Air traffic network congestion state propagation condition prediction method, device and equipment

Abstract

The invention provides an air traffic network congestion state propagation condition prediction method, device and equipment, and relates to the technical field of air traffic networks, and the prediction method comprises the steps: obtaining air route data of an air traffic network, airport terminal area airspace data, airport scene area data and flight flow data in a preset time period; constructing an air traffic hierarchical network model according to the airway data, the airport terminal area airspace data and the airport scene area data, wherein the air traffic hierarchical network model comprises area control airspace nodes, airport terminal area airspace nodes, airport scene area nodes and connecting edges among the three nodes; based on a preset infectious disease model, constructing a traffic jam propagation coupling network model according to the air traffic hierarchical network model; and solving the traffic jam propagation coupling network model according to the flight flow data to obtain a function that the average jam state density of the three nodes changes along with time. The prediction efficiency and the prediction result accuracy can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of air traffic network, and in particular to a method, device and equipment for predicting the propagation of congestion status of an air traffic network. Background Art

[0002] The air traffic network is an important part of the modern transportation system. It forms a complex network structure through multiple nodes and paths such as routes, airports, and aircraft. With the continuous increase in global air transportation demand, the capacity and operating efficiency of the air traffic network are facing increasing pressure. When the air traffic network is congested, it will not only cause flight delays, fuel waste, and increased operating costs for airlines, but may also affect flight safety. Therefore, it is necessary to predict the propagation of the congestion status of the air traffic network so that corresponding congestion relief strategies can be made in a timely manner based on the prediction results.

[0003] At present, a modeling method based on complex network theory is used to construct a prediction model for the propagation of air traffic network congestion status, and the constructed prediction model is used to predict the propagation of congestion status. However, the model of complex network theory is usually highly complex, which makes the existing technology have the problem of low prediction efficiency, and the existing technology also has the problem that the prediction model does not match the actual situation of the air traffic network, which makes the existing technology also have the problem of low accuracy of prediction results.

[0004] Based on this, how to improve the prediction efficiency and accuracy of the propagation of air traffic network congestion status has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] In view of this, a method, device and equipment for predicting the propagation of congestion status of an air traffic network are provided to solve the problems of low prediction efficiency and low accuracy of prediction results of the propagation of congestion status of an air traffic network in the prior art.

[0006] The present invention adopts the following technical solution: In a first aspect, the present invention provides a method for predicting the propagation of air traffic network congestion status, comprising: Acquire target data of an air traffic network, the target data including route data, airport terminal area airspace data, airport surface area data, and flight flow data within a preset time period, the duration of the preset time period being equal to a preset unit duration; According to the route data, the airport terminal area airspace data and the airport surface area data, an air traffic hierarchical network model is constructed, wherein the air traffic hierarchical network model includes regional control airspace nodes, airport terminal area airspace nodes, airport surface area nodes and connection edges between the three nodes, wherein the regional control airspace nodes are target locations of dense areas of route intersections determined according to the route data, and the connection edges are generated according to actual connectivity of traffic flows in the air traffic network; all the regional control airspace nodes are located in the regional control airspace layer, all the airport terminal area airspace nodes are located in the airport terminal area airspace layer, all the airport surface area nodes are located in the airport surface area layer, and the airport terminal area airspace layer is located between the regional control airspace layer and the airport surface area layer; Based on the preset infectious disease model and the air traffic hierarchical network model, a traffic congestion propagation coupling network model is constructed; the node states of each node in the air traffic hierarchical network model include a free state, a congested state and a removed state, and these three node states correspond to the susceptible state, the infected state and the removed state in the preset infectious disease model respectively; The traffic congestion propagation coupling network model is solved according to the flight flow data to obtain a function of the average congestion state density of the three types of nodes changing with time.

[0007] Optionally, constructing an air traffic hierarchical network model according to the route data, the airport terminal area airspace data and the airport surface area data specifically includes: Determine each route intersection point according to the route data, wherein the route intersection point refers to the intersection or confluence of two or more routes; Based on a preset clustering algorithm, clustering the route intersection points to obtain a plurality of route intersection point sets, wherein all the route intersection points in each of the route intersection point sets constitute a route intersection point dense area; Determine the target position of each of the route intersection dense areas as a regional controlled airspace node; Generating connection edges between different regional controlled airspace nodes according to the route data; Determine each of the airport terminal area airspace nodes according to the airport terminal area airspace data; For each of the airport terminal area airspace nodes, determine the target area control airspace node and the first target airport terminal area airspace node actually connected to the airport terminal area airspace node according to the airport terminal area airspace data, and generate connection edges between the target area control airspace node and the first target airport terminal area airspace node and the airport terminal area airspace node respectively; Determining each of the airport surface area nodes according to the airport surface area data; For each of the airport surface area nodes, based on the airport surface area data, determine the second target airport terminal area airspace node that the airport surface area node is actually connected to, and generate a connecting edge between the second target airport terminal area airspace node and the airport surface area node.

[0008] Optionally, determining the target position of each of the route intersection dense areas as a regional controlled airspace node specifically includes: Determine the center point of each of the route intersection dense areas as a regional controlled airspace node.

[0009] Optionally, the expression of the traffic congestion propagation coupling network model is:

[0010] in, Indicates that in the airport surface area layer, the node degree distribution is (0, )’s nodes, the density of nodes in a free state; represents the probability that the nodes in the airport surface area layer are affected by the nodes in the airport terminal area airspace layer and change from a free state to a congested state, , Indicates the maximum degree value of the node in the airport surface area layer to the airport terminal area airspace layer; Indicated in During the time period, the first target node in the airport surface area layer is affected by a node in the airport terminal area airspace layer that is connected to the first target node and is in a congested state, and the probability of the state of the first target node changing from other nodes to a congested state; Indicates that in the airport surface area layer, the node degree distribution is (0, ) nodes, the density of nodes in a congested state; represents the probability of a node in a congested state in the airport surface area layer changing to a removed state; represents the probability of a node in a congested state in the airspace layer of the airport terminal area changing to a removed state; represents the probability of a node in a congested state in the regional control airspace layer changing to a removed state; It means that in the airport terminal area airspace layer, the node degree distribution is The density of nodes in a free state among the nodes; , , , Indicates the maximum degree value of the nodes in the airport terminal area airspace layer to the airport surface area layer; Indicates the maximum degree value of the node in the airport terminal area airspace layer for the airport terminal area airspace layer; Indicates the maximum degree value of the nodes in the airport terminal area airspace layer with respect to the regional control airspace layer; Indicates the probability that the nodes in the airport terminal area airspace layer change from other node states to congestion states due to the influence of the nodes in the airport surface area layer; represents the probability that the nodes in the airspace layer of the airport terminal area change from other node states to congestion states due to the influence of the nodes in the airspace layer of the airport terminal area; represents the probability that the nodes in the airport terminal area airspace layer change from other node states to congestion states due to the influence of the nodes in the regional control airspace layer; Indicated in During the time period, the second target node in the airport terminal area airspace layer is affected by the node in the airport surface area layer that is connected to the second target node and is in a congested state, and the probability of the state of the second target node changing from other nodes to a congested state; Indicated in During the time period, the second target node in the airport terminal area airspace layer is affected by a node in the airport terminal area airspace layer that is connected to the second target node and is in a congested state, and the probability that the state of other nodes changes to a congested state; Indicated in During the time period, the second target node in the airport terminal area airspace layer is affected by the node in the regional control airspace layer that is connected to the second target node and is in a congested state, and the probability of the state of the second target node changing from other nodes to a congested state; It means that in the airport terminal area airspace layer, the node degree distribution is The density of nodes in congestion among the nodes; Indicates that in the regional control airspace layer, the node degree distribution is The density of nodes in a free state among the nodes; , , Indicates the maximum degree value of the node in the regional control airspace layer to the airport terminal area airspace layer; Indicates the maximum degree value of the nodes in the regional control airspace layer for the regional control airspace layer; represents the probability that a node in the regional control airspace layer is affected by a node in the airport terminal area airspace layer and changes from a free state to a congested state; represents the probability that a node in the regional control airspace layer changes from a free state to a congested state due to the influence of a node in the regional control airspace layer; Indicated in During the time period, the probability that the third target node in the regional control airspace layer is affected by the node in the airport terminal area airspace layer that is connected to the third target node and is in a congested state, and changes from other node states to a congested state; Indicated in During the time period, the probability that the third target node in the regional control airspace layer is affected by the node in the regional control airspace layer that is connected to the third target node and is in a congested state, and changes from other node states to a congested state; Indicates that in the regional control airspace layer, the node degree distribution is The density of nodes in a congested state among the nodes.

