Airport bus network optimization method and system integrating air traffic control information

Abstract

The invention discloses an airport bus network optimization method and system integrated with air traffic control information. The method comprises the following steps: acquiring a geographic range of an airport bus operation area, a passenger reservation demand generated by the influence of flight dynamic change and passenger online car-hailing order data according to the air traffic control information; determining all airport bus station positions in the airport bus operation area; establishing an objective function according to the passenger travel time cost and the airport bus operation cost, and establishing constraint conditions according to the maximum service passenger number of the airport bus starting station, the service level of the airport bus shift, and the lower limit and the upper limit of the time window when the passengers expect the airport bus to arrive; and solving the reservation response bus scheduling model to obtain an airport bus scheduling scheme. According to the method, the number of passengers taking airport buses and destinations of the passengers can be mastered in advance under the condition of flight change, the operation strategy is rapidly adjusted, and the vehicle scheduling is optimized, so that the waiting time and the on-board time of the passengers are effectively saved, and the satisfaction degree of the passengers under the condition of flight is improved.

Description

Technical Field

[0001] The present invention discloses a technology related to the resource scheduling of airport buses, and specifically, relates to an optimization method and system for an airport bus network integrating air traffic control information. Background Art

[0002] In the modern air transportation field, airport buses play a crucial role. They are mainly responsible for transporting passengers from the airport to different areas of the city, greatly facilitating passenger travel and strongly promoting the seamless connection of transportation between the airport and the city. However, there are some problems that need to be addressed urgently in the current operation mode of airport buses.

[0003] First of all, flight conditions are dynamic, and flight changes such as flight delays and cancellations occur frequently. This makes it difficult for airport buses to accurately estimate the passenger flow and flow direction at different times. The traditional operation mode of airport buses, that is, using fixed timetables and fixed routes, appears very rigid and lacks flexibility when facing such dynamic changes. As a result, in some periods, there is idle capacity of bus vehicles; while in other periods, there is a shortage of capacity.

[0004] Secondly, most of the existing airport bus stop settings are based on past experience, without fully considering the fact that the actual travel needs of passengers will change dynamically over time, and the reality that the urban traffic conditions will also evolve continuously. This leads to the ineffective satisfaction of the passenger connection needs in some areas, or the operation efficiency of airport buses on urban roads is greatly reduced due to unreasonable stop layouts.

[0005] Furthermore, currently, the operation of airport buses generally adopts a fixed departure interval and stop mode at stations. During off-peak hours, this mode is difficult to quickly respond to the personalized travel needs of passengers. Passengers often need to wait for a long time during the transfer process, and the travel experience is greatly affected. Especially when flight changes occur, the disadvantages of the traditional operation mode become more prominent, and it is impossible to meet the sudden needs of passengers in a timely manner. Passengers may face long waiting times during off-peak hours, or the travel time in the vehicle may increase due to unreasonable route planning, seriously affecting the travel experience of passengers.

[0006] Therefore, those skilled in the art urgently need to develop a new technical solution to solve the above problems. Summary of the Invention

[0007] To overcome the problems existing in the related technologies, the present invention discloses an optimization method and system for an airport bus network integrating air traffic control information.

[0008] According to the first aspect of the embodiments of the present invention, an optimization method for an airport bus network integrating air traffic control information is provided, and the method includes:

[0009] Obtain the geographical scope of the airport bus operation area, the passenger reservation demand affected by flight dynamic changes, and the passenger online car-hailing order data based on air traffic control information. The passenger reservation demand includes: the number of passengers, the reservation time window, and the destination.

[0010] Perform grid processing on the operation area, so that the operation area is divided into an airport bus operation area network composed of several grid cells.

[0011] Based on the distribution of drop-off locations in the passenger online car-hailing order data, statistically calculate the passenger flow demand of each grid cell, and screen out the high-frequency demand grid cells with passenger flow demand higher than the preset demand threshold.

[0012] Determine the locations of airport bus stops within the operation area according to the high-frequency demand grid cells.

[0013] Construct an airport bus scheduling optimization model. The objective function of the airport bus scheduling optimization model is the sum of the minimized passenger travel time cost and the minimized bus operation cost. The constraint conditions of the airport bus scheduling optimization model are established according to the maximum number of passengers served at the starting station of the airport bus, the service level of the airport bus schedule, the lower limit of the time window for passengers to expect the arrival of the airport bus, and the upper limit of the time window for passengers to expect the arrival of the airport bus.

[0014] Use a multi-layer coding optimization algorithm to solve the airport bus scheduling optimization model, and output the set of airport bus operation routes, the departure schedule, and the passenger allocation plan to optimize the airport bus operation area network.

[0015] Optionally, the determining the locations of airport bus stops within the operation area according to the high-frequency demand grid cells includes:

[0016] Merge adjacent high-frequency demand grid cells to form the first passenger flow hot zone, and then perform secondary merging on every two first passenger flow hot zones with a centroid distance less than or equal to the preset distance threshold.

[0017] Perform segmentation and adjustment on the first passenger flow hot zone after secondary merging, so that the horizontal expansion distance and the vertical expansion distance of the adjusted hot zone do not exceed the preset maximum service scale, and form the second passenger flow hot zone.

[0018] Score the high-frequency demand grid cells in each second passenger flow hot zone according to the number of adjacent grid cells of each high-frequency demand grid cell in the second passenger flow hot zone, and select the high-frequency demand grid cell with the highest scoring result as the location of the airport bus stop.

[0019] Optionally, the method for statistically analyzing the passenger flow demand of each grid cell based on the drop-off location distribution in the passenger online car-hailing order data and screening out the high-frequency demand grid cells with a passenger flow demand higher than a preset demand threshold includes:

[0020] Performing a grid index mapping operation on the drop-off locations in the passenger online car-hailing order data to determine the grid cell corresponding to each drop-off location ;

[0021] Counting the total number of passenger alighting events in the grid cell within a preset time period as the passenger flow demand of the grid cell ;

[0022] Taking the passenger flow demand higher than the preset demand threshold of the grid cell and determining it as a high-frequency demand grid cell ;

[0023] Obtaining the set of high-frequency demand grid cells as .

