A vehicle charging intelligent scheduling method, system, device and computer readable storage medium

Abstract

The application discloses a kind of vehicle charging intelligent scheduling method, system, equipment and computer readable storage medium, method includes: obtaining the multi-source fusion dataset of vehicle;SOC prediction trajectory data is generated based on temperature compensation model, determine to be charged vehicle;According to multidimensional factor, priority score is calculated;Based on priority score and charging pile, personnel and the constraint condition of warehouse plan generation charging operation scheme;Control charging equipment to execute charging operation.The application predicts SOC trend by temperature compensation, realizes active prevention overdischarge;Through multidimensional priority score and resource constraint optimization, improve charging resource utilization, solve the problem caused by state monitoring lag, single scheduling dimension and model parameter fixation, reduce battery overdischarge rate and manual operation cost.

Description

Technical Field

[0001] This application relates to the field of vehicle dispatching, specifically to a vehicle charging intelligent dispatching method, system, device, and computer-readable storage medium. Background Technology

[0002] With the increasing prevalence of new energy logistics vehicles, the demand for battery maintenance and management of vehicles in warehouses is growing. Ensuring the health of batteries and their readiness to respond to outbound instructions during long-term vehicle parking and waiting periods is a crucial aspect of logistics and warehousing management.

[0003] In related technologies, the charging scheduling of inventory vehicles typically employs onboard terminals or battery management systems to monitor battery status. Specific scheduling strategies generally involve: real-time monitoring of the battery's current state of charge (SOC); issuing an alarm when the SOC value falls below a preset fixed threshold; and arranging charging queues according to a first-come, first-served basis or solely based on the current SOC value.

[0004] However, the existing technologies mentioned above have the following technical problems: First, the existing technologies only make judgments based on the current static SOC value and cannot perceive the battery self-discharge trend. When the battery is found to be low, the battery may have already been over-discharged. Furthermore, the vehicle scheduling strategy only considers the single factor of battery power, resulting in a single scheduling dimension. Vehicles that urgently need to leave the warehouse may not be able to charge in time due to queuing. Summary of the Invention

[0005] This application provides a vehicle charging intelligent scheduling method, system, device, and computer-readable storage medium, which can solve the technical problems of lagging status monitoring and inability to charge in a timely manner in the prior art.

[0006] In a first aspect, embodiments of this application provide a vehicle charging intelligent scheduling method, characterized in that the vehicle charging intelligent scheduling method includes: Based on the multi-source fusion datasets of each vehicle and the historical discharge curve information of each vehicle, it is determined whether each vehicle needs to be charged and the vehicles to be charged are identified. The multi-source fusion datasets include the original vehicle dimension data, vehicle storage location dimension information and vehicle battery health dimension data. Based on the target data of each of the vehicles to be charged, a priority score for each vehicle to be charged is calculated. A charging operation plan is generated based on the priority score and preset constraints of each of the vehicles to be charged. The charging operation plan includes the attribute information, priority and charging information of each of the vehicles to be charged. The charging equipment is controlled to perform charging operations on each of the vehicles to be charged according to the charging operation plan.

[0007] In conjunction with the first aspect, in one implementation, determining whether each vehicle needs charging based on the acquired multi-source fusion dataset of each vehicle and the historical discharge curve information of each vehicle includes: Based on historical discharge curve information and multi-source fusion datasets of each vehicle, SOC prediction trajectory data for each vehicle is generated. Based on the comparison between the SOC predicted trajectory data and the preset safety threshold, it is determined whether the vehicle needs to be charged.

[0008] In conjunction with the first aspect, in one implementation, determining whether the vehicle needs to be charged based on the comparison result between the SOC predicted trajectory data and a preset safety threshold includes: Determine whether the SOC predicted trajectory data falls below the preset safety threshold within a preset time period; If the SOC predicted trajectory data is lower than the preset safety threshold within the preset time period, it is determined that the vehicle needs to be charged and the vehicle is identified as a vehicle to be charged. If the SOC predicted trajectory data is higher than the preset safety threshold within the preset time period, then it is determined that the vehicle does not need to be charged.

