CN116882590B - Flight plan optimization method, system and storage medium based on time sequence network model - Google Patents
Flight plan optimization method, system and storage medium based on time sequence network model Download PDFInfo
- Publication number
- CN116882590B CN116882590B CN202311127516.8A CN202311127516A CN116882590B CN 116882590 B CN116882590 B CN 116882590B CN 202311127516 A CN202311127516 A CN 202311127516A CN 116882590 B CN116882590 B CN 116882590B
- Authority
- CN
- China
- Prior art keywords
- airport
- time sequence
- network
- flight
- node
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 70
- 238000005457 optimization Methods 0.000 title claims abstract description 38
- 238000003860 storage Methods 0.000 title claims abstract description 8
- 238000004458 analytical method Methods 0.000 claims description 56
- 238000004891 communication Methods 0.000 claims description 18
- 238000011156 evaluation Methods 0.000 claims description 16
- 239000011159 matrix material Substances 0.000 claims description 13
- 238000005315 distribution function Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 8
- 238000010183 spectrum analysis Methods 0.000 claims description 8
- 238000004088 simulation Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 4
- 230000010006 flight Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 238000010276 construction Methods 0.000 abstract description 5
- 230000003068 static effect Effects 0.000 description 6
- 230000002123 temporal effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012916 structural analysis Methods 0.000 description 2
- 101100219189 Caenorhabditis elegans byn-1 gene Proteins 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003012 network analysis Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06314—Calendaring for a resource
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/067—Enterprise or organisation modelling
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The application discloses a flight plan optimization method, a system and a storage medium based on a time sequence network model, which are used for firstly and accurately evaluating the network structure and the survivability of a central airport network, providing a basis for improving the survivability of the airport network and providing data support for planning construction of the airport network and determination of a flight plan; secondly, inputting a national preliminary flight plan, carrying out preliminary deduction by using a time sequence network model, setting corresponding thresholds at the waypoints and airports, and identifying and early warning the waypoints and the situations exceeding the peak service capacity of the hub airport which occur in the preliminary deduction according to the flight plan; and finally, optimizing the flight time of the flight plan in the time sequence network model to achieve the pre-discovery and pre-optimization of the congestion conditions of the air route and the airport, thereby improving the utilization rate of the air route and the airport resources. The method solves the problem that the prior flight planning cannot realize the pre-identification and pre-optimization of the road congestion and the airport overload operation.
Description
Technical Field
The application relates to the technical field of flight plan optimization, in particular to a method, a system and a storage medium for flight plan optimization based on a time sequence network model.
Background
Airport networks, road networks, and power networks are not static in nature, and may change for a variety of reasons, such as emergency events, human work and rest time, etc., and adding or modifying routes (roads) may change the topology of the network. The time sequence network method moves the time information about the event from the dynamic system to the network, namely the dynamically occurring underlying structure, so that the characteristics of the real system can be described more accurately.
In the research of the aviation network, the aviation network is abstracted into a static network in the past, in the static network, the connection of the nodes ignores the duration time of contact, the contact interval time and the time sequence of repeated contact and contact, and the flight plan cannot be previewed and optimized. The rapid development of the aviation industry puts higher demands on the efficiency and safety of the aviation airport network, and an effective method for evaluating the aviation airport network is urgently needed, and the problems that the prior identification and pre-optimization of the route congestion and the airport overload operation cannot be achieved when the conventional flight planning is carried out are solved.
Disclosure of Invention
In order to solve the problems in the prior art, the application provides a time sequence network model-based flight plan optimization method, a time sequence network model-based flight plan optimization system and a time sequence network model-based storage medium, which can more accurately evaluate the network structure and the survivability of an airport network, provide a basis for improving the survivability of the airport network, provide data support for planning construction of the airport network and determination of a flight plan, make up the blank of analyzing the airport network by using the time sequence network model at present, solve the problems of pre-recognition and pre-optimization of route congestion and airport overload operation which cannot be realized during the conventional flight plan preparation, realize pre-discovery and pre-optimization, and have stronger innovation and practical significance.
In order to achieve the above purpose, the present application provides the following technical solutions: a flight plan optimization method based on a time sequence network model comprises the following steps:
s101, acquiring flight data, analyzing the periodicity of the flight data by using a power spectrum analysis method, and determining the inherent period of the flight data;
s102, constructing an airport multilayer time sequence network model based on the time sequence network model;
s103, constructing an airport time sequence network model topological structure analysis index comprising a time sequence degree, an average time sequence distance and a node centrality index, and analyzing the airport time sequence network model structure by utilizing the topological structure analysis index;
s104, constructing an airport time sequence network model survivability analysis index which comprises time sequence network efficiency and a time sequence maximum communication subgraph, and carrying out survivability analysis on the airport time sequence network model by utilizing the survivability analysis index;
s105, evaluating the network survivability of the airport: simulating the airport network by adopting strategies of intentional attack, random attack and incomplete information attack to obtain an airport time sequence network model network efficiency loss curve, analyzing the obtained network efficiency loss curve, identifying inflection points of the network efficiency loss curve, and completing the evaluation of the airport network survivability;
s106, inputting a preliminary flight plan, performing preliminary deduction by using a time sequence network model, setting corresponding thresholds at the waypoints and airports, identifying and early warning the waypoints and the situations exceeding the peak service capacity of the hub airport which appear in the preliminary deduction according to the flight plan, optimizing the flight plan time in the time sequence network model, and outputting the optimized flight plan.
Preferably, in step S101, the flight data includes civil aviation flight database document data and flight plan document data in a civil aviation flight information system.