[0011] Optionally, the degrees of the nodes in the air traffic hierarchical network model are set to be unrelated; Expressed as:

[0012] in, Represents the average degree value of the nodes in the airport surface area layer to the airport terminal area airspace layer; Indicates that a node is randomly selected from the airport surface area layer, and the node has j The probability that the edge is connected to the airport terminal area airspace layer; Represents the average degree value of the nodes in the airport terminal area airspace layer to the airport surface area layer; represents the average degree value of the nodes in the airport terminal area airspace layer for the airport terminal area airspace layer; Represents the average degree value of the nodes in the airport terminal area airspace layer with respect to the regional control airspace layer; Indicates that a node is randomly selected from the airport terminal area airspace layer, and the node has i The edge is connected to the airport surface area layer, and there is j The edge is connected to the airport terminal area airspace layer, and there is k The probability that the edge is connected to the regional control airspace layer; Represents the average degree value of the nodes in the regional control airspace layer with respect to the airport terminal area airspace layer; represents the average degree value of the nodes in the regional control airspace layer for the regional control airspace layer; Indicates that a node is randomly selected from the regional control airspace layer, and the node has j The edge is connected to the airport terminal area airspace layer, and there is k The probability that the edge is connected to the regional control airspace layer; Indicates that in the airport surface area layer, the node degree distribution is (0, ) nodes, the density of nodes in a congested state; It means that in the airport terminal area airspace layer, the node degree distribution is The density of nodes in congestion among the nodes; Indicates that in the regional control airspace layer, the node degree distribution is The density of nodes in a congested state among the nodes.

[0013] Optionally, after constructing the air traffic hierarchical network model according to the route data, the airport terminal area airspace data and the airport surface area data, the air traffic network congestion state propagation prediction method of the present invention further includes: Based on the air traffic hierarchical network model, the next generation matrix Calculating a basic reproduction number of the air traffic network, where the basic reproduction number is used to reflect the ability of a node in a congested state to propagate the congested state to nodes in a free state; in, F is the growth rate of congested nodes; V is the growth rate of nodes that change from congested state to free state.

[0014] Optionally, before constructing the air traffic hierarchical network model according to the route data, the airport terminal area airspace data and the airport surface area data, the air traffic network congestion state propagation prediction method of the present invention further includes: The target data is preprocessed to remove outliers in the target data.

[0015] Optionally, the preset infectious disease model is a susceptible-infectious-escape model.

[0016] In a second aspect, the present invention further provides a device for predicting the spread of air traffic network congestion status, comprising: An acquisition module, used to acquire target data of an air traffic network, wherein the target data includes route data, airport terminal area airspace data, airport surface area data, and flight flow data within a preset time period, wherein the duration of the preset time period is equal to the preset unit duration; A first construction module is used to construct an air traffic hierarchical network model according to the route data, the airport terminal area airspace data and the airport surface area data, wherein the air traffic hierarchical network model includes regional control airspace nodes, airport terminal area airspace nodes, airport surface area nodes and connection edges between the three nodes, the regional control airspace nodes are target locations of dense areas of route intersections determined according to the route data, and the connection edges are generated according to actual connectivity of traffic flows in the air traffic network; all the regional control airspace nodes are located in a regional control airspace layer, all the airport terminal area airspace nodes are located in an airport terminal area airspace layer, all the airport surface area nodes are located in an airport surface area layer, and the airport terminal area airspace layer is located between the regional control airspace layer and the airport surface area layer; A second construction module is used to construct a traffic congestion propagation coupling network model based on a preset infectious disease model and the air traffic hierarchical network model; the node state of each node in the air traffic hierarchical network model includes a free state, a congested state and a removed state, and these three node states correspond to the susceptible state, the infected state and the removed state in the preset infectious disease model respectively; A solution module is used to solve the traffic congestion propagation coupling network model according to the flight flow data to obtain a function of the average congestion state density of the three types of nodes changing with time.

[0017] In a third aspect, the present invention further provides a device for predicting the spread of air traffic network congestion status, comprising: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to implement the above-mentioned method for predicting the propagation of air traffic network congestion status.

[0018] The present invention adopts the above technical scheme, a method for predicting the propagation of air traffic network congestion status, including: obtaining target data of the air traffic network, the target data including route data, airport terminal area airspace data, airport surface area data and flight flow data within a preset time period, the duration of the preset time period is equal to the preset unit duration; constructing an air traffic hierarchical network model according to the route data, the airport terminal area airspace data and the airport surface area data, the air traffic hierarchical network model including regional control airspace nodes, airport terminal area airspace nodes, airport surface area nodes and connecting edges between the three nodes, the regional control airspace nodes are target locations of dense route intersection areas determined according to the route data, and the connecting edges are connected according to the actual traffic flow of the air traffic network. The traffic situation is generated; all regional control airspace nodes are located in the regional control airspace layer, all airport terminal area airspace nodes are located in the airport terminal area airspace layer, all airport surface area nodes are located in the airport surface area layer, and the airport terminal area airspace layer is located between the regional control airspace layer and the airport surface area layer; based on the preset infectious disease model and according to the air traffic hierarchical network model, a traffic congestion propagation coupling network model is constructed; the node states of each node in the air traffic hierarchical network model include free state, congestion state and removal state, and these three node states correspond to the susceptible state, infection state and removal state in the preset infectious disease model respectively; according to the flight flow data, the traffic congestion propagation coupling network model is solved to obtain the function of the average congestion state density of the three nodes changing with time.

[0019] Based on this, since the air traffic hierarchical network model includes regional control airspace nodes, airport terminal area airspace nodes, airport surface area nodes and the connecting edges between the three nodes (corresponding to actual traffic flows), it can be seen that the air traffic hierarchical network model of the present invention is consistent with the actual situation of the air traffic network, thereby making the prediction results of the traffic congestion propagation coupling network model constructed according to the air traffic hierarchical network model more accurate; and, based on the preset infectious disease model, the traffic congestion propagation coupling network model constructed according to the air traffic hierarchical network model has low model complexity, so that the present invention can reduce the amount of calculation when predicting the propagation of the congestion state of the air traffic network, thereby improving the prediction efficiency.

