Urban distribution vehicle dynamic scheduling system and method based on charging and battery swap cooperation

Abstract

The invention discloses an urban distribution vehicle dynamic scheduling system and method based on charging and battery replacement cooperation, and relates to the technical field of vehicle scheduling, and the method comprises the steps: calling the historical driving record of an urban distribution vehicle, extracting the load state, the driving distance and the consumed electric quantity of the urban distribution vehicle in a time window in the driving record, and obtaining a fitting function of different load states; acquiring urban map data, and marking the position of distribution point equipment and the position of a charging station; acquiring the real-time position and the residual electric quantity of the current vehicle, extracting to-be-replenished equipment, and calculating the replenishment degree of each to-be-replenished equipment; sorting the to-be-replenished equipment, and obtaining the next processing order of the vehicle according to each fitting function, thereby achieving the dynamic scheduling of the urban distribution vehicle. According to the method, multi-source data such as driving records, goods selling records and fitting functions are combined for analysis, dynamic scheduling of urban distribution vehicles is achieved, overall scheduling reasonability and reliability are improved, and efficient and stable operation requirements of the electric urban distribution vehicles can be met.

Description

Technical Field

[0001] This invention relates to the field of vehicle dispatching technology, specifically a dynamic dispatching system and method for urban distribution vehicles based on charging and battery swapping coordination. Background Technology

[0002] In the actual operation of electric urban distribution vehicles, replenishment is usually carried out according to a preset order dispatch sequence. However, when vehicles are on the road, they may run out of power and be unable to meet the range requirements of the remaining delivery tasks, requiring them to go to charging and battery swapping stations for replenishment in a timely manner. Traditional order dispatching methods usually plan order tasks and vehicle replenishment separately, failing to achieve coordinated linkage between charging / battery swapping and transportation scheduling. This can easily lead to conflicts between replenishment arrangements and order execution, resulting in insufficient overall scheduling rationality. If the scheduling plan does not comprehensively consider key factors such as vehicle range status, order distribution, and the location of charging and battery swapping stations, it can cause problems such as increased ineffective empty runs, mid-journey power depletion, and reduced transportation efficiency, failing to meet the needs of efficient and stable electric urban distribution vehicle operation. Summary of the Invention

[0003] The purpose of this invention is to provide a dynamic scheduling system and method for urban distribution vehicles based on charging and battery swapping coordination, so as to solve the problems raised in the prior art.

[0004] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0005] A dynamic scheduling method for urban distribution vehicles based on charging and battery swapping coordination includes the following steps: Historical driving records of urban distribution vehicles are retrieved, positioning sensors are deployed on the vehicles, and the load status, driving distance, and power consumption of the vehicles within a time window are extracted from the driving records. Based on several driving records, a fitting function of the driving distance and power consumption corresponding to different load statuses is obtained. Since the distance a vehicle travels with the same amount of electricity varies depending on its load condition, the fitting function for the change in distance traveled with electricity consumption is different under different load conditions. Therefore, this scheme needs to obtain different fitting functions to make subsequent vehicle scheduling more reliable.

[0006] Urban delivery vehicles are responsible for replenishing equipment at fixed delivery points to complete order tasks, obtaining city map data, and marking the locations of all delivery point equipment and charging / swapping stations in the city on the map; Obtain the real-time location and remaining battery power of the vehicle after completing an order or charging / swapping; extract the equipment to be replenished based on the historical sales records of each delivery point's equipment; and calculate the replenishment level of each equipment based on its location. The replenishment level indicates the priority of replenishing the equipment to be replenished for the current vehicle. The higher the value, the more priority the equipment needs to be replenished. Since the urgency and cargo vacancy rate are higher, it means that the equipment to be replenished needs to be replenished more promptly, and the replenishment level should be higher. However, the greater the actual road travel distance, the higher the travel cost and the longer the travel time for the current vehicle to reach the equipment to be replenished, which will reduce the replenishment level of the equipment. According to the replenishment level, the equipment to be replenished is sorted. Based on the location of the equipment at each distribution point and the location of the charging and battery swapping station, the charging and battery swapping station closest to each equipment to be replenished is obtained. Based on each fitted function, the next processing order for the vehicle is obtained, realizing dynamic scheduling of urban distribution vehicles.

