CN109658741A - A kind of sector short term traffic forecasting method and system - Google Patents
A kind of sector short term traffic forecasting method and system Download PDFInfo
- Publication number
- CN109658741A CN109658741A CN201811515708.5A CN201811515708A CN109658741A CN 109658741 A CN109658741 A CN 109658741A CN 201811515708 A CN201811515708 A CN 201811515708A CN 109658741 A CN109658741 A CN 109658741A
- Authority
- CN
- China
- Prior art keywords
- sector
- traffic
- period
- predetermined
- flow
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G5/00—Traffic control systems for aircraft, e.g. air-traffic control [ATC]
- G08G5/0043—Traffic management of multiple aircrafts from the ground
Abstract
The invention discloses a kind of sector short term traffic forecasting method and system, belong to air traffic control field.The method include that the course line distribution obtained in the adjacent sectors distribution and predetermined sector of predetermined sector constructs sector traffic flow network according to traffic flow traffic direction between each sector；And then analysis predetermined sector is influenced caused changes in flow rate by adjacent sectors in each period, establishes sector flux prediction model；Construct BP neural network model, setting model parameter；In prediction, the historical traffic data acquired with the period is trained BP neural network model using historical traffic data according to sector flux prediction model；Real-time traffic data are obtained, which is input to BP neural network to obtain prediction result.The present invention can reduce influence of the uncertain factor to volume forecasting, to ensure the accuracy of sector volume forecasting in short-term.
Description
Technical field
The present invention relates to air traffic control field more particularly to a kind of sector short term traffic forecasting method and system.
Background technique
With the fast development of air-transport industry, the magnitude of traffic flow sharp increase in the regions such as airport, termination environment, sector, warp
Often a large amount of traffic congestion can occur in schedule flight peak period, and the delay of large area flight, Aircraft Air is brought to wait, is high
The problems such as control load of intensity.To ensure air traffic safety, orderly operation, need accurately to carry out sector flow short
When predict, this auxiliary controller grasps in advance future a period of time air traffic situation and traffic congestion may occur
Situation, formulates air traffic control decision in time for controller and provides reference frame etc. and be of great significance.
Currently, there are two types of more common air traffic flow prediction methods: the data observed according to history, using average
Model, moving average model(MA model) etc., or probability statistical analysis flow distribution feature is carried out, it is predicted, another is according to winged
Row planning data, aircraft performance data, high-altitude wind data etc. predict the flight track of single rack aircraft, thus extrapolate
Predict aircraft by the flow of sector.Both the above prediction technique is to the uncertainties such as meteorology, flow control in flight course
Factor, and temporary condition occur and consider not enough, it is not high to will lead to prediction result accuracy, it is difficult to ensure reliability.
Summary of the invention
The embodiment of the invention provides a kind of sector short term traffic forecasting method and system, can
In conjunction with the embodiment of the present invention in a first aspect, providing a kind of sector short term traffic forecasting method, comprising:
The course line distribution in the adjacent sectors distribution and predetermined sector of predetermined sector is obtained, according to predetermined sector and adjacent fan
Traffic flow traffic direction between area constructs sector traffic flow network；
According to the sector traffic flow network, the predetermined sector is analyzed caused by each period is influenced by adjacent sectors
Sector changes in flow rate establishes sector flux prediction model；
BP neural network model is constructed, number of nodes, the sample training number of each layer of BP neural network model are set
And error threshold；
When needing to predict the period to be predicted of the predetermined sector, the predetermined sector is acquired when to be predicted
The historical traffic data of section, according to the sector flux prediction model, using the historical traffic data to the BP nerve net
Network model is trained；
Real-time traffic data of the predetermined sector before the period to be predicted are obtained, the real-time traffic data are input to
The volume forecasting result of predetermined period is obtained in BP neural network model after training.
In conjunction with the second aspect of the embodiment of the present invention, a kind of sector short term traffic forecasting system is provided, comprising:
Sector traffic flow network struction module, the boat in adjacent sectors distribution and predetermined sector for obtaining predetermined sector
Line distribution constructs sector traffic flow network according to traffic flow traffic direction between predetermined sector and adjacent sectors；
Sector flux prediction model constructs module, for analyzing the predetermined sector according to the sector traffic flow network
Sector changes in flow rate caused by being influenced in each period by adjacent sectors, establishes sector flux prediction model；
Setting module: for constructing BP neural network model, set each layer of BP neural network model number of nodes,
Sample training number and error threshold；
Training module, it is described predetermined for acquiring when needing to predict the period to be predicted of the predetermined sector
Historical traffic data of the sector in the period to be predicted utilizes the historical traffic data according to the sector flux prediction model
The BP neural network model is trained；
Prediction module will be described real-time for obtaining real-time traffic data of the predetermined sector before the period to be predicted
Data on flows is input to the volume forecasting result that predetermined period is obtained in the BP neural network model after training.
