Airport special vehicle real-time scheduling method and system based on digital twin model

Abstract

The application discloses an airport special vehicle real-time scheduling method based on a digital twin model, which comprises the following steps: an edge server receives special vehicle real-time information, calculates special vehicle priority according to the special vehicle real-time information, and sends the obtained special vehicle priority to a cloud center; the cloud center constructs a digital twin model based on an edge-cloud computing architecture, calculates flight priority, and determines a special vehicle scheduling scheme according to the flight priority and the special vehicle priority; the cloud center performs online simulation on the special vehicle scheduling scheme, issues real-time scheduling instructions to the special vehicle according to the simulation result, and sends the real-time scheduling instructions to the edge server. The method adopts the edge-cloud computing architecture to construct the digital twin model, considers real-time information of the special vehicle priority and the flight priority on the basis of the digital twin model, adjusts the scheduling plan of the special vehicle according to the flight priority, realizes real-time adjustment and accurate control of a flight guarantee process, and improves flight guarantee efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of airport vehicle scheduling, in particular to an airport special vehicle real-time scheduling method and system based on a digital twin model. BACKGROUND

[0002] The ground support of port flights is mainly borne by special vehicles, which plays a key role in determining the on-time departure rate of flights. This is also one of the most basic elements reflecting the efficiency of airport operations. Therefore, the scheduling strategy of airport special vehicles directly affects the efficiency of the airport and the departure time of the flight. However, with the rapid growth of air traffic in recent years, the number and frequency of port flights served by the airport have increased significantly, intensifying the pressure on airport ground services. In addition, the phenomenon of fluctuations between actual arrival time and estimated arrival time of flights is very common in many airports. For example, in China, the average on-time arrival rate of flights is only 88.7%. In fact, once the flight schedule fluctuates, the previous ground service plan must be adjusted. This also increases the burden of the airport to arrange special vehicles for turnaround flights. Due to the interweaving of these two factors, the scheduling process of special vehicles is affected. In the prior art, the research on ground service resource allocation is mainly divided into two aspects of optimization algorithm and offline simulation, but there is no real-time and accurate control of the ground service process. SUMMARY

[0003] In view of the defects in the prior art, the present application provides an airport special vehicle real-time scheduling method based on a digital twin model, which can adjust the vehicle scheduling plan in real time according to the fluctuation of the flight plan, realize real-time adjustment and accurate control of the flight support process, and improve the efficiency of flight support.

[0004] The present application provides an airport special vehicle real-time scheduling system based on a digital twin model, which can adjust the vehicle scheduling plan in real time according to the fluctuation of the flight plan, realize real-time adjustment and accurate control of the flight support process, and improve the efficiency of flight support.

[0005] In the first aspect, the present application provides an airport special vehicle real-time scheduling method based on a digital twin model, which includes the following steps:

[0006] The special vehicle terminal node sends the real-time information of the special vehicle to the edge server;

[0007] The edge server receives the real-time information of the special vehicle, calculates the priority of the special vehicle according to the real-time information of the special vehicle, and sends the calculated priority of the special vehicle to the cloud center;

[0008] The cloud center constructs a digital twin model based on an edge cloud computing architecture, calculates flight priorities based on special vehicle priorities, and determines a special vehicle scheduling scheme according to the flight priorities and the special vehicle priorities.

[0009] The cloud center performs online simulation on the special vehicle scheduling scheme, obtains simulation results, and sends real-time scheduling instructions to the special vehicles according to the simulation results.

[0010] The edge server receives the real-time scheduling instructions and schedules and commands the special vehicles according to the real-time scheduling instructions.

[0011] In a second aspect, the present application provides an airport special vehicle real-time scheduling system based on a digital twin model, which comprises a special vehicle terminal node, an edge server and a cloud center.

[0012] The edge server is configured to receive real-time special vehicle information, calculate special vehicle priorities according to the real-time special vehicle information, and send the calculated special vehicle priorities to the cloud center.

