CN109872033A - A kind of Airport Gate Position Scheduling method - Google Patents
A kind of Airport Gate Position Scheduling method Download PDFInfo
- Publication number
- CN109872033A CN109872033A CN201811639136.1A CN201811639136A CN109872033A CN 109872033 A CN109872033 A CN 109872033A CN 201811639136 A CN201811639136 A CN 201811639136A CN 109872033 A CN109872033 A CN 109872033A
- Authority
- CN
- China
- Prior art keywords
- flight
- plane
- seat
- chromosome
- airport
- 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.)
- Granted
Links
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of Airport Gate Position Scheduling methods, comprising: according to Flight Information in predistribution flight-table, establishes seat in the plane of approaching in each flight initial Q table corresponding with departure from port all combinations of seat in the plane；Approach seat in the plane and the combination of departure from port seat in the plane are filtered out in each flight using ε greedy search method, as the genome for characterizing each flight；After each flight is arranged in order, corresponding gene group constitutes chromosome, and calculates its fitness；Q table is updated according to each flight return value；By successive ignition chromosome and Q table is updated, obtains Gate Position Scheduling scheme.The present invention does not depend on the generation of initial population, and calculates fast convergence rate, while the utilization rate of airport seat in the plane can be greatly improved in the airport allocation plan obtained through the invention.
Description
Technical field
The invention belongs to dispatching distribution fields, more particularly, to a kind of Airport Gate Position Scheduling method.
Background technique
Gate Position Scheduling problem is NP (Non-deterministic Polynomial) complete problem, domestic many airports
Still the method for using manual allocation, however, Gate Position Scheduling scheme is exponentially increased with the continuous expansion of airport scale, this
Huge workload is brought to staff, realizes that the intelligence of Gate Position Scheduling is extremely urgent with facilitation.Gate Position Scheduling is asked
The solution of topic can make full use of Airport Resources, improve Airport Operation benefit and service quality, various modern numericals usually can be used
Derivation algorithm such as traditional genetic algorithm, simulated annealing etc..
Traditional genetic algorithm solves Gate Position Scheduling scheme, is a kind of feasible scheme.But traditional genetic algorithm solves knot
Fruit is very unstable, weakens seat in the plane, type constraint, needs self-correcting when intersecting, making a variation, convergence rate is slow, initial population is raw
The problems such as at difficulty.
Summary of the invention
In view of the drawbacks of the prior art, the purpose of the present invention is to provide a kind of Airport Gate Position Scheduling methods, it is intended to solve
Conventional genetic is single because seat in the plane type constrains, while causing seat in the plane utilization rate is low to ask the relying on larger of initialization population
Topic.
To achieve the above object, the present invention provides a kind of Airport Gate Position Scheduling methods, comprising:
(1) it according to Flight Information in predistribution flight-table, establishes each flight and respectively acts corresponding initial Q table；It specifically includes
Following steps:
(1.1) flight and airport seat in the plane information are obtained；
When whether whether the information include: flight number, type, be public affair, be VIP, be international airline, approach
It carves, depart from port moment, airdrome control business rule information and each seat in the plane correspond to type constraint information；
(1.2) according to above- mentioned information, the combination of approach in each flight seat in the plane and seat in the plane of departing from port is determined；
Specifically, each flight is using seat in the plane and the expression of departure from port seat in the plane of approaching, and will approach seat in the plane and departure from port seat in the plane are as flight
Corresponding two genes are located at the two neighboring gene of parity bit that is, in chromosome and represent a flight；
Preferably, for each flight, all possible assortment of genes is known as the corresponding motion space of the flight；
(1.3) to seat in the plane and the combination progress Q table initialization of departure from port seat in the plane of approaching in each flight；
Preferably, Q table initialization procedure are as follows:
Seat in the plane and the combination of departure from port seat in the plane of approaching in each flight are met according to airport business hard constraint, soft-constraint rule
Constraint condition assigns positive number, is unsatisfactory for constraint condition and assigns negative；
(2) to approach in each flight seat in the plane and the combination of departure from port seat in the plane using ε greedy search algorithms selection；
Preferably, ε greedy search algorithm are as follows: random given threshold α screens maximum Q in the movement of each flight as ε < α