As can be seen from the above technical solutions, the embodiment of the present invention has the advantage that
In the embodiment of the present invention, by constructing sector transportation network, and then sector discharge model is constructed, establish BP nerve net
The historical traffic that the period to be predicted is acquired after network, further according to sector discharge model, using historical traffic data to BP neural network
It is trained, inputs current sector flow, the data on flows of period to be predicted can be obtained.So that the volume forecasting of sector can
It to fully consider current real-time data on flows, and combines history with the data on flows of period, realizes and considering current outside
While uncertain factor influences, accurately sector flow in short-term is carried out using the flux prediction model and neural network of building
Prediction, safe and reliable reference information is provided for controller.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is traffic flow schematic network structure in sector provided in an embodiment of the present invention；
Fig. 2 is the method for predicting of sector in short-term one embodiment flow chart provided in an embodiment of the present invention；
Fig. 3 is the flow of sector in short-term forecasting system one embodiment structure chart provided in an embodiment of the present invention；
Specific embodiment
The embodiment of the invention provides a kind of sector short term traffic forecasting method and system, quasi- for carrying out to sector flow
True short-term prediction.
In order to make the invention's purpose, features and advantages of the invention more obvious and easy to understand, below in conjunction with the present invention
Attached drawing in embodiment, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that disclosed below
Embodiment be only a part of the embodiment of the present invention, and not all embodiment.Based on the embodiments of the present invention, this field
Those of ordinary skill's all other embodiment obtained without making creative work, belongs to protection of the present invention
Range.
It is sector traffic flow network composition referring to Fig. 1, Fig. 1, wherein region S1, S2, S3, S4, S5, S6 indicate sector.With
For S1 is as scheduled sector to be predicted, I1, I2, I3, I4, I5 indicate entry into the traffic flow of the sector S1, O1, O2, O3, O4 table
Show the traffic flow for exiting the sector S1, shown in table specific as follows:
| Traffic flow | Trend |
| I1 | S5->S1 |
| I2 | S6->S1 |
| I3 | S6->S1 |
| I4 | S2->S1 |
| I5 | S3->S1 |
| I6 | S4->S1 |
| O1 | S1->S5 |
| O2 | S1->S2 |
| O3 | S1->S3 |
| O4 | S1->S4 |
It is moved towards according to traffic flow shown in the table, definition:
(1) traffic flow of prediction sector upstream traffic flow: is entered by a sector.
(2) downstream traffic flow: by predicting that sector is withdrawn into the traffic flow of next sector.
Since flow of the sector S1 in the flow of t moment and the sector certain period of time has positive connection, predicting
When the flow of sector, upstream and downstream traffic flow flow distribution situation just must take into account.The path of traffic flow in sector will be predicted as a result,
Simplified, no longer the flight track in concern prediction sector, but according to the data on flows of several periods before prediction sector
And upstream and downstream traffic flow data models the magnitude of traffic flow of sector.
Referring to Fig. 2, a flow diagram of sector short term traffic forecasting method includes: in the embodiment of the present invention
S201, obtain predetermined sector adjacent sectors distribution and predetermined sector in course line distribution, according to predetermined sector with
Traffic flow traffic direction between adjacent sectors constructs sector traffic flow network；
Optionally, according to way point, joint, course line and the spatial information (si) in chart, the course line letter of predetermined sector is analyzed
Breath and adjacent sectors distribution, in conjunction with flight plan data, the history radar flying quality between each sector, analyze the traffic of each sector
Direction is flowed, and determines the inflow of each sector and exits data, establishes sector traffic flow network.
As shown in Figure 1, simplifying the sector and course line of aircraft navigation, pass through the magnitude of traffic flow analyzing the entrance of sector and exiting
And flow direction, sector traffic flow network is established, can be convenient the foundation of subsequent model of traffic flux forecast.