[0009] In conjunction with the first aspect, in one implementation, generating SOC prediction trajectory data for each of the vehicles based on historical discharge curve information and multi-source fusion datasets of each vehicle includes: Ambient temperature data is extracted from the vehicle's original dimensional data, and the ambient temperature data is input into the Arrhenius model to calculate the temperature compensation coefficient. Based on historical discharge curve information, temperature compensation coefficient, vehicle original dimension data, vehicle storage dimension information, and vehicle battery health dimension data, the SOC change curve within a preset time period is predicted in a rolling manner to obtain SOC prediction trajectory data.

[0010] In conjunction with the first aspect, in one implementation, the step of calculating the priority score of each of the vehicles to be charged based on the acquired target data of each vehicle to be charged includes: Multiple dimension factor values ​​are obtained from the target data of each of the vehicles to be charged; The priority score of each vehicle to be charged is obtained by weighting the values ​​of the multiple dimensional factors using a preset weighting formula.

[0011] In conjunction with the first aspect, in one implementation, generating a charging operation plan based on the priority scores and preset constraints of each of the vehicles to be charged includes: With the goal of maximizing the total priority weighted sum, the charging information of each of the vehicles to be charged is solved using a solution algorithm based on preset constraints to obtain the charging operation plan. The preset constraints include the number of available charging piles, staff shift capacity, and outbound plans.

[0012] In conjunction with the first aspect, in one implementation, the step of using the acquired multi-source fusion dataset of each vehicle includes: Real-time battery status data of the vehicle is collected by the vehicle terminal to obtain the vehicle's original dimensional data. By collecting vehicle storage location information and health record data through the logistics management system, we can obtain vehicle storage location dimension information and vehicle battery health dimension data. Vehicle outbound plan data is collected through the supply chain management system; The original vehicle dimension data, the vehicle storage location dimension information, the vehicle battery health dimension data, and the outbound plan data are timestamped and cleaned. The cleaned data is then fused to generate the multi-source fused dataset.

[0013] Secondly, embodiments of this application provide a vehicle charging intelligent scheduling system, characterized in that the vehicle charging intelligent scheduling system includes: The charging determination module is used to determine whether each vehicle needs to be charged and to identify the vehicle to be charged based on the multi-source fusion dataset of each vehicle and the historical discharge curve information of each vehicle. The multi-source fusion dataset includes the original dimension data of the vehicle, the dimension information of the vehicle storage location and the dimension data of the vehicle battery health. The priority calculation module is used to calculate the priority score of each of the vehicles to be charged based on the target data of each vehicle to be charged obtained. The scheme generation module is used to generate a charging operation scheme based on the priority score and preset constraints of each of the vehicles to be charged. The charging operation scheme includes the attribute information, priority and charging information of each of the vehicles to be charged. The operation control module is used to control the charging equipment to perform charging operations on each of the vehicles to be charged in accordance with the charging operation plan.

[0014] Thirdly, embodiments of this application provide a vehicle charging intelligent scheduling device, characterized in that the vehicle charging intelligent scheduling device includes a processor, a memory, and a vehicle charging intelligent scheduling program stored in the memory and executable by the processor, wherein when the vehicle charging intelligent scheduling program is executed by the processor, it implements the steps of the vehicle charging intelligent scheduling method as described in any one of claims 1 to 7.

[0015] Fourthly, embodiments of this application provide a computer-readable storage medium, characterized in that the computer-readable storage medium stores a vehicle charging intelligent scheduling program, wherein when the vehicle charging intelligent scheduling program is executed by a processor, it implements the steps of the vehicle charging intelligent scheduling method as described in any one of claims 1 to 7.

[0016] The beneficial effects of the technical solutions provided in this application include at least the following: By predicting battery status, the system anticipates battery SOC trends from current static values ​​to future dynamic trajectories. Priority scoring quantifies charging demands from a single energy level to a comprehensive business dimension. Based on a constraint-driven scheduling optimization engine, this application addresses the technical problems of high battery over-discharge risk due to lagging status monitoring and low charging resource utilization due to a single scheduling dimension. By employing predictive and multi-constraint optimization scheduling, it improves proactive battery maintenance and the balanced allocation efficiency of charging resources, avoids conflicts between charging operations and outbound plans, and enhances vehicle turnover efficiency in logistics warehousing. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating an embodiment of a vehicle charging intelligent scheduling method provided in this application. Figure 2 This is a schematic diagram of the SOC prediction trajectory generation and charging determination process provided in an embodiment of this application; Figure 3 This is a schematic diagram of the multi-constraint priority scheduling logic provided in the embodiments of this application; Figure 4 This is a schematic diagram of the functional modules of a vehicle charging intelligent scheduling system provided in an embodiment of this application. Detailed Implementation

[0018] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0019] First, some of the technical terms used in this application will be explained to help those skilled in the art understand this application.