[0024] Optionally, the method for segmenting and adjusting the first passenger flow hot zone after secondary merging to form a second passenger flow hot zone with the horizontal and vertical extension distances of the adjusted hot zone not exceeding a preset maximum service scale includes:

[0025] Calculating the maximum horizontal extension distance and the maximum vertical extension distance of each first passenger flow hot zone;

[0026] If the maximum horizontal extension distance of the first passenger flow hot zone is greater than , then segment the first passenger flow hot zone along the horizontal direction, where is the preset maximum service scale;

[0027] If the maximum vertical extension distance of the first passenger flow hot zone is greater than , then segment the first passenger flow hot zone along the vertical direction;

[0028] If both the maximum vertical extension distance and the maximum horizontal extension distance of the first passenger flow hot zone are greater than , then segment the first passenger flow hot zone along the direction with the largest extension distance;

[0029] Determine the segmentation position based on the principle of minimizing the absolute value of the difference between the sums of the passenger flow demands of all grid cells within each of the two hot zones formed after segmentation;

[0030] Segment the first passenger flow hot zone according to the segmentation direction and segmentation position until the maximum horizontal extension distance and the maximum vertical extension distance of all the hot zones after segmentation are both less than to obtain the second passenger flow hot zone ;

[0031] Denote the set of the second passenger flow hot zones within the geographical area where the airport bus operates as .

[0032] Optionally, the method for scoring the high-frequency demand grid cells in each of the second passenger flow hot zones is as follows: , where is the scoring result, is the number of adjacent grid cells of the th high-frequency demand grid cell in the second passenger flow hot zone ( ), is the passenger flow demand of the second passenger flow hot zone, and are weight coefficients, represents each grid cell, represents the high-frequency demand grid cell.

[0033] Optionally, the objective function of the airport bus scheduling optimization model is expressed as: , where is the objective function, is the passenger travel time cost, is the airport bus operation cost, and are weight coefficients, and the calculation formula for the passenger travel time cost is: , where , , , is the time required for the passenger to walk from the airport to the airport bus stop location; is the in-vehicle time of the passenger, is the service deviation time cost, represents the passenger reservation demand and the airport bus relationship. If the passenger reservation demand is served by the airport bus then , otherwise , is the distance between the airport where the passenger is located and the location of the airport bus stop, represents the average speed of the passenger walking to the location of the airport bus stop, represents the airport bus the distance between the starting station location and the airport bus stop location between, represents the airport bus from the station location traveling to the station location average running speed, is the time window lower limit for the passenger to expect the airport bus to reach the station location of, is the time window upper limit for the passenger to expect the airport bus to reach the station location of, is the airport bus the time when the passenger arrives at the station location in the formula for calculating the operating cost of the airport bus is: , where, , , , , is the vehicle fixed cost, is the operating variable cost, is the penalty cost for the airport bus deviating from the passenger's expected arrival time, is the penalty cost generated by the system rejecting the order, represents the airport bus whether to go from the starting station location to the station location if so then if not then , is the depreciation coefficient for each operation of the airport bus, is the fuel cost per unit mileage of the airport bus vehicle, is the cost per unit mileage of the airport bus driver, is the penalty coefficient for the airport bus arriving earlier than the passenger's expected arrival time at the station location, is the penalty coefficient for the airport bus arriving later than the passenger's expected arrival time at the station location, is the penalty cost coefficient generated by the system rejecting the order, is the airport bus set, is the set of airport bus stop locations.

[0034] Optionally, the airport bus network optimization method integrating air traffic control information is characterized in that the establishment process of the constraint conditions includes:

[0035] Establish the first constraint condition based on the maximum number of passengers served at the starting station location of the airport bus: , where is the maximum number of passengers served at the starting station location of the airport bus, represents the passenger reservation demand and the airport bus The relationship between them. If the passenger reservation demand is served by the airport bus then otherwise , is the set of passenger reservation demands, is the set of airport buses;

[0036] Establish the second constraint condition based on the service level of the airport bus schedule: , where is the minimum service level of the airport bus , is the maximum service level of the airport bus , represents whether the airport bus travels from the starting station location to the station location , if so then , if not then , is the set of airport bus station locations;

[0037] Establish the third constraint condition based on the lower bound of the time window when passengers expect the airport bus to arrive and the upper bound of the time window when passengers expect the airport bus to arrive: , where is the lower bound of the time window when passengers expect the airport bus to arrive at the station location , is the upper bound of the time window when passengers expect the airport bus to arrive at the station location .

[0038] Optionally, solving the airport bus scheduling optimization model using the multi-layer coding optimization algorithm includes:

[0039] Define the set of airport buses as the first-layer coding, where is the schedule vehicle number of the airport bus ;

[0040] Define the service reservation request sequence as the second-layer coding, where is the service reservation request of the airport bus ;

[0041] Define the departure time sequence as the third-layer coding, where is the flight number of the airport bus corresponding to the departure time at the starting station;

[0042] Design and generate an initial feasible solution by using a three-layer coding method .

[0043] According to the second aspect of the disclosed embodiments of the present invention, there is provided an airport bus network optimization system integrating air traffic control information, and the system includes:

[0044] A data acquisition module, which acquires the geographical scope of the airport bus operation area, the passenger reservation demand generated by the impact of flight dynamic changes, and the passenger online car-hailing order data according to the air traffic control information. The passenger reservation demand includes: the number of passengers, the reservation time window, and the destination;

[0045] A rasterization processing module, connected to the data acquisition module, rasterizes the operation area, so that the operation area is divided into an airport bus operation area network composed of a plurality of raster units;

[0046] A high-frequency raster determination module, connected to the rasterization processing module, statistically calculates the passenger flow demand of each raster unit based on the distribution of the getting-off locations in the passenger online car-hailing order data, and screens out the high-frequency demand raster units with the passenger flow demand higher than the preset demand threshold;

[0047] A station location determination module, connected to the high-frequency raster determination module, determines the airport bus station locations in the operation area according to the high-frequency demand raster units;

[0048] An optimization model construction module, connected to the station location determination module, constructs an airport bus scheduling optimization model. The objective function of the airport bus scheduling optimization model is the sum of the minimized passenger travel time cost and the minimized bus operation cost. The constraint conditions of the airport bus scheduling optimization model are established according to the maximum number of passengers served by the starting station of the airport bus, the service level of the airport bus schedule, the lower limit of the time window for the passengers to expect the airport bus to arrive, and the upper limit of the time window for the passengers to expect the airport bus to arrive;

[0049] An optimization model solving module, connected to the optimization model construction module, solves the airport bus scheduling optimization model by using a multi-layer coding optimization algorithm, and outputs the airport bus operation route set, the departure schedule, and the passenger allocation plan to optimize the airport bus operation area network.