S202, according to the sector traffic flow network, analyzing the predetermined sector is influenced in each period by adjacent sectors
Caused sector changes in flow rate, establishes sector flux prediction model；
In conjunction with sector traffic flow network, the flow that can analyze particular sector at the following a certain moment is influenced by adjacent sectors
And the sector changes in flow rate trend.
Optionally, according to predetermined sector current slot flow, current slot previous period flow, it is current when
Between the influx of section and the discharge of current slot, construct the flux prediction model of predetermined sector.
Due to sector subsequent time t+1 flow by the sector current time t and previous moment t-1 flow effect,
Flow of the upstream and downstream traffic flow simultaneously in current time t also has important influence to subsequent time t+1 prediction sector flow.Cause
This, according to sector traffic flow network, before known t moment, t-1 moment predict sector flow and upstream and downstream traffic flow flow
It puts, establishes such as drag:
Wherein, i ∈ N, j ∈ N.By taking Fig. 1 as an example, then i is equal to 6, j and is equal to 4.
In the model formation,Indicate future t+1 moment sector S1Flow；When indicating current
Carve the sector t S1Flow；Indicate t-1 moment sector S1Flow；Expression is worked as
Preceding moment t flows into sector S1I traffic flow flow；Indicate that current time t flows out sector
S1J traffic flow flow.According to above formula it is found that the t+1 moment predicts sector S1Flow and current time t sector S1Stream
Amount, t moment pass in and out the flow and the moment sector t-1 S of sector traffic flow1Flow existence function relationship.
In embodiments of the present invention, the moment t can be the period of preset duration, such as 5 minutes.
S203, building BP neural network model, set number of nodes, the sample training of each layer of BP neural network model
Number and error threshold；
Optionally, the historical traffic data for acquiring predetermined sector, using the historical traffic data by the period as sample number
According to being normalized, BP neural network model is constructed, the number of nodes of input layer, hidden layer and output layer is set separately.
Specifically, that is to say that place is normalized according to the following formula (1) in sample data to the historical traffic data of acquisition
Reason, makes the range of sample data between [0,1].
Wherein, xiIndicate the initial data of sample i, xminIndicate the minimum value in sample, xmaxIndicate the maximum in sample
Value,Data after indicating sample i normalized.
Construct 3 layers of BP neural network, respectively input layer, hidden layer and output layer.Further, according to the stream of sectors
Prediction model is measured, can be incited somebody to action Total i+j+2 data are as input layer, by the sector flow at the t+1 moment of predictionAs output layer.
Preferably, implying number of nodes is 2N+1, wherein N is implicit number of nodes.The setting of number of nodes is implied herein
The precision of volume forecasting can be improved, reduce prediction error.
Further, sample training number and error threshold are determined, and sector flow is realized by method of negative gradient descent method
Study and prediction, wherein receptance function are as follows:
S204, when need the period to be predicted of the predetermined sector is predicted when, acquire the predetermined sector to
The historical traffic data of prediction period, according to the sector flux prediction model, using the historical traffic data to the BP
Neural network model is trained；
It, can be larger if carrying out neural metwork training in advance since sector flow is influenced more obviously by temporary conditions such as weather
Degree influences the accuracy of prediction, so in embodiments of the present invention, be trained, can be promoted with period data according to history
The accuracy of prediction.
The historical traffic data for choosing the period identical as the period to be predicted, as the period to be predicted is on October on the same day 11
10:00-11:00, with the sector data on flows to be predicted of period, i.e. 1-10 in the October days sectors 10:00-11:00 before choosing 10 days
The data on flows of S1.
Further, time t is set as 5 minutes, then period 10:00-11:00 can be divided into 10:00,10:05,10:
10 ..., 10:50,11:00, totally 12 groups, a total of 120 groups of that 10 days historical traffic data, using this 120 groups of data as sample
This, is trained BP neural network model using the sample data.
Preferably, it is fitted the sector flow changing curve of the period to be predicted.Predicted value is fitted to curve, Jin Ercha
It sees the degree of agreement of actual value and predicted value, prediction effect can be evaluated and tested, avoid the occurrence of large error.
S205, real-time traffic data of the predetermined sector before the period to be predicted are obtained, by the real-time traffic data
The volume forecasting result of predetermined period is obtained in BP neural network model after being input to training.