Preferably, in step S102, the constructing an airport multi-layer timing network model based on the timing network model specifically includes the following steps:
s201, constructing an airport time sequence network adjacency matrix and constructingRepresenting an airport timing network, wherein->For a set of airport nodes contained in a network, and (2)>，/>For a set of contiguous edges of flights between airports,whereiniRepresenting a departure node, namely a departure airport (represented by airport numbers)jIndicating that the target node arrives at the airport (indicated by airport number),>is a collection of flight runtimes,wherein->Representing slave nodesiTo the nodejFlight departure time>Representing slave nodesiTo the nodejFlight run time;
s202, dividing the total time of flight data in the time sequence network into corresponding layers according to the inherent period of the flight data, adding corresponding time sequence data into the network in each layer, and constructing an airport multi-layer time sequence network model.
Preferably, in step S103, the timing in the network structure is analyzed by using a timing analysis index, including timing, timing out, timing, and analysis of power law, using a power law distribution function asWherein->Three parameters to be solved for the power law distribution function of the time sequence input, +.>For the node timing value, +.>Probability value for airport node with time sequence degree value k, +.>Three parameters to be solved for the time-series power law distribution function, < >>For node timing out value, +.>For a time sequence output value ofkThe probability value of the airport node, and fitting the data to obtain the parameter to be solved; and analyzing the network structure by using node centrality indexes, wherein the node centrality indexes comprise time sequence centrality, time sequence betweenness centrality and time sequence proximity centrality.
Preferably, in step S105, the method specifically includes the following steps:
s501, randomly selecting an attack order in an airport node set and forming an attack order set by using a random attack strategyWherein,nfor the number of the attacked airport nodes, v is the number of attacks, 1attack represents the 1 st attack, 2attack represents the 2 nd attack, vattack represents the v attack, and%>As attack type, random attack is also represented, and corresponding nodes in the network are deleted in sequence according to the collection sequence, and network efficiency and maximum communication subgraphs are calculated;
s502, the intentional attack strategy is divided into a sequence degree strength sequence attack, a sequence medium number center sequence attack and a sequence proximity center strength attack to form a sequence degree attack sequence set respectivelyWherein,nfor the number of the attacked airport nodes, v is the number of attacks, 1attack represents the 1 st attack, 2attack represents the 2 nd attack, vattack represents the v attack, and%>Representing a sequential strength ordering attack, a sequential betting attack order setWherein, the method comprises the steps of, wherein,nfor the number of attacked airport nodes, v is the number of attacks, 1attack represents the 1 st attack, 2attack represents the 2 nd attack, vattack represents the v th attack,prepresents a sequential mediate value ordering attack, a sequential proximity attack order set +.>Wherein, the method comprises the steps of, wherein,nnumbering the node of the attacked airport, v is the number of attacks, 1attack represents the 1 st attack, 2attack represents the 2 nd attack, and vattack represents the v-th attack, whereinbRepresenting time sequence proximity value ordering attack, sequentially deleting nodes according to a sequence set, and calculating network efficiency and a maximum communication subgraph;
s503, the attack mode of the incomplete information attack is to apply a deliberate attack strategy to the node set of the known information under the condition of given the known informationCarrying out attack, applying random attack strategy to nodes with unknown information, and forming a non-complete information attack sequence set according to the sequence of the known prior unknown nodesWherein, the method comprises the steps of, wherein,nfor the number of attacked airport nodes, v is the number of attacks, 1attack represents the 1 st attack, 2attack represents the 2 nd attack, vattack represents the v th attack,mrepresenting incomplete information attack, deleting nodes sequentially according to a sequence set, calculating network efficiency and a maximum communication subgraph, and obtaining an airport time sequence network model network efficiency loss curve through steps S501-S503;
s504, analyzing the obtained network efficiency loss curve, identifying inflection points of the network efficiency loss curve, and completing the evaluation of the network destructiveness of the airport.
Preferably, in step S106, the method specifically includes the following steps:
s601, importing flight plan data, screening out empty data, screening flight numbers, flight take-off time, flight time, take-off airports and destination airport key data, adding data with time attributes into an adjacent matrix based on the processed data, wherein each element in the matrix does not use simple 0,1 to indicate whether continuous edges exist or not, but is replaced by a list, adding the flight time data among node pairs into the list to store to form a flight plan time sequence adjacent matrix, importing route information and airport information, and setting route points and airport thresholds;
s602, performing deduction in advance by using a time sequence network model, and identifying and early warning the congestion points of the airlines and the situations exceeding the peak service capacity of the hub airport which occur in deduction according to the flight schedule;
and S603, optimizing the flight time of the flight plan in the time sequence network model, and outputting the optimized flight plan.
On the other hand, in order to achieve the above purpose, the present application further provides the following technical solutions: a time series network model-based flight plan optimization system, the system comprising:
the flight data acquisition module: the system is used for collecting flight data, analyzing the periodicity of the flight data by using a power spectrum analysis method, and determining the inherent period of the flight data;
the multi-layer time sequence network model building module: the airport multi-layer time sequence network model is constructed based on the time sequence network model;
the network model topology analysis module: the method comprises the steps of constructing an airport time sequence network model topological structure analysis index, wherein the airport time sequence network model topological structure analysis index comprises a time sequence degree, an average time sequence distance and a node centrality index, and analyzing the airport time sequence network model structure by utilizing the topological structure analysis index;
the network model survivability analysis module: the method comprises the steps of constructing an airport time sequence network model survivability analysis index, wherein the index comprises time sequence network efficiency and a time sequence maximum communication subgraph, and carrying out survivability analysis on the airport time sequence network model by utilizing the survivability analysis index;
the survivability evaluation module: the method comprises the steps of performing survivability evaluation on an airport network, performing simulation attack on the airport network by adopting strategies of intentional attack, random attack and incomplete information attack to obtain an airport time sequence network model network efficiency loss curve, analyzing the obtained network efficiency loss curve, identifying inflection points of the network efficiency loss curve, and finishing evaluation on the survivability of the airport network;
and a flight plan optimization module: the method is used for inputting a pre-flight plan, performing pre-deduction by using a time sequence network model, setting corresponding thresholds at waypoints and airports, identifying and early warning the waypoints and the situations exceeding the peak service capacity of the hub airport which appear in the pre-deduction according to the flight plan, optimizing the flight plan time in the time sequence network model, and outputting the optimized flight plan.
