] Table 1. Costs and Fees for Valet Services

[0136] Folding tram route (RMB / hour) Customer vehicle travel distance (RMB / hour) Basic fee for a single service (RMB) Valet driving costs 1 25 none Charging service fee 10 20 25

[0137] In the 17-node test road network, the Pareto front obtained from the model solution is as follows: Figure 5 As shown; where the horizontal axis represents the bi-objective model. The target value represents the total cost required to operate the valet platform; the vertical axis represents... The target value represents the total revenue obtained from valet service activities. This embodiment selects extreme points A and F on the Pareto front and a representative point E for detailed analysis. Figure 5 We can obtain:

[0138] (1) Point A is the optimal solution considering only the total system cost. At this point, both the total system cost and total revenue are minimized, with penalty costs accounting for 70% and operating costs and protocol costs accounting for a relatively low percentage. This solution shows that when the goal is to minimize costs, the system tends to build fewer stations and provide fewer services in order to reduce the platform's expenditures. However, this solution only has one protocol charging station and serves 3 users, resulting in a large number of orders that cannot be completed. This deviates from the service attributes of the platform and is an unfeasible extreme solution.

[0139] (2) Option F represents the solution that maximizes the total system revenue. Operating costs account for 67%, and agreement costs account for 27%. Three agreement charging stations are selected, and only one customer remains unserved. Comparing this to the lowest-cost solution reveals that the marginal revenue increase is far lower than the marginal cost increase. This reveals a key finding: blindly pursuing maximum revenue leads to overexpansion and an inefficient state of "returning revenue regardless of cost." Therefore, option F is also an unreasonable solution in reality.

[0140] (3) Comparing the two extreme cases, it was found that the optimal valet charging service allocation and agreement scheme should maximize revenue while minimizing total cost. Therefore, further analysis was conducted using the E-point scheme on the Pareto frontier as an example. Under this scheme, operating costs account for 54% of the total system cost, agreement costs account for 37%, and penalty costs are 9%. Although the total system cost is slightly higher than that of the A-point scheme (approximately 9.5%), the revenue increase is approximately 230%. In this case, the scheme constructs 3 agreement charging stations and completes 9 orders, significantly reducing penalty costs and concentrating resource investment on effective service links. Therefore, point E represents the Pareto improvement optimal solution that balances economy and service efficiency, verifying the important value of dual-objective collaborative optimization.

[0141] Table 2 presents the model solution results for the 17-node test road network. The table shows that from scheme A to F, the total system cost gradually increases, while the overall revenue shows an increasing trend, but the rate of increase gradually slows down. In particular, from scheme E to F, the cost increases by about 40%, while the revenue only increases by about 17%, demonstrating a significant diminishing marginal return. This indicates that as revenue approaches its upper limit, the cost required to increase revenue per unit increases significantly. Furthermore, the expansion of charging station schemes is closely related to system performance: as the number of protocol charging stations increases (e.g., from a single k4-point charging station to a combination of multiple charging stations), the number of unfulfilled orders gradually decreases, improving system service capacity, but also leading to increased costs and computational complexity. It is particularly noteworthy that while scheme F achieves maximum revenue, its CPU computation time surges to 1505 seconds, far exceeding other schemes, indicating that this scheme is difficult to find an optimal solution in the model. In practical applications, a balance must be struck between solution efficiency and revenue improvement. Therefore, in operation, attention should not only be paid to the critical point of diminishing marginal returns but also comprehensively consider computational resources and time costs to avoid real-time scheduling difficulties caused by pursuing theoretical optimality. Optimization should aim to strike a balance between benefits, costs, and computational efficiency to achieve sustainable system operation.

[0142] Table 2. Detailed experimental results of different feasible solution schemes.