[0013] The cloud center is configured to construct a digital twin model based on an edge cloud computing architecture, calculate flight priorities based on vehicle priorities, determine a special vehicle scheduling scheme according to the flight priorities and the special vehicle priorities, perform online simulation on the special vehicle scheduling scheme, obtain simulation results, send real-time scheduling instructions to the special vehicles according to the simulation results, and send the real-time scheduling instructions to the edge server.

[0014] The edge server is further configured to receive the real-time scheduling instructions and schedule and command the special vehicles according to the real-time scheduling instructions.

[0015] The present application has the following advantages:

[0016] The present application provides an airport special vehicle real-time scheduling method and system based on a digital twin model, which adopts a cloud computing and edge computing architecture to construct a digital twin model, so as to realize accurate and real-time control of special vehicles. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the specific embodiments of the present application or the prior art, the accompanying drawings needed to be used in the specific embodiments or prior art description will be briefly introduced. In all the drawings, similar elements or parts are generally identified by similar reference signs. In the drawings, the elements or parts are not necessarily drawn according to the actual proportions.

[0018] Figure 1 A flow chart of an airport special vehicle real-time scheduling method based on a digital twin model provided by a first embodiment of the present application is shown;

[0019] Figure 2 A structural block diagram of an airport special vehicle real-time scheduling system based on a digital twin model provided by another embodiment of the present application is shown. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0021] It should be understood that, when used in the specification and the appended claims, the terms "comprise" and "include" indicate the presence of the described features, integers, steps, operations, elements, and / or components, but do not exclude one or more other features, integers, steps, operations, elements, components, and / or groups thereof.

[0022] It should also be understood that the terms used in the present application specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in the present application specification and the appended claims, unless otherwise clearly indicated by the context, the singular forms "a", "an" and "the" are intended to include the plural forms as well.

[0023] It should be further understood that the term "and / or" used in the present application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.

[0024] As used in the specification and the appended claims, the term “if’ can be interpreted as meaning “when” or “upon” or “in response to a determination” or “in response to a detection” depending on the context. Similarly, the phrase “if it is determined” or “if [the described condition or event] is detected” can be interpreted as meaning “upon a determination” or “in response to a determination” or “upon a detection of [the described condition or event]” or “in response to a detection of [the described condition or event]” depending on the context.

[0025] It should be noted that the technical terms or scientific terms used in the present application should be understood as the general meaning understood by the skilled person in the field of the present application, unless otherwise specified.

[0026] As Figure 1 shown, a flowchart of a method for airport special vehicle real-time scheduling based on a digital twin model according to a first embodiment of the present application is shown, which includes the following steps:

[0027] The special vehicle terminal node sends the special vehicle real-time information to the edge server;

[0028] The edge server receives the special vehicle real-time information, calculates the special vehicle priority according to the special vehicle real-time information, and sends the calculated special vehicle priority to the cloud center;

[0029] The cloud center constructs a digital twin model based on the edge-cloud computing architecture, calculates the flight priority based on the special vehicle priority, and determines the special vehicle scheduling scheme according to the flight priority and the special vehicle priority;

[0030] The cloud center performs online simulation on the special vehicle scheduling scheme, obtains simulation results, and issues real-time scheduling instructions to the special vehicle according to the simulation results, and sends the real-time scheduling instructions to the edge server;

[0031] The edge server receives the real-time scheduling instructions and schedules and commands the special vehicle according to the real-time scheduling instructions.

[0032] In this embodiment, the special vehicle terminal node is four different types of autonomous special vehicles, and the four special vehicles are directly connected to the edge server. The special vehicle terminal node is mainly responsible for collecting special vehicle real-time information and sending it to the edge server, including: the running time of the special vehicle completing the ground service task, the position and speed of the special vehicle, and the state of the special vehicle. The special vehicle terminal node also receives instructions issued by the edge server to control its operation in real time, such as guiding the route, speed control and scheduling command. The special vehicle terminal node and other objects such as roads, flights, stations and buildings form the physical entities of the digital twin model.