[0050] Optionally, the station location determination module is used for: ​

[0051] Merge adjacent high-frequency demand grid cells to form the first passenger flow hot zone, and then perform secondary merging on every two first passenger flow hot zones whose centroid distances are less than or equal to the preset distance threshold;

[0052] Segment and adjust the first passenger flow hot zone after secondary merging so that the horizontal extension distance and the vertical extension distance of the adjusted hot zone do not exceed the preset maximum service scale, thereby forming the second passenger flow hot zone;

[0053] Score the high-frequency demand grid cells in each of the second passenger flow hot zones according to the number of adjacent grid cells of each high-frequency demand grid cell in the second passenger flow hot zone, and select the high-frequency demand grid cell with the highest scoring result as the location of the airport bus stop.

[0054] In summary, through the technical solutions in the disclosed embodiments of the present invention, the following beneficial effects can be achieved:

[0055] (1) Multiple factors such as flight dynamic changes, actual passenger needs, and real-time urban traffic conditions are comprehensively considered. Based on these comprehensive considerations, the dynamic and flexible adjustment of the airport bus operation routes and departure times is realized. Such adjustment not only improves the operation efficiency of the airport bus, but also enhances the competitiveness of the airport bus in the urban transportation system, making it more advantageous in the competition with other transportation modes;

[0056] (2) Adopting the reservation response mode, the operator can accurately obtain the travel needs of passengers before they travel. Especially in the case of special situations such as flight changes, such as delays and cancellations, the operation strategy can be quickly adjusted based on this demand information. In this way, the waiting time of passengers for the bus and the time spent in the vehicle can be effectively shortened, thereby greatly improving the satisfaction of passengers with the airport bus service;

[0057] (3) By accurately identifying and analyzing the alternative airport bus stop locations, the site layout of the airport bus network can be optimized to make it more scientific and reasonable. Such layout adjustment can better cover the hot spots where passengers travel more concentratedly, expand the coverage of the airport bus service, and enable more passengers to conveniently enjoy the airport bus service.

[0058] Other features and advantages of the present invention will be described in detail in the subsequent specific implementation part. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The drawings are used to provide a further understanding of the present disclosure, and constitute a part of the specification. Together with the following specific implementation manners, they are used to explain the present disclosure, but do not constitute a limitation to the present disclosure. In the drawings:

[0060] Figure 1It is a schematic flow chart of an airport bus network optimization method integrating air traffic control information shown according to an exemplary embodiment;

[0061] Figure 2 It is according to Figure 1 A schematic flow chart of a site location determination method shown;

[0062] Figure 3 It is a schematic diagram for identifying high-frequency demand grid cells;

[0063] Figure 4 It is a schematic diagram for hot zone merging;

[0064] Figure 5 It is a schematic diagram of the travel behavior characteristics of online car-hailing passengers;

[0065] Figure 6 It is a schematic diagram of the spatial distribution of alternative airport bus site locations;

[0066] Figure 7 It is a schematic diagram of the airport bus line distribution in a planning scheme;

[0067] Figure 8 It is a schematic structural diagram of an airport bus network optimization system integrating air traffic control information shown according to an exemplary embodiment. Detailed implementation manners

[0068] The following will detail the specific implementation manners disclosed in the present invention with reference to the accompanying drawings. It should be understood that the specific implementation manners described herein are only for the purpose of illustration and explanation of the present disclosure, and are not used to limit the present disclosure.

[0069] Figure 1 It is a schematic flow chart of an airport bus network optimization method integrating air traffic control information shown according to an exemplary embodiment, as Figure 1 shown, the method includes:

[0070] In step 101, according to the air traffic control information, obtain the geographical scope of the airport bus operation area, the passenger reservation demand generated by the impact of flight dynamic changes, and the passenger online car-hailing order data.

[0071] In the disclosed embodiments of the present invention, in view of the dynamic changes of flights and in combination with the operating characteristics of airport buses, an optimization method for airport bus networks integrating air traffic control information is proposed, focusing on solving the following key problems: for flights with flight schedule changes, adopt a reservation response method to accurately obtain information such as the number of passengers taking the airport bus and their destinations; use the order data of airport online car-hailing to identify alternative airport bus stops and provide a reasonable stop layout for the subsequent design of the airport bus network; transform the airport bus scheduling problem into a semi-flexible demand-responsive problem, comprehensively consider flight dynamic information, passenger reservation data, and urban traffic conditions, and optimize the operating routes and departure times of airport buses to ensure the flexibility and efficiency of airport bus operations.

[0072] Among them, the passenger reservation requirements include: the number of passengers, the reservation time window, and the destination.

[0073] Exemplarily, the geographical scope of the bus operation area is obtained by loading a predefined geospatial data file, and the information obtained contains the exact geographical boundaries of this geographical area, denoted as .

[0074] The passenger reservation requirements generated under the influence of aviation dynamics, including information such as the number of passengers, the reservation time window, and the destination, are recorded as a set for each passenger reservation requirement , so the passenger reservation requirements under the influence of aviation dynamics can be recorded as a set .

[0075] Collect passenger online car-hailing order data, extract the geographical coordinates of the passenger drop-off locations corresponding to each valid order record, denoted as , so the passenger online car-hailing order data can be recorded as a set . It should be noted that the passenger online car-hailing order data collected in the disclosed embodiments of the present invention is electronic order data, including taxi orders and online car-hailing orders registered for private cars.

[0076] In step 102, the operation area is rasterized so that the operation area is divided into an airport bus operation area network composed of several grid cells.

[0077] Exemplarily, for this step 102, if the layout planning of the airport bus stop locations in the airport bus operation area has been completed before executing step 102, the planned airport bus stop locations can be directly obtained, skipping steps 102-104, and directly jumping to steps 105 and 106 after executing step 101 to schedule the airport bus. If there is no planning for the airport bus stop locations within this geographical area, alternative airport bus stops can be identified, an airport bus scheduling optimization model can be constructed, and solved according to the following steps 102-step 106.

[0078] For example, for the convenience of subsequent research, the geographical area is rasterized: a size parameter representing the spatial resolution of the raster cell is set, that is, the preset side length of the raster cell, denoted as . Based on the precise geographical boundary of the research area (i.e., the geographical area where the airport bus operates) and the preset side length of the raster cell , through function calculation, raster cells covering the research area are generated, and the UTM coordinates of each raster cell , the reference origin , and the precise size are recorded as a set . Therefore, all the rasters covering the research area are denoted as set .

[0079] In step 103, based on the distribution of the alighting locations in the passenger online car-hailing order data, the passenger flow demand of each raster cell is statistically calculated, and the high-frequency demand raster cells with a passenger flow demand higher than the preset demand threshold are screened out.