[0020] SOC: State of charge, refers to the ratio of the remaining capacity of a battery to the capacity of a fully charged battery, usually expressed as a percentage. SOH: Battery Health Status, reflects the rate at which the battery retains its current capacity relative to its rated capacity, and is used to assess the degree of battery aging; TBOX: Vehicle-mounted telematics terminal, used to collect vehicle battery data and upload it via network; PDCA closed loop: refers to the quality management cycle of Plan, Do, Check, Act. In this application, it refers to the process of adjusting model parameters by comparing predicted and actual data. To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0021] This application provides a vehicle charging intelligent scheduling method applied to logistics and warehousing scenarios. It requires the maintenance and management of the battery status of inventory new energy vehicles. The system needs to achieve proactive prediction of charging demand, multi-dimensional priority ranking, and optimal scheduling under resource constraints, solving the problems of passive response, resource conflicts, and poor model adaptability in traditional charging management.

[0022] Reference Figure 1 , Figure 1 The diagram shown is a flowchart of a vehicle charging intelligent scheduling method provided by the present invention. Figure 1 As shown, the method includes the following steps: Step S10: Based on the multi-source fusion dataset of each vehicle and the historical discharge curve information of each vehicle, determine whether each vehicle needs to be charged and identify the vehicles to be charged.

[0023] Specifically, the system first collects real-time battery status data of the vehicle through the vehicle-mounted terminal (TBOX) to obtain the vehicle's raw dimensional data, including voltage, current, temperature, and current SOC; it then collects the vehicle's storage location information and health record data through the logistics management system (VLS) to obtain vehicle storage location dimensional information and vehicle battery health dimensional data (SOH); and finally, it collects the vehicle's outbound plan data through the supply chain management system (SCM). During the generation of the multi-source fusion dataset, data time-series alignment, outlier removal, and SOC rationality verification are performed. Time-series alignment: Based on the TBOX upload timestamp, the nearest neighbor matching method is used to align the VLS storage location data and SCM record data to the same time axis, with an alignment tolerance of ±1 hour. Outlier removal: Outliers are removed from the SOC time-series data using the 3σ criterion. Time stamps are marked as abnormal. A logical threshold is used to verify the voltage data. When the total voltage exceeds the nominal voltage by ±20%, it is marked as abnormal. SOC rationality verification: The SOC reported by TBOX is compared with the SOC estimated by BMS. If the deviation is >5% and continues for 3 sampling cycles, the SOC estimated by BMS (Battery Management System) shall be taken as the standard and the TBOX data shall be marked as abnormal. If there is a significant contradiction between voltage and SOC, such as SOC >50% but total voltage <70% of nominal voltage, a data quality alarm is triggered. The system performs timestamp alignment and data cleaning on the above multi-source data, removes outliers, and generates a multi-source fusion dataset.