[0020] In addition, the prediction data used in the present invention is the flight flow data of the air traffic network within a preset time period. It can be seen that the prediction data used in the present invention is a small amount of real-time data, which further enables the present invention to reduce the amount of calculation and improve prediction efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0022] Figure 1 It is a flow chart of a method for predicting the propagation of air traffic network congestion status provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of the construction principle of a regional control airspace network provided by an embodiment of the present invention; Figure 3 is a schematic diagram of an air traffic hierarchical network model provided by an embodiment of the present invention; Figure 4 It is a structural schematic diagram of a device for predicting the propagation of air traffic network congestion status provided by an embodiment of the present invention; Figure 5 It is a structural schematic diagram of an air traffic network congestion status propagation situation prediction device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] To make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described in detail below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other implementation methods obtained by ordinary technicians in this field without creative work belong to the scope of protection of the present invention.

[0024] Figure 1 FIG. 1 is a flow chart of a method for predicting the propagation of air traffic network congestion status provided by an embodiment of the present invention. Figure 1 As shown, the method for predicting the propagation of air traffic network congestion status includes: Step 101: Acquire target data of an air traffic network, the target data including route data, Terminal Controlled Airspace (TCA) data, Airport Surface Area (AS) data, and flight flow data within a preset time period, wherein the duration of the preset time period is equal to the preset unit duration.

[0025] Among them, flight flow refers to the number of flights passing through a certain air traffic management unit in unit time. The air traffic management unit includes a certain point on the route, a certain route and a certain operating area.

[0026] Step 102: construct an air traffic hierarchical network model based on route data, airport terminal airspace data and airport surface area data. The air traffic hierarchical network model includes area controlled airspace (ACA) nodes, airport terminal airspace nodes, airport surface area nodes and connection edges between the three nodes. The area controlled airspace nodes are target locations of dense areas of route intersections determined based on route data. The connection edges are generated based on actual traffic flow connectivity of the air traffic network. All area controlled airspace nodes are located in the area controlled airspace layer, all airport terminal airspace nodes are located in the airport terminal airspace layer, all airport surface area nodes are located in the airport surface area layer, and the airport terminal airspace layer is located between the area controlled airspace layer and the airport surface area layer.

[0027] In the embodiment of the present invention, an air traffic hierarchical network model is constructed based on route data, airport terminal area airspace data and airport surface area data, which may specifically include: (1) Based on the route data, determine the route intersection points. The route intersection point refers to the intersection or confluence of two or more routes.

[0028] Specifically, the route data includes the path point coordinates of each route, the length of the route, the connection relationship between different routes, etc. By traversing all routes, the intersection point between different routes can be calculated, and the intersection point is the route intersection point.

[0029] (2) Based on a preset clustering algorithm, each route intersection point is clustered to obtain multiple route intersection point sets. All the route intersection points in each route intersection point set constitute a route intersection point dense area.

[0030] Specifically, the preset clustering algorithm may be a clustering algorithm in the prior art such as Density-Based Spatial Clustering of Applications with Noise (DBSCAN) or a k-means clustering algorithm.

[0031] The preset clustering algorithm performs clustering according to the location coordinates of the route intersection points. Therefore, the route intersection points in each route intersection point set (i.e., each cluster) are located in the same area. In an embodiment of the present invention, all the route intersection points in each route intersection point set are defined to constitute a route intersection point dense area.

[0032] (3) Determine the target location of each route intersection dense area as an area controlled airspace node.

[0033] Specifically, the target position of the area with dense route intersections can be the center point of the area with dense route intersections. Of course, those skilled in the art can also select other positions of the area with dense route intersections as the target position of the present application.

[0034] (4) Based on the route data, the connecting edges between the nodes of different regional controlled airspaces are generated to obtain the regional controlled airspace network.

[0035] Specifically, first, the actual connectivity of traffic flows between nodes in different regional controlled airspaces is determined based on route data, and then, for any two regional controlled airspace nodes, if there is traffic flow between the two regional controlled airspace nodes, a connecting edge is generated between the two regional controlled airspace nodes.

[0036] In a specific example, Figure 2 It is a schematic diagram of the construction principle of a regional control airspace network provided by an embodiment of the present invention. Figure 2 In (a), the triangles in Figure 1 represent route intersections, the straight lines represent routes, and Figure 2 (b) is a regional controlled airspace network constructed based on Figure 2 (a) based on the above method. In Figure 2 (a), when clustering the route intersections based on the preset clustering algorithm, four route intersection sets are obtained, namely, route intersection set 1, route intersection set 2, route intersection set 3, and route intersection set 4. The target position of route intersection set 1 is selected as the regional controlled airspace node D, the target position of route intersection set 2 is selected as the regional controlled airspace node C, the target position of route intersection set 3 is selected as the regional controlled airspace node A, and the target position of route intersection set 4 is selected as the regional controlled airspace node B. For every two regional controlled airspace nodes, based on the route data, it is determined whether there is a traffic flow between the two regional controlled airspace nodes. If so, a connecting edge is generated between the two regional controlled airspace nodes. As shown in Figure (b), there is traffic flow between regional control airspace node A and regional control airspace node B, but there is no traffic flow between regional control airspace node B and regional control airspace node D. The traffic flow between regional control airspace node A and regional control airspace node B means that there is an actual route between regional control airspace node A and regional control airspace node B.

[0037] (5) Determine the airspace nodes of each airport terminal area based on the airport terminal area airspace data.

[0038] Specifically, the airport terminal area airspace is predetermined and determined, for example, the Shanghai airport terminal area airspace. In the present invention, an airport terminal area airspace in an actual situation is determined as an airport terminal area airspace node.

[0039] (6) For each airport terminal area airspace node, determine the target area controlled airspace node and the first target airport terminal area airspace node that the airport terminal area airspace node is actually connected to based on the airport terminal area airspace data, and generate connecting edges between the target area controlled airspace node and the first target airport terminal area airspace node and the airport terminal area airspace node.

[0040] Specifically, Figure 3 FIG. 1 is a schematic diagram of an air traffic hierarchical network model provided by an embodiment of the present invention. Figure 3 As shown, the innermost layer is the regional control airspace layer (i.e., the ACA layer), the middle layer is the airport terminal area airspace layer (i.e., the TCA layer), and the outermost layer is the airport surface area layer (i.e., the AS layer).

[0041] In a specific example, Figure 3 As shown, for airport terminal area airspace node 1 (i.e., TCA 1), when determining the target area control airspace node and the first target airport terminal area airspace node actually connected to TCA 1 based on the airport terminal area airspace data, it can be determined that TCA 1 is actually connected to TCA 2 and ACA 1. Therefore, a connecting edge is generated between TCA 1 and TCA 2, and a connecting edge is generated between TCA 1 and ACA 1.

[0042] The actual connectivity between TCA 1 and ACA 1 means that there are departing flights entering ACA 1 from TCA 1 and / or there are arriving flights entering TCA 1 from ACA 1.

[0043] (7) Determine the nodes of each airport surface area based on the airport surface area data.

[0044] Specifically, the airport surface area is predetermined and determined, for example, the airport surface area of ​​Shanghai Pudong International Airport and the airport surface area of ​​Shanghai Hongqiao International Airport. The two airport surface areas are actually connected to the terminal area airspace of Shanghai Airport respectively. In the present invention, an airport surface area in the actual situation is determined as an airport surface area node.

[0045] (8) For each airport surface area node, determine the second target airport terminal area airspace node that the airport surface area node is actually connected to based on the airport surface area data, and generate a connection edge between the second target airport terminal area airspace node and the airport surface area node.