It is worth corresponding approach seat in the plane and the combination of departure from port seat in the plane, otherwise, any seat in the plane and the departure from port machine of approaching of equal random screening in each flight
Bit combination；
(3) it is approached seat in the plane and departure from port seat in the plane combination building chromosome according to each flight of selection, and calculates the suitable of chromosome
Response；
Preferably, according to above-mentioned ε greedy search algorithm screening obtain each flight approach seat in the plane and departure from port seat in the plane combination, benefit
With movement-gene shine table building twice of size of flight number chromosome, more specifically, chromosome is screened by N number of flight
Approach seat in the plane and departure from port seat in the plane group be combined into；
Preferably, for chromosome, because the chromosome congression of the different buildings of gene in N number of genome is known as state sky
Between；
Using the objective optimization function for including in chromosome as fitness function, that is, leaves the port by bridge number, free time, drags
Drag number；But in view of the difference of multiple target units and influence amplitude, the present invention uses method for normalizing and Exchanger Efficiency with Weight Coefficient Method
Solve the problems, such as multiple-objection optimization, the calculation formula of specific fitness value are as follows: F=α Br+βFt+γRn
Wherein:
Wherein, FtRepresent free time, BrIt represents and depends on bridge number, RnIt represents and pulls number, F represents fitness value, α, beta, gamma
It is constant；
(4) it examines whether chromosome meets constraint condition, the chromosome fitness value of constraint condition will be met as each boat
The return value of class；
Specifically, the chromosome of above-mentioned acquisition checks whether eligible constraint by constraint test function (Check)；If
It is eligible, then return value R=F, otherwise return value R=-0.01；
(5) Q table is updated according to each flight return value；
Preferably, Q table is updated using SARSA algorithm:
Qi(st)=(1- α) Qi(st)+α(R+λ(Qi(st+1)))
Wherein: α is learning rate, and λ is discount factor, Qi(St) represent i-th of flight approach in t iteration seat in the plane and from
Combine corresponding Q value, Q in port seat in the planei(St+1) represent i-th of flight approach in (t+1) secondary iteration seat in the plane and departure from port seat in the plane combination
Corresponding Q value；
(6) according to the number of iterations is preset, step (2)~(5) are repeated, the chromosome of constraint condition will be met as seat in the plane point
With scheme.
Contemplated above technical scheme through the invention, compared with prior art, can obtain it is following the utility model has the advantages that
(1) present invention not only allows for the constraint of different types of machines, while each flight is all made of two gene representations, enhances
The readability of chromosome；Further chromosome is checked whether to meet constraint condition using constraint test function, avoids dyeing
The redundancy of body.
(2) present invention does not need the generation of initial population, screens Q by ε greedy search algorithmijIt is worth corresponding seat in the plane of approaching
With the combination of departure from port seat in the plane, chromosome is further constructed, avoids dependence of the traditional genetic algorithm to initial population, while not taking
Traditional chromosomal variation and intersection, accelerates convergence rate.
Detailed description of the invention
Fig. 1 is the flow chart of Gate Position Scheduling method provided by the invention:
Fig. 2 is the flow chart of intensified learning provided in an embodiment of the present invention.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, with reference to the accompanying drawings and embodiments, right
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
Fig. 1 is the flow chart of Gate Position Scheduling method, the corresponding stream for specifically showing algorithm process in Gate Position Scheduling method of Fig. 2
Cheng Tu, as depicted in figs. 1 and 2, a kind of Airport Gate Position Scheduling method provided by the invention, comprising:
(1) all combinations according to Flight Information in predistribution flight-table, to approach in each flight seat in the plane and seat in the plane of departing from port
Carry out the initialization of Q table；Specific steps are as follows:
(1.1) flight and airport seat in the plane information are obtained；
When whether whether the information include: flight number, type, be public affair, be VIP, be international airline, approach
It carves, depart from port moment, airdrome control business rule information and each seat in the plane correspond to type constraint information；
(1.2) according to above- mentioned information, the combination of approach in each flight seat in the plane and seat in the plane of departing from port is determined；
Specifically, each flight is using seat in the plane and the expression of departure from port seat in the plane of approaching, and will approach seat in the plane and departure from port seat in the plane are as flight