[0007] Preferably, the fitting function for the change in driving distance with electricity consumption under different load conditions includes: Driving records refer to the collection of historical data related to the driving status generated during the driving process of a vehicle, including driving time, vehicle location, driving distance, power consumption, load status, etc.; extract the load status, driving distance and power consumption of urban distribution vehicles within a time window in each driving record. The time window refers to the period of time during which urban distribution vehicles are in a continuous and effective driving state. Load status includes empty, lightly loaded, half-loaded and fully loaded. The driving distance and power consumption of the driving records under different load conditions are obtained, and the fitting function of the driving distance as a function of power consumption under different load conditions is obtained. The fitting function is a linear function.

[0008] Preferably, the equipment for retrieving goods awaiting replenishment includes: Get the real-time vehicle location after the order is completed or after charging / battery swapping, as well as the location of equipment and charging / battery swapping stations at each delivery point; Based on the navigation platform, the actual road distance from the real-time vehicle location to the location of each delivery point equipment is obtained; the historical average speed of the vehicle is acquired, and the estimated time for the vehicle to reach the delivery point equipment is calculated based on the actual road distance from the vehicle to the delivery point equipment. Obtain historical sales records of goods at the distribution point equipment and calculate the vacancy rate of the goods at the distribution point equipment when the estimated time is reached from the current time. If the vacancy rate of goods is greater than the preset vacancy rate threshold, the equipment at the distribution point will be designated as equipment to be replenished, and thus all equipment to be replenished will be obtained.

[0009] Preferably, the calculation of the goods vacancy rate of the delivery point equipment when the estimated time is reached from the current time includes: Obtain historical sales records of goods at the distribution point equipment, extract the sales quantity of goods corresponding to multiple time windows in a single day, use the sales quantity of each time window as training samples, set up training and validation sets, input them into the constructed network model for training, and the trained network model outputs the sales quantity of goods in any given time window. The network model is an LSTM model. LSTM stands for Long Short-Term Memory Network, an artificial intelligence model specifically designed for processing time series data. In this solution, based on the sales volume of goods in multiple time windows, it can accurately predict the sales volume of goods in any given time window, providing data support for calculating the vacancy rate of goods for equipment awaiting replenishment and for replenishment scheduling. This improves the timeliness and rationality of replenishment scheduling and avoids equipment shortages or over-replenishment. The specific construction and training process of the LSTM model is existing technology and will not be elaborated here. Obtain the maximum number of goods N0 that can be assembled at the distribution point equipment, and the current inventory quantity N. cur Input the estimated duration of the time window from the current time into the trained network model to predict the number of sales N within the time window. D Calculate the vacancy rate of goods at the distribution point equipment: .

[0010] Preferably, the replenishment status of each piece of equipment to be replenished is calculated, including: Get the duration of a device that needs to be replenished in the state of needing replenishment up to the current time. The state of needing replenishment is the state in which the quantity of goods in the device is less than a preset quantity threshold. Normalize the duration to get the current urgency level of the device. Get the replenishment status of each piece of equipment to be replenished: C i =Q i ×V i / L i , where C i Q represents the replenishment level of the i-th equipment to be replenished. i V represents the urgency level of the i-th equipment to be replenished. i Let L be the idle rate of the i-th equipment awaiting replenishment. i The actual road distance from the real-time vehicle location to the i-th replenishment device is denoted as .

[0011] Preferably, dynamic scheduling of urban distribution vehicles includes: Sort the equipment to be replenished in descending order of replenishment level; The safe battery level range for the vehicle is set to be greater than E, where E is a constant greater than 0; Find the nearest charging / swapping station to the replenishment device M1 with serial number 1. Calculate the first actual road distance traveled by the vehicle from its current location to the replenishment device M1. Based on the current load status of the vehicle, substitute the first distance into the corresponding fitting function to obtain the first power consumption required for the vehicle to travel. Calculate the second actual road distance traveled by the vehicle from the replenishment device M1 to the nearest charging / swapping station. Based on the quantity of goods that need to be replenished after the vehicle arrives at the replenishment device M1, predict the load status of the vehicle when it goes to the nearest charging / swapping station, and substitute the second distance into the corresponding fitting function to obtain the second power consumption required for the vehicle to travel. Obtain the vehicle's current remaining battery power. If the value of the current remaining battery power minus the first and second battery power is within the safe battery power range, set the vehicle's next processing order to replenishment device M1. If the vehicle is outside the safe power range, obtain the nearest charging / swapping station to the replenishment device M2 with serial number 2. Based on the above judgment criteria, calculate the remaining power value of the vehicle after it departs from the current location, passes through the replenishment device M2, and arrives at the nearest charging / swapping station (the remaining power value refers to: the vehicle's current remaining power minus the power consumed by the vehicle from the current location, passing through the replenishment device M2, and then minus the power consumed from the replenishment device M2 to the nearest charging / swapping station). Compare this value with the safe power range, and so on, to obtain the vehicle's next processing order.