[0033] The edge servers are distributed at different locations on the ground, covering the entire working area of the special vehicle, and receive real-time information sent by the special vehicle, perform preliminary processing, and then send it to the cloud center. For example, the duration process of the special vehicle can be completed at the edge server, and a regression is performed through a machine learning algorithm to adapt to the trend of the duration at different time intervals in a day. Through simple regression fitting calculation, the relationship between the duration of the special vehicle running work and the different time intervals in a day can be obtained and sent to the cloud center as a supply for formulating a scheduling plan. The edge server can also transmit information such as the position, state, and speed of the special vehicle between the special vehicle terminal node and the cloud center, and the edge server can also calculate the priority of the special vehicle according to the real-time information of the vehicle, and send the calculated priority of the special vehicle to the cloud center. After receiving the real-time scheduling instruction sent by the cloud center, the special vehicle is scheduled and commanded according to the real-time scheduling instruction. Each edge server is responsible for collecting and processing the information of the special vehicles within its coverage range, thereby quickly reducing the excessive or unbalanced computing burden. Therefore, the edge server not only can collect real-time raw data and improve distributed intelligence in the processing process, but also can reduce the computing load of the cloud center, and realize real-time control of the special vehicle.

[0034] Specifically, the priority of the special vehicle is measured by two parts, i.e., the time and resource consumption spent by the special vehicle to complete the target flight task. The edge server calculates the priority of the special vehicle according to the real-time information of the vehicle, which includes: determining a first priority according to the time spent by the special vehicle to complete the target flight task. The calculation formula of the first priority Priority1 is as follows:

[0035] Priority1 = -(T1 + T2)

[0036] T1 = T m + T n

[0037] In the formula, Priority1 is the first priority, T1 represents the remaining time for the special vehicle to complete the current task. T2 represents the time for completing the target flight ground service task. T1 can be divided into two parts T m and T n ; T m represents the time spent by the special vehicle to reach the target flight point. Due to the edge cloud-based digital twin model, it can be calculated by the nearby edge server and sent to the cloud center to update the digital twin model information in real time. T nis the time for completing the ground service task when reaching the target flight. The priority is determined according to the size of the value of the first priority, that is, the more time the special vehicle takes to complete the target flight task, the lower the level of the first priority. Since the running time interval data of each special vehicle is recorded by the edge server, in the cloud center, these time interval data can be fitted by a machine learning algorithm, such as an interval value data regression algorithm.

[0038] The method for calculating the priority of the special vehicle according to the real-time information of the special vehicle further comprises: determining a second priority according to the resource consumption of the special vehicle, and the calculation formula of the second priority Priority2 is as follows:

[0039]

[0040] In the formula, Priority2 is the second priority, P(v) represents the power when the speed is the average speed v, s represents the path length of the special vehicle, and t(v) represents the time taken by the special vehicle to reach the target flight point, which can be represented by T m . Under the same conditions, the priority is determined according to the size of the value of the second priority, that is, the higher the energy consumption, the lower the level of the second priority.

[0041] The priority of the special vehicle Priority vehicle is calculated by the following equation,

[0042] Priority vehicle = γ·Priority1+ ρ·Priority2

[0043] wherein Priority vehicle is the priority of the special vehicle, and γ, ρ are index weights.

[0044] The edge server sends the calculated priority of the special vehicle to the cloud center.

[0045] The cloud center builds a digital twin model based on the edge cloud computing architecture, and builds seven intelligent twin objects: twin special vehicles, twin roads, twin roadside units, twin base stations, twin buildings, twin time, and twin flights. At the same time, all these twin objects have simple computing and interaction functions, which can improve the intelligence level of physical targets without increasing additional costs, and update their hardware to complete some simple intelligent functions. By redefining the action and interaction rules of the agent, various traffic scenarios can be simulated and evaluated, and knowledge of different scenarios can be obtained through AI, data mining and machine learning. The cloud center receives real-time information of the special vehicle terminal node sent by the edge server, can detect the evolution of the physical scene situation, calculates the flight priority based on the priority of the special vehicle, determines the special vehicle scheduling scheme according to the flight priority and the priority of the special vehicle, and performs online simulation on the special vehicle scheme. The simulation and verification of the scheduling scheme are obtained, and the simulation results are obtained according to the simulation results. Real-time scheduling instructions are issued to the special vehicle, and the real-time scheduling instructions are sent to the edge server. The edge server schedules and controls the operation and movement of the special vehicle.