[0080] For example, a raster index mapping operation is performed on the alighting locations in the passenger online car-hailing order data to determine the raster cell corresponding to each alighting location ; the total number of alighting events in the raster cell within the preset time period is statistically calculated as the passenger flow demand of the raster cell ; the raster cells with a passenger flow demand higher than the preset demand threshold are determined as high-frequency demand raster cells ; the high-frequency demand raster cell set is obtained as .

[0081] Specifically, a deterministic mapping function from geographical coordinates to raster indices is defined . According to the origin, cell size, and direction of the raster system, the geographical coordinates ( ) are converted into a set of index numbers ([[]] ) that uniquely identify the raster cell to which the alighting location belongs. This index number consists of the raster column number in the longitude direction and the raster row number in the latitude direction.

[0082] Performing a raster index mapping operation on the passenger online car-hailing order data set can complete the rasterization process of the alighting location data, so that the alighting location in each order is accurately assigned to a specific geographical raster cell. For each raster cell that successfully matches the passenger alighting location (The grid cell is uniquely identified by its column number and row number), and the total number of alighting events carried by it within a preset unit time period is counted, denoted as the grid cell The passenger flow demand within a specific time period . Set a preset demand threshold . For all grid cells that have completed passenger flow counting, compare their passenger flow demand with the preset threshold . If the passenger flow demand of a certain grid cell meets the condition , then this grid cell is identified as a high-frequency demand grid cell, as shown in Figure 3 . Record the UTM coordinates , the reference origin , and the precise dimensions of the identified high-frequency demand grid cell as the high-frequency demand grid cell . Therefore, the high-frequency demand grid set can be denoted as .

[0083] In step 104, determine the location of the airport bus stops within the operation area according to this high-frequency demand grid cell.

[0084] Specifically, Figure 2 is a schematic flow chart of a method for determining the stop location as shown in Figure 1 , as shown in Figure 2 . This step 104 includes:

[0085] In step 1041, merge adjacent high-frequency demand grid cells to form the first passenger flow hot zone, and then perform a secondary merge on every two first passenger flow hot zones whose centroid distance is less than or equal to the preset distance threshold.

[0086] Exemplarily, based on the high-frequency demand grid cells obtained in the above steps, use a clustering method based on grid adjacency relationships to identify and aggregate spatially adjacent high-frequency demand grid cells to form a preliminary passenger flow hot zone. Each independently connected area is defined as a first passenger flow hot zone . The coordinates of each first passenger flow hot zone can be calculated by the following formula:

[0087] ,

[0088] ,

[0089] where and are the centroid coordinates of the first passenger flow hot zone respectively. and are respectively the UTM coordinates of the high-frequency demand grid cells that make up the first passenger flow hot zone ; is the passenger flow demand of the high-frequency demand grid cells that make up the first passenger flow hot zone ; On the basis of forming the first passenger flow hot zone, a preset distance threshold is set. For any two first passenger flow hot zones

[0090] and , the centroid distance between the first passenger flow hot zones is calculated according to ; if the centroid distance between them is less than or equal to the preset distance threshold , then these two first passenger flow hot zones are merged to form a new and larger first passenger flow hot zone, as shown in . This process is iterated until all the first passenger flow hot zones that meet the merger conditions are merged . Figure 4

[0091] In step 1042, the first passenger flow hot zone after secondary merger is segmented and adjusted so that the horizontal expansion distance and the vertical expansion distance of the adjusted hot zone do not exceed the preset maximum service scale, forming the second passenger flow hot zone

[0092] Specifically, calculate the maximum horizontal expansion distance and the maximum vertical expansion distance of each first passenger flow hot zone; if the maximum horizontal expansion distance of this first passenger flow hot zone is greater than , then segment this first passenger flow hot zone along the horizontal direction, where is the preset maximum service scale; if the maximum vertical expansion distance of this first passenger flow hot zone is greater than , then segment this first passenger flow hot zone along the vertical direction; if the maximum vertical expansion distance and the maximum horizontal expansion distance of this first passenger flow hot zone are both greater than , then segment this first passenger flow hot zone along the direction with the largest expansion distance; determine the segmentation position based on the principle that the absolute value of the difference between the sums of the passenger flow demands of all the grid cells inside the two hot zones formed after segmentation is the smallest; segment this first passenger flow hot zone according to the segmentation direction and the segmentation position until the maximum horizontal expansion distance of all the hot zones after segmentation​ and the maximum vertical spanwise distance are both less than , to obtain the second passenger flow hot zone ; Denote the set of the second passenger flow hot zones within the geographical area served by the airport bus as .

[0093] In step 1043, score the high-frequency demand grid cells in each of the second passenger flow hot zones according to the number of adjacent grid cells of each high-frequency demand grid cell, and select the high-frequency demand grid cell with the highest scoring result as the location of the airport bus stop.

[0094] Specifically, the method for scoring the high-frequency demand grid cells in each second passenger flow hot zone is as follows: , where is the scoring result, is the number of adjacent grid cells of the rd high-frequency demand grid cell in this second passenger flow hot zone ( ), is the passenger flow demand of this second passenger flow hot zone, and are weight coefficients, represents each grid cell, represents the high-frequency demand grid cell.

[0095] After obtaining the scoring results of each high-frequency demand grid cell, then sort these high-frequency demand grid cells in descending order according to the numerical values of the scoring results. Determine the grid cell where the candidate airport bus stop location is located as the grid cell with the highest score, and select the central point coordinates of this grid cell as the candidate airport bus stop location. Perform the above operations on each of the second passenger flow hot zones one by one, so as to accurately determine the layout locations of all airport bus stops. At the same time, the passenger flow information between each of the second passenger flow hot zones is also accurately matched with the locations of each airport bus stop.

[0096] In step 105, construct an airport bus scheduling optimization model.

[0097] Among them, the objective function of the airport bus scheduling optimization model is the sum of the minimized passenger travel time cost and the minimized bus operation cost. The constraint conditions of this airport bus scheduling optimization model are established according to the maximum number of passengers served by the starting station of the airport bus, the service level of the airport bus schedule, the lower limit of the time window when passengers expect the airport bus to arrive, and the upper limit of the time window when passengers expect the airport bus to arrive.

[0098] For example, the costs to be considered in the design of the airport bus network include the passenger travel time cost and the airport bus operation cost. Therefore, a reservation-responsive bus scheduling model based on aviation dynamics is established with the goal of minimizing the sum of the passenger travel time cost and the airport bus operation cost.

[0099] Specifically, an objective function is established based on the passenger travel time cost and the airport bus operation cost , where is the objective function, is the passenger travel time cost, is the airport bus operation cost, and are the weight coefficients. The calculation formula for the passenger travel time cost is: , where , , , is the time required for the passenger to walk from the airport to the airport bus stop location; is the in-vehicle time of the passenger, is the service deviation time cost, represents the passenger reservation demand and the airport bus relationship. If the passenger reservation demand is served by the airport bus , then , otherwise , is the distance between the airport where the passenger is located and the airport bus stop location, represents the average walking speed of the passenger to the airport bus stop location, represents the starting station location of the airport bus and the airport bus stop location distance, represents the airport bus from the station location driving to the station location average running speed, is the time window lower limit for the passenger to expect the airport bus to reach the station location , is the time window upper limit for the passenger to expect the airport bus to reach the station location , is the time when the passenger in the airport bus reaches the station location . The calculation formula for the airport bus operation cost is: , where , , , , is the vehicle fixed cost, is the operating variable cost, is the penalty cost for the airport bus deviating from the passenger's expected arrival time, is the penalty cost generated by the system rejecting an order, represents the airport bus whether it travels from the starting site location to the site location , if so then , if not then , is the depreciation coefficient for each operation of the airport bus, is the fuel cost per unit mileage of the airport bus vehicle, is the cost per unit mileage for the driver of the airport bus, is the penalty coefficient for the airport bus arriving earlier than the passenger's expected arrival time at the site location, is the penalty coefficient for the airport bus arriving later than the passenger's expected arrival time at the site location, is the penalty cost coefficient generated by the system rejecting an order, is the set of airport buses, is the set of airport bus site locations.

[0100] Establish the first constraint condition based on the maximum number of passengers served at the starting site location of the airport bus: , where, is the maximum number of passengers served at the starting site location of the airport bus, represents the passenger reservation demand and the airport bus relationship. If the passenger reservation demand is served by the airport bus then , otherwise , is the set of passenger reservation demands, is the set of airport buses;

[0101] Establish the second constraint condition based on the service level of the airport bus schedule: , where, is the minimum service level of the airport bus , is the maximum service level of the airport bus , represents the airport bus whether it travels from the starting site location to the site location , if so then , if not then , is the set of airport bus stop locations;

[0102] Establish the third constraint condition based on the lower limit of the time window when passengers expect the airport bus to arrive and the upper limit of the time window when passengers expect the airport bus to arrive: , where is the lower limit of the time window when passengers expect the airport bus to arrive at the stop location , is the upper limit of the time window when passengers expect the airport bus to arrive at the stop location .

[0103] It can be understood that restricting the capacity of the airport bus schedule is to ensure that the demand carried by each airport bus schedule does not exceed the total carrying capacity of its actual vehicle; restricting the service level of the airport bus schedule is to ensure the service quality of each airport bus schedule; restricting the airport bus to arrive at the passenger's alighting stop within the upper limit of the time window when passengers expect the airport bus to arrive.

[0104] In step 106, a multi-layer coding optimization algorithm is used to solve the airport bus scheduling optimization model, and the airport bus operation route set, departure schedule, and passenger allocation plan are output to optimize the airport bus operation area network.

[0105] Exemplarily, in order to achieve the efficient solution of the reservation response bus scheduling model, an optimization algorithm based on Adaptive Large Neighborhood Search (ALNS) is proposed in the disclosed embodiments of the present invention. By dynamically adjusting the combination of destruction and repair operations, it flexibly explores the solution space and quickly generates a low-cost and high-service-quality scheduling plan in the scenario of dynamic flight changes.

[0106] Specifically, a three-layer coding method is used to design the solution: Define the set of airport buses as the first-layer coding, where is the shift vehicle number of the airport bus ; Define the service reservation request sequence as the second-layer coding, where is the service reservation request of the airport bus ; Define the departure time sequence as the third-layer coding, where is the departure time of the initial station corresponding to the shift vehicle number of the airport bus ; Use a three-layer coding method to design and generate an initial feasible solution .

[0107] Passenger demand allocation: Using a greedy strategy, allocate each passenger reservation demand to the airport bus , giving priority to meeting the time window constraint and service capacity limit. The allocation rule is:

[0108]

[0109] According to the passenger demand allocation result, use the Dijkstra algorithm to generate the initial airport bus operation route and calculate the departure time under the shortest path .

[0110] Feasibility verification: Check whether the generated initial feasible solution meets the constraint conditions established in step 103 above. If there are conflicts, repair them by adjusting the departure time or reallocating passengers until a feasible solution that meets the constraint conditions is obtained.

[0111] Define multiple groups of destruction operations (Destroy) and repair operations (Repair), and select the optimal operation combination through a dynamic weight adjustment mechanism:

[0112] Design four destruction operators to expand the neighborhood of the candidate solution, specifically including:

[0113] Random removal operator , which means randomly removing from the current solution the passenger reservation demand , obtaining the solution after random removal and adding the removed reservation demand back to the list of demands to be responded to .

[0114] Maximum time window conflict removal operator : Define the time window conflict , and give priority to removing the passengers with the most serious time window conflicts to obtain the solution after removing the maximum time window conflicts and adding the removed reservation demand back to the list of demands to be responded to .

[0115] Inefficient path removal operator : Based on screen out the shift with the highest path cost , regard it as an inefficient path and remove it to obtain the solution after inefficient removal and adding the removed reservation demand back to the list of demands to be responded to .

[0116] Worst destruction operator : Define the destruction cost , where represents the total cost of the current solution , represents the hypothetical solution after removing the reservation request . The disruption cost is sorted in descending order, and the reservation requests ranked at the top are selected for removal to obtain the solution after the worst disruption removal , and the removed reservation requirements are re-added to the list of demands to be responded .

[0117] For the disrupted solution and the list of demands to be responded , two repair operators are designed to accelerate the neighborhood search process. Specifically:

[0118] Random repair operator : Traverse each reservation request in the list of demands to be responded , and randomly insert it into , update the airport bus set , the service reservation request sequence and the departure time sequence . Until all the reservation requests in the list of demands to be responded are inserted, and finally a new solution is obtained.

[0119] Greedy repair operator : Define the repair cost , where represents the total cost of the current solution , represents the hypothetical solution after inserting the reservation request in the list of demands to be responded . The repair cost is sorted in ascending order, and the repair is performed in the way of selecting the one ranked at the top according to the principle of the smallest cost change to obtain the new repaired solution , update the airport bus set , the service reservation request sequence and the departure time sequence . Until all the reservation requests in the list of demands to be responded are inserted, and finally a new solution is obtained.