On the other hand, in order to achieve the above purpose, the present application further provides the following technical solutions: a computer readable storage medium having stored thereon a computer program which when processed for execution implements the flight plan optimization method.
The beneficial effects of the application are as follows:
1) Firstly, the application can evaluate the network structure and the survivability of the airport network more accurately, provides a basis for improving the survivability of the airport network, and provides data support for planning construction of the airport network and determination of the flight plan. And secondly, inputting a pre-flight plan, carrying out pre-deduction by using a time sequence network model, setting corresponding thresholds at the waypoints and the airports, identifying and early warning the waypoints and the situations exceeding the peak service capacity of the hub airport which appear in the pre-deduction according to the flight plan, and finally optimizing the flight time of the flight plan in the time sequence network simulation to realize the pre-discovery and pre-optimization of the congestion situations of the waypoints and the airports, thereby improving the utilization rate of the resources of the waypoints and the airports. The method makes up the blank of analyzing the airport network by using the time sequence network model at present, solves the problems that the prior flight planning can not realize the pre-identification and pre-optimization of the route congestion and the overload operation of the airport, realizes the pre-discovery and pre-optimization, and has stronger innovation and practical significance.
2) The application mainly adds the flight operation data or the flight plan data into the network for analysis based on the time sequence network model, and compared with the static network, the database data set has large data volume, more data characteristics and more accurate structural analysis. By analyzing the flight operation data, the structural characteristics of the airport network can be more accurately analyzed and the survivability of the airport network can be evaluated. By analyzing the flight plan data and utilizing the time sequence network model to conduct deduction in advance, corresponding thresholds are set on the airlines and the airports, the situation that the airline congestion points appear in deduction according to the flight plan and the situation that the traffic-hub airport peak service capacity is exceeded are identified and early-warned, the flight plan time can be optimized in the time sequence network model, the occurrence of the congestion of the airlines and the airports can be relieved, and the method has high innovation and practical significance. The method solves the problems that the congestion of the air way and the airport can only be passively adjusted, but the pre-discovery and the pre-optimization can not be realized.
Drawings
FIG. 1 is a flow chart of a flight data processing and power spectrum analysis method;
FIG. 2 is a schematic diagram of a multi-layer timing network model;
FIG. 3 is a flow chart of airport network structure analysis and survivability analysis;
FIG. 4 is a flow chart of flight plan previewing, route, airport congestion identification and early warning based on a time series network model;
FIG. 5 is a schematic diagram of a flight plan optimization system module according to the present application;
in the figure, a 110-flight data acquisition module; 120-a multi-layer time sequence network model building module; 130-a network model topology analysis module; 140-a network model survivability analysis module; 150-a survivability evaluation module; 160-flight plan optimization module.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Referring to fig. 1-4, the present application provides a technical solution: a flight plan optimization method based on a time sequence network model comprises the following specific processes:
(1) Collecting flight data, as shown in fig. 1, analyzing the periodicity of the flight data by using a power spectrum analysis method, and determining the inherent period of the flight data;
(2) Constructing an airport multi-layer time sequence network model, wherein the multi-layer time sequence network structure is shown in figure 2;
(3) Constructing an airport time sequence network model topological structure analysis index which comprises a time sequence entering degree, a time sequence exiting degree, a time sequence degree, an average time sequence distance and an airport node centrality index: timing centrality, timing betweenness centrality, timing proximity centrality;
(4) Constructing an airport time sequence network model survivability analysis index, and selecting a time sequence network efficiency and a time sequence maximum connected subgraph as the airport time sequence network model survivability analysis index;
(5) The simulation attack is carried out on the airport network by adopting the deliberate attack, the random attack and the incomplete information attack, the obtained airport time sequence network model network efficiency loss curve is analyzed, and the inflection point of the network efficiency loss curve is identified, so that the damage resistance of the airport network is evaluated.
(6) The method comprises the steps of inputting a national preliminary flight plan, carrying out preliminary deduction by using a time sequence network model, setting corresponding thresholds at waypoints and airports, identifying and early warning the waypoints and the situations exceeding the peak service capacity of the hub airport which appear in the preliminary deduction according to the flight plan, and optimizing the flight plan time in the time sequence network model.
Further, the flight data in the step (1) comprises a civil aviation flight database document and a flight plan document in the civil aviation flight information system, and the data is periodically analyzed.
Further, the constructing of the airport multilayer time sequence network model in the step (2) is based on the time sequence network model construction, and comprises the following steps:
(2.1) constructing an airport sequential network adjacency matrix, constructingAirport timing network of representations, wherein(nodes) is the set of airport nodes contained in the network, < >>，/>(edge) is a set of flights between airports, < ->，/>(time) is a set of flight runtimes,wherein->Representing slave nodesiTo the nodejFlight departure time>Representing slave nodesiTo the nodejFlight run time.
Wherein the method comprises the steps ofIs a slave nodeiTo the nodejAll flight run time sets contained.
Wherein the method comprises the steps ofRepresenting slave nodes in observation period TiTo the nodejIs the first of (2)mTake-off time of flight of next flight>Representing slave nodes in observation period TiTo the nodejIs the first of (2)mThe flight time of the flight is executed next time.
(2.2) total time of flight data in the time-series networkDividing the airport multi-layer time sequence network model into corresponding layers according to the inherent period, and adding corresponding time sequence data into the network in each layer to construct the airport multi-layer time sequence network model.