[0143] plan Total system cost / yuan System revenue / yuan Protocol charging station solution Uncompleted orders / unit cpu / s A 199 87.2 k4 7 1 B 200.4 129.6 k4 6 8.9 C 208.8 184 k2, k4 4 3.3 D 210.9 224.8 k2, k4 3 3.2 E 219.8 288.8 k2, k3, k4 1 32.9 F 308 338 k1, k4, k5 1 1505

[0144] To examine the superiority of the E-point solution, point F was selected as a control group, and a detailed analysis of the charging station's service performance was conducted. For example... Figure 6 (E-point scheme) and Figure 7 (Solution F) illustrates the service allocation network relationships under two different strategies. Comparative analysis reveals that Solution E demonstrates significant advantages in multi-objective collaboration, intensive resource utilization, and improved service efficiency. The specific analysis is as follows:

[0145] The two schemes differ fundamentally in their service network structure and scheduling logic. Scheme E, with charging stations k2 and k4 exhibiting a "hub-radiation" service network, achieves a high degree of seamless integration between "pickup-charging-return" by controlling the spatiotemporal relationship between customers and charging stations. Scheme F, prioritizing high-profit orders, leads to a fragmented service network and increased valet travel time; for example, "long-distance orders" from j6 to k5 require two more time slots compared to scheme E's j6 to k4. In contrast, as shown in Table 3, scheme E, through precise spatiotemporal coordinated scheduling, reduces the total service time for valet drivers from 68 time units to 61 units, serving the same number of customers (9) in a shorter time.

[0146] In summary, the E-point solution achieves efficient utilization of valet resources and charging pile resources by accurately scheduling customer charging demand duration and arrival time. It also verifies the correctness of the Pareto frontier and the effectiveness of the model built in this embodiment.

[0147] Table 3. Service allocation and service duration of valet members under the two schemes.

[0148]

[0149] Driven by the "dual carbon" goals, the electric vehicle industry is developing rapidly, but the operational efficiency of charging infrastructure has become a key bottleneck. This embodiment focuses on the process reengineering and system optimization of valet charging services, proposing a sustainable, asset-light operation paradigm from the perspectives of scheduling optimization and resource sharing. By constructing a dynamic scheduling model with "decoupled pickup and return," designing a government-enterprise cooperative charging pile sharing mechanism, and applying an improved Epsilon constraint algorithm for solving the problem, simulation experiments based on a 17-node test road network yield the following conclusions:

[0150] (1) Extreme cost minimization or revenue maximization schemes are unlikely to achieve optimal overall system efficiency. However, the Pareto equilibrium solution obtained through dual-objective optimization can achieve a revenue increase of more than 200% with a cost increase of less than 10%, thus realizing a qualitative leap in operational efficiency. At the same time, the optimized "hub-radius" service network can significantly reduce the valet's on-the-go time, improve the turnover rate of charging piles, and avoid time and space mismatches such as station congestion and equipment idleness during disordered charging.

[0151] (2) The “decoupling of pick-up and return” service process breaks the constraints of “car charging and waiting”, freeing valet operators from passive waiting and achieving a high degree of connection between valet charging tasks in the time and space dimensions. This not only directly reduces operating costs, but also improves the flexibility of valet charging services, laying the operational foundation for the further expansion of valet charging services into a one-stop service platform for “vehicle energy and maintenance management”.

[0152] (3) The cooperation model of “government-enterprise collaboration and resource sharing” not only reduces the infrastructure investment of the platform, but also improves the turnover rate and service response capability of charging piles through the professional scheduling of the platform, forming a virtuous cycle of “business efficiency improvement” and “social resource optimization”, and providing a new idea for the intensive operation of urban charging infrastructure.

[0153] Example 2

[0154] Embodiment 2 of the present invention introduces an optimized scheduling system for valet charging of electric vehicles.

[0155] like Figure 8 The electric vehicle valet charging optimization scheduling system shown includes:

[0156] The acquisition module is configured to acquire electric vehicle valet charging service orders that include at least customer location and charging demand information.

[0157] The building module is configured to construct a bi-objective mixed integer linear programming model with the objective functions of minimizing total cost and maximizing revenue, based on the acquired valet charging service orders, valet status, and charging station information.

[0158] The solver module is configured to solve the objective function of the constructed bi-objective mixed integer linear programming model to obtain the scheduling scheme for valet charging of electric vehicles.

[0159] The scheduling module is configured to assign valet charging staff to pick up and charge electric vehicles based on the customer's location and scheduling plan. After charging is completed, the valet charging staff will then be assigned to pick up and return the vehicles to the charging station, thus completing the optimized scheduling of valet charging for electric vehicles.