[0046] In a specific example, Figure 3As shown, for the airport surface area node 1 (i.e., AS 1), when determining the second target airport terminal area airspace node to which AS 1 is actually connected based on the airport surface area data, it can be determined that AS 1 is actually connected to TCA 1, and therefore, a connection edge is generated between AS 1 and TCA 1. The actual connection between AS 1 and TCA 1 means that there is a takeoff flight entering TCA 1 from AS 1, and / or there is a landing flight entering AS 1 from TCA 1.

[0047] It should be noted that usually one AS corresponds to one TCA, and one TCA may contain multiple ASs. Therefore, an AS node is connected to a TCA node by an edge, but there is no edge connection between AS nodes. A TCA node may be connected to multiple AS nodes.

[0048] Step 103: Based on the preset infectious disease model and the air traffic layered network model, a traffic congestion propagation coupling network model is constructed; the node states of each node in the air traffic layered network model include a free state (i.e., a state where there is no congestion at all times), a congested state, and a removal state (i.e., recovery from a congested state to a smooth state), and these three node states correspond to the susceptible state, the infected state, and the removal state in the preset infectious disease model, respectively.

[0049] In practical applications, AS nodes, TCA nodes, and ACA nodes represent the main areas where air traffic flows converge and concentrate. When the air traffic flow in these areas reaches a high level, congestion will occur. The connection of air traffic convergence areas often causes congestion to produce a cascade effect in multiple areas, and this congestion propagation follows a pattern similar to the epidemic propagation between individuals. Therefore, the present invention constructs a traffic congestion propagation coupling network model based on a preset infectious disease model.

[0050] In an embodiment of the present invention, the preset infectious disease model may be a susceptible-infectious-removed (SIR) model. Disease transmission is irreversible, that is, epidemiological transmission is a one-way diffusion, reflecting congestion transmission. Therefore, the traditional infectious disease model is considered to be suitable for explaining the propagation of air traffic congestion caused by a single congestion source (that is, the present invention is suitable for predicting the propagation of air traffic congestion caused by a single congestion source).

[0051] The expression of the traffic congestion propagation coupled network model is: -dimensional ordinary differential equations, as follows: ...... (1) in, Indicates that in the AS layer, the node degree distribution is (0, ) nodes, the density of nodes in a free state. In the AS layer, the node degree distribution is (0, ), that is, the node has 0 edges connected to the AS layer and Edge connection. , it should be noted that the s on the left side of the formula is lowercase, and the S on the right side of the formula is uppercase. Indicates that in the AS layer, the node degree distribution is (0, ), the number of nodes in the free state, Indicates that in the AS layer, the node degree distribution is (0, )’s total number of nodes.

[0052] , Indicates the maximum degree of the nodes in the AS layer to the TCA layer. Figure 3 As shown in the figure, in the AS layer, the degree value of AS 1 to the TCA layer is 1 (that is, AS 1 is connected to the TCA layer by one edge), and the degree values ​​of other AS nodes to the TCA layer are all 1. Therefore, The value of is 1.

[0053] It represents the probability that a node in the airport surface area layer changes from a free state to a congested state due to the influence of a node in the airport terminal area airspace layer.

[0054] Indicated in During a time period, the first target node in the airport surface area layer is affected by the node in the airport terminal area airspace layer that is connected to the first target node and is in a congested state, and the probability of changing from other node states to a congested state. It should be noted that the state of the node needs to be determined based on the flight flow data within a time period. In the present invention, the state of the node is determined based on the flight flow data of the node within a preset unit time length, wherein the preset unit time length can be half an hour or one hour, etc. Indicates the number of time periods, where the duration of each time period is the preset unit duration.

[0055] In the airport surface area layer, the node degree distribution is (0, ) nodes, the density of nodes in a congested state. , In the airport surface area layer, the node degree distribution is (0, ) nodes, the number of nodes in congestion state.

[0056] It represents the probability that the node state of a node in the airport surface area layer that is in a congested state will change to a removed state. It represents the probability that the node state of a node in the airport terminal area airspace layer that is in a congested state changes to a removed state. It represents the probability that the node state of a node in the regional control airspace layer that is in a congested state changes to a removed state.

[0057] In the airport terminal area airspace layer, the node degree distribution is The density of nodes in a free state among the nodes. In the airport terminal airspace layer, the node degree distribution is The node has The edge connection is connected to the TCA layer The edge connection with the ACA layer Edge connection. , as above, the s on the left side of the formula is lowercase, and the S on the right side of the formula is uppercase. In the airport terminal area airspace layer, the node degree distribution is The number of nodes in the free state among the nodes, In the airport terminal area airspace layer, the node degree distribution is The total number of nodes.

[0058] , , . Indicates the maximum degree value of the node in the airport terminal area airspace layer to the airport surface area layer. It represents the maximum degree value of the node in the airport terminal area airspace layer for the airport terminal area airspace layer. It represents the maximum degree of the node in the airport terminal area airspace layer to the regional control airspace layer. The principle of their value selection can be found in The value principle of .

[0059] Indicates the probability that the nodes in the airport terminal area airspace layer change from other node states to congestion states due to the influence of the nodes in the airport surface area layer; represents the probability that the nodes in the airspace layer of the airport terminal area change from other node states to congestion states due to the influence of the nodes in the airspace layer of the airport terminal area; It represents the probability that the nodes in the airport terminal area airspace layer change from other node states to congestion states due to the influence of the nodes in the regional control airspace layer.

[0060] Indicated in During the time period, the second target node in the airport terminal area airspace layer is affected by the node in the airport surface area layer that is connected to the second target node and is in a congested state, and the probability of the state of the second target node changing from other nodes to a congested state; Indicated in During the time period, the second target node in the airport terminal area airspace layer is affected by a node in the airport terminal area airspace layer that is connected to the second target node and is in a congested state, and the probability that the state of other nodes changes to a congested state; Indicated in During the time period, the second target node in the airport terminal area airspace layer is affected by the node in the regional control airspace layer that is connected to the second target node and is in a congested state, and the probability of changing from other node states to a congested state.

[0061] In the airport terminal area airspace layer, the node degree distribution is The density of nodes in a congested state among the nodes. , In the airport terminal area airspace layer, the node degree distribution is The number of nodes in the congested state among the nodes.

[0062] In the regional control airspace layer, the node degree distribution is The density of nodes in a free state among the nodes. In the regional control airspace layer, the node degree distribution is Node, that is, the node has The edge connection with the ACA layer Edge connection. , as above, the s on the left side of the formula is lowercase, and the S on the right side of the formula is uppercase. In the regional control airspace layer, the node degree distribution is The number of nodes in the free state among the nodes, In the regional control airspace layer, the node degree distribution is The total number of nodes.

[0063] , . Indicates the maximum degree value of the node in the regional control airspace layer to the airport terminal area airspace layer; Represents the maximum degree value of the nodes in the regional control airspace layer for the regional control airspace layer.

[0064] represents the probability that a node in the regional control airspace layer is affected by a node in the airport terminal area airspace layer and changes from a free state to a congested state; It represents the probability that a node in the regional control airspace layer changes from a free state to a congested state due to the influence of a node in the regional control airspace layer.

[0065] Indicated in During the time period, the probability that the third target node in the regional control airspace layer is affected by the node in the airport terminal area airspace layer that is connected to the third target node and is in a congested state, and changes from other node states to a congested state; Indicated in During the time period, the third target node in the regional control airspace layer is affected by the node in the regional control airspace layer that is connected to the third target node and is in a congested state, and the probability of changing from other node states to a congested state.

[0066] In the regional control airspace layer, the node degree distribution is The density of nodes in a congested state among the nodes. , In the regional control airspace layer, the node degree distribution is The number of nodes in the congested state among the nodes.

[0067] It should be noted that , , , , , , , , The value of is set by the forecaster based on actual experience.

[0068] In the embodiment of the present invention, due to the existence of traffic congestion propagation coupling network model , , , , , These parameters enable the model to describe the propagation of traffic congestion between nodes in each layer, as well as the propagation of traffic congestion between nodes in different layers, making the model more consistent with the actual propagation of congestion status, thereby making the prediction results of the present invention more accurate.

[0069] In order to further simplify the model, the degrees of the nodes in the air traffic hierarchical network model are assumed to be unrelated, that is, the degree of any node is unrelated to the degree of its adjacent nodes. Based on this, the degree of the traffic congestion propagation coupled network model is Expressed as: ...... (2) in, It represents the average degree value of the nodes in the airport surface area layer to the airport terminal area airspace layer. Indicates that a node is randomly selected from the airport surface area layer. j The probability of an edge being connected to the airport terminal area airspace layer; Represents the average degree value of the nodes in the airport terminal area airspace layer to the airport surface area layer; represents the average degree value of the nodes in the airport terminal area airspace layer for the airport terminal area airspace layer; Represents the average degree value of the nodes in the airport terminal area airspace layer with respect to the regional control airspace layer; Indicates that a node is randomly selected from the airport terminal area airspace layer. i The edge is connected to the airport surface area layer, j The edge is connected to the airport terminal area airspace layer, and there is k The probability of an edge being connected to the regional control airspace layer; Represents the average degree value of the nodes in the regional control airspace layer with respect to the airport terminal area airspace layer; represents the average degree value of the nodes in the regional control airspace layer for the regional control airspace layer; Indicates that a node is randomly selected from the regional control airspace layer. j The edge is connected to the airport terminal area airspace layer, and there is k The probability that an edge is connected to the regional control airspace layer. Indicates that in the airport surface area layer, the node degree distribution is (0, ) nodes, the density of nodes in a congested state; It means that in the airport terminal area airspace layer, the node degree distribution is The density of nodes in congestion among the nodes; Indicates that in the regional control airspace layer, the node degree distribution is The density of nodes in a congested state among the nodes.

[0070] The relevant parameters involved here are joint degree distribution, marginal degree distribution, average degree value ( ) and the second moment ( ), see Table 1 for details.

[0071] Table 1

[0072] In Table 1, for each row, the value calculation formula on the right corresponds to the parameter on the left, for example yes The value calculation formula of .

[0073] Among them, the joint degree distribution is used to describe the connection characteristics of a node in a multi-layer network, including: , and . Indicates that in the AS layer, the node degree distribution is (0, j )’s total number of nodes. Indicates the total number of nodes in the AS layer. , , , For the meaning of the parameters in the relevant format, please refer to the meaning of the parameters in the relevant format, which will not be repeated here. , and The calculation formula is as follows: ...... (3) here, Indicates the total number of nodes in the congested state in the AS layer; Indicates the total number of nodes in the free state in the AS layer; Indicates the total number of nodes in the removed state in the AS layer. , , For the TCA layer parameters, see , and meaning. , , For the parameters of the ACA layer, see , and For the meaning of other parameters in formula (3), please refer to the meaning of other parameters with the same or similar format, which will not be repeated here. For example, Please refer to the meaning of and The meaning of Indicates that in the AS layer, the node degree distribution is (0, j ), and the total number of nodes in a congested state. It should be noted that in the present invention, N The total number of corresponding nodes, I Corresponding to the congestion state,S Corresponding to the free state, R Corresponding to the removed state.

[0074] The marginal degree distribution is obtained from the joint degree distribution, which indicates the connection between a node and a specific layer. The marginal degree distribution includes: , , , , , Indicates the number of connections between the nodes in the TCA layer and the AS layer. i probability. Indicates the number of connections between nodes in the TCA layer and the TCA layer is j probability. The number of connections between the nodes in the TCA layer and the ACA layer is k probability. The number of connections between the nodes in the ACA layer and the TCA layer is j probability. Indicates the number of connections between nodes in the ACA layer and the ACA layer is k probability.

[0075] For the remaining parameters in Table 1, When , these parameters are average values, when When , these parameters are second-order moments. The average degree value and second-order moment are used to describe the characteristics of the degree distribution of network nodes. The average degree value represents the average number of connections of nodes in the network. It is the average value of the degree of each node in the network, which reflects the degree of connection of the nodes in the network. The average degree value can be used to measure the density of the network. The second-order moment represents the average value of the square of the node degree, which reflects the distribution of the node degree. When the second-order moment is large, it means that there are some nodes with a very large number of connections in the network.

[0076] Step 104: Solve the traffic congestion propagation coupled network model based on the flight flow data to obtain a function of the average congestion state density of the three types of nodes changing with time.

[0077] Specifically, it can be seen from the above content that the present invention obtains the flight flow data of the air traffic network within a preset time period. Based on this, the preset time period is determined as the starting time period, and the initial state of each node can be determined according to the flight flow data. The initial state should include a congested state and a free state.

[0078] Then, based on the air traffic hierarchical network model, according to the determined initial state of each node, the initial values ​​of each unknown in formula (1) are statistically calculated, that is, , , , , , .

[0079] Next, the initial values ​​of the unknown variables are brought into the traffic congestion propagation coupled network model for solution, and the function of the average congestion state density of the three types of nodes changing with time can be obtained. The function is as follows: ...... (4) in, Indicated in The density of nodes in the congested state in the AS layer during the time period. Indicated in The density of nodes in the congested state in the TCA layer during the time period. Indicated in The density of nodes in the congested state in the ACA layer during the time period.

[0080] In a specific example, assuming that the preset unit time is 30 minutes, and the preset time period is 15:00-15:30 on a certain day, this time period is the initial time period, which is recorded as = 0, and the initial values ​​of the unknown variables determined according to the flight flow data of the initial time period are brought into the traffic congestion propagation coupled network model for solution, and we can get =1 (i.e. 15:30-16:00), =2 (i.e. 16:00-16:30), =3 (i.e. 16:30-17:00),......, =Z, these time periods , and . Where Z is a positive integer. Generally, the maximum value of Z is 10.

[0081] The embodiment of the present invention adopts the above-mentioned technical solution. Since the air traffic hierarchical network model includes regional control airspace nodes, airport terminal area airspace nodes, airport surface area nodes and the connecting edges between the three nodes (corresponding to actual traffic flows), it can be seen that the air traffic hierarchical network model of the present invention is consistent with the actual situation of the air traffic network, thereby making the prediction results of the traffic congestion propagation coupling network model constructed according to the air traffic hierarchical network model more accurate; and, based on the preset infectious disease model, the traffic congestion propagation coupling network model constructed according to the air traffic hierarchical network model has low model complexity, so that the present invention can reduce the amount of calculation when predicting the propagation of the congestion state of the air traffic network, thereby improving the prediction efficiency.

[0082] In addition, the prediction data used in the present invention is the flight flow data of the air traffic network within a preset time period. It can be seen that the prediction data used in the present invention is a small amount of real-time data, which further enables the present invention to reduce the amount of calculation and improve prediction efficiency.

[0083] In the embodiment of the present invention, after constructing the air traffic hierarchical network model based on the route data, the airport terminal area airspace data and the airport surface area data, the air traffic network congestion state propagation prediction method of the present invention may further include: Based on the air traffic hierarchical network model, using the next generation matrix The basic reproduction number R0 of the air traffic network is calculated. R0 is used to reflect the ability of a node in a congested state to spread the congestion state among the nodes in a free state. Specifically, R0 indicates how many free state nodes a congested node can influence and transform into congested nodes on average. This transformation is due to the influence of a congested node spreading among all free state points.

[0084] in, F is the growth rate of congested nodes; V is the growth rate of nodes that change from congested state to free state.

[0085] Specifically, the matrix Γ can be represented by the following matrix transformation: ...... (5) R0 is R0=ρ(Γ), where ρ(Γ) is the spectral radius of the matrix Γ.

[0086] In the embodiment of the present invention, before constructing the air traffic hierarchical network model based on the route data, the airport terminal area airspace data and the airport surface area data, the air traffic network congestion state propagation prediction method may further include: The target data is preprocessed to remove outliers in the target data.

[0087] Specifically, the present invention can remove the outliers in the target data by selecting outliers in the target data by relevant forecasters (ie, technicians in the field), and responding to data deletion operations by the relevant forecasters.

[0088] Based on a general inventive concept, the present invention also provides a device for predicting the propagation of air traffic network congestion status. Figure 4 Schematic diagram of a device for predicting the spread of air traffic network congestion status provided by an embodiment of the present invention. Figure 4 As shown, the air traffic network congestion state propagation situation prediction device includes: The acquisition module 41 is used to acquire target data of the air traffic network, the target data including route data, airport terminal area airspace data, airport surface area data and flight flow data within a preset time period, and the duration of the preset time period is equal to the preset unit duration.

[0089] The first construction module 42 is used to construct an air traffic hierarchical network model based on route data, airport terminal area airspace data and airport surface area data. The air traffic hierarchical network model includes regional control airspace nodes, airport terminal area airspace nodes, airport surface area nodes and connecting edges between the three nodes. The regional control airspace nodes are target locations in the dense area of ​​route intersections determined based on the route data, and the connecting edges are generated based on the actual connectivity of the traffic flow in the air traffic network; all regional control airspace nodes are located in the regional control airspace layer, all airport terminal area airspace nodes are located in the airport terminal area airspace layer, all airport surface area nodes are located in the airport surface area layer, and the airport terminal area airspace layer is located between the regional control airspace layer and the airport surface area layer.

[0090] The second construction module 43 is used to construct a traffic congestion propagation coupling network model based on the preset infectious disease model and the air traffic layered network model; the node state of each node in the air traffic layered network model includes a free state, a congested state and a removed state, and these three node states correspond to the susceptible state, the infected state and the removed state in the preset infectious disease model respectively.

[0091] The solution module 44 is used to solve the traffic congestion propagation coupling network model according to the flight flow data, and obtain the function of the average congestion state density of the three types of nodes changing with time.

[0092] Optionally, the first building module 42 may be specifically used for: (1) Determine each route intersection point based on the route data, where the route intersection point refers to the intersection or confluence of two or more routes.

[0093] (2) Based on a preset clustering algorithm, the route intersection points are clustered to obtain a plurality of route intersection point sets, wherein all the route intersection points in each of the route intersection point sets constitute a route intersection point dense area.

[0094] (3) Determine the target location of each of the densely populated areas of route intersections as a regional controlled airspace node.

[0095] (4) Generate connecting edges between different regional controlled airspace nodes based on the route data.

[0096] (5) Determine each of the airport terminal area airspace nodes based on the airport terminal area airspace data.

[0097] (6) For each of the airport terminal area airspace nodes, determine the target area controlled airspace node and the first target airport terminal area airspace node to which the airport terminal area airspace node is actually connected based on the airport terminal area airspace data, and generate connecting edges between the target area controlled airspace node and the first target airport terminal area airspace node and the airport terminal area airspace node respectively.

[0098] (7) Determining each of the airport surface area nodes based on the airport surface area data.

[0099] (8) For each of the airport surface area nodes, determine, based on the airport surface area data, a second target airport terminal area airspace node to which the airport surface area node is actually connected, and generate a connection edge between the second target airport terminal area airspace node and the airport surface area node.

[0100] Optionally, the target position of the route intersection point dense area may specifically be the center point of the route intersection point dense area.

[0101] Optionally, the expression of the traffic congestion propagation coupling network model can be:

[0102] in, Indicates that in the airport surface area layer, the node degree distribution is (0, )’s nodes, the density of nodes in a free state; represents the probability that the nodes in the airport surface area layer are affected by the nodes in the airport terminal area airspace layer and change from a free state to a congested state, , Indicates the maximum degree value of the node in the airport surface area layer to the airport terminal area airspace layer; Indicated in During the time period, the first target node in the airport surface area layer is affected by a node in the airport terminal area airspace layer that is connected to the first target node and is in a congested state, and the probability of the state of the first target node changing from other nodes to a congested state; Indicates that in the airport surface area layer, the node degree distribution is (0, ) nodes, the density of nodes in a congested state; represents the probability of a node in a congested state in the airport surface area layer changing to a removed state; represents the probability of a node in a congested state in the airspace layer of the airport terminal area changing to a removed state; represents the probability of a node in a congested state in the regional control airspace layer changing to a removed state; It means that in the airport terminal area airspace layer, the node degree distribution is The density of nodes in a free state among the nodes; , , , Indicates the maximum degree value of the nodes in the airport terminal area airspace layer to the airport surface area layer; Indicates the maximum degree value of the node in the airport terminal area airspace layer for the airport terminal area airspace layer; Indicates the maximum degree value of the nodes in the airport terminal area airspace layer with respect to the regional control airspace layer; Indicates the probability that the nodes in the airport terminal area airspace layer change from other node states to congestion states due to the influence of the nodes in the airport surface area layer; represents the probability that the nodes in the airspace layer of the airport terminal area change from other node states to congestion states due to the influence of the nodes in the airspace layer of the airport terminal area; represents the probability that the nodes in the airport terminal area airspace layer change from other node states to congestion states due to the influence of the nodes in the regional control airspace layer; Indicated in During the time period, the second target node in the airport terminal area airspace layer is affected by the node in the airport surface area layer that is connected to the second target node and is in a congested state, and the probability of the state of the second target node changing from other nodes to a congested state; Indicated in During the time period, the second target node in the airport terminal area airspace layer is affected by a node in the airport terminal area airspace layer that is connected to the second target node and is in a congested state, and the probability that the state of other nodes changes to a congested state; Indicated in During the time period, the second target node in the airport terminal area airspace layer is affected by the node in the regional control airspace layer that is connected to the second target node and is in a congested state, and the probability of the state of the second target node changing from other nodes to a congested state; It means that in the airport terminal area airspace layer, the node degree distribution is The density of nodes in congestion among the nodes; Indicates that in the regional control airspace layer, the node degree distribution is The density of nodes in a free state among the nodes; , , Indicates the maximum degree value of the node in the regional control airspace layer to the airport terminal area airspace layer; Indicates the maximum degree value of the nodes in the regional control airspace layer for the regional control airspace layer; represents the probability that a node in the regional control airspace layer is affected by a node in the airport terminal area airspace layer and changes from a free state to a congested state; represents the probability that a node in the regional control airspace layer changes from a free state to a congested state due to the influence of a node in the regional control airspace layer; Indicated in During the time period, the probability that the third target node in the regional control airspace layer is affected by the node in the airport terminal area airspace layer that is connected to the third target node and is in a congested state, and changes from other node states to a congested state; Indicated in During the time period, the probability that the third target node in the regional control airspace layer is affected by the node in the regional control airspace layer that is connected to the third target node and is in a congested state, and changes from other node states to a congested state; Indicates that in the regional control airspace layer, the node degree distribution is The density of nodes in a congested state among the nodes.