Further, the step (3) is to analyze the network topology structure and the survivability of the airport, as shown in fig. 3, and specifically includes the following steps:
(3.1) analyzing the time sequence degree in the network structure, including the time sequence degree,timing and analysis of its power law and using a power law distribution function asAnd fitting the results to determine parametersThe method is characterized in that under the condition of model data value, the power law distribution function can be used for fitting well.
Wherein the method comprises the steps ofFor the time sequence degree, T is the data natural period length, < >>To number the network layers of the time-sequential multi-layer network,is->The ingress value of the layer network,/>For time sequence out degree->Is->The value of the degree of egress of the layer network,/>For the timing network total metric,/->Indicate->The sum of the ingress and egress values of the layer network.
And (3.2) analyzing the average time sequence distance in the network structure, wherein the average time sequence distance is a parameter for representing the distance between each node on the network and the average node taking the consumption time as an index.
Wherein the method comprises the steps ofFor node i to nodejT is the network natural period length, +.>For the departure time of the nth flight, +.>Is the firstnFlight time of the secondary flight.
And (3.3) carrying out the study on the node centrality in the network structure, wherein the study comprises indexes such as time sequence centrality, time sequence medium centrality, time sequence proximity centrality and the like.
Timing centrality (temporal degree centrality, TD)
The greater the timing of a node means the higher the centrality of the timing of the node, which is more important in the timing network. The larger the network size, the higher the maximum possible value of the degree of timing. To eliminate the impact of network scale changes on centrality, it is necessary to divide byN-1 normalization.
Wherein the method comprises the steps ofIs->The central value of the time sequence degree of the layer network, N is the number of network nodes, < ->Indicate->The sum of the ingress and egress values of the layer network.
Center of time series betweenness (temporal betweenness centrality, TB)
Calculating all shortest paths of any two nodes in the network, if a plurality of the shortest paths pass through a certain node, then considering that the intermediacy of the node is high, and then the nodeThe timing medium centrality calculation formula of (c) is as follows.
Wherein the method comprises the steps ofRepresents the number k node->The median centrality value of the layer network,kthe value is 1 to N +>Is at observation time +.>Is passed +.>The number of nodes>Is at observation time +.>The shortest path total number of all node pairs.
Timing proximity centrality (temporal closeness centrality, TC):
the shortest timing distance of a node to other nodes in the graph is small, and its proximity centrality is high. Near centrality is closer to geometrically central location than intermediate centrality, nodeThe timing proximity centrality calculation formula of (c) is as follows.
Wherein the method comprises the steps ofIs numbered k node->Proximity centrality value of layer network, +.>Is the number of nodes->Representation->The sum of the average timing distances to all other nodes.
Further, in the step (4), constructing an airport time sequence network model survivability analysis index, wherein the index comprises time sequence network efficiency and a time sequence maximum communication subgraph, and storing the result as a time sequence network efficiency database.
Time sequential network efficiency:
wherein the method comprises the steps ofIs the number of nodes->Representing nodesiTo the nodejAverage timing distance.
Further, in the step (5), the simulation attack is carried out on the airport network by using the attack modes of intentional attack, random attack and incomplete information attack on the airport network, the obtained airport time sequence network model network efficiency and maximum communication subgraph loss curve are analyzed, and the inflection points are identified, so that the airport network destructiveness is evaluated. The time sequence network survivability analysis index comprises time sequence network efficiency and time sequence network maximum communication subgraph.
(5.1) random attack strategy is to randomly select an attack order in the airport node set and form an attack order setMiddle right upper markrFor attack type superscript, hererAlso denoted random attack, 1attack represents attack 1, 2attack represents attack 2, vattack represents attack v,nnumbering the nodes of the attacked airport, sequentially deleting the nodes according to the sequence set, and calculating the network efficiency and the maximum communication subgraph.
(5.2) the intentional attack strategy is divided into a sequence degree strength sequence attack, a sequence medium number center sequence attack and a sequence proximity center strength attack, and a sequence degree attack sequence set is formed respectively，Middle right upper markkSuperscript for attack type, wherekRepresenting a time sequential strength ordering attack, 1attack represents the 1 st attack, 2attack represents the 2 nd attack, vattack represents the v attack, nnumbering the attacked airport nodes, the set of sequential betweenness attack order +.>Middle right upper markpSuperscript for attack type, wherepRepresents a sequential mediate value ordering attack, the right subscript is the attack frequency subscript vattack represents the v-th attack,nnumbering the attacked airport nodes, the set of time sequence proximity attack order +.>Middle and right superscriptbSuperscript for attack type, wherebRepresents a time sequence proximity value ordering attack, the right subscript is an attack frequency subscript vattack represents a v-th attack,nnumbering the nodes of the attacked airport, sequentially deleting the nodes according to the sequence set, and calculating the network efficiency and the maximum communication subgraph.
(5.3) the attack mode of the incomplete information attack is to apply the intentional attack strategy to the node set of the known information under the condition of given known information, apply the random attack strategy to the node of the unknown information, and form the incomplete information attack sequence set according to the sequence of the known and the unknown nodesMiddle right upper markmSuperscript for attack type, wheremRepresenting a non-complete information attack, 1attack represents the 1 st attack, 2attack represents the 2 nd attack, vattack represents the v attack,nand (3) numbering the nodes of the attacked airport, sequentially deleting the nodes according to a sequence set, calculating network efficiency and a maximum communication subgraph, and obtaining a network efficiency loss curve of the airport time sequence network model through the steps (5.1) - (5.3).
And (5.4) analyzing the obtained airport time sequence network model network efficiency and the maximum connected subgraph loss curve, identifying inflection points of the airport time sequence network model network efficiency and the maximum connected subgraph loss curve, and completing the evaluation of the airport network survivability.