[0120] Randomly combine the disruption operator and the repair operator designed in the above steps pairwise to generate Operator pair group 。

[0121] Define the initial weight of each operator pair and the initial score is 。 。

[0122] Repeat the above steps for iterative optimization until the stopping criterion of the algorithm is met.

[0123] Based on the updated operator pair weights, select the combination of destruction and repair operations for the next iteration according to the roulette wheel strategy.

[0124] According to the determined operator pair , it can be known that the destruction operator and the repair operator are selected for this iteration. Perform operations on the current solution according to the destruction operation and the repair operation to obtain a new solution 。

[0125] Represent the current solution, the new solution and the optimal solution respectively , and is the objective function value. If , then ; if , then ; if , calculate the simulated annealing probability , generate a random number , if , then ; otherwise, the new solution is not accepted . Specifically, the calculation formula of the annealing probability

[0126] is as follows:

[0127] After each iteration, update its score according to the improvement degree of the operation on the objective function. If the solution generated after the destruction and repair operations of the operator pair is the new global optimal solution , the score increases by ; if the solution generated after the destruction and repair operations of the operator pair is a better candidate solution , the score increases by ; if the solution generated after the destruction and repair operations of the operator pair is a new feasible solution but does not improve the objective function value, Score increase 。

[0128] Every number of iterations, update the operator pair weights. Specifically, the update formula for the operator pair is:

[0129]

[0130] where is the learning rate.

[0131] The algorithm terminates when any of the following conditions are met: (1) reaching the maximum number of iterations; (2) the global optimal solution has not been improved for consecutive iterations; (3) the computation time exceeds the threshold.

[0132] After triggering the termination condition, the algorithm terminates and outputs the optimal scheduling plan 。This includes the set of airport bus operation routes, departure schedules, passenger allocation plans, and the objective function value within the scheduling plan.

[0133] In addition, some defined variables in the disclosed embodiments of the present invention need to be explained:

[0134] Define the 0-1 variable , if the airport bus travels from the starting station location to the station location , then , otherwise it is equal to . Where the station location belongs to the set N of airport bus station locations, and the airport bus belongs to the set of airport buses .

[0135] Define the 0-1 variable indicating the relationship between the passenger reservation demand and the airport bus . If the passenger reservation demand is served by the airport bus , then , otherwise .

[0136] Define the continuous variable indicating the time when the airport bus arrives at the station location .

[0137] Define the continuous variable indicating the time when the airport bus travels from the starting station location to the station location Average running speed, m / s.

[0138] Example:

[0139] The data used in this example are the online car-hailing order records of a certain city, collected from some online car-hailing platforms during a specific period. The total amount of data is 1,726,511. This data is based on actual operation records, has a high spatio-temporal resolution and good data integrity, and can relatively truly reflect the travel behavior characteristics of online car-hailing passengers in a certain city, such as Figure 5 shown. Select the order data with the departure place being the airport as the order data of passengers' online car-hailing, so as to identify the locations of alternative airport bus stops, provide a reasonable stop layout for the subsequent design of the airport bus network, and finally select 81 alternative express bus stops, Figure 6 which is the spatial distribution of the locations of alternative airport bus stops. The reservation platform has received a total of 18 passenger reservation demands affected by flight dynamics.

[0140] As Figure 7 shown, the planned airport bus line is 38.65 km in total length, and the estimated travel time is 45 minutes. From the perspective of passengers' psychology, such a duration is acceptable for medium and long-distance travel. By comparing the spatial straight-line distance of the line with the travel distance of the airport bus, it is calculated that the total detour distance of the airport bus is 12.53 km, the average detour distance is 1.14 km, and the non-straightness coefficient of the line is 1.43, indicating that the line has a wide coverage range and the detour degree is within an acceptable range. Taking the average running speed of the airport bus as 35 km / h as an example, by comparing and analyzing the arrival times of passengers taking the express bus and taking the online car-hailing, it can be seen that the maximum delay in the arrival time of passengers taking the airport bus is 18.76 minutes, accounting for about 1 / 4 of the total travel time of the passenger, and the average delay time is 1.52 minutes. Thus, it can be seen that the overall operation efficiency of the line is relatively high and the additional waiting time of passengers is less. The optimized line has 14 stop sites, meeting the limit of the maximum number of stops. The average distance between stops of the line is 2.78 km. The optimal line can meet 88.89% of the passengers' demands, indicating that the service quality of the line is relatively high and can effectively improve the travel experience of passengers.

[0141] The above results also show that the airport bus network optimization method integrating air traffic control information proposed by the present invention has good characteristics and can be extended to practical applications.

[0142] Figure 8 is a schematic structural diagram of an airport bus network optimization system integrating air traffic control information shown according to an exemplary embodiment. As Figure 8 shown, the system 800 includes:

[0143] A data acquisition module 810, which obtains the geographical scope of the airport bus operation area, the passenger reservation demand generated by the impact of flight dynamics changes, and the passenger online car-hailing order data according to the air traffic control information. The passenger reservation demand includes: the number of passengers, the reservation time window, and the destination.

[0144] A rasterization processing module 820, connected to the data acquisition module 810, performs rasterization processing on the operation area, so that the operation area is divided into an airport bus operation area network composed of several grid cells.

[0145] A high-frequency grid determination module 830, connected to the rasterization processing module 820, statistically analyzes the passenger flow demand of each grid cell based on the distribution of the alighting locations in the passenger online car-hailing order data, and filters out the high-frequency demand grid cells with a passenger flow demand higher than the preset demand threshold.

[0146] A station location determination module 840, connected to the high-frequency grid determination module 830, determines the location of the airport bus stations in the operation area according to the high-frequency demand grid cells.

[0147] An optimization model construction module 850, connected to the station location determination module 840, constructs an airport bus scheduling optimization model. The objective function of the airport bus scheduling optimization model is the sum of the minimized passenger travel time cost and the minimized bus operation cost. The constraint conditions of the airport bus scheduling optimization model are established according to the maximum number of passengers served at the starting station of the airport bus, the service level of the airport bus schedule, the lower limit of the time window for passengers to expect the arrival of the airport bus, and the upper limit of the time window for passengers to expect the arrival of the airport bus.