[0160] The detailed steps are the same as those of the electric vehicle valet charging optimization scheduling method provided in Example 1, and will not be repeated here.

[0161] Example 3

[0162] Embodiment 3 of the present invention provides a computer-readable storage medium.

[0163] A computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the valet charging optimization scheduling method for electric vehicles as described in Embodiment 1 of the present invention.

[0164] The detailed steps are the same as those of the electric vehicle valet charging optimization scheduling method provided in Example 1, and will not be repeated here.

[0165] Example 4

[0166] Embodiment 4 of the present invention provides an electronic device.

[0167] An electronic device includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, it implements the steps in the valet charging optimization scheduling method for electric vehicles as described in Embodiment 1 of the present invention.

[0168] The detailed steps are the same as those of the electric vehicle valet charging optimization scheduling method provided in Example 1, and will not be repeated here.

[0169] Example 5

[0170] Embodiment 5 of the present invention provides a computer program product.

[0171] A computer program product includes software code, wherein the program in the software code performs the steps of the valet charging optimization scheduling method for electric vehicles as described in Embodiment 1 of the present invention.

[0172] The detailed steps are the same as those of the electric vehicle valet charging optimization scheduling method provided in Example 1, and will not be repeated here.

[0173] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.

[0174] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0175] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0176] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1The steps of the function specified in one or more boxes.

[0177] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the invention.

[0178] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

[0179] The above description is merely a preferred embodiment of this practice and is not intended to limit the scope of this practice. Various modifications and variations can be made to this practice by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this practice should be included within the protection scope of this practice.

Claims

1. A method for optimizing and scheduling of guest charging of an electric vehicle, applied to a guest charging service platform, characterized in that, include: Obtain electric vehicle valet charging service orders that include at least the customer's location and charging needs. Based on the obtained valet charging service orders, valet status, and charging station information, a bi-objective mixed-integer linear programming model is constructed with the objective functions of minimizing total cost and maximizing revenue. The various parameters and key decision variables required for model construction are defined as follows: I is the set of customer-employee resting points, i ; K is the set of charging stations, k ; J is the set of customer points, j ; E is the set of customer-employees, ; T is the total duration of the customer-employee charging activity, where any one moment is represented as t; is the actual travel time between nodes; Cost1 is the unit time driving cost of the valet driving the folding tram; Cost2 is the unit time driving cost of a valet driving a customer's vehicle; For the initial moment, substitute for the guest Located at rest point i, ,otherwise 0; Cap represents the number of charging piles in social charging stations; The proportion of charging piles allocated from social charging stations to valet platforms; M is a large positive integer; D is the total number of orders received by the system; V is the charging speed of the charging piles; For customers The demand for vehicle charging. The service fee per unit time for a valet driver to drive a customer's vehicle; The service fee per unit time for a valet to drive a folding vehicle to the customer's location; The basic service fee charged per charge for charging customers; For charging stations The cost of the agreement; Penalty cost per unit for orders that are not completed; The percentage of revenue that the agency platform takes from the client's earnings. = ； = ； = ； = ； Let t represent the number of available charging stations in charging station k during time period t. The charging time of customer j's vehicle at the charging station; The departure time for valet e to serve customer j in picking up their car; The departure time for valet e to serve customer j in returning the car; Set a penalty cost for incomplete orders, which is the total number of orders D minus the number of orders that were returned within the specified time, multiplied by [the penalty cost]. Based on the valet's service process, the driving cost is obtained. The first objective function, i.e., the total operating cost, is expressed as: The service fee for a valet to drive a folding electric vehicle to the customer's location is The service fee for a valet driver to take the user's vehicle to the charging station is... The entire valet service process includes two round trips for the customer to and from the charging station, represented by twice the pick-up fee, plus a base fee for a single service. The second objective function is expressed as: The constraints of the objective function include: charging station constraints: Formulas (3) and (4) indicate that any vehicle pick-up and return service must be performed at the selected protocol charging station; Formula (5) restricts the use of charging stations once they are built; Formula (6) indicates that for any protocol charging station at any time, the number of charging vehicles allocated by the system is less than or equal to the charging station capacity. State transitivity constraints: Formula (7) represents the number of available charging piles in the charging station at time t=0; Formula (8) represents the number of charging piles available in the charging station during time period t. The number of available charging piles is related to the number of vehicles entering and leaving the charging station during the t-1 time period; Formula (9) represents the number of vehicles leaving the station at t=0 time. The status of the valet's stay depends on the valet's initial location and task allocation during the initial time period; Formula (10) represents the valet's position at rest point i at time t. The number is calculated by subtracting the number of agents who left at the current moment from the number of agents who returned at the current moment, and then adding the number of agents who returned at the current moment. Charging service constraints: Formula (11) restricts the valet service personnel The service is unique; formulas (12) and (13) represent any customer The vehicle pick-up and return tasks can be served at most once; Formula (14) not only limits the flow conservation of entering and leaving the charging station, but also stipulates that the customer's vehicle pick-up and return services are at the same charging station; Formula (15) is the formula for calculating the charging time; Formula (16) connects the vehicle pick-up task and the vehicle return task, that is, it ensures that customer j's vehicle can only be picked up by the valet after it is fully charged. Charging time constraints: Formulas (17) and (18) are expressions for the departure time of valet e serving customer j in the car pick-up task; Formulas (19) and (20) are expressions for the departure time of valet e serving customer j in the car return task; Formula (21) represents the latest time limit for vehicle delivery to customer for the car return task; Formula (22) is the value constraint of the variable. Solve the objective function of the constructed bi-objective mixed integer linear programming model to obtain the scheduling scheme for valet charging of electric vehicles; Based on the customer's location and the scheduling plan, valet charging staff are assigned to pick up and charge the vehicle. Once charging is complete, valet charging staff are then assigned to retrieve and return the vehicle to the charging station, thus optimizing the scheduling of valet charging for electric vehicles.