Corresponding two genes are located at the two neighboring gene of parity bit that is, in chromosome and represent a flight；
Preferably, for each flight, all possible assortment of genes is known as the corresponding motion space of the flight；
(1.3) to seat in the plane and the combination progress Q table initialization of departure from port seat in the plane of approaching in each flight；
Preferably, Q table initialization procedure are as follows:
According to airport business hard constraint, soft-constraint rule, all seat in the plane and the departure from port seats in the plane of approaching for including for each flight
Combination meets constraint condition and assigns positive number, is unsatisfactory for constraint condition and assigns negative；
(2) to approach in each flight seat in the plane and the combination of departure from port seat in the plane using ε greedy search algorithms selection；
Preferably, ε greedy search algorithm are as follows: random given threshold α screens maximum Q in the movement of each flight as ε < α
It is worth corresponding approach seat in the plane and the combination of departure from port seat in the plane, otherwise, any seat in the plane and the departure from port machine of approaching of equal random screening in each flight
Bit combination；
(3) it is approached seat in the plane and departure from port seat in the plane combination building chromosome according to each flight of selection, and calculates the suitable of chromosome
Response；
Preferably, according to above-mentioned ε greedy search algorithm screening obtain each flight approach seat in the plane and departure from port seat in the plane combination, benefit
With movement-gene shine table building two times of sizes of flight number chromosome, more specifically, chromosome is screened by N number of flight
Approach seat in the plane and departure from port seat in the plane group be combined into；
Preferably, for chromosome, because the chromosome congression of the different buildings of gene in N number of genome is known as state sky
Between；
Using the objective optimization function for including in chromosome as fitness function, that is, leaves the port by bridge number, free time, drags
Drag number；But in view of the difference of multiple target units and influence amplitude, the present invention uses method for normalizing and Exchanger Efficiency with Weight Coefficient Method
Solve the problems, such as multiple-objection optimization, the calculation formula of specific fitness value are as follows: F=α Br+βFt+γRn
Wherein:
Wherein, FtRepresent free time, BrIt represents and depends on bridge number, RnIt represents and pulls number, F represents fitness value, α, beta, gamma
It is constant；
(4) it examines whether chromosome meets constraint condition, the chromosome fitness value of constraint condition will be met as each boat
The return value of class；
The chromosome of above-mentioned acquisition checks whether eligible constraint by constraint test function (Check)；If meeting item
Part, then return value R=F, otherwise return value R=-0.01；
(5) Q table is updated according to each flight return value；
Preferably, Q table is updated using SARSA algorithm:
Qi(st)=(1- α) Qi(st)+α(R+λ(Qi(st+1)))
Wherein: α is learning rate, and λ is discount factor, Qi(St) represent i-th of flight approach in t iteration seat in the plane and from
Combine corresponding Q value, Q in port seat in the planei(St+1) represent i-th of flight approach in (t+1) secondary iteration seat in the plane and departure from port seat in the plane combination
Corresponding Q value；
(6) step (2)~(5) are repeated, works as the number of iterations > default the number of iterations termination algorithm, constraint condition will be met
Chromosome is as Gate Position Scheduling scheme.
As it will be easily appreciated by one skilled in the art that the foregoing is merely illustrative of the preferred embodiments of the present invention, not to
The limitation present invention, any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should all include
Within protection scope of the present invention.
Claims (6)
1. a kind of Airport Gate Position Scheduling method characterized by comprising
(1) according to Flight Information in predistribution flight-table, Q is carried out to all combinations of approach in each flight seat in the plane and seat in the plane of departing from port
Table initialization；
(2) according to the comparison of the threshold value of setting and the Q value of each flight, approach seat in the plane and a departure from port are filtered out in each flight
Seat in the plane combination；
(3) it is corresponded to using the genome of approach seat in the plane and depart from port seat in the plane as each flight according to putting in order for each flight setting
Genome constructs chromosome, and calculates the fitness of chromosome；
(4) it examines whether chromosome meets constraint condition, the fitness value of the chromosome of constraint condition will be met as each flight
Corresponding return value；
(5) Q table is updated according to each flight return value；
(6) according to the number of iterations is preset, step (2)~(5) are repeated, will finally meet the chromosome of constraint condition as seat in the plane point
With scheme.