[0148] An optimization model solving module 860, connected to the optimization model construction module 850, uses a multi-layer coding optimization algorithm to solve the airport bus scheduling optimization model, and outputs a set of airport bus operation routes, a departure schedule, and a passenger allocation plan to optimize the airport bus operation area network.

[0149] Optionally, the station location determination module 840 is used for:

[0150] Merge adjacent high-frequency demand grid cells to form a first passenger flow hot zone, and then perform secondary merging on every two first passenger flow hot zones with a centroid distance less than or equal to the preset distance threshold.

[0151] Perform segmentation and adjustment on the first passenger flow hot zone after secondary merging, so that the horizontal expansion distance and the vertical expansion distance of the adjusted hot zone do not exceed the preset maximum service scale, and form a second passenger flow hot zone.

[0152] Score the high-frequency demand grid cells in each of the second passenger flow hot zones according to the number of adjacent grids of each high-frequency demand grid cell, and select the high-frequency demand grid cell with the highest scoring result as the location of the airport bus stop.

[0153] In summary, the present disclosure relates to an airport bus network optimization method and system integrating air traffic control information. The method includes: obtaining the geographical scope of the airport bus operation area, the passenger reservation demand generated by flight dynamic changes, and the passenger online car-hailing order data according to the air traffic control information; determining the locations of all airport bus stops within the airport bus operation area; establishing an objective function based on the passenger travel time cost and the airport bus operation cost, and establishing constraint conditions based on the maximum number of passengers served by the starting station of the airport bus, the service level of the airport bus schedule, the lower limit of the time window when passengers expect the airport bus to arrive, and the upper limit of the time window when passengers expect the airport bus to arrive; solving the reservation response bus scheduling model to obtain the airport bus scheduling plan. It can quickly adjust the operation strategy and optimize the vehicle scheduling by mastering in advance the number of passengers taking the airport bus and their destinations in the event of flight changes, thereby effectively saving the waiting time and in-vehicle time of passengers, and further improving the passenger satisfaction in the case of flights.

[0154] The preferred embodiments of the present disclosure have been described in detail above in conjunction with the accompanying drawings. However, the present disclosure is not limited to the specific details in the above embodiments. Within the scope of the technical concept of the present disclosure, various simple modifications can be made to the technical solutions of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.

[0155] In addition, it should be noted that, in the case of no contradiction, the various specific technical features described in the above specific embodiments can be combined in any suitable manner. To avoid unnecessary repetition, the present disclosure will not separately describe various possible combination methods.

[0156] In addition, any combination can be made between various different embodiments of the present disclosure as long as it does not violate the idea of the present disclosure, and it should also be regarded as the content disclosed by the present disclosure.

Claims

1. An optimization method for the airport bus network integrating air traffic control information, characterized in that The method includes: Obtaining the geographical scope of the airport bus operation area, the passenger reservation demand generated by the impact of flight dynamic changes, and the passenger online car-hailing order data according to the air traffic control information. The passenger reservation demand includes: the number of passengers, the reservation time window, and the destination. Performing grid processing on the operation area to divide the operation area into an airport bus operation area network composed of a number of grid cells. Based on the distribution of the getting-off locations in the passenger online car-hailing order data, statistically calculating the passenger flow demand of each grid cell, and screening out the high-frequency demand grid cells with a passenger flow demand higher than the preset demand threshold. Determining the location of the airport bus stops within the operation area according to the high-frequency demand grid cells. Constructing an airport bus scheduling optimization model. The objective function of the airport bus scheduling optimization model is the sum of the minimized passenger travel time cost and the minimized bus operation cost. The constraint conditions of the airport bus scheduling optimization model are established according to the maximum number of passengers served by the starting station of the airport bus, the service level of the airport bus schedule, the lower limit of the time window when passengers expect the airport bus to arrive, and the upper limit of the time window when passengers expect the airport bus to arrive. Using a multi-layer coding optimization algorithm to solve the airport bus scheduling optimization model, and outputting the airport bus operation route set, the departure schedule, and the passenger allocation plan to optimize the airport bus operation area network.

2. The airport bus network optimization method integrating air traffic control information according to claim 1, wherein The determining the location of the airport bus stops within the operation area according to the high-frequency demand grid cells includes: Merging adjacent high-frequency demand grid cells to form the first passenger flow hot zone, and then performing secondary merging on every two first passenger flow hot zones with a centroid distance less than or equal to the preset distance threshold. Performing segmentation and adjustment on the first passenger flow hot zone after secondary merging so that the horizontal extension distance and the vertical extension distance of the adjusted hot zone do not exceed the preset maximum service scale, forming the second passenger flow hot zone. Scoring the high-frequency demand grid cells in each second passenger flow hot zone according to the number of adjacent grid cells of each high-frequency demand grid cell in the second passenger flow hot zone, and selecting the high-frequency demand grid cell with the highest scoring result as the location of the airport bus stop.

3. The method for optimizing the airport bus network integrating air traffic control information according to claim 1, wherein The statistically calculating the passenger flow demand of each grid cell based on the distribution of the getting-off locations in the passenger online car-hailing order data and screening out the high-frequency demand grid cells with a passenger flow demand higher than the preset demand threshold includes: Perform a grid index mapping operation on the drop-off locations in the passenger online car-hailing order data to determine the grid cells corresponding to each drop-off location ; Count the total number of passenger alighting events of the grid cell within a preset time period as the passenger flow demand of the grid cell ; The passenger flow demand higher than the preset demand threshold of the grid cell is determined as a high-frequency demand grid cell ; Obtain the set of high-frequency demand grid cells as .

4. The airport bus network optimization method integrating air traffic control information according to claim 2, characterized in that The performing segmentation and adjustment on the first passenger flow hot zone after secondary merging so that the horizontal extension distance and the vertical extension distance of the adjusted hot zone do not exceed the preset maximum service scale, forming the second passenger flow hot zone includes: Calculate the maximum horizontal span distance of each first passenger flow hot zone and the maximum vertical span distance ; If the maximum horizontal extent of the first passenger flow hot zone is greater than , then the first passenger flow hot zone is segmented in the horizontal direction, where is the preset maximum service scale; If the maximum vertical span distance of the first passenger flow hot zone is greater than , then the first passenger flow hot zone is segmented along the vertical direction; If the maximum vertical span distance and the maximum horizontal span distance of the first passenger flow hot zone are both greater than , then the first passenger flow hot zone is segmented along the direction with the maximum span distance; Determining the segmentation position based on the principle that the absolute value of the difference between the sums of the passenger flow demands of all grid cells within the two hot zones formed after segmentation is the smallest. Divide the first passenger flow hot zone according to the division direction and division position until the maximum horizontal extension distance and the maximum vertical extension distance of all the hot zones after division are both less than , and obtain the second passenger flow hot zone ; Denote the set of the second passenger flow hotspots within the geographical area where the airport bus operates as .