Further, as shown in fig. 4, step (6) performs pre-deduction by inputting a pre-flight plan and applying a time sequence network model, sets corresponding thresholds at waypoints and airports, identifies and pre-warns the situation that the waypoints and the situation exceed the peak service capacity of the hub airport appear in the pre-deduction according to the flight plan, and optimizes the time of the flight plan in the time sequence network model:
and (6.1) importing flight plan data, preprocessing the data, namely screening the data, screening out empty data, screening flight numbers, flight departure time, flight time, departure airport and destination airport key data, adding data with time attributes into an adjacent matrix based on the processed data, wherein each element in the matrix does not use simple 0,1 to indicate whether continuous edges exist or not, but is replaced by a list, adding the flight time data among node pairs into the list to store to form a flight plan time sequence adjacent matrix, importing route information and airport information, and setting route and airport thresholds.
And (6.2) carrying out deduction in advance by using a time sequence network model, and identifying and early warning the route congestion points and the situations exceeding the peak service capacity of the hub airport which occur in deduction according to the flight schedule.
And (6.3) optimizing the flight time of the flight plan in the time sequence network model to realize the pre-discovery and pre-optimization of the congestion conditions of the air route and the airport, thereby improving the utilization rate of the air route and the airport resources.
The application has reasonable conception and clear process, can improve the accuracy of the structural analysis of the dynamic system, provides basis for improving the survivability of the airport network, and provides data support for the planning and construction of the airport network, and the addition of the time attribute also enables the flight time optimization under various view angles to be possible in the network model. The method makes up the blank of analyzing the airport network by using the time sequence network model at present, and compared with the static network analysis, the method can overcome the inadaptability of the static network to the dynamic system commonly used at present and improve the accuracy of analysis.
Based on the same inventive concept as the above method embodiment, the present application further provides a flight plan optimization system based on a time-series network model, for implementing the flight plan optimization method based on the time-series network model described in the above embodiment, as shown in fig. 5, where the system specifically includes:
the flight data acquisition module 110: the system is used for collecting flight data, analyzing the periodicity of the flight data by using a power spectrum analysis method, and determining the inherent period of the flight data;
the multi-layer timing network model building module 120: the airport multi-layer time sequence network model is constructed based on the time sequence network model;
network model topology analysis module 130: the method comprises the steps of constructing an airport time sequence network model topological structure analysis index, wherein the airport time sequence network model topological structure analysis index comprises a time sequence degree, an average time sequence distance and a node centrality index, and analyzing the airport time sequence network model structure by utilizing the topological structure analysis index;
the network model survivability analysis module 140: the method comprises the steps of constructing an airport time sequence network model survivability analysis index, wherein the index comprises time sequence network efficiency and a time sequence maximum communication subgraph, and carrying out survivability analysis on the airport time sequence network model by utilizing the survivability analysis index;
the survivability evaluation module 150: the method comprises the steps of performing survivability evaluation on an airport network, performing simulation attack on the airport network by adopting strategies of intentional attack, random attack and incomplete information attack to obtain an airport time sequence network model network efficiency loss curve, analyzing the obtained network efficiency loss curve, identifying inflection points of the network efficiency loss curve, and finishing evaluation on the survivability of the airport network;
the flight plan optimization module 160: the method is used for inputting a pre-flight plan, performing pre-deduction by using a time sequence network model, setting corresponding thresholds at waypoints and airports, identifying and early warning the waypoints and the situations exceeding the peak service capacity of the hub airport which appear in the pre-deduction according to the flight plan, optimizing the flight plan time in the time sequence network model, and outputting the optimized flight plan.
Based on the same inventive concept as the above-described method embodiments, the present embodiments also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the flight plan optimization method.
The flight plan optimization method comprises the following steps:
acquiring flight data, analyzing the periodicity of the flight data by using a power spectrum analysis method, and determining the inherent period of the flight data;
constructing an airport multilayer time sequence network model based on the time sequence network model;
constructing topological structure analysis indexes of the airport time sequence network model, wherein the topological structure analysis indexes comprise time sequence degree, average time sequence distance and node centrality indexes, and analyzing the airport time sequence network model structure by utilizing the topological structure analysis indexes;
constructing an airport time sequence network model survivability analysis index which comprises time sequence network efficiency and a time sequence maximum communication subgraph, and carrying out survivability analysis on the airport time sequence network model by utilizing the survivability analysis index;
airport network survivability assessment: simulating the airport network by adopting strategies of intentional attack, random attack and incomplete information attack to obtain an airport time sequence network model network efficiency loss curve, analyzing the obtained network efficiency loss curve, identifying inflection points of the network efficiency loss curve, and completing the evaluation of the airport network survivability;
inputting a pre-flight plan, carrying out pre-deduction by using a time sequence network model, setting corresponding thresholds at waypoints and airports, identifying and early warning the waypoints and the situations exceeding the peak service capacity of the hub airport which appear in the pre-deduction according to the flight plan, optimizing the flight plan time in the time sequence network model, and outputting the optimized flight plan.
The application makes up the blank of analyzing the airport network by using the time sequence network model at present, solves the problems that the prior flight planning cannot realize the pre-recognition and pre-optimization of the road congestion and the overload operation of the airport, realizes the pre-discovery and pre-optimization, and has stronger innovation and practical significance.
Although the present application has been described with reference to the foregoing embodiments, it will be apparent to those skilled in the art that modifications may be made to the embodiments described, or equivalents may be substituted for elements thereof, and any modifications, equivalents, improvements and changes may be made without departing from the spirit and principles of the present application.