2. Airport Gate Position Scheduling method as described in claim 1, which is characterized in that step (1) specifically comprises the following steps:
(1.1) flight and airport seat in the plane information are obtained；
(1.2) according to acquired information, approach seat in the plane and the combination of departure from port seat in the plane of each flight are determined；
(1.3) to approach seat in the plane and the combination progress Q table initialization of departure from port seat in the plane in each flight.
3. Airport Gate Position Scheduling method as claimed in claim 2, which is characterized in that the flight and airport seat in the plane packet
Include: flight number, type, whether be public affair, whether be VIP, whether be international airline, the moment of approaching, departure from port moment, airport tune
Degree business rule information and each seat in the plane correspond to type constraint information.
4. Airport Gate Position Scheduling method as claimed in claim 1 or 3, which is characterized in that the Q table initialization procedure are as follows:
Is met by constraint condition and assigns positive number, no for each flight motion space according to airport business hard constraint, soft-constraint condition
Meet constraint condition and assigns negative.
5. Airport Gate Position Scheduling method as described in claim 1, which is characterized in that the fitness value of the chromosome are as follows: F=
αBr+βFt+γRn
Wherein:
FtRepresent free time, BrIt represents and depends on bridge number, RnIt represents and pulls number, F represents fitness value, α, and beta, gamma is constant.
6. the Airport Gate Position Scheduling method as described in right 5, which is characterized in that the assignment of each flight return value of step (4)
Method are as follows:
The chromosome of acquisition checks whether to meet constraint condition by constraint test function；If eligible, return value R=F,
Otherwise return value R=-0.01.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811639136.1A CN109872033B (en) | 2018-12-29 | 2018-12-29 | Airport position allocation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811639136.1A CN109872033B (en) | 2018-12-29 | 2018-12-29 | Airport position allocation method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109872033A true CN109872033A (en) | 2019-06-11 |
| CN109872033B CN109872033B (en) | 2021-02-26 |
Family
ID=66917319
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811639136.1A Active CN109872033B (en) | 2018-12-29 | 2018-12-29 | Airport position allocation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109872033B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110264005A (en) * | 2019-06-21 | 2019-09-20 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN110443448A (en) * | 2019-07-01 | 2019-11-12 | 华中科技大学 | A kind of aircraft seat in the plane classification prediction technique and system based on two-way LSTM |
| CN110549896A (en) * | 2019-08-28 | 2019-12-10 | 哈尔滨工程大学 | charging station selection method based on reinforcement learning |
| CN111079274A (en) * | 2019-12-04 | 2020-04-28 | 深圳市机场股份有限公司 | Intelligent machine position allocation method, computer device and storage medium |
| CN111178004A (en) * | 2019-12-30 | 2020-05-19 | 北京富通东方科技有限公司 | Rule digital representation method for airport parking space resource allocation |
| CN111951145A (en) * | 2020-08-12 | 2020-11-17 | 青岛民航凯亚系统集成有限公司 | GA-DQN-based shutdown position allocation method |
| CN117237241A (en) * | 2023-11-15 | 2023-12-15 | 湖南自兴智慧医疗科技有限公司 | Chromosome enhancement parameter adjustment method and device |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1153337A (en) * | 1997-07-30 | 1999-02-26 | Fujitsu Ltd | Optimization method and device using object-oriented genetic algorithm |
| CN107679669A (en) * | 2017-10-19 | 2018-02-09 | 云南大学 | A kind of airport aircraft gate dispatching method and system based on meta-heuristic method |
-
2018
- 2018-12-29 CN CN201811639136.1A patent/CN109872033B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH1153337A (en) * | 1997-07-30 | 1999-02-26 | Fujitsu Ltd | Optimization method and device using object-oriented genetic algorithm |
| CN107679669A (en) * | 2017-10-19 | 2018-02-09 | 云南大学 | A kind of airport aircraft gate dispatching method and system based on meta-heuristic method |
Non-Patent Citations (3)
| Title |
|---|
| 沈洋: "民航机场机位分配问题的遗传算法研究", 《中国管理科学》 * |
| 王本年等: "RLGA: 一种基于强化学习机制的遗传算法", 《电子学报》 * |