[0046] The specific method for calculating the flight priority based on the priority of the special vehicle and determining the special vehicle scheduling scheme according to the flight priority and the priority of the special vehicle is as follows: the ground support service task of the target flight is decomposed into a unit subtask sequence; the priority of the special vehicle is matched with each unit subtask of the ground support service to obtain a preliminary allocation scheme; when all sub-class support processes of the target flight are matched with the special vehicle with the highest priority, the estimated flight support end time under the preliminary allocation scheme is obtained; the flight priority is calculated according to the estimated flight support end time published by the airport and the estimated flight support end time under the preliminary allocation scheme; the flights are sorted according to the flight priority; the priority of the corresponding special vehicle is matched according to the high and low of the flight priority, until all flights are allocated to the special vehicle to meet its ground support service.

[0047] Wherein, the flight priority Priority flight is calculated as follows:

[0048] Priority flight =-β*k*(t Eend -t end )+ε*(1-k)*(t end -t Eend )

[0049] When all sub-class support processes of the target flight are matched with the special vehicle with the highest priority, the time t end of the flight support process under this allocation scheme can be obtained. Therefore, t end represents the estimated flight support end time, and t Eendrepresent the estimated flight support end time published by the airport, β, ε represent the weight, k represents a pointer parameter, k is as follows:

[0050]

[0051] k is 1, representing that the estimated flight support end time is less than the estimated flight support end time published by the airport, k is 0, representing that the estimated flight support end time is greater than the estimated flight support end time published by the airport. Therefore, when calculating the priority of all flights on the ground, the cloud center will compare the priorities of all flights, select the flight with the highest priority to lock the special vehicle with the highest priority, and then the flight will exit the loop, and other flights will continue to circulate and be assigned until all flights are assigned to special vehicles to meet their ground support services.

[0052] The embodiment provides an airport special vehicle real-time scheduling method based on a digital twin model, which adopts cloud computing and edge computing architecture to construct a digital twin model to realize accurate and real-time control of special vehicles, adopts an edge server to collect and process special vehicle information within its coverage range, and the edge server not only collects real-time raw data and improves distributed intelligence in the processing process, but also reduces the computing load of the cloud center. On the basis of the digital twin model, considering the real-time information of the special vehicle priority and the flight priority, the scheduling plan of the special vehicle can be adjusted in real time according to the flight priority, the real-time adjustment and accurate control of the flight support process are realized, and the flight support efficiency is improved.

[0053] After the special vehicle scheduling scheme is formulated, in order to cope with the common fluctuations in actual execution, real-time edge adjustment based on digital twins is needed for the special vehicle working process, so that the simulation scheduling result is consistent with the actual execution, the ground service time can be shortened, and the flight on-time departure rate can be improved. Real-time edge adjustment based on digital twins includes multi-section ground service operation adjustment.

[0054] The multi-section ground service operation adjustment includes two parts: real-time speed adjustment of a single special vehicle and multi-link special vehicle speed adjustment.

[0055] The method for real-time speed adjustment of a single special vehicle: the fluctuation of the special vehicle in the actual execution of the support task process is explained by the deviation between the planned time interval [t str ,t end ] and the real-time time interval [t′ str ,t′ end ], t str represents the planned start time of the special vehicle for flight support, t end represents the estimated flight support end time, t′ str represents the actual start time of the special vehicle for flight support, t′end represent the actual end time of the special vehicle flight support. When t ≠ t' str str or t ≠ t' end end , it means that fluctuations will occur in the actual implementation. Therefore, the edge server calculates the speed of the special vehicle in real time, and the calculation formula is as follows:

[0056]

[0057] where s represents the path length of the special vehicle. In fact, according to the safety regulations of the airport, the priority speed of the special vehicle is limited in the interval [v max ,v min ], which is obtained according to the current traffic condition, and will be reset in the following two cases, and the calculation formula is as follows:

[0058]

[0059] Multi-link special vehicle speed adjustment method: when the speed reset cannot ensure the elimination of the fluctuation of the special vehicle priority, the edge server will recalculate the expected arrival time of the special vehicle, and the calculation formula is as follows:

[0060]

[0061] The time for the special vehicle to complete the ground service task will also be recalculated in the edge server, and the calculation formula is as follows:

[0062] T'm end = t' end + Tm

[0063] For another special vehicle responsible for the next ground service task, the edge server will adjust the start time of its task, and the calculation formula is as follows:

[0064] t' str (t) = Max{T' end , t str}

[0065] Finally, the speed of the next special vehicle will be reset by the edge server, and the calculation formula is as follows:

[0066]

[0067] If the speed of the next special vehicle v(t) ∈ [v min ,v max ], it means that the fluctuation caused by the last special vehicle is eliminated, and the real-time edge adjustment is ended; otherwise, it will be reset according to the following formula:

[0068] ​​

[0069] At the same time, the adjustment process will continue until the fluctuations are completely eliminated.

[0070] The airport special vehicle real-time scheduling method based on the digital twin model provided by the embodiment of the application adopts a real-time edge adjustment method to adjust and redistribute the speed of a single special vehicle and the speed of a multi-link special vehicle, eliminate disturbances in the working process of the special vehicle, shorten the ground service time, improve the flight on-time departure rate, and enable the scheduling scheme to be effectively executed.

[0071] In the above embodiment, an airport special vehicle real-time scheduling method based on a digital twin model is provided, and the application also provides an airport special vehicle real-time scheduling system based on a digital twin model. Please refer to Figure 2 , which is a structural block diagram of an airport special vehicle real-time scheduling system based on a digital twin model provided by another embodiment of the application. Since the device embodiment is basically similar to the method embodiment, it is described more simply, and the related parts refer to the part of the method embodiment. The device embodiment described below is only schematic.

[0072] As Figure 2 shown, a structural block diagram of an airport special vehicle real-time scheduling system based on a digital twin model provided by another embodiment of the application is shown, which includes a special vehicle terminal node, an edge server and a cloud center. The special vehicle terminal node sends real-time information of the special vehicle to the edge server. The edge server is used to receive the real-time information of the special vehicle, calculate the priority of the special vehicle according to the real-time information of the special vehicle, and send the calculated priority of the special vehicle to the cloud center. The cloud center is used to construct a digital twin model based on an edge-cloud computing architecture, calculate a flight priority based on the priority of the vehicle, determine a special vehicle scheduling scheme according to the flight priority and the priority of the special vehicle, perform online simulation on the special vehicle scheduling scheme, obtain a simulation result, issue a real-time scheduling instruction to the special vehicle according to the simulation result, and send the real-time scheduling instruction to the edge server. The edge server receives the real-time scheduling instruction and schedules and commands the special vehicle according to the real-time scheduling instruction.

[0073] The edge server comprises a first priority calculation module configured to determine a first priority according to a time taken by the special vehicle to complete a target flight task, the first priority being equal to a reciprocal of a sum of a remaining time for the special vehicle to complete a current task and a time for the special vehicle to complete a ground service task at a target flight point. The edge server further comprises a second priority calculation module configured to determine a second priority according to resource consumption of the special vehicle, the second priority being equal to a reciprocal of a product of a power when the speed of the special vehicle is an average speed and a time taken by the special vehicle to reach the target flight point. The priority of the special vehicle is calculated according to the first priority and the second priority with different weights. The edge server further comprises a command and dispatch module configured to dispatch and command the special vehicle according to a real-time dispatch instruction sent by the cloud center.