Real-time traffic data before the period to be predicted refer to the newest data on flows before the period to be predicted,
By taking sector S1 to be predicted as an example, the period to be predicted is 10:00-11:00, then acquires same day 8:50-8:55, the friendship of 8:55-9:00
Through-current capacity data.Specifically, acquire real-time radar data, flight plan data, according to sector flux prediction model, obtain t,
Traffic flow flow when sector flow and t when t-1 is input in BP neural network as input data.
It in embodiments of the present invention, can be according to current stream of sectors of the sector data on flows to following a period of time in real time
It measures and is predicted, it, can by being trained with period data to neural network thus according to current real time data, and in conjunction with history
To reduce influence of the burst weather conditions to volume forecasting, the accuracy of volume forecasting is ensured.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
A kind of sector short term traffic forecasting method is essentially described above, it below will be to a kind of sector short term traffic forecasting system
System is described in detail.
Fig. 3 shows short term traffic forecasting system embodiment structure chart in sector in the embodiment of the present invention.
Sector traffic flow network struction module 310, for obtain predetermined sector adjacent sectors be distributed and predetermined sector in
Course line distribution traffic flow network in sector is constructed according to traffic flow traffic direction between predetermined sector and adjacent sectors；
Optionally, the sector traffic flow network struction module 310 includes:
First analytical unit, for analyzing each sector according to way point, joint, course line and the spatial information (si) in chart
Route information and sector distribution；
Second analytical unit, for analyzing each fan according to flight plan data, the history radar flying quality between each sector
The traffic flow direction in area, and determine the inflow of each sector and exit data；
Construction unit, for establishing sector traffic flow network.
Sector flux prediction model constructs module 320, for analyzing the predetermined fan according to the sector traffic flow network
Sector changes in flow rate caused by area is influenced in each period by adjacent sectors, establishes sector flux prediction model；
Optionally, the sector flux prediction model building module 320 includes:
Construction unit, for according to the previous period flow of predetermined sector current slot flow, current slot,
The influx of current slot and the discharge of current slot, construct the flux prediction model of predetermined sector.
Setting module 330 sets the number of nodes of each layer of BP neural network model for constructing BP neural network model
Amount, sample training number and error threshold；
Optionally, the setting module 330 includes:
Acquisition unit, for acquiring the historical traffic data of predetermined sector, using the historical traffic data by the period as
Sample data is normalized；
The number of nodes of input layer, hidden layer and output layer is set separately for constructing BP neural network model in construction unit
Amount.
Training module 340, for acquiring described pre- when needing to predict the period to be predicted of the predetermined sector
Determine sector and the historical traffic number is utilized according to the sector flux prediction model in the historical traffic data of period to be predicted
It is trained according to the BP neural network model；
It is optionally, described that the BP neural network model is trained using the historical traffic data further include:
It is fitted the sector flow changing curve of the period to be predicted.
Prediction module 350, for obtaining real-time traffic data of the predetermined sector before the period to be predicted, by the reality
When data on flows be input in the BP neural network model after training to obtain the volume forecasting result of predetermined period.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In the above-described embodiments, it all emphasizes particularly on different fields to the description of each embodiment, is not described in detail or remembers in some embodiment
The part of load may refer to the associated description of other embodiments.
Those of ordinary skill in the art may be aware that each embodiment described in conjunction with the examples disclosed in this document
Module, unit and/or method and step can be realized with the combination of electronic hardware or computer software and electronic hardware.This
A little functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Specially
Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not
It is considered as beyond the scope of this invention.
In several embodiments provided herein, it should be understood that disclosed system, device and method can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of logical function partition, there may be another division manner in actual implementation, such as multiple units or components
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be through some interfaces, the indirect coupling of device or unit
It closes or communicates to connect, can be electrical property, mechanical or other forms.
The unit as illustrated by the separation member may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, it can and it is in one place, or may be distributed over multiple
In network unit.It can select some or all of unit therein according to the actual needs to realize the mesh of this embodiment scheme
's.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
The above, the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although referring to before
Stating embodiment, invention is explained in detail, those skilled in the art should understand that: it still can be to preceding
Technical solution documented by each embodiment is stated to modify or equivalent replacement of some of the technical features；And these
It modifies or replaces, the spirit and scope for technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution.