Claims (5)
1. A flight plan optimization method based on a time sequence network model is characterized by comprising the following steps:
s101, acquiring flight data, analyzing the periodicity of the flight data by using a power spectrum analysis method, and determining the inherent period of the flight data;
s102, constructing an airport multilayer time sequence network model based on the time sequence network model, which specifically comprises the following steps:
s201, constructing an airport time sequence network adjacency matrix, and constructing G= { N, E and T } to represent an airport time sequence network, wherein N is an airport node set contained in the network, N (G) = 1,2,3,4 and 5..N, E is a flight continuous edge set among airports, and E (G) = (i) 1 ,j 1 ),(i 2 ,j 2 ),(i 3 ,j 3 ),...,(i E ,j E ) Where i denotes the origin node, the departure airport, j denotes the destination node, the arrival airport, T is the flight run time set, T (G) = { (T) 12 ,σ 12 ),(t 13 ,σ 13 )…(t ij ,σ ij ) }, t is ij Representing departure time of flights from node i to node j, sigma ij Representing the flight run time from node i to node j; the airport timing network adjacency matrix is as follows:
wherein T is [i,j] A set of all flight runs contained from node i to node j;
wherein the method comprises the steps ofRepresenting departure time of mth flight from node i to node j in observation period T，/>Representing a flight time of an mth flight from node i to node j in the observation period T;
s202, dividing the total time of flight data in a time sequence network into corresponding layers according to the inherent period of the flight data, adding corresponding time sequence data into the network in each layer, and constructing an airport multi-layer time sequence network model;
s103, constructing an airport time sequence network model topological structure analysis index comprising a time sequence degree, an average time sequence distance and a node centrality index, and analyzing the airport time sequence network model structure by utilizing the topological structure analysis index;
in step S103, the timing in the network structure is analyzed by using the timing analysis index, including the timing, the timing out, the timing, and the analysis of the power law, using the power law distribution function asAndwherein A is in ,B in ,λ in Three parameters, k, to be solved for a power law distribution function of time series power in For the node timing metric, P (k in ) A is the probability value of an airport node with a time sequence degree value of k out ,B out ,λ out Three parameters, k, to be solved for a time series power law distribution function out For node timing out value, P (k) out ) The probability value of the airport node with the time sequence degree value k is obtained, and fitting is carried out on the data to obtain parameters to be solved;
analyzing the average time sequence distance in the network structure, wherein the average time sequence distance is a parameter representing the distance between each node on the network and the average node taking the consumption time as an index;
wherein the method comprises the steps ofFor the average time sequence distance from node i to node j, T is the network inherent period length, T n For the departure time of the nth flight, Δt n The flight time for the nth flight;
analyzing the network structure by using node centrality indexes, wherein the node centrality indexes comprise time sequence centrality, time sequence betweenness centrality and time sequence proximity centrality;
timing centrality:
the greater the time sequence degree of a node means the higher the time sequence degree centrality of the node, and the node occupies a more important position in a time sequence network; the larger the network scale, the higher the maximum possible value of the timing degree; to eliminate the impact of network scale changes on centrality, normalization by dividing by N-1 is required, expressed as follows:
wherein the method comprises the steps ofIs the T th i The central value of the time sequence degree of the layer network, N is the number of network nodes, < ->Represents the T th i The sum of the ingress value and the egress value of the layer network;
timing betweenness centrality:
calculating all shortest paths of any two nodes in the network, if a plurality of the shortest paths pass through a certain node, considering that the intermediacy of the node is high, and calculating the time sequence intermediacy of the node i by the following calculation formula:
wherein the method comprises the steps ofRepresenting the T th node numbered k i The median centrality value of the layer network, k is 1 to N, < ->Is the number of k nodes traversed in the shortest path in the observation time T, d i，j Is the total number of shortest paths for all node pairs in the observation time T;
timing proximity centrality:
the shortest time sequence distance from the node to other nodes in the graph is very small, so that the proximity centrality is very high, and compared with the intermediate centrality, the proximity centrality is closer to the geometric central position, and the time sequence proximity centrality calculation formula of the node i is as follows:
wherein the method comprises the steps ofIs numbered k node T i Proximity centrality value of layer network, N is the number of nodes, < ->Representing i the sum of the average timing distances to all other nodes;
s104, constructing an airport time sequence network model survivability analysis index which comprises time sequence network efficiency and a time sequence maximum communication subgraph, and carrying out survivability analysis on the airport time sequence network model by utilizing the survivability analysis index;
s105, evaluating the network survivability of the airport: simulating the airport network by adopting strategies of intentional attack, random attack and incomplete information attack to obtain an airport time sequence network model network efficiency loss curve, analyzing the obtained network efficiency loss curve, identifying inflection points of the network efficiency loss curve, and completing the evaluation of the airport network survivability;
s106, inputting a preliminary flight plan, performing preliminary deduction by using a time sequence network model, setting corresponding thresholds at waypoints and airports, identifying and early warning the waypoints and the situations exceeding the peak service capacity of the hub airport which appear in the preliminary deduction according to the flight plan, optimizing the flight plan time in the time sequence network model, and outputting an optimized flight plan;
in step S106, the method specifically includes the following steps:
s601, importing flight plan data, preprocessing the flight data, namely screening data, screening empty data, screening flight numbers, flight departure time, flight time, departure airport and destination airport key data, adding data with time attributes into an adjacent matrix based on the processed data, wherein each element in the matrix does not need to be simply 0,1 to represent whether a continuous edge exists or not, but is replaced by a list, adding the flight time data among node pairs into the list to store the flight plan time sequence adjacent matrix, importing route information and airport information, and setting route points and airport thresholds;
s602, performing deduction in advance by using a time sequence network model, and identifying and early warning the congestion points of the airlines and the situations exceeding the peak service capacity of the hub airport which occur in deduction according to the flight schedule;
and S603, optimizing the flight time of the flight plan in the time sequence network model, and outputting the optimized flight plan.