2. The valet charging optimization scheduling method for electric vehicles as described in claim 1, characterized in that, An improved Epsilon constraint algorithm based on interval constraints is used to solve the objective function of the constructed bi-objective mixed integer linear programming model, and the Pareto optimal solution set is obtained, which includes at least the protocol charging station site selection scheme and the valet task scheduling plan.

3. The valet charging optimization scheduling method for electric vehicles as described in claim 1, characterized in that, The steps of the improved Epsilon constraint algorithm based on interval constraints include: Solve the first objective function and the second objective function respectively to obtain the minimum cost and its corresponding revenue, and the maximum revenue and its corresponding cost; A number of constraint values ​​are evenly selected within the range from the minimum cost to the maximum cost. The profit constraint is transformed into an interval constraint, and a feasible solution of the first objective function is found under each constraint interval. Collect the feasible solutions obtained, compare them using Pareto dominance relations, filter and output all non-dominated solutions to form a Pareto optimal solution set.

4. The system of the valet charging optimization scheduling method for electric vehicles as described in any one of claims 1-3, characterized in that, include: The acquisition module is configured to acquire electric vehicle valet charging service orders that include at least customer location and charging demand information. The building module is configured to construct a bi-objective mixed integer linear programming model with the objective functions of minimizing total cost and maximizing revenue, based on the acquired valet charging service orders, valet status, and charging station information. The solver module is configured to solve the objective function of the constructed bi-objective mixed integer linear programming model to obtain the scheduling scheme for valet charging of electric vehicles. The scheduling module is configured to assign valet charging staff to pick up and charge electric vehicles based on the customer's location and scheduling plan. After charging is completed, the valet charging staff will then be assigned to pick up and return the vehicles to the charging station, thus completing the optimized scheduling of valet charging for electric vehicles.

5. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the valet charging optimization scheduling method for electric vehicles as described in any one of claims 1-3.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the program, it implements the steps of the valet charging optimization scheduling method for electric vehicles as described in any one of claims 1-3.

7. A computer program product, comprising software code, characterized in that, The program in the software code performs the steps of the valet charging optimization scheduling method for electric vehicles as described in any one of claims 1-3.

Images