Metaheuristics for air traffic management / Nicolas Durand [and three others].

Format:

Book

Author/Creator:

Durand, Nicolas, author.

Series:

Computer Engineering Series. Metaheuistic Set ; Volume 2

Language:

English

Subjects (All):

Air traffic control--Management.

Air traffic control.

Physical Description:

1 online resource (215 p.)

Edition:

1st ed.

Place of Publication:

London, England ; Hoboken, New Jersey : iSTE : Wiley, 2016.

Summary:

Air Traffic Management involves many different services such as Airspace Management, Air Traffic Flow Management and Air Traffic Control. Many optimization problems arise from these topics and they generally involve different kinds of variables, constraints, uncertainties. Metaheuristics are often good candidates to solve these problems. The book models various complex Air Traffic Management problems such as airport taxiing, departure slot allocation, en route conflict resolution, airspace and route design. The authors detail the operational context and state of art for each problem. They introduce different approaches using metaheuristics to solve these problems and when possible, compare their performances to existing approaches.

Contents:

Cover

Title Page

Copyright

Contents

Introduction

Chapter 1: The Context of Air Traffic Management

1.1. Introduction

1.2. Vocabulary and units

1.3. Missions and actors of the air traffic management system

1.4. Visual flight rules and instrumental flight rules

1.5. Airspace classes

1.6. Airspace organization and management

1.6.1. Flight information regions and functional airspace blocks

1.6.2. Lower and upper airspace

1.6.3. Controlled airspace: en route, approach or airport control

1.6.4. Air route network and airspace sectoring

1.7. Traffic separation

1.7.1. Separation standard, loss of separation

1.7.2. Conflict detection and resolution

1.7.3. The distribution of tasks among controllers

1.7.4. The controller tools

1.8. Traffic regulation

1.8.1. Capacity and demand

1.8.2. Workload and air traffic control complexity

1.9. Airspace management in en route air traffic control centers

1.9.1. Operating air traffic control sectors in real time

1.9.2. Anticipating sector openings (France and Europe)

1.10. Air traffic flow management

1.11. Research in air traffic management

1.11.1. The international context

1.11.2. Research topics

Chapter 2: Air Route Optimization

2.1. Introduction

2.2. 2D-route network

2.2.1. Optimal positioning of nodes and edges using geometric algorithms

2.2.2. Node positioning, with fixed topology, using a simulated annealing or a particle swarm optimization algorithm

2.2.3. Defining 2D-corridors with a clustering method and a genetic algorithm

2.3. A network of separate 3D-tubes for the main traffic flows

2.3.1. A simplified 3D-trajectory model

2.3.1.1. 3D-trajectories with lateral or vertical deviations

2.3.1.2. Deviation costs for the simplified model

2.3.1.3. A simple criterion for 3D-trajectory separation.

2.3.2. Problem formulations and possible strategies

2.3.2.1. Sequential approach or global optimization

2.3.2.2. Problem difficulty and choice of algorithms

2.3.3. An A* algorithm for the "1 versus n" problem

2.3.3.1. General description of tree-search or graph-search methods

2.3.3.2. The A* algorithm

2.3.3.3. State space representation for the simplified 3D-trajectory model

2.3.3.4. Cost and heuristic for the simplified 3D-trajectory model

2.3.4. A hybrid evolutionary algorithm for the global problem

2.3.4.1. General description of an evolutionary algorithm

2.3.4.2. Encoding individuals

2.3.4.3. Initial population

2.3.4.4. Fitness criterion

2.3.4.5. Parent selection

2.3.4.6. The crossover operator

2.3.4.7. The mutation operator, for simple test-cases

2.3.4.8. The mutation operator for complex test-cases and real data

2.3.4.9. Selecting individuals for the new population

2.3.5. Results on a toy problem, with the simplified 3D-trajectory model

2.3.5.1. Description of the toy problem and test-cases

2.3.5.2. Results of the A* algorithm on the toy problem

2.3.5.3. Results of the evolutionary algorithm on the toy problem

2.3.6. Application to real data, using a more realistic 3D-tube model

2.3.6.1. Traffic flow model and computation

2.3.6.2. A more realistic 3D-tube model based on aircraft performances

2.3.6.3. Attributes of the 3D-tubes

2.3.6.4. Detection of 3D-tubes intersections

2.3.6.5. Adaptation of the algorithms