2. The time series network model-based flight plan optimization method as claimed in claim 1, wherein: in step S101, the flight data includes civil aviation flight database document data and flight plan document data in the civil aviation flight information system.
3. The time series network model-based flight plan optimization method as claimed in claim 1, wherein: in step S105, the method specifically includes the steps of:
s501, randomly selecting an attack order in an airport node set and forming an attack order set by using a random attack strategyN is the number of the node of the attacked airport, v is the number of attacks, 1attack represents the 1 st attack, vattack represents the v attack, and corresponding nodes in the network are deleted in sequence according to the collection sequence, and the network efficiency and the maximum communication subgraph are calculated;
s502, the intentional attack strategy is divided into a sequence degree strength sequence attack, a sequence medium number center sequence attack and a sequence proximity center strength attack to form a sequence degree attack sequence set respectivelyk represents the strength of sequence order attack, sequence order set of sequence bets->p represents a sequential mediate value ordering attack, sequential proximity attack order set +.>b represents a time sequence proximity value ordering attack, and sequentially deletes nodes according to a sequence set and calculates network efficiency and a maximum communication subgraph;
s503, the attack mode of the incomplete information attack is to apply the intentional attack strategy to the node set of the known information under the condition of given known information, apply the random attack strategy to the node of the unknown information, and form the incomplete information attack sequence set according to the sequence of the prior known and the subsequent unknown nodesm represents incomplete information attack, and finally, sequentially deleting nodes according to a sequence set, calculating network efficiency and a maximum communication subgraph, and obtaining an airport time sequence network model network efficiency loss curve through steps S501-S503;
s504, analyzing the obtained network efficiency loss curve, identifying inflection points of the network efficiency loss curve, and completing the evaluation of the network destructiveness of the airport.
4. A system of a time series network model based flight plan optimization method according to any one of claims 1-3, characterized in that: the system comprises:
the flight data acquisition module: the system is used for collecting flight data, analyzing the periodicity of the flight data by using a power spectrum analysis method, and determining the inherent period of the flight data;
the multi-layer time sequence network model building module: the airport multi-layer time sequence network model is constructed based on the time sequence network model;
the network model topology analysis module: the method comprises the steps of constructing an airport time sequence network model topological structure analysis index, wherein the airport time sequence network model topological structure analysis index comprises a time sequence degree, an average time sequence distance and a node centrality index, and analyzing the airport time sequence network model structure by utilizing the topological structure analysis index;
the network model survivability analysis module: the method comprises the steps of constructing an airport time sequence network model survivability analysis index, wherein the index comprises time sequence network efficiency and a time sequence maximum communication subgraph, and carrying out survivability analysis on the airport time sequence network model by utilizing the survivability analysis index;
the survivability evaluation module: the method comprises the steps of performing survivability evaluation on an airport network, performing simulation attack on the airport network by adopting strategies of intentional attack, random attack and incomplete information attack to obtain an airport time sequence network model network efficiency loss curve, analyzing the obtained network efficiency loss curve, identifying inflection points of the network efficiency loss curve, and finishing evaluation on the survivability of the airport network;
and a flight plan optimization module: the method is used for inputting a pre-flight plan, performing pre-deduction by using a time sequence network model, setting corresponding thresholds at waypoints and airports, identifying and early warning the waypoints and the situations exceeding the peak service capacity of the hub airport which appear in the pre-deduction according to the flight plan, optimizing the flight plan time in the time sequence network model, and outputting the optimized flight plan.
5. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when processed and executed, implements a flight plan optimization method according to any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311127516.8A CN116882590B (en) | 2023-09-04 | 2023-09-04 | Flight plan optimization method, system and storage medium based on time sequence network model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311127516.8A CN116882590B (en) | 2023-09-04 | 2023-09-04 | Flight plan optimization method, system and storage medium based on time sequence network model |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116882590A CN116882590A (en) | 2023-10-13 |
| CN116882590B true CN116882590B (en) | 2023-11-24 |
Family
ID=88264730
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311127516.8A Active CN116882590B (en) | 2023-09-04 | 2023-09-04 | Flight plan optimization method, system and storage medium based on time sequence network model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116882590B (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104751683A (en) * | 2015-03-27 | 2015-07-01 | 中国民用航空飞行学院 | Airport plane taxi scheduling and commanding system and method |
| CN111191843A (en) * | 2019-12-30 | 2020-05-22 | 南京航空航天大学 | Airport delay prediction method based on time sequence network propagation dynamic equation |
| CN111738425A (en) * | 2020-08-07 | 2020-10-02 | 北京航空航天大学 | Airport delay reason analysis method based on graph mining |
| CN112489498A (en) * | 2020-11-25 | 2021-03-12 | 中国电子科技集团公司第二十八研究所 | Fine route change planning method for route traffic |