5. The method for optimizing an airport bus network integrating air traffic control information according to claim 2, wherein The method for scoring each high-frequency demand grid cell in the second passenger flow hot zone is as follows: , where is the scoring result, is the number of adjacent grid cells of the th high-frequency demand grid cell in the second passenger flow hot zone ( ), is the passenger flow demand of the second passenger flow hot zone, and are weight coefficients, represents each grid cell, represents the high-frequency demand grid cell.

6. The method for optimizing the airport bus network integrating air traffic control information according to claim 1, characterized in that The objective function of the airport bus scheduling optimization model is expressed as: , where is the objective function, is the travel time cost of passengers, is the operating cost of airport buses, and are the weight coefficients. The calculation formula for the travel time cost of passengers is: , where , , , is the time required for passengers to walk from the airport to the airport bus stop location; is the in-vehicle time of passengers, is the service deviation time cost, represents the passenger reservation demand and the airport bus The relationship between them is that if the passenger reservation demand is served by the airport bus , then , otherwise . is the distance between the airport where the passenger is located and the airport bus stop location, represents the average walking speed of passengers to the airport bus stop location, represents the airport bus The distance between the starting station location and the airport bus stop location , represents the airport bus From the stop location Drive to the stop location The average running speed of, is the time window lower limit for the passenger to expect the airport bus To reach the stop location , is the time window upper limit for the passenger to expect the airport bus to reach the stop location , is the airport bus The time when passengers arrive at the stop location . The calculation formula for the operating cost of airport buses is: , where , , , , is the vehicle fixed cost, is the operating variable cost, is the penalty cost for the airport bus deviating from the passenger's expected arrival time, The penalty cost generated by the system for rejecting an order Indicates the airport bus Whether to travel from the starting station location to the station location If so, then If not, then , Is the depreciation coefficient for each operation of the airport bus Is the fuel cost per unit mileage of the airport bus vehicle Is the cost per unit mileage for the driver of the airport bus Is the penalty coefficient for the actual arrival time of the airport bus being earlier than the passenger's expected arrival time at the station location Is the penalty coefficient for the actual arrival time of the airport bus being later than the passenger's expected arrival time at the station location Is the penalty cost coefficient generated by the system for rejecting an order Is the airport bus collection Is the set of airport bus station locations 7. The method for optimizing the airport bus network integrating air traffic control information according to claim 1, characterized in that, The process of establishing the constraint conditions includes: Establish the first constraint condition based on the maximum number of passengers served at the starting station of the airport bus: , where is the maximum number of passengers served at the starting station of the airport bus, represents the passenger reservation demand and the airport bus The relationship between them is that if the passenger reservation demand is served by the airport bus , then , otherwise . is the set of passenger reservation demands, is the set of airport buses; Establish the second constraint condition according to the service level of the airport bus schedule: , where is the minimum service level of the airport bus , is the maximum service level of the airport bus , indicates whether the airport bus travels from the starting site location to the site location . If so, then . If not, then , is the set of airport bus stop locations; Establish the third constraint condition based on the lower limit of the time window when passengers expect the airport bus to arrive and the upper limit of the time window when passengers expect the airport bus to arrive: , where is the lower limit of the time window when passengers expect the airport bus to arrive at the station location , and is the upper limit of the time window when passengers expect the airport bus to arrive at the station location .

8. The airport bus network optimization method integrating air traffic control information according to claim 1, characterized in that The using a multi-layer coding optimization algorithm to solve the airport bus scheduling optimization model includes: Group the airport buses Define it as the first-level code, where is the vehicle number of the scheduled flight of the airport bus ; Define the service reservation request sequence as the second-layer coding, where is the service reservation request for the airport bus ; Define the departure time sequence as the third-layer encoding, where is the vehicle number of the airport bus corresponding to the departure time at the starting station of the corresponding shift; Design and generate the initial feasible solution by using a three-layer coding method .

9. An airport bus network optimization system integrating air traffic control information, characterized in that, The system includes: A data acquisition module, which acquires the geographical scope of the airport bus operation area, the passenger reservation demand generated by the impact of flight dynamics changes, and the passenger online car-hailing order data according to the air traffic control information. The passenger reservation demand includes: the number of passengers, the reservation time window, and the destination. A rasterization processing module, connected to the data acquisition module, rasterizes the operation area, so that the operation area is divided into an airport bus operation area network composed of a number of grid cells. A high-frequency grid determination module, connected to the rasterization processing module, statistically calculates the passenger flow demand of each grid cell based on the distribution of the alighting locations in the passenger online car-hailing order data, and screens out the high-frequency demand grid cells with the passenger flow demand higher than the preset demand threshold. A station location determination module, connected to the high-frequency grid determination module, determines the airport bus station locations within the operation area according to the high-frequency demand grid cells. An optimization model construction module, connected to the station location determination module, constructs an airport bus scheduling optimization model. The objective function of the airport bus scheduling optimization model is the sum of the minimized passenger travel time cost and the minimized bus operation cost. The constraint conditions of the airport bus scheduling optimization model are established according to the maximum number of passengers served by the starting station of the airport bus, the service level of the airport bus schedule, the lower limit of the time window when passengers expect the airport bus to arrive, and the upper limit of the time window when passengers expect the airport bus to arrive. An optimization model solution module, connected to the optimization model construction module, uses a multi-layer coding optimization algorithm to solve the airport bus scheduling optimization model, and outputs the airport bus operation route set, the departure schedule, and the passenger allocation plan to optimize the airport bus operation area network.

10. The airport bus network optimization system integrating air traffic control information according to claim 9, characterized in that The station location determination module is used for: Merging adjacent high-frequency demand grid cells to form a first passenger flow hot zone, and then performing secondary merging on every two first passenger flow hot zones with the centroid distance less than or equal to the preset distance threshold. Performing segmentation and adjustment on the first passenger flow hot zone after secondary merging, so that the horizontal extension distance and the vertical extension distance of the adjusted hot zone do not exceed the preset maximum service scale, forming a second passenger flow hot zone. Scoring the high-frequency demand grid cells in each second passenger flow hot zone according to the number of adjacent grid cells of each high-frequency demand grid cell in the second passenger flow hot zone, and selecting the high-frequency demand grid cell with the highest scoring result as the airport bus station location.

Images