Claims (10)
1. a kind of sector short term traffic forecasting method characterized by comprising
Obtain the course line distribution in the adjacent sectors distribution and predetermined sector of predetermined sector, according to predetermined sector and adjacent sectors it
Between traffic flow traffic direction, construct sector traffic flow network；
According to the sector traffic flow network, analyzing the predetermined sector in each period is influenced caused sector by adjacent sectors
Changes in flow rate establishes sector flux prediction model；
BP neural network model is constructed, number of nodes, sample training number and the mistake of each layer of BP neural network model are set
Poor threshold value；
When needing to predict the period to be predicted of the predetermined sector, the predetermined sector is acquired in the period to be predicted
Historical traffic data, according to the sector flux prediction model, using the historical traffic data to the BP neural network mould
Type is trained；
Real-time traffic data of the predetermined sector before the period to be predicted are obtained, the real-time traffic data are input to training
BP neural network model afterwards is to obtain the volume forecasting result of predetermined period.
2. the method according to claim 1, wherein the adjacent sectors for obtaining predetermined sector are distributed and make a reservation for
Course line distribution in sector constructs sector traffic flow network according to traffic flow traffic direction between predetermined sector and adjacent sectors
Specifically:
According to way point, joint, course line and the spatial information (si) in chart, route information and the adjacent sectors of predetermined sector are analyzed
Distribution；
According to flight plan data, the history radar flying quality between each sector, the traffic flow direction of each sector is analyzed, and is determined
The data on flows that predetermined sector flows into and exits；
Establish sector traffic flow network.
3. the method according to claim 1, wherein described according to the sector traffic flow network, described in analysis
Sector changes in flow rate caused by predetermined sector is influenced in each period by adjacent sectors, it is specific to establish sector flux prediction model
Are as follows:
According to the inflow of predetermined sector current slot flow, previous the period flow, current slot of current slot
The discharge of amount and current slot, constructs the flux prediction model of predetermined sector.
4. the method according to claim 1, wherein the building BP neural network model, sets the BP mind
Number of nodes, sample training number and error threshold through each layer of network model specifically:
The historical traffic data for acquiring predetermined sector, the historical traffic data is normalized by the period as sample data
Processing；
BP neural network model is constructed, the number of nodes of input layer, hidden layer and output layer is set separately.
5. the method according to claim 1, wherein it is described using the historical traffic data to the BP after training
Neural network model is trained further include:
It is fitted the sector flow changing curve of the period to be predicted.
6. a kind of sector short term traffic forecasting system characterized by comprising
Sector traffic flow network struction module, the course line point in adjacent sectors distribution and predetermined sector for obtaining predetermined sector
Cloth constructs sector traffic flow network according to traffic flow traffic direction between predetermined sector and adjacent sectors；
Sector flux prediction model constructs module, for analyzing the predetermined sector each according to the sector traffic flow network
Sector changes in flow rate, establishes sector flux prediction model caused by period is influenced by adjacent sectors；
Setting module: for constructing BP neural network model, number of nodes, the sample of each layer of BP neural network model are set
Frequency of training and error threshold；
Training module, for acquiring the predetermined sector when needing to predict the period to be predicted of the predetermined sector
In the historical traffic data of period to be predicted, according to the sector flux prediction model, using the historical traffic data to institute
BP neural network model is stated to be trained；
Prediction module, for obtaining real-time traffic data of the predetermined sector before the period to be predicted, by the real-time traffic
Data are input to the BP neural network model after training to obtain the volume forecasting result of predetermined period.
7. system according to claim 6, which is characterized in that the sector traffic flow network struction module includes:
First analytical unit, for analyzing the boat of each sector according to way point, joint, course line and the spatial information (si) in chart
Line information and sector distribution；
Second analytical unit, for analyzing each sector according to flight plan data, the history radar flying quality between each sector
Traffic flow direction, and determine the data on flows that predetermined sector flows into and exits；
Construction unit, for establishing sector traffic flow network.
8. system according to claim 6, which is characterized in that the sector flux prediction model constructs module and includes:
Construction unit, for according to the previous period flow of predetermined sector current slot flow, current slot, current
The influx of period and the discharge of current slot, construct the flux prediction model of predetermined sector.
9. system according to claim 6, which is characterized in that the setting module includes:
Acquisition unit, for acquiring the historical traffic data of predetermined sector, using the historical traffic data by the period as sample
Data are normalized；
The number of nodes of input layer, hidden layer and output layer is set separately for constructing BP neural network model in construction unit.