[0024] In this embodiment, determining whether a vehicle needs charging is based on future trend predictions, referring to... Figure 2 Step S10 specifically includes: First, based on historical discharge curve information and multi-source fusion datasets for each vehicle, SOC prediction trajectory data for each vehicle is generated. Since the battery self-discharge rate is significantly affected by ambient temperature, this embodiment introduces a physical model for correction, specifically including: Ambient temperature data is extracted from the original vehicle dimensional data. Using a temperature compensation model based on the Arrhenius formula, the temperature-compensated battery self-discharge rate is calculated based on the ambient temperature data. The temperature compensation model based on the Arrhenius formula is expressed as follows: ,in, The self-discharge rate of the battery after temperature compensation represents the percentage decrease in SOC per day. The baseline self-discharge rate constant was obtained by calibrating the SOC decay data of the same batch of batteries at a standard temperature of 25°C. Battery activation energy is a physical parameter that characterizes the degree of influence of temperature on the self-discharge rate. The ideal gas constant is 8.314. The average daily ambient temperature is collected by temperature sensors in the storage area and is calculated as the daily average. Next, based on the current SOC value and the temperature-compensated battery self-discharge rate, the total decrease in SOC during the prediction period is calculated using the SOC trajectory rolling prediction formula, which is as follows: ,in, , This represents the total decrease in SOC during the forecast period. The temperature-compensated self-discharge rate for day i. The time step for day i is 86,400 seconds (i.e., 1 day), and n is the number of days to predict, which can be 7, 14, or 30 days. The system recalculates using the latest actual SOC data every 24 hours. And update the predicted trajectory to form SOC predicted trajectory data; Secondly, based on the comparison results between the SOC predicted trajectory data and the preset safety threshold, it is determined whether the vehicle needs to be charged. The judgment logic is: to determine whether there are any points in the SOC predicted trajectory data that are lower than the preset safety threshold within a preset time period. If the SOC predicted trajectory data is lower than the preset safety threshold within the preset time period, the vehicle is determined to need charging and is identified as a vehicle to be charged; otherwise, if the predicted battery level is consistently higher than the safety threshold, the vehicle will not be included in this scheduling and will continue to be monitored. This example also includes alarm trigger determination: when the predicted SOC is less than the 30% threshold, an alarm is automatically triggered and the vehicle enters the scheduling queue; the threshold can be dynamically adjusted. Determination rules: when the rolling forecast shows that the vehicle's SOC will drop below 30% within the next 7 days, a level 2 alarm is triggered and the vehicle enters the scheduling queue; when the current SOC is already below 30% or is predicted to drop below 20% within 3 days, a level 1 alarm is triggered, allowing the vehicle to jump the queue. The connection after entering the scheduling queue: the vehicle's VIN, current SOC, predicted threshold arrival time, SOH, parking duration, and storage location information that triggered the alarm are packaged into a data packet of vehicles to be scheduled and pushed to the priority scoring module as one of the scoring input factors.

[0025] Step S20: Calculate the priority score of each of the vehicles to be charged based on the target data of each vehicle to be charged.

[0026] Specifically, when charging resources are limited, vehicles must be sorted, and the system obtains multiple dimensional factor values ​​from the target data of each vehicle to be charged. The multiple dimensions of factors include at least: SOC urgency factor, parking duration factor, battery health factor, and outbound urgency factor; among them, the SOC urgency factor is negatively correlated with the predicted minimum charge, the parking duration factor is positively correlated with the age of the battery, the battery health factor is negatively correlated with the SOH, and the outbound urgency factor is negatively correlated with the time remaining before the planned outbound date. The system calculates the priority score using a multi-objective comprehensive priority scoring formula, which is as follows: ,in, The overall priority score ranges from 0 to 100. The higher the value, the higher the charging priority; Weighting coefficient, default value , , , =0.15, supports dynamic adjustment based on season or business stage, with dynamic weight adjustment rules, such as during the summer high-temperature period (June-August). Increased to 0.40 (SOC urgency weight increased); one week before bulk shipment. Increased to 0.25 (urgency weight increased); when inventory turnover is low. Increased to 0.35 (time weighting increased); The formulas for calculating each dimension factor are as follows: ,in t represents the current battery state of charge (%), 80% is the target SOC for charging, and 30% is the safety threshold. The lower the SOC, the better. The higher; The number of days of parking is calculated from the timestamp of entry into the VLS system. ,in The current battery health status (%) is obtained from the SCM system BMS file; The countdown days for shipment are obtained from the SCM outbound plan.

[0027] Step S30: Generate a charging operation plan based on the priority score and preset constraints of each of the vehicles to be charged.

[0028] Specifically, the charging operation plan includes the attribute information (such as VIN, parking space), priority, and charging information (such as suggested charging time period and assigned charging pile number) of each of the vehicles to be charged. Reference Figure 3 The process of generating a charging operation plan includes: establishing a 0-1 integer programming model with the goal of maximizing the total priority score, and using a solution algorithm to solve for the optimal scheduling plan under constraints of equipment, personnel, window, and health. The objective function of the integer programming optimization model is: ,in, The total score for the scheduling plan is... Rate the priority of vehicles. The variable is 0-1 (0 = not scheduled, 1 = scheduled into the current batch). The constraints include: the number of vehicles in a single batch is less than or equal to the equipment limit, the number of vehicles in a single batch is less than or equal to the personnel processing capacity limit, and the number of vehicles in a single batch is less than or equal to the maximum allowable time window for outbound shipments. The choice of algorithm is based on the size of the vehicles to be scheduled: when the number of vehicles to be charged n≤50, the branch and bound method is used to find the exact solution; when the number of vehicles to be charged n>50, the genetic algorithm is used to find the approximate solution. The genetic algorithm parameters are configured as follows: population size 100, crossover rate 0.8, mutation rate 0.05, and 100 generations.

[0029] The output results are the optimal subset of charging vehicles and the corresponding charging pile and personnel allocation scheme.

[0030] The preset constraints include, but are not limited to: Charging pile availability limit: The number of vehicles charging at the same time cannot exceed the total number of available charging piles. Personnel shift capacity constraints: Charging operations require manual insertion or confirmation of the charging gun, and the workload allocated within the same shift cannot exceed the maximum processing capacity of the personnel. Outbound plan constraints: Vehicles scheduled for outbound must complete charging and reach the target SOC before the outbound time window; Battery health constraints: Abnormal batteries with SOH below a certain value will not be included in the regular scheduling and will directly trigger a special alarm.

[0031] Step S40: Control the charging equipment to perform charging operations on each of the vehicles to be charged according to the charging operation plan.

[0032] Specifically, the system converts the generated charging operation plan into a specific work order and sends it to the operator's handheld terminal or charging control device. The operator finds the vehicle in the corresponding storage location for charging according to the instructions. The system monitors the charging progress in real time. When the SOC reaches the target value, it automatically archives the data and releases the charging resources.

[0033] SOC Compliance Verification: After charging is complete, the BMS automatically reports the actual SOC. If it meets the standard, it is archived. The standard is: a final SOC reported by the BMS after charging is ≥80% to be considered compliant. If the final SOC is between 75% and 80%, it is recorded as "basically compliant," and the reasons are analyzed, such as charging interruption or insufficient charging pile power. If the final SOC is <75%, it is considered "non-compliant," and automatic rescheduling is triggered, adding the vehicle to the priority queue for the next day. Archiving operation: For compliant vehicles, a "Charging Completion Record" is generated, including VIN, SOC before charging, SOC after charging, actual charging duration, charging pile number used, operator's employee number, and charging start / end timestamp. The record is written to the "Charging History Table" in the database as a data source for PDCA iteration. At the same time, the "Last Charging Time" field of the vehicle in the VLS system is updated.

[0034] PDCA Iteration: Feedback on the deviation between actual SOC and predicted SOC automatically triggers monthly model parameter updates. Prediction Deviation Calculation: After each charging cycle, the predicted and actual SOC trajectories for the vehicle over the previous 7 days are extracted, and the root mean square error (RMSE) is calculated as √(Σ(predicted SOC_i - actual SOC_i)² / n). If RMSE > 5%, the prediction model is considered to have a significant bias. Model Parameter Update: The model iteration task is automatically executed at midnight on the 1st of each month, summarizing the RMSE data of all vehicles from the previous month, and recalibrating the Arrhenius equation using the least squares method. The parameters minimize the overall RMSE. The updated parameters are distributed to the prediction engine through the configuration center and take effect the following month. Weight parameter optimization: The satisfaction of the scheduling results of each rating factor in the previous month is statistically analyzed. If the adjustment direction of a factor weight is consistent with the improvement direction of satisfaction, the adjustment is fixed. Otherwise, it is reverted to the original weight, forming an A / B test closed loop for weight configuration.

[0035] This embodiment transforms the original charging management, which relied on manual experience, into data-driven intelligent scheduling through the above steps. This avoids over-discharging of batteries, balances the charging load, and ensures efficient logistics outbound operations.

[0036] Reference Figure 4 , Figure 4 This diagram illustrates the functional modules of a vehicle charging intelligent scheduling system provided in this embodiment. This system corresponds to the method described in Embodiment 1. Figure 4 As shown, the intelligent vehicle charging scheduling system includes: The charging determination module is used to determine whether each vehicle needs to be charged and to identify the vehicle to be charged based on the multi-source fusion dataset of each vehicle and the historical discharge curve information of each vehicle. The multi-source fusion dataset includes the original dimension data of the vehicle, the dimension information of the vehicle storage location and the dimension data of the vehicle battery health. The priority calculation module is used to calculate the priority score of each of the vehicles to be charged based on the target data of each vehicle to be charged obtained. The scheme generation module is used to generate a charging operation scheme based on the priority score and preset constraints of each of the vehicles to be charged. The charging operation scheme includes the attribute information, priority and charging information of each of the vehicles to be charged. The operation control module is used to control the charging equipment to perform charging operations on each of the vehicles to be charged in accordance with the charging operation plan.

[0037] The specific functional implementation details of each module can be found in the description of the method steps in Embodiment 1, and will not be repeated here. The system can be deployed on a cloud server and interact with TBOX, VLS, SCM and charging equipment through API interfaces.

[0038] This application also provides a vehicle charging intelligent scheduling device. The vehicle charging intelligent scheduling device includes a processor, a memory, and a vehicle charging intelligent scheduling program stored in the memory and executable by the processor. When the vehicle charging intelligent scheduling program is executed by the processor, it implements the steps of the vehicle charging intelligent scheduling method as described in Embodiment 1.

[0039] This application also provides a computer-readable storage medium. The computer-readable storage medium stores a vehicle charging intelligent scheduling program, wherein when executed by a processor, the vehicle charging intelligent scheduling program implements the steps of the vehicle charging intelligent scheduling method as described in Embodiment 1.

[0040] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0041] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made based on the description and drawings of this application, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application. For example, although the above embodiments use a temperature compensation model based on the Arrhenius formula to illustrate temperature compensation, those skilled in the art can also use other predictive models that can use environmental data to correct self-discharge trends, all of which fall within the protection scope of this application.

[0042] It should be noted that the sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0043] The terms "comprising" and "having," and any variations thereof, in the specification, claims, and accompanying drawings of this application are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus. The terms "first," "second," and "third," etc., are used to distinguish different objects, etc., and do not indicate a sequence, nor do they limit "first," "second," and "third" to different types.

[0044] In the description of the embodiments of this application, terms such as "exemplary," "for example," or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "exemplary," "for example," or "for instance" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of terms such as "exemplary," "for example," or "for instance" is intended to present the relevant concepts in a concrete manner.

[0045] In the description of the embodiments of this application, unless otherwise stated, " / " means "or". For example, A / B can mean A or B. The "and / or" in the text is merely a description of the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. In addition, in the description of the embodiments of this application, "multiple" means two or more.

[0046] In some processes described in the embodiments of this application, multiple operations or steps are included in a specific order. However, it should be understood that these operations or steps may not be executed in the order they appear in the embodiments of this application, or they may be executed in parallel. The sequence number of the operation is only used to distinguish different operations, and the sequence number itself does not represent any execution order. In addition, these processes may include more or fewer operations, and these operations or steps may be executed sequentially or in parallel, and these operations or steps may be combined.

[0047] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

Claims

1. A method for intelligent scheduling of vehicle charging, characterized in that, The aforementioned intelligent vehicle charging scheduling method includes: Based on the multi-source fusion datasets of each vehicle and the historical discharge curve information of each vehicle, it is determined whether each vehicle needs to be charged and the vehicles to be charged are identified. The multi-source fusion datasets include the original vehicle dimension data, vehicle storage location dimension information and vehicle battery health dimension data. Based on the target data of each of the vehicles to be charged, a priority score for each vehicle to be charged is calculated. A charging operation plan is generated based on the priority score and preset constraints of each of the vehicles to be charged. The charging operation plan includes the attribute information, priority and charging information of each of the vehicles to be charged. The charging equipment is controlled to perform charging operations on each of the vehicles to be charged according to the charging operation plan.

2. The intelligent vehicle charging scheduling method as described in claim 1, characterized in that, The step of determining whether each vehicle needs charging based on the acquired multi-source fusion dataset and historical discharge curve information of each vehicle includes: Based on historical discharge curve information and multi-source fusion datasets of each vehicle, SOC prediction trajectory data for each vehicle is generated. Based on the comparison between the SOC predicted trajectory data and the preset safety threshold, it is determined whether the vehicle needs to be charged.

3. The intelligent vehicle charging scheduling method as described in claim 2, characterized in that, The step of determining whether the vehicle needs to be charged based on the comparison result between the SOC predicted trajectory data and the preset safety threshold includes: Determine whether the SOC predicted trajectory data falls below the preset safety threshold within a preset time period; If the SOC predicted trajectory data is lower than the preset safety threshold within the preset time period, it is determined that the vehicle needs to be charged and the vehicle is identified as a vehicle to be charged. If the SOC predicted trajectory data is higher than the preset safety threshold within the preset time period, then it is determined that the vehicle does not need to be charged.

4. The intelligent vehicle charging scheduling method as described in claim 2, characterized in that, The method for generating SOC prediction trajectory data for each vehicle based on historical discharge curve information and multi-source fusion datasets of each vehicle includes: Ambient temperature data is extracted from the vehicle's original dimensional data, and the ambient temperature data is input into the Arrhenius model to calculate the temperature compensation coefficient. Based on historical discharge curve information, temperature compensation coefficient, vehicle original dimension data, vehicle storage dimension information, and vehicle battery health dimension data, the SOC change curve within a preset time period is predicted in a rolling manner to obtain SOC prediction trajectory data.

5. The intelligent vehicle charging scheduling method as described in claim 1, characterized in that, The step of calculating the priority score for each of the vehicles to be charged based on the acquired target data includes: Multiple dimension factor values ​​are obtained from the target data of each of the vehicles to be charged; The priority score of each vehicle to be charged is obtained by weighting the values ​​of the multiple dimensional factors using a preset weighting formula.

6. The intelligent vehicle charging scheduling method as described in claim 1, characterized in that, The step of generating a charging operation plan based on the priority scores and preset constraints of each of the vehicles to be charged includes: With the goal of maximizing the total priority weighted sum, the charging information of each of the vehicles to be charged is solved using a solution algorithm based on preset constraints to obtain the charging operation plan. The preset constraints include the number of available charging piles, staff shift capacity, and outbound plans.

7. The intelligent vehicle charging scheduling method as described in claim 1, characterized in that, The multi-source fusion dataset obtained from each vehicle includes: Real-time battery status data of the vehicle is collected by the vehicle terminal to obtain the vehicle's original dimensional data. By collecting vehicle storage location information and health record data through the logistics management system, we can obtain vehicle storage location dimension information and vehicle battery health dimension data. Vehicle outbound plan data is collected through the supply chain management system; The original vehicle dimension data, the vehicle storage location dimension information, the vehicle battery health dimension data, and the outbound plan data are timestamped and cleaned. The cleaned data is then fused to generate the multi-source fused dataset.

8. A vehicle charging intelligent scheduling system, characterized in that, The intelligent vehicle charging scheduling system includes: The charging determination module is used to determine whether each vehicle needs to be charged and to identify the vehicle to be charged based on the multi-source fusion dataset of each vehicle and the historical discharge curve information of each vehicle. The multi-source fusion dataset includes the original dimension data of the vehicle, the dimension information of the vehicle storage location and the dimension data of the vehicle battery health. The priority calculation module is used to calculate the priority score of each of the vehicles to be charged based on the target data of each vehicle to be charged obtained. The scheme generation module is used to generate a charging operation scheme based on the priority score and preset constraints of each of the vehicles to be charged. The charging operation scheme includes the attribute information, priority and charging information of each of the vehicles to be charged. The operation control module is used to control the charging equipment to perform charging operations on each of the vehicles to be charged in accordance with the charging operation plan.

9. A vehicle charging intelligent scheduling device, characterized in that, The vehicle charging intelligent scheduling device includes a processor, a memory, and a vehicle charging intelligent scheduling program stored in the memory and executable by the processor, wherein when the vehicle charging intelligent scheduling program is executed by the processor, it implements the steps of the vehicle charging intelligent scheduling method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a vehicle charging intelligent scheduling program, wherein when the vehicle charging intelligent scheduling program is executed by a processor, it implements the steps of the vehicle charging intelligent scheduling method as described in any one of claims 1 to 7.

Images