[0103] Optionally, the degrees of the nodes in the air traffic hierarchical network model are set to be unrelated; Expressed as:

[0104] in, Represents the average degree value of the nodes in the airport surface area layer to the airport terminal area airspace layer; Indicates that a node is randomly selected from the airport surface area layer, and the node has j The probability that the edge is connected to the airport terminal area airspace layer; Represents the average degree value of the nodes in the airport terminal area airspace layer to the airport surface area layer; represents the average degree value of the nodes in the airport terminal area airspace layer for the airport terminal area airspace layer; Represents the average degree value of the nodes in the airport terminal area airspace layer with respect to the regional control airspace layer; Indicates that a node is randomly selected from the airport terminal area airspace layer, and the node has i The edge is connected to the airport surface area layer, and there is j The edge is connected to the airport terminal area airspace layer, and there is k The probability that the edge is connected to the regional control airspace layer; Represents the average degree value of the nodes in the regional control airspace layer with respect to the airport terminal area airspace layer; represents the average degree value of the nodes in the regional control airspace layer for the regional control airspace layer; Indicates that a node is randomly selected from the regional control airspace layer, and the node has j The edge is connected to the airport terminal area airspace layer, and there is k The probability that the edge is connected to the regional control airspace layer; Indicates that in the airport surface area layer, the node degree distribution is (0, ) nodes, the density of nodes in a congested state; It means that in the airport terminal area airspace layer, the node degree distribution is The density of nodes in congestion among the nodes; Indicates that in the regional control airspace layer, the node degree distribution is The density of nodes in a congested state among the nodes.

[0105] Optionally, the air traffic network congestion state propagation prediction device of the present invention may further include a basic reproduction number calculation module for: Based on the air traffic hierarchical network model, the next generation matrix A basic regeneration number of the air traffic network is calculated, where the basic regeneration number is used to reflect the ability of a node in a congested state to propagate the congested state among nodes in a free state.

[0106] in, F is the growth rate of congested nodes; V is the growth rate of nodes that change from congested state to free state.

[0107] Optionally, the air traffic network congestion state propagation prediction device of the present invention may further include a data preprocessing module for: The target data is preprocessed to remove outliers in the target data.

[0108] Optionally, the preset infectious disease model is a susceptible-infectious-escape model.

[0109] Based on a general inventive concept, the present invention also provides a device for predicting the propagation of air traffic network congestion status. Figure 5 Schematic diagram of a device for predicting the spread of air traffic network congestion status provided by an embodiment of the present invention. Figure 5 As shown, the air traffic network congestion state propagation situation prediction device 500 includes: at least one processor 510; and, A memory 530 is communicatively connected to at least one processor 510; wherein, The memory 530 stores instructions 520 executable by at least one processor, and the instructions 520 are executed by at least one processor 510, so that the at least one processor 510 can implement the method for predicting the propagation of air traffic network congestion status described in the above embodiment.

[0110] It can be understood that the same or similar parts of the above embodiments can be referenced to each other, and the contents not described in detail in some embodiments can refer to the same or similar contents in other embodiments.

[0111] It should be noted that, in the description of the present invention, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. In addition, in the description of the present invention, unless otherwise specified, the meaning of "plurality" refers to at least two.

[0112] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present invention includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present invention belong.

[0113] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0114] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0115] In addition, each functional unit in each embodiment of the present invention may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0116] The storage medium mentioned above can be a read-only memory, a magnetic disk or an optical disk, etc.

[0117] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0118] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for predicting the spread of air traffic network congestion status, characterized in that: include: Acquire target data of an air traffic network, the target data including route data, airport terminal area airspace data, airport surface area data, and flight flow data within a preset time period, the duration of the preset time period being equal to a preset unit duration; According to the route data, the airport terminal area airspace data and the airport surface area data, an air traffic hierarchical network model is constructed, wherein the air traffic hierarchical network model includes regional control airspace nodes, airport terminal area airspace nodes, airport surface area nodes and connection edges between the three nodes, the regional control airspace nodes are target locations of dense areas of route intersections determined according to the route data, and the connection edges are generated according to actual connectivity of traffic flows in the air traffic network; All the regional control airspace nodes are located at the regional control airspace layer, all the airport terminal area airspace nodes are located at the airport terminal area airspace layer, all the airport surface area nodes are located at the airport surface area layer, and the airport terminal area airspace layer is located between the regional control airspace layer and the airport surface area layer; Based on the preset infectious disease model and the air traffic hierarchical network model, a traffic congestion propagation coupling network model is constructed; the node states of each node in the air traffic hierarchical network model include a free state, a congested state and a removed state, and these three node states correspond to the susceptible state, the infected state and the removed state in the preset infectious disease model respectively; The traffic congestion propagation coupling network model is solved according to the flight flow data to obtain a function of the average congestion state density of the three types of nodes changing with time.

2. The method for predicting the spread of air traffic network congestion status according to claim 1, characterized in that: The step of constructing an air traffic hierarchical network model according to the route data, the airport terminal area airspace data and the airport surface area data specifically includes: Determine each route intersection point according to the route data, wherein the route intersection point refers to the intersection or confluence of two or more routes; Based on a preset clustering algorithm, clustering the route intersection points to obtain a plurality of route intersection point sets, wherein all the route intersection points in each of the route intersection point sets constitute a route intersection point dense area; Determine the target position of each of the route intersection dense areas as a regional controlled airspace node; Generating connection edges between different regional controlled airspace nodes according to the route data; Determine each of the airport terminal area airspace nodes according to the airport terminal area airspace data; For each of the airport terminal area airspace nodes, determine the target area control airspace node and the first target airport terminal area airspace node actually connected to the airport terminal area airspace node according to the airport terminal area airspace data, and generate connection edges between the target area control airspace node and the first target airport terminal area airspace node and the airport terminal area airspace node respectively; Determining each of the airport surface area nodes according to the airport surface area data; For each of the airport surface area nodes, based on the airport surface area data, determine the second target airport terminal area airspace node that the airport surface area node is actually connected to, and generate a connecting edge between the second target airport terminal area airspace node and the airport surface area node.

3. The method for predicting the spread of air traffic network congestion status according to claim 2, characterized in that: The step of determining the target position of each of the route intersection dense areas as a regional controlled airspace node specifically includes: Determine the center point of each of the route intersection dense areas as a regional controlled airspace node.