10. system according to claim 6, which is characterized in that described refreshing to the BP using the historical traffic data
It is trained through network model further include:
It is fitted the sector flow changing curve of the period to be predicted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811515708.5A CN109658741A (en) | 2018-12-12 | 2018-12-12 | A kind of sector short term traffic forecasting method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811515708.5A CN109658741A (en) | 2018-12-12 | 2018-12-12 | A kind of sector short term traffic forecasting method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109658741A true CN109658741A (en) | 2019-04-19 |
Family
ID=66112922
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811515708.5A Pending CN109658741A (en) | 2018-12-12 | 2018-12-12 | A kind of sector short term traffic forecasting method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109658741A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110633875A (en) * | 2019-11-20 | 2019-12-31 | 南京萨利智能科技有限公司 | Method and device for predicting airway flow and computer storage medium |
| CN111523641A (en) * | 2020-04-10 | 2020-08-11 | 南京航空航天大学 | ConvLSTM-SRU-based sector delay prediction method |
| CN112417762A (en) * | 2020-11-25 | 2021-02-26 | 中国民航大学 | Sector flow short-term prediction method based on decomposition integration methodology |
| CN113055923A (en) * | 2019-12-27 | 2021-06-29 | 中国移动通信集团湖南有限公司 | Mobile network traffic prediction method, device and equipment |
| CN113660176A (en) * | 2021-08-16 | 2021-11-16 | 中国电信股份有限公司 | Traffic prediction method and device for communication network, electronic device and storage medium |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101201978A (en) * | 2007-12-20 | 2008-06-18 | 四川川大智胜软件股份有限公司 | Method for predicting short-run air traffic flux based on real time radar and flight information |
| CN101533566A (en) * | 2009-02-23 | 2009-09-16 | 民航数据通信有限责任公司 | Method for predicting air traffic flow and device thereof |
| CN101950493A (en) * | 2010-09-10 | 2011-01-19 | 四川大学 | Flow scheduling method of regional air traffic network |
| CN102074126A (en) * | 2011-01-19 | 2011-05-25 | 清华大学 | Historical radar data based air traffic flow analysis system and method |
| CN102568249A (en) * | 2011-12-20 | 2012-07-11 | 中国船舶重工集团公司第七0九研究所 | Flight flow alarm method based on dynamic airspace capacity and system thereof |
| US8594917B2 (en) * | 2011-01-25 | 2013-11-26 | Nextgen Aerosciences, Llc | Method and apparatus for dynamic aircraft trajectory management |
| CN103530704A (en) * | 2013-10-16 | 2014-01-22 | 南京航空航天大学 | Predicating system and method for air dynamic traffic volume in terminal airspace |
| CN105160201A (en) * | 2015-09-30 | 2015-12-16 | 成都民航空管科技发展有限公司 | Genetic algorithm back propagation (GABP) neural network based controller workload prediction method and system |
| CN105788249A (en) * | 2014-12-16 | 2016-07-20 | 高德软件有限公司 | Traffic flow prediction method, prediction model generation method and device |
-
2018
- 2018-12-12 CN CN201811515708.5A patent/CN109658741A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101201978A (en) * | 2007-12-20 | 2008-06-18 | 四川川大智胜软件股份有限公司 | Method for predicting short-run air traffic flux based on real time radar and flight information |
| CN101533566A (en) * | 2009-02-23 | 2009-09-16 | 民航数据通信有限责任公司 | Method for predicting air traffic flow and device thereof |
| CN101950493A (en) * | 2010-09-10 | 2011-01-19 | 四川大学 | Flow scheduling method of regional air traffic network |
| CN102074126A (en) * | 2011-01-19 | 2011-05-25 | 清华大学 | Historical radar data based air traffic flow analysis system and method |
| US8594917B2 (en) * | 2011-01-25 | 2013-11-26 | Nextgen Aerosciences, Llc | Method and apparatus for dynamic aircraft trajectory management |
| CN102568249A (en) * | 2011-12-20 | 2012-07-11 | 中国船舶重工集团公司第七0九研究所 | Flight flow alarm method based on dynamic airspace capacity and system thereof |
| CN103530704A (en) * | 2013-10-16 | 2014-01-22 | 南京航空航天大学 | Predicating system and method for air dynamic traffic volume in terminal airspace |