2.3.6.6. Results in the French airspace

2.3.6.7. Results in the European airspace

2.4. Conclusion on air route optimization

Chapter 3: Airspace Management

3.1. Airspace sector design

3.2. Functional airspace block definition

3.2.1. Simulated annealing algorithm

3.2.2. Ant colony algorithm

3.2.3. A fusion-fission method.

3.2.4. Comparison of fusion-fission and classical graph partitioning methods

3.3. Prediction of air traffic control sector openings

3.3.1. Problem difficulty and possible approaches

3.3.2. Using a genetic algorithm

3.3.3. Tree-search methods, constraint programming

3.3.4. A neural network for workload prediction

3.3.5. Conclusion on the prediction of sector openings

Chapter 4: Departure Slot Allocation

4.1. Introduction

4.2. Context and related works

4.2.1. Ground holding

4.2.1.1. Satisfying sector capacity constraints

4.2.1.2. Solving the conflicts

4.3. Conflict-free slot allocation

4.3.1. Conflict detection

4.3.2. Sliding forecast time window

4.3.3. Evolutionary algorithm

4.3.3.1. Variables and data structures

4.3.3.2. Constraints

4.3.3.3. Fitness function

4.3.3.4. Mutation operator

4.3.3.5. Crossover operator

4.3.3.6. Sharing

4.3.3.7. Parameters

4.4. Results

4.4.1. Evolution of the problem size

4.4.2. Numerical results

4.5. Concluding remarks

Chapter 5: Airport Traffic Management

5.1. Introduction

5.1.1. Airports' main challenges

5.1.2. Known difficulties

5.1.3. Optimization problems in airport traffic management

5.2. Gate assignment

5.2.1. Problem description

5.2.2. Resolution methods

5.3. Runway scheduling

5.3.1. Problem description

5.3.2. An example of problem formulation

5.3.3. Resolution methods

5.4. Surface routing

5.4.1. Problem description

5.4.2. Related work

5.5. Global airport traffic optimization

5.5.1. Problem description

5.5.2. Coordination scheme between the different predictive systems

5.5.3. Simulation results

5.6. Conclusion

Chapter 6: Conflict Detection and Resolution

6.1. Introduction

6.2. Conflict resolution complexity

6.3. Free-flight approaches

6.3.1. Reactive techniques.

6.3.2. Iterative approach

6.3.3. An example of reactive approach: neural network trained by evolutionary algorithms

6.3.3.1. Problem modeling

6.3.3.2. The inputs

6.3.3.3. The neural network structure

6.3.3.4. Learning the neural network weights

6.3.3.5. Evolutionary algorithm used

6.3.3.6. Computing the fitness

6.3.3.7. The learning examples

6.3.3.8. Numerical results

6.3.4. A limit to autonomous approaches: the speed constraint

6.4. Iterative approaches

6.5. Global approaches

6.6. A global approach using evolutionary computation

6.6.1. Maneuver modeling

6.6.2. Uncertainty modeling

6.6.3. Real-time management

6.6.4. Evolutionary algorithm implementation

6.6.4.1. General description

6.6.4.2. The horizon effect

6.6.4.3. The fitness function

6.6.4.4. Use of partial separability

6.6.4.5. The adapted crossover operator

6.6.4.6. Theoretical study of a simple example

6.6.4.7. Probability of improvement

6.6.4.8. Application to conflict resolution

6.6.5. Alternative modeling

6.6.6. One-day traffic statistics

6.6.7. Introducing automation in the existing system

6.7. A global approach using ant colony optimization

6.7.1. Problem modeling

6.7.2. Algorithm description

6.7.3. Algorithm improvement: constraint relaxation

6.7.4. Results

6.7.5. Conclusion and further work

6.8. A new framework for comparing approaches

6.8.1. Introduction

6.8.2. Trajectory prediction model

6.8.2.1. Maneuvers

6.8.2.2. Decision variables

6.8.2.3. Cost

6.8.2.4. Handling uncertainties

6.8.3. Conflict detection

6.8.4. Benchmark generation

6.8.5. Conflict resolution

6.8.5.1. Evolutionary algorithm

6.8.5.1.1. Principles

6.8.5.1.2. Fitness function

6.8.5.1.3. Adapted crossover and mutation

6.8.5.2. Constraint programming

6.8.5.2.1. CSP model.

6.8.5.2.2. Solution search

6.8.5.3. Optimization

6.8.5.4. Results

6.8.5.4.1. Benchmark

6.8.5.4.2. Conflict resolution

6.8.5.4.3. Computing times

6.8.5.4.4. Cost of solutions

6.8.5.5. Conclusion and further work

6.9. Conclusion

Conclusion

Bibliography

Index.

Notes:

Description based upon print version of record.

Includes bibliographical references and index.

Description based on online resource; title from PDF title page (ebrary, viewed February 17, 2016).

ISBN:

9781119261537

1119261538

9781119261520

111926152X

OCLC:

933442909