[0074] The cloud center comprises an intelligent twin construction module and a dispatch scheme generation module. The intelligent twin construction module describes and designs artificial elements such as vehicles and infrastructures and their mutual relationships in a twin model by means of software-defined objects (SDOs), software-defined relationships (SDRs) and software-defined processes (SDPs), and constructs seven intelligent twin objects: a twin special vehicle, a twin road, a twin roadside unit, a twin base station, a twin building, a twin time and a twin flight. All these twin objects have simple calculation and interaction functions. The dispatch scheme generation module is configured to decompose a ground support service task of a target flight into a sequence of unit sub-tasks, match the priority of the special vehicle with each unit sub-task of the ground support service to obtain a preliminary allocation scheme, obtain an estimated end time of the flight support under the preliminary allocation scheme when all sub-class support service processes of the target flight are matched with the special vehicle with the highest priority, calculate a flight priority according to an estimated end time of the flight support published by the airport and the estimated end time of the flight support under the preliminary allocation scheme, sort the flights according to the flight priority, and match the priority of the corresponding special vehicle according to the high and low of the flight priority until all flights are allocated to the special vehicle to meet the ground support service. The cloud center further comprises a simulation module configured to perform online simulation on the special vehicle dispatch scheme to obtain a simulation result, and send a real-time dispatch instruction to the edge server according to the simulation result.

[0075] The cloud center further comprises an edge adjustment module configured to perform real-time edge adjustment on a working process of the special vehicle based on digital twinning, the real-time edge adjustment comprising multi-segment ground service operation adjustment.

[0076] The embodiment of the application provides an airport special vehicle real-time scheduling system based on a digital twin model, which has the same inventive concept and beneficial effects as the airport special vehicle real-time scheduling method based on the digital twin model, and details are not repeated here.

[0077] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, but not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present application, and they should be covered in the scope of the claims and the description of the present application.

Claims

1. A real-time dispatching method for airport special vehicles based on a digital twin model, characterized in that, Includes the following steps: The special vehicle terminal node sends real-time information about the special vehicle to the edge server; The edge server receives real-time information about special vehicles, calculates the priority of special vehicles based on the real-time information, and sends the calculated priority to the cloud center. The cloud center builds a digital twin model based on an edge computing architecture, calculates flight priorities based on special vehicle priorities, and determines special vehicle dispatching schemes based on flight priorities and special vehicle priorities. The cloud center conducts online simulation of the special vehicle dispatching scheme, obtains simulation results, issues real-time dispatching instructions to special vehicles based on the simulation results, and sends the real-time dispatching instructions to the edge server. The edge server receives real-time dispatch instructions and dispatches and directs special vehicles to work according to these instructions. The method for calculating the priority of special vehicles based on real-time information of special vehicles includes: The first priority is determined based on the time taken by the special vehicle to complete the target flight mission. The first priority is equal to the negative of the sum of the remaining time for the special vehicle to complete the current mission and the time to complete the ground service mission for the target flight. The remaining time for the special vehicle to complete the current mission is equal to the time taken by the special vehicle to reach the target flight point and the time taken to complete the ground service mission upon arrival at the target flight. The formula for calculating the first priority is as follows: Priority1 = -(T1 + T2) T1=T m +T n In the formula, Priority1 is the first priority, T1 represents the remaining time for the special vehicle to complete the current task, and T2 represents the time to complete the ground service task for the target flight. T1 can be divided into two parts T m and T n ;T m The value represents the time it takes for a special vehicle to reach the target flight point, T. n This refers to the time required to complete ground service tasks upon arrival at the target flight.

2. The method as described in claim 1, characterized in that, The method for calculating the priority of special vehicles based on real-time information of special vehicles also includes: The second priority is determined based on the resource consumption of special vehicles. The second priority is equal to the negative of the product of the power of the special vehicle at its average speed and the time taken for the special vehicle to reach the target flight point. The priority of special vehicles is calculated based on the different weights of the first priority and the second priority.

3. The method as described in claim 2, characterized in that, The method for calculating flight priority based on special vehicle priority, and determining the special vehicle dispatching plan based on flight priority and special vehicle priority, specifically includes: The ground support service tasks for the target flight are broken down into a sequence of unit sub-tasks; A preliminary allocation plan is obtained by matching the priority of special vehicles with each unit sub-task of ground support services. When all sub-class support service processes of the target flight are matched with the special vehicle with the highest priority, the estimated flight support end time under the preliminary allocation plan is obtained. Flight priority is calculated based on the estimated flight service completion time released by the airport and the estimated flight service completion time under the preliminary allocation plan. Flights are sorted according to their priority. Special vehicles are assigned to flights based on their priority, until all flights are assigned special vehicles to provide ground support services.

4. The method as described in claim 1, characterized in that, After determining the special vehicle dispatching scheme and before the online simulation of the special vehicle dispatching scheme, the process also includes: performing real-time edge adjustments based on digital twins on the special vehicle operation process, wherein the real-time edge adjustments include adjustments to multiple ground service operations.

5. A real-time dispatching system for airport special vehicles based on a digital twin model, characterized in that, include: The system includes a special vehicle terminal node, an edge server, and a cloud center. The special vehicle terminal node sends real-time information about special vehicles to the edge server. The edge server is used to receive real-time information about special vehicles, calculate the priority of special vehicles based on the real-time information, and send the calculated priority of special vehicles to the cloud center. The cloud center is used to build a digital twin model based on the edge computing architecture, calculate flight priority based on vehicle priority, determine special vehicle dispatching scheme based on flight priority and special vehicle priority, perform online simulation of special vehicle dispatching scheme, obtain simulation results, issue real-time dispatching instructions to special vehicles based on simulation results, and send real-time dispatching instructions to edge servers. The edge server is also used to receive real-time dispatch instructions and to dispatch and direct special vehicles to work according to the real-time dispatch instructions. The edge server includes a first priority calculation module, which is used to determine a first priority based on the time taken by the special vehicle to complete the target flight mission. The first priority is equal to the negative of the sum of the remaining time for the special vehicle to complete the current mission and the time to complete the ground service mission of the target flight. The remaining time for the special vehicle to complete the current mission is equal to the time taken by the special vehicle to reach the target flight point and the time taken to complete the ground service mission when reaching the target flight. The formula for calculating the first priority is as follows: Priority1 = -(T1 + T2) T1=T m +T n In the formula, Priority1 is the first priority, T1 represents the remaining time for the special vehicle to complete the current task, and T2 represents the time to complete the ground service task for the target flight. T1 can be divided into two parts T m and T n ;T m The value represents the time it takes for a special vehicle to reach the target flight point, T. n This refers to the time required to complete ground service tasks upon arrival at the target flight.

6. The system as described in claim 5, characterized in that, The edge server also includes a second priority calculation module, which is used to determine a second priority based on the resource consumption of the special vehicle. The second priority is equal to the negative of the product of the power of the special vehicle at its average speed and the time taken for the special vehicle to reach the target flight point. The priority of the special vehicle is calculated based on the different weights of the first priority and the second priority.

7. The system as described in claim 6, characterized in that, The cloud center includes a scheduling scheme generation module, which is used to decompose the ground support service tasks of the target flight into a sequence of unit sub-tasks. A preliminary allocation plan is obtained by matching the priority of special vehicles with each unit sub-task of ground support services. When all sub-class support service processes of the target flight are matched with the special vehicle with the highest priority, the estimated flight support end time under the preliminary allocation plan is obtained. Flight priority is calculated based on the estimated flight service completion time released by the airport and the estimated flight service completion time under the preliminary allocation plan. Flights are sorted according to their priority. Special vehicles are assigned to flights based on their priority, until all flights are assigned special vehicles to provide ground support services.

8. The system as described in claim 6, characterized in that, The cloud center also includes an edge adjustment module, which is used to perform real-time edge adjustments based on digital twins on the working process of special vehicles. The real-time edge adjustments include adjustments to the operation of multiple ground services.

Images