| 田晨等: "基于遗传算法的机场机位分配策略", 《计算机工程》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110264005A (en) * | 2019-06-21 | 2019-09-20 | 北京百度网讯科技有限公司 | Method and apparatus for generating information |
| CN110443448A (en) * | 2019-07-01 | 2019-11-12 | 华中科技大学 | A kind of aircraft seat in the plane classification prediction technique and system based on two-way LSTM |
| CN110443448B (en) * | 2019-07-01 | 2022-03-29 | 华中科技大学 | Bidirectional LSTM-based airplane position classification prediction method and system |
| CN110549896A (en) * | 2019-08-28 | 2019-12-10 | 哈尔滨工程大学 | charging station selection method based on reinforcement learning |
| CN111079274A (en) * | 2019-12-04 | 2020-04-28 | 深圳市机场股份有限公司 | Intelligent machine position allocation method, computer device and storage medium |
| CN111079274B (en) * | 2019-12-04 | 2024-04-09 | 深圳市机场股份有限公司 | Intelligent allocation method for machine position, computer device and storage medium |
| CN111178004A (en) * | 2019-12-30 | 2020-05-19 | 北京富通东方科技有限公司 | Rule digital representation method for airport parking space resource allocation |
| CN111178004B (en) * | 2019-12-30 | 2023-12-26 | 北京富通东方科技有限公司 | Regular digital representation method for airport stand resource allocation |
| CN111951145A (en) * | 2020-08-12 | 2020-11-17 | 青岛民航凯亚系统集成有限公司 | GA-DQN-based shutdown position allocation method |
| CN111951145B (en) * | 2020-08-12 | 2022-06-10 | 青岛民航凯亚系统集成有限公司 | GA-DQN-based shutdown position distribution method |
| CN117237241A (en) * | 2023-11-15 | 2023-12-15 | 湖南自兴智慧医疗科技有限公司 | Chromosome enhancement parameter adjustment method and device |
| CN117237241B (en) * | 2023-11-15 | 2024-02-06 | 湖南自兴智慧医疗科技有限公司 | Chromosome enhancement parameter adjustment method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109872033B (en) | 2021-02-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109872033A (en) | A kind of Airport Gate Position Scheduling method | |
| CN111159426B (en) | Industrial map fusion method based on graph convolution neural network | |
| CN106020230B (en) | A kind of multiple no-manned plane method for allocating tasks under power consumption constraint | |
| CN106529574B (en) | Image classification method based on sparse autocoder and support vector machines | |
| CN104516785B (en) | A kind of cloud computing resources dispatch system and method | |
| CN105050192B (en) | Interference management method based on virtual subdistrict in dense network | |
| CN103593400A (en) | Lightning activity data statistics method based on modified Apriori algorithm | |
| CN109544998A (en) | A kind of flight time slot distribution Multipurpose Optimal Method based on Estimation of Distribution Algorithm | |
| CN105184415B (en) | A kind of Distribution Networks Reconfiguration design method | |
| CN109460900B (en) | Transition flight distribution method for newly-built satellite hall in airport | |
| CN106789320A (en) | A kind of multi-species cooperative method for optimizing wireless sensor network topology | |
| CN111121784A (en) | Unmanned reconnaissance aircraft route planning method | |
| CN110912718A (en) | Method for reducing power consumption of heterogeneous three-dimensional on-chip network layout | |
| CN104731811B (en) | A kind of clustering information evolution analysis method towards extensive dynamic short text | |
| Tian et al. | Spatio-temporal position prediction model for mobile users based on LSTM | |
| CN111157002A (en) | Aircraft 3D path planning method based on multi-agent evolutionary algorithm | |
| CN109002878A (en) | A kind of GA Optimized BP Neural Network | |
| CN109214572A (en) | One kind is based on EPSO-BP to commercial building lamp decoration energy consumption prediction technique | |
| Sun et al. | Wireless sensor network node localization based on genetic algorithm | |
| CN105469644B (en) | Solving Flight Conflicts method and apparatus | |
| CN117094443A (en) | Hub airport flight transfer connectivity optimization method and device based on number of hits | |
| Pei et al. | UAV swarm for connectivity enhancement of multiple isolated sensor networks for Internet of things application | |
| CN109359671A (en) | A kind of classification intelligent extract method of Hydropower Station Reservoir Dispatching rule | |
| CN104268639A (en) | Ship piloting and scheduling method based on forest model and improved genetic algorithm | |
| CN111698690B (en) | Cognitive wireless network spectrum allocation method based on improved niche inheritance |
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 |