4. The method for predicting the spread of air traffic network congestion status according to claim 1, characterized in that: The expression of the traffic congestion propagation coupled network model is: in, Indicates that in the airport surface area layer, the node degree distribution is (0, )’s nodes, the density of nodes in a free state; represents the probability that the nodes in the airport surface area layer are affected by the nodes in the airport terminal area airspace layer and change from a free state to a congested state, , Indicates the maximum degree value of the node in the airport surface area layer to the airport terminal area airspace layer; Indicated in During the time period, the first target node in the airport surface area layer is affected by a node in the airport terminal area airspace layer that is connected to the first target node and is in a congested state, and the probability of the state of the first target node changing from other nodes to a congested state; Indicates that in the airport surface area layer, the node degree distribution is (0, ) nodes, the density of nodes in a congested state; represents the probability of a node in a congested state in the airport surface area layer changing to a removed state; represents the probability of a node in a congested state in the airspace layer of the airport terminal area changing to a removed state; represents the probability of a node in a congested state in the regional control airspace layer changing to a removed state; It means that in the airport terminal area airspace layer, the node degree distribution is The density of nodes in a free state among the nodes; , , , Indicates the maximum degree value of the nodes in the airport terminal area airspace layer to the airport surface area layer; Indicates the maximum degree value of the node in the airport terminal area airspace layer for the airport terminal area airspace layer; Indicates the maximum degree value of the nodes in the airport terminal area airspace layer with respect to the regional control airspace layer; Indicates the probability that the nodes in the airport terminal area airspace layer change from other node states to congestion states due to the influence of the nodes in the airport surface area layer; represents the probability that the nodes in the airspace layer of the airport terminal area change from other node states to congestion states due to the influence of the nodes in the airspace layer of the airport terminal area; represents the probability that the nodes in the airport terminal area airspace layer change from other node states to congestion states due to the influence of the nodes in the regional control airspace layer; Indicated in During the time period, the second target node in the airport terminal area airspace layer is affected by the node in the airport surface area layer that is connected to the second target node and is in a congested state, and the probability of the state of the second target node changing from other nodes to a congested state; Indicated in During the time period, the second target node in the airport terminal area airspace layer is affected by a node in the airport terminal area airspace layer that is connected to the second target node and is in a congested state, and the probability that the state of other nodes changes to a congested state; Indicated in During the time period, the second target node in the airport terminal area airspace layer is affected by the node in the regional control airspace layer that is connected to the second target node and is in a congested state, and the probability of the state of the second target node changing from other nodes to a congested state; It means that in the airport terminal area airspace layer, the node degree distribution is The density of nodes in congestion among the nodes; Indicates that in the regional control airspace layer, the node degree distribution is The density of nodes in a free state among the nodes; , , Indicates the maximum degree value of the node in the regional control airspace layer to the airport terminal area airspace layer; Indicates the maximum degree value of the nodes in the regional control airspace layer for the regional control airspace layer; represents the probability that a node in the regional control airspace layer is affected by a node in the airport terminal area airspace layer and changes from a free state to a congested state; represents the probability that a node in the regional control airspace layer changes from a free state to a congested state due to the influence of a node in the regional control airspace layer; Indicated in During the time period, the probability that the third target node in the regional control airspace layer is affected by the node in the airport terminal area airspace layer that is connected to the third target node and is in a congested state, and changes from other node states to a congested state; Indicated in During the time period, the probability that the third target node in the regional control airspace layer is affected by the node in the regional control airspace layer that is connected to the third target node and is in a congested state, and changes from other node states to a congested state; Indicates that in the regional control airspace layer, the node degree distribution is The density of nodes in a congested state among the nodes.

5. The method for predicting the spread of air traffic network congestion status according to claim 4, characterized in that: It is assumed that the degrees of the nodes in the air traffic hierarchical network model are unrelated; the degrees of the nodes in the traffic congestion propagation coupled network model are Expressed as: in, Represents the average degree value of the nodes in the airport surface area layer to the airport terminal area airspace layer; Indicates that a node is randomly selected from the airport surface area layer, and the node has j The probability that the edge is connected to the airport terminal area airspace layer; Represents the average degree value of the nodes in the airport terminal area airspace layer to the airport surface area layer; represents the average degree value of the nodes in the airport terminal area airspace layer for the airport terminal area airspace layer; Represents the average degree value of the nodes in the airport terminal area airspace layer with respect to the regional control airspace layer; Indicates that a node is randomly selected from the airport terminal area airspace layer, and the node has i The edge is connected to the airport surface area layer, and there is j The edge is connected to the airport terminal area airspace layer, and there is k The probability that the edge is connected to the regional control airspace layer; Represents the average degree value of the nodes in the regional control airspace layer with respect to the airport terminal area airspace layer; represents the average degree value of the nodes in the regional control airspace layer for the regional control airspace layer; Indicates that a node is randomly selected from the regional control airspace layer, and the node has j The edge is connected to the airport terminal area airspace layer, and there is k The probability that the edge is connected to the regional control airspace layer; Indicates that in the airport surface area layer, the node degree distribution is (0, ) nodes, the density of nodes in a congested state; It means that in the airport terminal area airspace layer, the node degree distribution is The density of nodes in congestion among the nodes; Indicates that in the regional control airspace layer, the node degree distribution is The density of nodes in a congested state among the nodes.

6. The method for predicting the spread of air traffic network congestion status according to claim 1, characterized in that: After constructing the air traffic hierarchical network model according to the route data, the airport terminal area airspace data and the airport surface area data, the method further includes: Based on the air traffic hierarchical network model, the next generation matrix Calculating a basic reproduction number of the air traffic network, where the basic reproduction number is used to reflect the ability of a node in a congested state to propagate the congested state to nodes in a free state; in, F is the growth rate of congested nodes; V is the growth rate of nodes that change from congested state to free state.

7. The method for predicting the spread of air traffic network congestion status according to claim 1, characterized in that: Before constructing the air traffic hierarchical network model according to the route data, the airport terminal area airspace data and the airport surface area data, the method further includes: The target data is preprocessed to remove outliers in the target data.

8. The method for predicting the spread of air traffic network congestion status according to claim 1, characterized in that: The preset infectious disease model is a susceptible-infectious-escape model.

9. A device for predicting the spread of air traffic network congestion, characterized in that: include: An acquisition module, used to acquire target data of an air traffic network, wherein the target data includes route data, airport terminal area airspace data, airport surface area data, and flight flow data within a preset time period, wherein the duration of the preset time period is equal to the preset unit duration; A first construction module is used to construct an air traffic hierarchical network model according to the route data, the airport terminal area airspace data and the airport surface area data, wherein the air traffic hierarchical network model includes regional control airspace nodes, airport terminal area airspace nodes, airport surface area nodes and connection edges between the three nodes, the regional control airspace nodes are target locations of dense areas of route intersections determined according to the route data, and the connection edges are generated according to actual connectivity of traffic flows in the air traffic network; All the regional control airspace nodes are located at the regional control airspace layer, all the airport terminal area airspace nodes are located at the airport terminal area airspace layer, all the airport surface area nodes are located at the airport surface area layer, and the airport terminal area airspace layer is located between the regional control airspace layer and the airport surface area layer; A second construction module is used to construct a traffic congestion propagation coupling network model based on a preset infectious disease model and the air traffic hierarchical network model; the node state of each node in the air traffic hierarchical network model includes a free state, a congested state and a removed state, and these three node states correspond to the susceptible state, the infected state and the removed state in the preset infectious disease model respectively; A solution module is used to solve the traffic congestion propagation coupling network model according to the flight flow data to obtain a function of the average congestion state density of the three types of nodes changing with time.

10. An air traffic network congestion status propagation prediction device, characterized in that: include: at least one processor; as well as, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to implement the method for predicting the propagation of congestion status of an air traffic network according to any one of claims 1 to 8.

Images