Urban and rural logistics collaborative scheduling method and system based on battery swap battery turnover

Abstract

The application discloses a kind of urban and rural logistics collaborative scheduling method and system based on battery turnover, its method with electric logistics vehicle operator as optimization subject, obtains city multi-source data, constructs the collaborative scheduling model of fusion conventional freight task and battery turnover task;The process that electric logistics vehicle is carried standard battery in the process of executing urban and rural distribution task, unloads full battery at city node and recycles empty battery, is unified modeling at specified node through fast battery replacement supplement vehicle itself power;With the maximum net income of logistics operator as target, establish the optimization model including conventional freight distribution income, battery transportation income, vehicle fixed cost, distance cost, overtime cost and battery replacement and loading and unloading cost, generate vehicle driving, loading and unloading, backhaul and self-battery integrated scheduling scheme.The method of the application can improve the utilization rate of urban and rural two-way transport capacity, promote the transfer of rural surplus new energy in the form of battery to urban load center.

Description

Technical Field

[0001] This invention relates to the fields of energy internet, smart logistics and transportation energy coupling scheduling technology, specifically to a method and system for coordinated scheduling of urban and rural logistics based on battery swapping turnover. Background Technology

[0002] In recent years, the installed capacity of new energy sources such as distributed photovoltaic and decentralized wind power in rural areas has continued to expand. However, due to constraints such as low local electricity load, scarcity of controllable resources, and insufficient capacity of power transmission channels, the local consumption space during peak power generation periods is limited, and the problem of wind and solar curtailment occurs frequently. The idle power generation resources of rural new energy sources have not been efficiently utilized. At the same time, the demand for urban last-mile logistics delivery and electric vehicle battery swapping services continues to rise, and the frequency and intensity of electric logistics vehicle operation have increased significantly. The vehicle's energy replenishment efficiency and turnover efficiency directly determine the overall operational efficiency of the urban logistics system.

[0003] While existing electric logistics vehicle collaborative new energy dispatching solutions can alleviate the problem of new energy consumption through vehicle grid charging and discharging regulation, driving route optimization, and orderly charging management, there are many shortcomings and limitations in actual operation: First, there are scheduling conflicts. Direct charging and discharging of electric logistics vehicles takes a long time, which can easily squeeze the logistics and delivery window, creating a significant contradiction with the high-efficiency logistics and delivery needs of cities. Second, resource utilization is one-sided. Existing solutions focus on optimizing vehicle operation and charging behavior, without coordinating the dispatching of standardized battery swapping as an independent and reusable energy carrier, and cannot build an energy utilization link for the circulation of batteries between urban and rural areas. Third, the capacity utilization rate is low. The logistics capacity for urban and rural round trips is not deeply coordinated with the empty battery return mission, resulting in serious waste of idle capacity resources on urban return trips and insufficient overall vehicle operating efficiency. Traditional electric logistics vehicle dispatching solutions focus on single technology optimization goals and do not build a systematic and implementable dispatching framework around the core benefits of logistics operators, making it difficult to adapt to the large-scale application needs of coordinated development of urban and rural energy and logistics. Summary of the Invention

[0004] Technical problem: In view of the problems existing in the existing technology, such as long vehicle refueling time, insufficient utilization of urban and rural transportation capacity, lack of battery swapping circulation mechanism, and insufficient coordination between new energy consumption and logistics operation, this invention proposes an urban and rural logistics collaborative scheduling method and system based on battery swapping turnover.

[0005] Technical solution: A method for coordinated scheduling of urban and rural logistics based on battery swapping turnover, comprising the following steps:

[0006] Step 1: Obtain urban and rural transportation network data, regular freight order data, data on the availability of fully charged batteries at rural battery swapping stations, data on the recovery of empty batteries at urban battery swapping stations, vehicle status data, and real-time traffic data for the target area, and preprocess the obtained data.

[0007] Step 2: Construct a collaborative network model for urban and rural logistics and battery swapping based on the preprocessed data. The collaborative network model includes logistics distribution center nodes, customer nodes, rural full battery supply nodes, urban battery swapping service nodes, and road connection edges.

[0008] Step 3: Based on historical order data, historical traffic data, rural new energy output data and real-time operation data, generate the following forecast results for regular freight demand, rural full-battery availability, urban battery swapping demand, and road segment travel time within the scheduling cycle.

[0009] Step 4: With the goal of maximizing the net profit of electric logistics vehicle operators, construct a collaborative optimization scheduling model to jointly determine the driving route of each vehicle, the customer service order, the full battery load, the empty battery return volume, and the vehicle's own battery swapping time.

[0010] Step 5: Output the urban-rural collaborative scheduling scheme for electric logistics vehicles based on the solution results of Step 4, and update the real-time traffic data, order execution status and node inventory status according to the preset rolling cycle, and make rolling corrections to the collaborative scheduling scheme until the end of the scheduling cycle.

[0011] Furthermore, in step 1, the data obtained includes:

[0012] 1) Urban and rural transportation network data, including road length, speed limits, traffic capacity, average travel time, and traffic restrictions;

[0013] 2) Regular freight order data, including order origin and destination, cargo weight or volume, earliest service time, latest service time, and revenue per order;

[0014] 3) Data on the availability of fully charged batteries at rural battery swapping stations, including the full battery inventory of each rural battery swapping station at each time period, the amount of batteries that can be added to the inventory, and the corresponding new energy consumption label.

[0015] 4) Data on empty battery recovery at city battery swapping stations, including the number of empty batteries to be returned to each city's battery swapping stations, the city's battery swapping demand, and the operational capacity of each node.

[0016] 5) Vehicle status data, including the vehicle's current location, remaining driving battery power, cargo capacity, number of batteries that can be installed, vehicle fixed start-up cost, and unit driving cost;

[0017] 6) Real-time traffic data, including real-time congestion status of each road segment, travel time correction values, and abnormal interruption information.

[0018] Furthermore, in step 2, the constructed urban-rural logistics-battery swapping collaborative network model is represented as follows:

[0019] ;

[0020] in, The set of nodes must include at least the set of logistics and distribution center nodes. Customer node set Rural battery supply node clusters and a collection of urban battery swapping service nodes ; The set of road connecting edges; The set of edge weights must include at least the road segment distance weights. Road segment travel time weighting And the accessibility status weight of road segments.

[0021] Preferably, in the urban-rural logistics-battery swapping collaborative network model, the electric logistics vehicle performs at least one of the following auxiliary tasks while completing regular freight orders:

[0022] 1) Load full batteries from rural battery supply nodes and transport them to urban battery swapping service nodes;

[0023] 2) Empty batteries are collected from urban battery swapping service nodes and transported to rural full-battery supply nodes;

[0024] 3) Perform fast battery swapping for the vehicle itself at nodes where battery swapping is permitted.

[0025] Furthermore, in step 3, a prediction model is used to predict key state variables within the scheduling period, specifically including:

[0026] Long Short-Term Memory (LSTM) networks are used to forecast the demand for regular freight and the availability of fully charged batteries in rural areas on a day-ahead basis. Gradient boosting tree models or rolling time-domain models are used to forecast the demand for battery swapping in urban areas and the travel time of road sections on a rolling intraday basis. The availability of fully charged batteries in rural areas is determined by the current full battery inventory of rural battery swapping stations, the charging completion volume during periods of renewable energy surplus, and the station's operational capacity.

[0027] Furthermore, in step 4, the objective function of the collaborative optimization scheduling model is:

[0028] ;

[0029] in, Net revenue for electric logistics vehicle operators during the dispatch cycle; For revenue from regular cargo delivery; For revenue from transporting swapped batteries; Fixed costs for vehicles; Cost of distance F; Cost of overtime; Costs associated with battery swapping and loading / unloading.

[0030] The constraints of the cooperative optimization scheduling model include:

[0031] 1) Vehicle path continuity constraints are used to ensure that vehicles start from the distribution center and eventually return to the distribution center, and that the access relationship of intermediate nodes satisfies flow conservation.

[0032] 2) Customer time window constraint, used to ensure that the order service start time is not earlier than the earliest service time, and the part exceeding the latest service time is included in the timeout;

[0033] 3) Vehicle load capacity constraint, used to ensure that the total amount of conventional goods, fully charged batteries and empty batteries carried by the vehicle does not exceed the vehicle's rated load capacity;

[0034] 4) Battery inventory balance constraint, used to ensure that the full battery inventory in rural nodes, the empty battery inventory in urban nodes, and the number of full / empty batteries on vehicles meet the time period balance relationship.

[0035] 5) Vehicle self-battery swapping constraint, which is used to ensure that the vehicle only swaps batteries at nodes where battery swapping is permitted, and each self-battery swap consumes one set of fully loaded batteries and adds one set of empty batteries to be returned.

[0036] 6) Vehicle range constraint, used to ensure that the remaining driving power of the vehicle is not lower than the preset safety threshold when the vehicle is driving between adjacent nodes;

[0037] 7) Node operation capacity constraints are used to ensure that the full battery delivery capacity of rural nodes and the empty battery recycling and battery swapping service capacity of urban nodes do not exceed their rated operation capacity.

[0038] Preferably, the battery inventory balance constraint includes:

[0039] ;

[0040] ;

[0041] in, For vehicles During the period Number of fully charged batteries carried. For vehicles During the period The number of empty batteries carried. and These represent the loading volume for the corresponding time period. and These represent the unloading volume for the corresponding time period;

[0042] The vehicle range constraints include:

[0043] ;

[0044] ;

[0045] in, For vehicle k in time period The remaining driving power, For vehicles on the side On-road energy consumption, This refers to the amount of electricity replenished for a single self-swap. and These represent the lower and upper limits of the vehicle's remaining driving battery power, respectively.

[0046] Further, in step 5, the rolling correction process includes:

[0047] Step 5.1: Generate the initial driving route, customer service sequence, and full / empty battery transportation plan for each vehicle based on the previous day's forecast results;

[0048] Step 5.2: At the arrival of each rolling period, update the real-time traffic status, order completion status, vehicle battery status, full battery inventory in rural nodes and empty battery inventory in urban nodes.

[0049] Step 5.3: Using the executed paths as fixed prefixes and the unexecuted tasks as the set to be optimized, re-optimize the vehicle routes, loading and unloading plans, and self-battery swapping plans for the remaining scheduling period.

[0050] Step 5.4: When it is detected that the road congestion is worsening, the customer time window is changing, the supply of full batteries in rural nodes is insufficient, or the backlog of empty batteries in urban nodes exceeds the threshold, a local rescheduling is triggered.

[0051] Step 5.5: Until the end of the scheduling cycle, output the complete vehicle execution trajectory, order completion status, battery turnover status, and net operating revenue results.

[0052] The technical solution of this invention also provides: a coordinated scheduling system for urban and rural logistics and new energy consumption based on battery swapping turnover, including a data acquisition module, a network modeling module, a predictive analysis module, an optimized scheduling module, a scheduling execution module, and a rolling correction module, for implementing the above-mentioned scheduling method.

[0053] Preferably, the data acquisition module is used to collect urban and rural transportation network data, regular freight order data, data on the availability of fully charged batteries at rural battery swapping stations, data on the recovery of empty batteries at urban battery swapping stations, vehicle status data, and real-time traffic data; the network modeling module is used to construct a collaborative network model for urban and rural logistics and battery swapping; the predictive analysis module is used to output prediction results for regular freight demand, prediction results for the availability of fully charged batteries in rural areas, prediction results for battery swapping demand in urban areas, and prediction results for road segment travel time; the optimization scheduling module is used to construct and solve a collaborative optimization scheduling model with the goal of maximizing the net profit of logistics operators, and output vehicle routes, order service order, full battery loading plan, empty battery return plan, and vehicle self-battery swapping plan; the scheduling execution module is used to send the optimized scheduling results to the vehicle terminal and the operation management platform, and receive execution feedback; and the rolling correction module is used to re-optimize unexecuted tasks based on real-time status changes.

[0054] Compared with the prior art, the present invention, employing the above technical solution, has the following technical effects:

[0055] 1. By replacing the long-term charging process of vehicles with standard battery swapping technology, the vehicles themselves adopt a fast battery swapping method, which significantly shortens the charging time and reduces the impact on the timeliness of regular logistics and delivery.

[0056] 2. Integrate the forward transportation of fully charged batteries in rural areas, the reverse transportation of empty batteries in urban areas, and the regular cargo distribution into a unified model to improve vehicle utilization and return loading rates during the round trip between urban and rural areas.

[0057] 3. Utilize the full battery inventory formed in rural areas during periods of surplus new energy, and realize the spatial scheduling of new energy through the spatial transfer of standard swapping batteries, thereby improving the transfer and consumption capacity of surplus new energy in rural areas.

[0058] 4. Using a turnover revenue model for unified billing of battery swapping transportation services can naturally cover both battery delivery and empty battery return, facilitating project implementation and commercial settlement.

[0059] 5. By combining daily planning with intraday rolling adjustments, we can improve our adaptability to traffic congestion, order fluctuations, and changes in inventory at key points. Attached Figure Description

[0060] Figure 1 This is a flowchart of the urban-rural logistics collaborative scheduling method based on battery swapping turnover according to the present invention;

[0061] Figure 2 This is a schematic diagram illustrating the operation of the electric logistics vehicle of the present invention in performing conventional freight transport, full-battery transportation, empty battery return transport, and vehicle self-battery swapping.

[0062] Figure 3This diagram illustrates a comparison between the method of this invention and the traditional pure freight dispatching method in terms of vehicle utilization, net revenue, and the effect of new energy consumption. Detailed Implementation

[0063] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of the application will be further described in detail below with reference to the accompanying drawings. The described embodiments are only a part of the embodiments involved in this invention. All non-innovative embodiments based on these embodiments by other researchers in the art are within the protection scope of this invention. Furthermore, the step numbers in the embodiments of this invention are only set for ease of explanation and do not limit the order of the steps. The execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0064] Example 1

[0065] Using a county-level urban and rural logistics network as an application scenario, the system consists of one urban distribution center, four rural battery swapping stations, three urban battery swapping service nodes, and several regular customer nodes. Each rural battery swapping station maintains a full battery inventory available for use during the midday peak of new energy vehicle demand, while the urban battery swapping service nodes generate demand for empty batteries awaiting return and for last-mile battery swapping services. The operator deploys several electric logistics vehicles, each with space for both regular cargo loading and standard battery swapping capacity, and the vehicles themselves are recharged via rapid battery swapping.

[0066] like Figure 1 As shown, the method for coordinated scheduling of urban and rural logistics and new energy consumption based on battery swapping turnover provided by the present invention includes the following steps:

[0067] Step 1: Acquisition and preprocessing of multi-source data.

[0068] The system acquires urban and rural traffic network data, regular freight order data, data on the availability of fully charged batteries at rural battery swapping stations, data on the recycling of empty batteries at urban battery swapping stations, vehicle status data, and real-time traffic data through the operation management platform, battery swapping station management system, vehicle terminals, and traffic data interfaces; and performs outlier removal, missing value filling, time alignment, and standardization on the raw data.

[0069] Among them, the data on the supply of full batteries at rural battery swapping stations is used to reflect the number of standard full batteries that can be transported to cities by logistics vehicles after being charged during periods of new energy surplus; the data on the recovery of empty batteries at urban battery swapping stations is used to reflect the number of empty batteries to be returned after providing battery swapping services to end users or delivery vehicles at urban nodes; and the vehicle status data includes the vehicle's current location, remaining driving power, current cargo load, current number of full batteries, and current number of empty batteries.

[0070] Step 2: Modeling of the urban-rural logistics-battery swapping collaborative network.

[0071] Constructing a collaborative network model for urban and rural logistics and battery swapping:

[0072] ;

[0073] in, The set of nodes must include at least the set of logistics and distribution center nodes. Customer node set Rural battery supply node clusters and a collection of urban battery swapping service nodes ; The set of road connecting edges; The set of edge weights must include at least the road segment distance weights. Road segment travel time weighting and the accessibility status weight of road segments;

[0074] The vehicles in this network need to perform the following tasks simultaneously: fulfilling customer order delivery tasks; loading batteries at rural nodes and transporting them to urban nodes; collecting empty batteries at urban nodes and transporting them back to rural nodes; and quickly swapping batteries for the vehicles themselves at nodes where battery swapping is permitted.

[0075] Step 3: Demand and Status Forecasting.

[0076] Based on historical orders, historical traffic data, rural new energy-related data, and real-time operating status, a day-ahead forecasting model and an intraday forecasting model are constructed.

[0077] This embodiment illustrates the operation of an electric logistics vehicle performing conventional freight transport, full-battery transportation, empty-battery return transport, and vehicle self-battery swapping, as shown below. Figure 2 As shown, the day-ahead forecasting model outputs baseline forecasts for regular freight demand, rural full-battery availability, and urban battery swapping demand for each time period of the next scheduling day; the intraday forecasting model is used to correct travel time, order status, and node inventory status within the rolling period. Regular freight demand and rural full-battery availability are predicted using a Long Short-Term Memory (LSTM) network; urban battery swapping demand and travel time are predicted using an XGBoost model combined with a rolling update mechanism.

[0078] Step 4: Construct a collaborative optimization scheduling model.

[0079] This invention aims to maximize the net profit of logistics operators by constructing a collaborative optimization scheduling model:

[0080] ;

[0081] in, Net revenue for electric logistics vehicle operators during the dispatch cycle; For revenue from regular cargo delivery; For revenue from transporting swapped batteries; Fixed costs for vehicles; Cost of distance F; Cost of overtime; Costs associated with battery swapping and loading / unloading;

[0082] As a preferred embodiment, the specific expressions for each part are as follows:

[0083] Revenue from regular cargo delivery:

[0084] ;

[0085] in, This is a collection of regular freight orders. For orders The service revenue, For orders Decision variables for whether or not the task is completed as required.

[0086] Revenue from battery swapping transportation:

[0087] ;

[0088] in, For the set of scheduling periods, To generate revenue from delivery services, standard fully charged batteries from rural areas were transported to battery swapping stations in cities. The revenue generated from returning empty city batteries to rural charging stations; , These represent the number of orders completed.

[0089] In particular, , For the time period Rural nodes completed within To city nodes and city nodes To rural nodes The number of battery swapping orders; therefore, this invention integrates the transportation revenue of fully charged batteries and empty batteries into the battery swapping service revenue obtained by the logistics operator.

[0090] Vehicle fixed costs:

[0091] ;

[0092] in, For vehicle assembly, For the fixed operating costs of the vehicle, For vehicles Decision variables for whether to enable it.

[0093] Distance cost:

[0094] ;

[0095] in, Cost per unit distance For vehicles Is it driving on the side? Decision variables.

[0096] Overtime cost:

[0097] ;

[0098] in, For orders The unit timeout penalty coefficient, For orders The timeout amount.

[0099] Battery swapping and loading / unloading costs:

[0100] ;

[0101] in, The cost of a single battery swap for a vehicle. For vehicles During the period Number of self-replacement cycles, For unit battery loading and unloading costs, For time period The number of fully loaded batteries at rural nodes For time period The number of empty batteries loaded at city nodes is recycled.

[0102] It is particularly important to note that in this embodiment, the charging cost and discharging revenue of the swapped batteries are not included in the logistics operator's optimization objectives. This is because the logistics operator is only responsible for the transportation, loading, unloading, and return of the standard swapped batteries, as well as the battery swapping operations of the vehicles themselves. Rural swapping stations or battery operators are responsible for the charging and asset management of the standard batteries.

[0103] Therefore, the revenue from battery swapping transportation is defined as the service revenue obtained by the logistics operator for completing the battery swapping turnaround service, rather than the revenue from electricity sales.

[0104] Step 4.1: Key Constraints

[0105] 1) Vehicle path continuity constraints

[0106] This is used to ensure that each vehicle departs from the distribution center and eventually returns to the distribution center, and that the inflow and outflow of nodes are conserved.

[0107] 2) Customer time window constraints

[0108] If the vehicle arrives at the customer's service node after the customer's latest service start time, the excess time will be counted as overtime. .

[0109] 3) Vehicle load capacity constraints

[0110] ;

[0111] in, For vehicles During the period The quantity of regular cargo carried, and These represent the capacity occupied by a single fully charged and empty battery, respectively. This refers to the vehicle's rated loading capacity.

[0112] 4) Battery inventory balance constraints

[0113] ;

[0114] ;

[0115] 5) Inventory balance constraints in rural and urban areas

[0116] ;

[0117] ;

[0118] in, For rural nodes During the period Full battery inventory Add a certain number of fully charged batteries available for this period. For city nodes Time period Empty battery inventory, This refers to the number of newly added empty batteries awaiting return during this period.

[0119] 6) Vehicle self-battery swapping and range constraints

[0120] ;

[0121] ;

[0122] And satisfy:

[0123] ;

[0124] This means that a vehicle can only perform self-battery swapping when it is fully loaded with at least one set of batteries.

[0125] 7) Node operation capacity constraints

[0126] This is used to limit the capacity of rural nodes to deliver full batteries and the capacity of urban nodes to provide battery swapping services and recover empty batteries to not exceed the node's rated operating capacity.

[0127] Step 4.2: Solution Method

[0128] In one optional embodiment, during the day-ahead phase, candidate driving routes are generated using a shortest path algorithm based on predicted travel time and order demand, and a mixed-integer programming model is used to solve for vehicle task allocation, loading and unloading plans, and self-battery swapping plans; during the intraday phase, the remaining tasks are re-optimized on a rolling basis based on real-time traffic and inventory status.

[0129] Step 5: Rolling execution and correction.

[0130] The system updates real-time traffic status, order execution status, full battery inventory at rural nodes, and empty battery inventory at urban nodes according to a preset rolling cycle, and performs partial rescheduling for unfinished tasks until the end of the scheduling cycle.

[0131] The final output includes:

[0132] 1) The complete travel route and arrival / departure times for each vehicle;

[0133] 2) The completion status and timeout status of each order;

[0134] 3) The number of fully charged batteries transported from each rural node to the urban node;

[0135] 4) The number of empty batteries transported from each city node to the rural node;

[0136] 5) Number of self-battery swaps and battery swapping nodes for each vehicle;

[0137] 6) Regular freight revenue, battery swapping transportation revenue, fixed costs, distance costs, overtime costs, battery swapping and loading / unloading costs, and net revenue during the scheduling period.

[0138] Example 2:

[0139] A collaborative scheduling system for urban and rural logistics and new energy consumption based on battery swapping turnover is provided, including:

[0140] The data acquisition module is used to collect and store order, vehicle, node inventory, and road operation data;

[0141] The network modeling module is used to construct a collaborative network model for urban and rural logistics and battery swapping.

[0142] The predictive analysis module is used to output the predicted results of freight demand, battery swapping demand, available full-battery capacity, and travel time.

[0143] The optimization scheduling module is used to solve the model for maximizing the net revenue of logistics operators;

[0144] The scheduling and execution module is used to send vehicle routes, loading and unloading tasks, and self-battery swapping instructions to the vehicle terminal;

[0145] The rolling correction module is used to re-optimize the unexecuted parts of the task when the real-time status changes;

[0146] The operations management platform provides data visualization, alerts, human-machine intervention, and statistical analysis functions.

[0147] Preferably, in this embodiment, the operation management platform processes the following:

[0148] 1) Data visualization: used to display vehicle location, remaining vehicle battery power, completed freight orders, full battery transport volume, empty battery return volume, customer timeout status, and node inventory status;

[0149] 2) Alarms: Used to output alarm information when traffic is interrupted, node inventory is abnormal, vehicle battery power is too low, or customer timeout risk increases;

[0150] 3) Human-machine intervention: Used to support operators in manually adjusting vehicle task priorities, vehicle battery swapping nodes, and order allocation strategies;

[0151] 4) Statistical analysis: Used to output the results of regular freight revenue, battery swapping transportation revenue, fixed costs, distance costs, overtime costs, battery swapping and loading / unloading costs, and net revenue analysis within the scheduling cycle.

[0152] The illustration shows a comparison between the method of this invention and the traditional pure freight dispatching method in terms of vehicle utilization, net revenue, and the effect of new energy consumption. Figure 3 As shown, the method of this invention can improve the utilization rate of two-way transportation capacity between urban and rural areas without significantly affecting the timeliness of logistics, promote the transfer and consumption of surplus rural new energy in the form of battery swapping to urban load centers, and take into account both logistics operation benefits and new energy utilization effects.

[0153] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for coordinated scheduling of urban and rural logistics based on battery swapping turnover, characterized in that, Includes the following steps: Step 1: Obtain urban and rural transportation network data, regular freight order data, data on the availability of fully charged batteries at rural battery swapping stations, data on the recovery of empty batteries at urban battery swapping stations, vehicle status data, and real-time traffic data for the target area, and preprocess the obtained data. Step 2: Construct a collaborative network model for urban and rural logistics and battery swapping based on the preprocessed data. The collaborative network model includes logistics distribution center nodes, customer nodes, rural full battery supply nodes, urban battery swapping service nodes, and road connection edges. Step 3: Based on historical order data, historical traffic data, rural new energy output data and real-time operation data, use a prediction model to generate the following prediction results for regular freight demand, rural full-battery availability, urban battery swapping demand and road travel time within the scheduling cycle. Step 4: With the goal of maximizing the net profit of electric logistics vehicle operators, construct a collaborative optimization scheduling model to determine the driving route of each vehicle, the customer service order, the full battery load, the empty battery return volume, and the vehicle's own battery swapping time. Step 5: Output the urban-rural collaborative scheduling scheme for electric logistics vehicles based on the solution results of Step 4, and update the real-time traffic data, order execution status and node inventory status according to the preset rolling cycle, and make rolling corrections to the collaborative scheduling scheme until the end of the scheduling cycle.

2. The scheduling method according to claim 1, characterized in that, The data obtained in step 1 includes: Urban and rural transportation network data, including road length, speed limits, traffic capacity, average travel time, and traffic restrictions; Standard freight order data includes order origin and destination, cargo weight or volume, earliest service time, latest service time, and revenue per order; Data on the availability of fully charged batteries at rural battery swapping stations includes the full battery inventory of each rural battery swapping station at different times, the amount of batteries that can be added to the inventory, and the corresponding new energy consumption label. Data on empty battery recovery at city battery swapping stations includes the number of empty batteries awaiting return at each city's battery swapping stations, the city's battery swapping demand, and the operational capacity of each node. Vehicle status data includes the vehicle's current location, remaining driving battery power, cargo capacity, number of batteries that can be installed, vehicle fixed start-up cost, and unit driving cost; Real-time traffic data, including real-time congestion status, travel time correction values, and abnormal interruption information for each road segment; The data preprocessing includes outlier removal, missing value imputation, time alignment, and standardization.

3. The scheduling method according to claim 1, characterized in that, The urban-rural logistics-battery swapping collaborative network model constructed in step 2 is represented as follows: ； in, The set of nodes must include at least the set of logistics and distribution center nodes. Customer node set Rural battery supply node clusters and a collection of urban battery swapping service nodes ; The set of road connecting edges; The set of edge weights must include at least the road segment distance weights. Road segment travel time weighting and the accessibility status weight of road segments; In the aforementioned urban-rural logistics-battery swapping collaborative network model, electric logistics vehicles perform at least one of the following auxiliary tasks while fulfilling regular freight orders: Full batteries are loaded from rural battery supply nodes and transported to urban battery swapping service nodes; Empty batteries are collected from urban battery swapping service nodes and transported to rural full-battery supply nodes. Perform fast battery swapping for the vehicle itself at nodes where battery swapping is permitted.

4. The scheduling method according to claim 1, characterized in that, Step 3 uses a prediction model to predict key state variables within the scheduling period. The prediction model includes: Long Short-Term Memory (LSTM) networks are used to forecast the demand for regular freight and the availability of fully charged batteries in rural areas; gradient boosting tree models or rolling time-domain models are used to forecast the demand for battery swapping in urban areas and the travel time of road sections. The predicted amount of fully charged batteries available in rural areas is determined by the combined factors of the full battery inventory at rural battery swapping stations, the charging volume completed during periods of renewable energy surplus, and the station's operational capacity.

5. The scheduling method according to claim 3, characterized in that, The objective function of the collaborative optimization scheduling model described in step 4 is: ； in, Net revenue for electric logistics vehicle operators during the dispatch cycle; For revenue from regular cargo delivery; For revenue from transporting swapped batteries; Fixed costs for vehicles; Cost of distance F; Cost of overtime; Costs associated with battery swapping and loading / unloading; The revenue from regular cargo delivery is expressed as follows: ； in, This is a collection of regular freight orders. For orders The service revenue, For orders Decision variables regarding whether or not the task is completed as required; The revenue from transporting the swapped batteries is expressed as follows: ； in, For the set of scheduling periods, To generate revenue from delivery services, standard fully charged batteries from rural areas are being transported to battery swapping stations in cities. The revenue generated from returning empty city batteries to rural charging stations; , These represent the number of orders completed. The fixed cost of the vehicle is expressed as: ； in, For vehicle assembly, For the fixed operating costs of the vehicle, For vehicles Decision variables for whether to enable it; The distance cost is expressed as: ； in, Cost per unit distance For vehicles Is it driving on the side? Decision variables; The timeout cost is expressed as: ； in, For orders The unit timeout penalty coefficient, For orders Timeout amount; The costs of battery swapping and loading / unloading are expressed as follows: ； in, The cost of a single battery swap for a vehicle. For vehicles During the period Number of self-replacement cycles, For unit battery loading and unloading costs, For time period The number of fully loaded batteries at rural nodes For time period The number of empty batteries loaded at city nodes is recovered.

6. The scheduling method according to claim 5, characterized in that, The constraints of the collaborative optimization scheduling model described in step 4 include: Vehicle path continuity constraints are used to ensure that vehicles depart from the distribution center and eventually return to the distribution center, and that the access relationships of intermediate nodes satisfy flow conservation. Customer time window constraints are used to ensure that the order service start time is not earlier than the earliest service time, and the portion exceeding the latest service time is counted as overtime. Vehicle load capacity constraints are used to ensure that the total amount of conventional cargo, fully charged batteries, and empty batteries carried by the vehicle does not exceed the vehicle's rated load capacity. Battery inventory balance constraint is used to ensure that the full battery inventory in rural nodes, the empty battery inventory in urban nodes, and the number of full / empty batteries on vehicles meet the time period balance relationship. Vehicle self-battery swapping constraint is used to ensure that the vehicle only swaps batteries at nodes where battery swapping is permitted, and that each self-battery swap consumes one set of fully loaded batteries and adds one set of empty batteries to be returned. Vehicle range constraint is used to ensure that the remaining driving power of the vehicle is not lower than a preset safety threshold when the vehicle is traveling between adjacent nodes. The node operation capacity constraint is used to ensure that the full battery delivery capacity of rural nodes and the empty battery recycling and battery swapping service capacity of urban nodes do not exceed their rated operation capacity.

7. The scheduling method according to claim 6, characterized in that, The battery inventory balance constraints include: ； ； in, For vehicles During the period Number of fully charged batteries carried. For vehicles During the period The number of empty batteries carried. and These represent the loading volume for the corresponding time period. and These represent the unloading volume for the corresponding time period; The vehicle range constraints include: ； ； in, For vehicle k in time period The remaining driving power, For vehicles on the side On-road energy consumption, This refers to the amount of electricity replenished for a single self-swap. and These represent the lower and upper limits of the vehicle's remaining driving battery power, respectively.

8. The scheduling method according to claim 1, characterized in that, The rolling correction process described in step 5 includes: Step 5.1: Generate the initial driving route, customer service sequence, and full and empty battery transportation plan for each vehicle based on the previous day's forecast results; Step 5.2: At the arrival of each rolling period, update the real-time traffic status, order completion status, vehicle battery status, full battery inventory in rural nodes and empty battery inventory in urban nodes. Step 5.3: Using the executed paths as fixed prefixes and the unexecuted tasks as the set to be optimized, re-optimize the vehicle routes, loading and unloading plans, and self-battery swapping plans for the remaining scheduling period. Step 5.4: When it is detected that the road congestion is worsening, the customer time window is changing, the supply of full batteries in rural nodes is insufficient, or the backlog of empty batteries in urban nodes exceeds the threshold, a local rescheduling is triggered. Step 5.5: Until the end of the scheduling cycle, output the complete vehicle execution trajectory, order completion status, battery turnover status, and net operating revenue results.

9. A coordinated scheduling system for urban and rural logistics and new energy consumption based on battery swapping turnover, used to implement the scheduling method described in any one of claims 1 to 8, characterized in that, include: The data acquisition module is used to collect urban and rural transportation network data, regular freight order data, data on the availability of fully charged batteries at rural battery swapping stations, data on the recovery of empty batteries at urban battery swapping stations, vehicle status data, and real-time traffic data. The network modeling module is used to construct a collaborative network model for urban and rural logistics and battery swapping. The predictive analysis module is used to output the forecast results of regular freight demand, the forecast results of the available capacity of fully charged batteries in rural areas, the forecast results of battery swapping demand in urban areas, and the forecast results of road segment travel time. The optimization scheduling module is used to build and solve a collaborative optimization scheduling model with the goal of maximizing the net profit of logistics operators, and outputs vehicle routes, order service order, full battery loading plan, empty battery return plan and vehicle self-battery swapping plan. The scheduling execution module is used to send the optimized scheduling results to the vehicle terminal and the operation management platform, and to receive execution feedback; The rolling correction module is used to re-optimize unexecuted tasks based on real-time status changes.

10. The scheduling system according to claim 9, characterized in that, The operation management platform handles the following: Data visualization: used to display vehicle location, remaining vehicle battery power, completed freight orders, full battery transport volume, empty battery return volume, customer timeout status, and node inventory status; Alarms: Used to output alarm information when traffic is interrupted, node inventory is abnormal, vehicle battery power is too low, or customer timeout risk increases; Human-machine intervention: used to support operators in manually adjusting vehicle task priorities, vehicle battery swapping nodes, and order allocation strategies; Statistical analysis: used to output the results of regular freight revenue, battery swapping transportation revenue, fixed costs, distance costs, overtime costs, battery swapping and loading / unloading costs, and net revenue analysis within the scheduling cycle.

Images