| CN105788249A (en) * | 2014-12-16 | 2016-07-20 | 高德软件有限公司 | Traffic flow prediction method, prediction model generation method and device |
| CN105160201A (en) * | 2015-09-30 | 2015-12-16 | 成都民航空管科技发展有限公司 | Genetic algorithm back propagation (GABP) neural network based controller workload prediction method and system |
Non-Patent Citations (5)
| Title |
|---|
| 周志靖等: ""空中交通航空飞行流量优化预测仿真"", 《计算机仿真》 * |
| 崔德光等: ""空中交通流量预测的人工神经网络和回归组合方法"", 《清华大学学报（自然科学版）》 * |
| 陈丹等: ""基于贝叶斯估计的短时空域扇区交通流量预测"", 《西南交通大学学报》 * |
| 陈雪平等: ""基于BP神经网络的短时交通流预测"", 《公路交通技术》 * |
| 陶冶等: ""基于神经网络的空中交通管制决策支持系统"", 《交通与计算机》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110633875A (en) * | 2019-11-20 | 2019-12-31 | 南京萨利智能科技有限公司 | Method and device for predicting airway flow and computer storage medium |
| CN113055923A (en) * | 2019-12-27 | 2021-06-29 | 中国移动通信集团湖南有限公司 | Mobile network traffic prediction method, device and equipment |
| CN113055923B (en) * | 2019-12-27 | 2022-06-17 | 中国移动通信集团湖南有限公司 | Mobile network traffic prediction method, device and equipment |
| CN111523641A (en) * | 2020-04-10 | 2020-08-11 | 南京航空航天大学 | ConvLSTM-SRU-based sector delay prediction method |
| CN112417762A (en) * | 2020-11-25 | 2021-02-26 | 中国民航大学 | Sector flow short-term prediction method based on decomposition integration methodology |
| CN112417762B (en) * | 2020-11-25 | 2022-04-29 | 中国民航大学 | Sector flow short-term prediction method based on decomposition integration methodology |
| CN113660176A (en) * | 2021-08-16 | 2021-11-16 | 中国电信股份有限公司 | Traffic prediction method and device for communication network, electronic device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109658741A (en) | A kind of sector short term traffic forecasting method and system | |
| CN104156594B (en) | Dynamic flight station-crossing time estimation method based on Bayes network | |
| CN104751681B (en) | Statistical learning model based gate position allocation method | |
| Hu et al. | Receding horizon control for aircraft arrival sequencing and scheduling | |
| CN100483477C (en) | Method for predicting short-run air traffic flux based on real time radar and flight information | |
| US8577587B2 (en) | Methods and systems for determining required interval management performance (RIMP) | |
| Baspinar et al. | Analysis of delay characteristics of European air traffic through a data-driven airport-centric queuing network model | |
| Choi et al. | Artificial neural network models for airport capacity prediction | |
| CN111091225B (en) | Urban rail transit short-term passenger flow prediction method based on deep learning | |
| CN112508305A (en) | Public place entrance pedestrian flow prediction method based on LSTM | |
| Ma et al. | Integrated optimization of terminal manoeuvring area and airport | |
| CN114464017B (en) | Queuing theory-based airport group flight delay estimation method | |
| CN110009939B (en) | Flight delay prediction and sweep analysis method based on ASM | |
| Çeçen et al. | Optimising aircraft arrivals in terminal airspace by mixed integer linear programming model | |
| CN110991913A (en) | Busy airport peak time congestion risk analysis method | |
| Dönmez et al. | Air traffic management in parallel-point merge systems under wind uncertainties | |
| Yang et al. | Stochastic scheduling of ground movement problem integrated with taxiway routing and gate/stand allocation | |
| CN104882029B (en) | Real-time supervision alarm method based on the estimation of 4D track | |
| CN106157699A (en) | High density Flying Area in Airport aircraft slide Situation Awareness method | |
| CN111611332B (en) | Optimization method and system for route transfer | |
| CN112201082B (en) | N-point replacement method for flight release time slot | |
| Wang et al. | A network flow approach for optimizing the passenger throughput at an airport security checkpoint | |
| SAHADEVAN et al. | Predictability improvement of scheduled flights departure time variation using supervised machine learning | |
| Mori | Off-block time prediction using operators’ prediction history | |
| Idris et al. | Estimating airspace capacity based on risk mitigation metrics |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190419 |