[0012] Preferably, the dynamic scheduling of urban distribution vehicles also includes: pre-setting the warning power range of the vehicle; when the next order to be processed by the vehicle cannot be determined, calculating the actual road travel distance from the vehicle's location to the nearest charging and battery swapping station; inputting the actual road travel distance into the corresponding fitting function according to the vehicle's load status at this time to obtain the required power consumption e; if the value of the vehicle's current remaining power minus e is within the warning power range, prompting the vehicle to charge or swap the battery in time.

[0013] The specific charging or battery swapping method can be selected by the operator based on actual operational needs and on-site conditions. For example, when the vehicle's remaining battery power is low and it is urgent to continue the restocking task, the battery swapping method should be given priority to shorten the refueling time; when there are few orders, ample time, and no available battery swapping station nearby, the charging method can be selected to complete the refueling.

[0014] A dynamic dispatching system for urban distribution vehicles based on charging and battery swapping coordination includes a fitting function determination module, a location marking module, a replenishment degree calculation module, and a vehicle dynamic dispatching module. Fitting function determination module: used to retrieve the historical driving records of urban distribution vehicles, deploy positioning sensors on urban distribution vehicles, extract the load status, driving distance and power consumption of urban distribution vehicles within a time window from the driving records, and obtain the fitting function of driving distance as a function of power consumption corresponding to different load statuses based on several driving records. Location marking module: City delivery vehicles are responsible for replenishing equipment at fixed delivery points to complete order tasks. This module is used to obtain city map data and mark the locations of all delivery point equipment and charging / swapping stations within the city on the map. Replenishment level calculation module: used to obtain the real-time location and remaining power of the current vehicle after completing an order or charging / battery swapping; based on the historical sales records of each delivery point's equipment, extract the equipment to be replenished; and calculate the replenishment level of each equipment to be replenished based on its location. The vehicle dynamic scheduling module is used to sort the equipment to be replenished according to the replenishment level, find the nearest charging and battery swapping station to each equipment to be replenished based on the location of the equipment at each delivery point and the location of the charging and battery swapping station, and obtain the next processing order for the vehicle based on each fitted function, so as to realize the dynamic scheduling of urban distribution vehicles.

[0015] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention provides a dynamic scheduling system and method for urban distribution vehicles based on charging and battery swapping coordination, including: retrieving historical driving records of urban distribution vehicles, extracting the load status, driving distance, and power consumption of urban distribution vehicles within a time window from the driving records, and obtaining fitting functions for different load statuses; acquiring urban map data and marking the locations of delivery point equipment and charging / battery swapping stations; acquiring the real-time location and remaining power of the current vehicles, extracting equipment to be replenished, and calculating the replenishment level of each equipment to be replenished; sorting the equipment to be replenished, and obtaining the next processing order for the vehicle based on each fitting function, thereby realizing dynamic scheduling of urban distribution vehicles. This invention achieves dynamic scheduling of urban distribution vehicles by combining multi-source data such as driving records, goods sales records, and fitting functions for analysis, improving the overall scheduling rationality and reliability, and helping to meet the needs of efficient and stable operation of electric urban distribution vehicles. Attached Figure Description

[0016] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a flowchart illustrating a dynamic scheduling method for urban distribution vehicles based on charging and battery swapping coordination according to the present invention. Detailed Implementation

[0018] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this disclosure. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this disclosure as detailed in the appended claims.

[0019] Example: Figure 1 As shown, this invention provides a technical solution for dynamic scheduling of urban distribution vehicles based on charging and battery swapping coordination, comprising the following steps: Historical driving records of urban delivery vehicles are retrieved, positioning sensors are deployed on these vehicles, and the load status, distance traveled, and power consumption of the vehicles within a time window are extracted from the driving records. Based on several driving records, a fitting function is obtained to show the change in distance traveled with power consumption under different load statuses, specifically including: Driving records refer to a collection of historical data related to the driving status of a vehicle during its operation, including driving time, vehicle location, distance traveled, power consumption, and load status. The load status, distance traveled, and power consumption of the urban distribution vehicle within a time window are extracted from each driving record. A time window refers to the period during which the urban distribution vehicle is in a continuous and effective driving state. Load status includes empty, lightly loaded, half-loaded, and fully loaded. In this embodiment, empty means the vehicle carries zero cargo; lightly loaded means the vehicle's cargo load does not exceed 30% of its rated load capacity; half-loaded means the vehicle's cargo load is greater than 30% but not more than 70% of its rated load capacity; and fully loaded means the vehicle's cargo load is greater than 70% but not more than 100% of its rated load capacity.

[0020] The driving distance and power consumption of the driving records under different load conditions are obtained, and the fitting function of the driving distance as a function of power consumption under different load conditions is obtained. The fitting function is a linear function.

[0021] Since the distance traveled by a vehicle with the same amount of electricity varies depending on its load condition, the fitting function for the change in distance traveled with electricity consumption is different under different load conditions. In this scheme, the fitting function is a linear function, expressed as y=kx+b, where x is the independent variable, y is the dependent variable, k is the slope, and b is the intercept. The specific calculation can be obtained by the least squares method, which will not be elaborated here.

[0022] The city delivery vehicles are responsible for replenishing equipment at fixed delivery points to complete order tasks, obtaining city map data, and marking the locations of all delivery point equipment and charging / battery swapping stations in the city on the map.

[0023] In this embodiment, the urban distribution vehicle is a cargo transport vehicle, the distribution point equipment is a fixed-location device that needs to be replenished, specifically referring to a vending machine, the order task refers to replenishing the vending machine, and the goods are water, beverages, etc. with a fixed weight, such as mineral water of a certain brand with the same specifications.

[0024] Get the real-time vehicle location after the order is completed or after charging / battery swapping, as well as the location of equipment and charging / battery swapping stations at each delivery point; Based on the navigation platform, the actual road distance from the real-time vehicle location to the location of each delivery point equipment is obtained; the historical average speed of the vehicle is acquired, and the estimated time for the vehicle to reach the delivery point equipment is calculated based on the actual road distance from the vehicle to the delivery point equipment.

[0025] Obtain historical sales records for the vending machines at the distribution point. These records refer to historical transaction data generated by actual user purchases during normal operation of the vending machines. Calculate the vacancy rate of the vending machines at the distribution point when the estimated time has elapsed since the current time. Specifically, this includes: The system obtains historical sales records of goods from the distribution point equipment, extracts the sales quantity of goods corresponding to multiple time windows in a single day, uses the sales quantity of each time window as training samples, sets up training and validation sets, and inputs them into the constructed network model for training. The trained network model outputs the sales quantity of goods within any given time window. The network model is an LSTM model.

[0026] LSTM, or Long Short-Term Memory Network, is an artificial intelligence model specifically designed for processing time-series data. In this solution, based on the sales volume of goods in multiple time windows, it can accurately predict the sales volume of goods in any given time window, providing data support for calculating the vacancy rate of goods for equipment awaiting replenishment and for replenishment scheduling. This improves the timeliness and rationality of replenishment scheduling and avoids equipment shortages or over-replenishment. The specific construction and training process of the LSTM model is existing technology and will not be elaborated here.

[0027] Obtain the maximum number of goods N0 that can be assembled at the distribution point equipment, and the current inventory quantity N. cur Input the estimated duration of the time window from the current time into the trained network model to predict the number of sales N within the time window. D Calculate the vacancy rate of goods at the distribution point equipment: The vacancy rate represents the degree of vacancy of goods in the equipment at the distribution point. The value ranges from 0 to 1. The higher the value, the closer it is to 1, indicating that there are fewer goods in the equipment at the distribution point and the degree of vacancy is higher, and the more necessary it is to replenish the goods.

[0028] If the vacancy rate of goods is greater than the preset vacancy rate threshold, the equipment at the distribution point will be designated as equipment to be replenished, and thus all equipment to be replenished will be obtained.

[0029] The process retrieves the duration of time a device awaiting replenishment has been in a state of being out of stock, prior to the current moment. The state of being out of stock is defined as the quantity of goods in the device being out of stock being less than a preset threshold. The duration is then normalized to obtain the urgency level of the device. Here, the duration represents the length of time the device has been out of stock. The longer the duration, the more urgent the need for replenishment. Normalization is a technique that maps the urgency level to 0 to 1. The longer the duration, the greater the urgency level. This can be referenced in the sigmoid technique, which will not be elaborated here.

[0030] Get the replenishment status of each piece of equipment to be replenished: C i =Q i ×V i / L i , where C i Q represents the replenishment level of the i-th equipment to be replenished. i V represents the urgency level of the i-th equipment to be replenished. i Let L be the idle rate of the i-th equipment awaiting replenishment. i The actual road distance from the real-time vehicle location to the i-th replenishment device is denoted as .

[0031] The replenishment level indicates the priority of replenishing the equipment to be replenished for the current vehicle. The higher the value, the more priority the equipment needs to be replenished. Since the urgency and cargo vacancy rate are higher, it means that the equipment to be replenished needs to be replenished more promptly, and the replenishment level should be higher. However, the greater the actual road travel distance, the higher the travel cost and the longer the travel time for the current vehicle to reach the equipment to be replenished, which will reduce the replenishment level of the equipment.

[0032] Based on replenishment needs, the equipment awaiting replenishment is sorted. According to the location of the equipment at each distribution point and the location of charging / swapping stations, the charging / swapping station closest to each piece of equipment is determined. Then, based on various fitted functions, the next processing order for each vehicle is obtained, enabling dynamic scheduling of urban delivery vehicles. Specifically, this includes: Sort the equipment to be replenished in descending order of replenishment level; The safe battery level range for the vehicle is set to be greater than E, where E is a constant greater than 0; Find the nearest charging / swapping station to the replenishment device M1 with serial number 1. Calculate the first actual road distance the vehicle travels from its current location to the replenishment device M1. Based on the vehicle's current load status, substitute the first distance into the corresponding fitting function to obtain the first power consumption required for the vehicle's journey. Calculate the second actual road distance the vehicle travels from the replenishment device M1 to the nearest charging / swapping station. Based on the quantity of goods the vehicle needs to replenish after arriving at the replenishment device M1, predict the vehicle's load status when heading to the nearest charging / swapping station, and substitute the second distance into the corresponding fitting function to obtain the second power consumption required for the vehicle's journey. Both the first and second power consumption are the power consumption required.

[0033] Obtain the vehicle's current remaining battery power. If the value of the current remaining battery power minus the first and second battery power is within the safe battery power range, set the vehicle's next processing order to replenishment device M1. If the vehicle is outside the safe power range, obtain the nearest charging / swapping station to the replenishment device M2 with serial number 2. Based on the above judgment criteria, calculate the remaining power value of the vehicle after it departs from the current location, passes through the replenishment device M2, and arrives at the nearest charging / swapping station (the remaining power value refers to: the vehicle's current remaining power minus the power consumed by the vehicle from the current location, passing through the replenishment device M2, and then minus the power consumed from the replenishment device M2 to the nearest charging / swapping station). Compare this value with the safe power range, and so on, to obtain the vehicle's next processing order.

[0034] A pre-set warning battery level range for the vehicle is defined in this embodiment as 0% to 15%. When the battery level is between 0% and 15%, the vehicle is considered to be in a warning state and requires immediate charging. If the vehicle's next order cannot be determined, the actual road distance from the vehicle's location to the nearest charging / battery swapping station is calculated. Based on the vehicle's current load status, this actual road distance is input into the corresponding fitting function to obtain the required battery consumption, e. If the difference between the vehicle's current remaining battery level and e falls within the warning battery level range, the vehicle is prompted to charge or swap batteries promptly. The specific charging or battery swapping method can be selected by the operator based on actual operational needs and site conditions. For example, when the vehicle's remaining battery level is low and it urgently needs to continue restocking, battery swapping is preferred to shorten the charging time. When there are few orders, ample time, and no available battery swapping stations nearby, charging can be chosen to complete the charging process.

[0035] This embodiment also provides a dynamic dispatching system for urban distribution vehicles based on charging and battery swapping coordination, including: a fitting function determination module, a location marking module, a replenishment degree calculation module, and a vehicle dynamic dispatching module; Fitting function determination module: used to retrieve the historical driving records of urban distribution vehicles, deploy positioning sensors on urban distribution vehicles, extract the load status, driving distance and power consumption of urban distribution vehicles within a time window from the driving records, and obtain the fitting function of driving distance as a function of power consumption corresponding to different load statuses based on several driving records. Location marking module: City delivery vehicles are responsible for replenishing equipment at fixed delivery points to complete order tasks. This module is used to obtain city map data and mark the locations of all delivery point equipment and charging / swapping stations within the city on the map. Replenishment level calculation module: used to obtain the real-time location and remaining power of the current vehicle after completing an order or charging / battery swapping; based on the historical sales records of each delivery point's equipment, extract the equipment to be replenished; and calculate the replenishment level of each equipment to be replenished based on its location. The vehicle dynamic scheduling module is used to sort the equipment to be replenished according to the replenishment level, find the nearest charging and battery swapping station to each equipment to be replenished based on the location of the equipment at each delivery point and the location of the charging and battery swapping station, and obtain the next processing order for the vehicle based on each fitted function, so as to realize the dynamic scheduling of urban distribution vehicles.

[0036] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. Furthermore, specific embodiments have been described above. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps described in the claims can be performed in a different order than that shown in the embodiments and still achieve the desired result. Additionally, the processes depicted in the drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0037] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

[0038] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A dynamic scheduling method for urban distribution vehicles based on charging and battery swapping coordination, characterized in that, Includes the following steps: Historical driving records of urban distribution vehicles are retrieved, positioning sensors are deployed on the vehicles, and the load status, driving distance, and power consumption of the vehicles within a time window are extracted from the driving records. Based on several driving records, a fitting function of the driving distance and power consumption corresponding to different load statuses is obtained. Urban delivery vehicles are responsible for replenishing equipment at fixed delivery points to complete order tasks, obtaining city map data, and marking the locations of all delivery point equipment and charging / swapping stations in the city on the map; Obtain the real-time location and remaining battery power of the vehicle after completing an order or charging / swapping; extract the equipment to be replenished based on the historical sales records of each delivery point's equipment; and calculate the replenishment level of each equipment based on its location. According to the replenishment level, the equipment to be replenished is sorted. Based on the location of the equipment at each distribution point and the location of the charging and battery swapping station, the charging and battery swapping station closest to each equipment to be replenished is obtained. Based on each fitted function, the next processing order for the vehicle is obtained, realizing dynamic scheduling of urban distribution vehicles.

2. The method for dynamic scheduling of urban distribution vehicles based on charging and battery swapping coordination according to claim 1, characterized in that, The fitting function for the change in driving distance as a function of electricity consumption under different load conditions was obtained, including: Extract the load status, travel distance, and power consumption of urban distribution vehicles within a time window from each driving record. The time window refers to the period during which urban distribution vehicles are in a continuous and effective driving state. The load status includes empty, lightly loaded, half-loaded, and fully loaded. The driving distance and power consumption of driving records under different load conditions are obtained, and a fitting function is obtained for the driving distance as a function of power consumption under different load conditions. The fitting function is a linear function.

3. The method for dynamic scheduling of urban distribution vehicles based on charging and battery swapping coordination according to claim 1, characterized in that, Pick up equipment awaiting replenishment, including: Get the real-time vehicle location after the order is completed or after charging / battery swapping, as well as the location of equipment and charging / battery swapping stations at each delivery point; Based on the navigation platform, the actual road distance from the real-time vehicle location to the location of each delivery point equipment is obtained; the historical average speed of the vehicle is acquired, and the estimated time for the vehicle to reach the delivery point equipment is calculated based on the actual road distance from the vehicle to the delivery point equipment. Obtain the historical sales records of the goods at the delivery point equipment, and calculate the vacancy rate of the goods at the delivery point equipment when the estimated time is reached from the current time. If the vacancy rate of goods is greater than the preset vacancy rate threshold, the equipment at the distribution point will be designated as equipment to be replenished, and thus all equipment to be replenished will be obtained.

4. The method for dynamic scheduling of urban distribution vehicles based on charging and battery swapping coordination according to claim 3, characterized in that, Calculating the cargo vacancy rate of the delivery point equipment when the estimated time is reached from the current time includes: The historical sales records of goods at the distribution point equipment are obtained, and the sales quantity of goods corresponding to multiple time windows in a single day is extracted. The sales quantity of each time window is used as a training sample, and a training set and a validation set are set and input into the constructed network model for training. The trained network model outputs the sales quantity of goods in any given time window. The network model is an LSTM model. Obtain the maximum number of goods N0 that can be assembled at the distribution point equipment, and the current inventory quantity N. cur Input the estimated duration of the time window from the current time into the trained network model to predict the number of sales N within the time window. D Calculate the vacancy rate of goods at the distribution point equipment: .

5. A method for dynamic scheduling of urban distribution vehicles based on charging and battery swapping coordination according to claim 3, characterized in that, Calculate the replenishment status of each piece of equipment to be replenished, including: The duration of a device awaiting replenishment is obtained from the current moment back to the previous moment. The state of awaiting replenishment is when the quantity of goods in the device is less than a preset quantity threshold. The duration is normalized to obtain the current urgency level of the device awaiting replenishment. Get the replenishment status of each piece of equipment to be replenished: C i =Q i ×V i / L i , where C i Q represents the replenishment level of the i-th equipment to be replenished. i V represents the urgency level of the i-th equipment to be replenished. i Let L be the idle rate of the i-th equipment awaiting replenishment. i The actual road distance from the real-time vehicle location to the i-th replenishment device is denoted as .

6. The method for dynamic scheduling of urban distribution vehicles based on charging and battery swapping coordination according to claim 1, characterized in that, To achieve dynamic dispatching of urban distribution vehicles, including: Sort the equipment to be replenished in descending order of replenishment level; The safe battery level range for the vehicle is set to be greater than E, where E is a constant greater than 0; Find the nearest charging / swapping station to the replenishment device M1 with serial number 1. Calculate the first actual road distance traveled by the vehicle from its current location to the replenishment device M1. Based on the current load status of the vehicle, substitute the first distance into the corresponding fitting function to obtain the first power consumption required for the vehicle to travel. Calculate the second actual road distance traveled by the vehicle from the replenishment device M1 to the nearest charging / swapping station. Based on the quantity of goods that need to be replenished after the vehicle arrives at the replenishment device M1, predict the load status of the vehicle when it goes to the nearest charging / swapping station, and substitute the second distance into the corresponding fitting function to obtain the second power consumption required for the vehicle to travel. Obtain the vehicle's current remaining battery power. If the value of the current remaining battery power minus the first and second battery power is within the safe battery power range, set the vehicle's next processing order to replenishment device M1. If the vehicle is not within the safe power range, obtain the nearest charging / swapping station to the replenishment device M2 with serial number 2. Based on the above judgment criteria, calculate the remaining power value of the vehicle after it starts from the current location, passes through the replenishment device M2, and arrives at the nearest charging / swapping station. Compare this value with the safe power range, and so on, to obtain the next processing order for the vehicle.

7. A method for dynamic scheduling of urban distribution vehicles based on charging and battery swapping coordination according to claim 6, characterized in that, To achieve dynamic scheduling of urban delivery vehicles, the following steps are also taken: pre-setting the warning power range of vehicles; when the next order to be processed by a vehicle cannot be determined, calculating the actual road distance from the vehicle's location to the nearest charging and battery swapping station; inputting the actual road distance into the corresponding fitting function based on the vehicle's load status at this time to obtain the required power consumption e; if the value of the vehicle's current remaining power minus e is within the warning power range, prompting the vehicle to charge or swap its battery in a timely manner.

8. A dynamic scheduling system for urban distribution vehicles based on charging and battery swapping coordination, used to execute the dynamic scheduling method for urban distribution vehicles based on charging and battery swapping coordination as described in any one of claims 1-7, characterized in that, The system includes a fitting function determination module, a location labeling module, a replenishment degree calculation module, and a vehicle dynamic scheduling module; Fitting function determination module: used to retrieve the historical driving records of urban distribution vehicles, deploy positioning sensors on urban distribution vehicles, extract the load status, driving distance and power consumption of urban distribution vehicles within a time window from the driving records, and obtain the fitting function of driving distance as a function of power consumption corresponding to different load statuses based on several driving records. Location marking module: City delivery vehicles are responsible for replenishing equipment at fixed delivery points to complete order tasks. This module is used to obtain city map data and mark the locations of all delivery point equipment and charging / swapping stations within the city on the map. Replenishment level calculation module: used to obtain the real-time location and remaining power of the current vehicle after completing an order or charging / battery swapping; based on the historical sales records of each delivery point's equipment, extract the equipment to be replenished; and calculate the replenishment level of each equipment to be replenished based on its location. The vehicle dynamic scheduling module is used to sort the equipment to be replenished according to the replenishment level, find the nearest charging and battery swapping station to each equipment to be replenished based on the location of the equipment at each delivery point and the location of the charging and battery swapping station, and obtain the next processing order for the vehicle based on each fitted function, so as to realize the dynamic scheduling of urban distribution vehicles.

Images