| CN113759894A (en) * | 2020-05-22 | 2021-12-07 | 株式会社东芝 | Information processing device, information processing method, information processing system, and computer program |
| CN114464017A (en) * | 2022-01-27 | 2022-05-10 | 南京航空航天大学 | Queuing theory-based airport group flight delay estimation method |
| CN115311902A (en) * | 2022-03-25 | 2022-11-08 | 中国航空无线电电子研究所 | Real-time route planning and optimizing method based on multilayer time sequence network |
| CN115564188A (en) * | 2022-09-16 | 2023-01-03 | 中国民航大学 | Flight plan robustness evaluation system and method |
| CN115713872A (en) * | 2022-11-11 | 2023-02-24 | 中国航空无线电电子研究所 | SOA-based environment self-adaptive route planning method |
| CN116246496A (en) * | 2023-05-10 | 2023-06-09 | 北京航空航天大学 | Flight plan planning method based on flight and flow collaborative environment |
| CN116523138A (en) * | 2023-05-08 | 2023-08-01 | 南京航空航天大学 | Terminal airport flight time optimization method considering passenger transit trip selection |
| CN116659504A (en) * | 2023-05-31 | 2023-08-29 | 中国民用航空飞行学院 | Real-time flight data estimation method based on Kalman filtering method |
-
2023
- 2023-09-04 CN CN202311127516.8A patent/CN116882590B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104751683A (en) * | 2015-03-27 | 2015-07-01 | 中国民用航空飞行学院 | Airport plane taxi scheduling and commanding system and method |
| CN111191843A (en) * | 2019-12-30 | 2020-05-22 | 南京航空航天大学 | Airport delay prediction method based on time sequence network propagation dynamic equation |
| CN113759894A (en) * | 2020-05-22 | 2021-12-07 | 株式会社东芝 | Information processing device, information processing method, information processing system, and computer program |
| CN111738425A (en) * | 2020-08-07 | 2020-10-02 | 北京航空航天大学 | Airport delay reason analysis method based on graph mining |
| CN112489498A (en) * | 2020-11-25 | 2021-03-12 | 中国电子科技集团公司第二十八研究所 | Fine route change planning method for route traffic |
| CN114464017A (en) * | 2022-01-27 | 2022-05-10 | 南京航空航天大学 | Queuing theory-based airport group flight delay estimation method |
| CN115311902A (en) * | 2022-03-25 | 2022-11-08 | 中国航空无线电电子研究所 | Real-time route planning and optimizing method based on multilayer time sequence network |
| CN115564188A (en) * | 2022-09-16 | 2023-01-03 | 中国民航大学 | Flight plan robustness evaluation system and method |
| CN115713872A (en) * | 2022-11-11 | 2023-02-24 | 中国航空无线电电子研究所 | SOA-based environment self-adaptive route planning method |
| CN116523138A (en) * | 2023-05-08 | 2023-08-01 | 南京航空航天大学 | Terminal airport flight time optimization method considering passenger transit trip selection |
| CN116246496A (en) * | 2023-05-10 | 2023-06-09 | 北京航空航天大学 | Flight plan planning method based on flight and flow collaborative environment |
| CN116659504A (en) * | 2023-05-31 | 2023-08-29 | 中国民用航空飞行学院 | Real-time flight data estimation method based on Kalman filtering method |
Non-Patent Citations (7)
| Title |
|---|
| Robustness Analysis for China’s Airport Network Based on Multi-Layer Temporal Complex Network Model;Jiuxia Guo 等;《International Conference on Transportation and Development 2023》;第14-24页 * |
| 中国航空网络时序特征分析;牟建红;黄格;吕欣;;电子科技大学学报(第03期);第144-150页 * |
| 基于冗余度的复杂网络抗毁性及节点重要度评估模型;王梓行;姜大立;漆磊;陈星;赵禹博;;复杂系统与复杂性科学(第03期);第81-88页 * |
| 基于大数据的作战体系协同时序网络分析;伍文峰;郭圣明;贺筱媛;胡晓峰;;指挥与控制学报(第02期);第150-159页 * |
| 基于网络模体特征攻击的网络抗毁性研究;贾承丰;韩华;完颜娟;吕亚楠;;复杂系统与复杂性科学(第04期);第46-53页 * |
| 航空公司机队的鲁棒性规划启发式算法;汪瑜;孙宏;;系统工程理论与实践(第04期);第963-970页 * |
| 航空公司机队集中调度理论研究;孙宏;张翔;徐杰;;中国管理科学(第01期);第86-89页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116882590A (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Ren et al. | Characterizing air traffic networks via large-scale aircraft tracking data: A comparison between China and the US networks | |
| CN109784636A (en) | Fraudulent user recognition methods, device, computer equipment and storage medium | |
| CN104102745B (en) | Complex network community method for digging based on Local Minimum side | |
| Yin et al. | Machine learning techniques for taxi-out time prediction with a macroscopic network topology | |
| CN108683448B (en) | Influence node identification method and system suitable for aviation network | |
| Bianco et al. | Locating sensors to observe network arc flows: exact and heuristic approaches | |
| Alvioli et al. | Rockfall susceptibility and network-ranked susceptibility along the Italian railway | |
| Akbari et al. | An online optimization approach to post-disaster road restoration | |
| EP2763083A1 (en) | Route modeler for improving desired environmental and economic flight characteristics | |
| CN116468186B (en) | Flight delay time prediction method, electronic equipment and storage medium | |
| Zhang et al. | Research on a model of node and path selection for traffic network congestion evacuation based on complex network theory | |
| CN102571431A (en) | Group concept-based improved Fast-Newman clustering method applied to complex network | |
| Du et al. | Traffic events oriented dynamic traffic assignment model for expressway network: a network flow approach | |
| Ai et al. | A deep learning approach to predict the spatial and temporal distribution of flight delay in network | |
| CN112270445A (en) | Flight delay wave and comprehensive evaluation method based on statistical analysis and classification prediction | |
| de Souza et al. | MOCHA: A tool for mobility characterization | |
| Ren et al. | A measure of identifying influential waypoints in air route networks | |
| CN114781704A (en) | Flight delay prediction method based on station-passing flight guarantee process | |
| CN110991913A (en) | Busy airport peak time congestion risk analysis method | |
| CN116882590B (en) | Flight plan optimization method, system and storage medium based on time sequence network model | |
| CN111008730B (en) | Crowd concentration prediction model construction method and device based on urban space structure | |
| KR102081377B1 (en) | Determination method and system of optimal performance threshold for short and middle span bridge network | |
| Chunyu et al. | Discrete bat algorithm and application in community detection | |
| Nasiboglu | Dijkstra solution algorithm considering fuzzy accessibility degree for patch optimization problem | |
| Szafranko | Evaluation of data obtained from expert opinions in multi-criteria analyses of construction investment variants |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |