En-route Sector Research Articles

Short-term multi-step-ahead sector-based traffic flow prediction based on the attention-enhanced graph convolutional LSTM network (AGC-LSTM)

AbstractAccurate sector-based air traffic flow predictions are essential for ensuring the safety and efficiency of the air traffic management (ATM) system. However, due to the inherent spatial and temporal dependencies of air traffic flow, it is still a challenging problem. To solve this problem, some methods are proposed considering the relationship between sectors, while the complicated spatiotemporal dynamics and interdependencies between traffic flow of route segments related to the sector are not taken into account. To address this challenge, the attention-enhanced graph convolutional long short-term memory network (AGC-LSTM) model is applied to improve the short-term sector-based traffic flow prediction, in which spatial structures of route segments related to the sector are considered for the first time. Specifically, the graph convolutional networks (GCN)-LSTM network model was employed to capture spatiotemporal dependencies of the flight data, and the attention mechanism is designed to concentrate on the informative features from key nodes at each layer of the AGC-LSTM model. The proposed model is evaluated through a case study of the typical enroute sector in the central–southern region of China. The prediction results show that MAE reduces by 14.4% compared to the best performing GCN-LSTM model among the other five models. Furthermore, the study involves comparative analyses to assess the influence of route segment range, input and output sequence lengths, and time granularities on prediction performance. This study helps air traffic managers predict flight situations more accurately and avoid implementing overly conservative or excessively aggressive flow management measures for the sectors.

Preliminary design of an ATC support tool for the implementation of the Ad Hoc Separation Minima concept in an en-route sector.

The current aim in response to the anticipated growth in air traffic demand is to expand airspace capacity. However, this poses a challenge, as many airspace volumes are nearing saturation. An influential factor in determining airspace capacity is separation minima, which have remained unchanged for more than two decades. It seems that technological developments in recent years, such as new aircraft capabilities and ATC (Air Traffic Control) support tools, may eventually enhance current separation minima standards. Consequently, there is a push to improve separation management by introducing new operational concepts. Ad Hoc separation minima are one such concept, allowing different separation values to be applied within the same airspace volume based on factors such as aircraft models, weights, and wind conditions, among others. These values are computed individually for each aircraft pair in each situation. Implementing different separation minima values within the same airspace volume requires a significant change in certain ATC activities. In addition, new functionalities or ATC support tools are essential, as Air Traffic Control Officers (ATCO) cannot mentally determine the appropriate separation value for each situation. To address this, a new tool, the Ad Hoc Separation Minima Tool (ASMT), is proposed. It aims to integrate this concept seamlessly into an en-route (ENR) sector without increasing ATCOs workload and altering ATC responsibilities. This study provides a high-level overview of the ASMT architecture, and its functional system has been evaluated in a simulated ENR sector using MATLAB®.

Air Traffic Control software implemented in RADAR

This study presents the flight plan data related to aircraft performance and is tested against the aircraft performance database. The Significant Meteorological Information Reports - SIGMET will be generated by the system according to the selected turbulence areas by attaching different AIS data to an exercise that can change the simulation objectives. The exercise must be assigned to one or more courses to be able to attach meteorological data when viewing a data recording; changes can be made to the aircraft as in a normal exercise run, while the other instructions will be loaded from the recorded data file. A data recording is airspace dependent, changing the airspace can make the data recording fail during playback. Video Recording is only available for the RADAR Simulator. A video recording can be made at any time during a simulation session; a data recording can be selected only at the beginning of the simulation session and cannot be started during the simulation session; if the simulator is integrated with the Voice Communication System and the audio channels, then a sound recording window will automatically pop-up. For this study, an ideal case, for the configuration presentation we will assume that the 3D Tower Simulator is composed of 4 LCD/Projectors to create the out-of-the- window view, 180 degrees, 2 Pseudo-Pilots, and 1 Supervisor/FEEDER Position. The 4 image generators will be provided by SIM01, SIM02, SIM03, and SIM04. The Pseudo-Pilots positions will be provided by SIM05 and SIM06. The Supervisor/Feeder Position will be provided by SIM07. For the Tower Controller Working Positions, we will provide the following information displays: DE – Flight Data Equipment/Clearance Delivery, MET – Meteorological Information, LCP –Lights Control Panel, and a RADAR Image. Station SIM08 will be used. Stations SIM01, SIM02, SIM03, and SIM04 are equipped with one large LCD Display or a Projector; Stations SIM05 and SIM07 are equipped with 2 monitors, one for the RADAR Image and the other one for the bird-eye view over the airport; Station SIM06 is equipped with one monitor for the bird-eye view over the airport; Station SIM08 is equipped with 4 monitors providing all necessary information for the Tower Controller Working Positions. SIM07, as presented above, is the FEEDER/SUPERVISOR for the RADAR Simulator, the approach sector is “TMA” and the application will be started on the second monitor, the first monitor is used for the 3D Tower Simulator. SIM07 is also FEEDER/SUPERVIZOR for the 3D Tower Simulator, the station function will be “3DTWR” and the sector will be the previously created 3D Tower configuration, “TOWER”. On SIM08 will add a RADAR Image for the Tower Controller Working Positions, sector is “TMA”, the application will be started on monitor 4, and the station function is “TWR”. Usually, for an aircraft departing from an airport inside an approach sector, the first owner will be the tower until passing the maximum flight level/ altitude for the tower, the second owner will be the approach sector and the third owner will be the en-route sector. In this case, the tower sector has power over the approach sector, and the en-route sector, the approach sector has power over the en-route sector. The outside FIR sectors will be used in the determination of the next en-route sector, for coordination purposes. If the VFR points do not appear on the RADAR Map after the “DRAW” button has been pushed, use the “MAP MENU” – “VFR” button. The aircraft performance database is not airspace structure dependent. When a new airspace structure is created the aircraft performance database will remain unchanged.

Analysing the benefits of trajectory deviations for planar trajectory optimisation

Aircraft traverse airspace sectors under the supervision of Air Traffic Controllers by following navigation points. The trajectories can deviate from these points under the supervision of controllers. However, the controllers have to consider various factors for managing air traffic which increases their workload. We aim to offline analyse the potential benefits of trajectory deviations, by tactically shifting navigation points for planar trajectory optimisation of multiple aircraft at an enroute sector level. Historic deviations of trajectories are considered for this analysis to implement them at practical level. Within nominal speed and turning rate of aircraft trajectories, 5.47% reduction in time cost and an annual fuel saving worth US$ 29.32 million has been estimated using shifts for an airspace sector.

Autonomous planning of optimal four-dimensional trajectory for real-time en-route airspace operation with solution space visualisation

One of the challenges in applying autonomous operation-based conflict detection and resolution (CD&R) techniques to practice is their functional completeness, such as the ability to simultaneously consider three-dimensional (3D) scenarios, controlled time of arrival, restricted areas, trajectory recovery, and multi-stakeholder performance preferences. Besides, the effective interaction between controllers, pilots and autonomous operating system can better support the CD&R to work in practice, where humans are able to intuitively understand the rationale for solutions given by automatic decision-making tools. To bridge the gap, a novel operational framework for four-dimensional (4D) trajectory conflict management in the context of free route airspace is proposed. Airspace discretisation based on a 3D grid is used to facilitate the consideration of restricted areas and to balance calculation speed and optimal effect. The core of this framework is a two-stage real-time autonomous 4D trajectory planning method in a restricted en-route sector with multiple flight levels enhanced by solution space visualisation. Stage one is a trajectory pre-planning model based on a visibility graph and the Dijkstra algorithm considering the conflict between aircraft and emerging restricted areas. Stage two is a real-time conflict-free and fuel-optimal 4D trajectory re-planning model. The space–time prism is employed to enable the planned trajectory to meet the controlled time of arrival and trajectory recovery requirements, where the performance preferences of both the air traffic management and airspace users are taken into account. The reachable solution space representation is applied to realise the solution space visualisation that has the potential to support the human–machine interaction and air–ground coordination. A simulation scenario is established to validate the effectiveness, efficiency, stability, and timeliness of the proposed method. Results show that in an artificial en-route sector, the average extra flight distance, average flight delay, average extra fuel consumption, and average computing time for conflict resolution were less than 0.41 km, 2.1 s, 1.5 kg, and 0.08 s in the saturated scenario, respectively, and the domino effect of the flight conflict did not show a significant rise with the increase of traffic density, which verified that the proposed autonomous trajectory operation methodology is a promising approach to facilitate autonomous air traffic management in the future.

An Air Traffic Controller Action Extraction-Prediction Model Using Machine Learning Approach

In air traffic control, the airspace is divided into several smaller sectors for better management of air traffic and air traffic controller workload. Such sectors are usually managed by a team of two air traffic controllers: planning controller (D-side) and executive controller (R-side). D-side controller is responsible for processing flight-plan information to plan and organize the flow of traffic entering the sector. R-side controller deals with ensuring safety of flights in their sector. A better understanding and predictability of D-side controller actions, for a given traffic scenario, may help in automating some of its tasks and hence reduce workload. In this paper, we propose a learning model to predict D-side controller actions. The learning problem is modeled as a supervised learning problem, where the target variables are D-side controller actions and the explanatory variables are the aircraft 4D trajectory features. The model is trained on six months of ADS-B data over an en-route sector, and its generalization performance was assessed, using crossvalidation, on the same sector. Results indicate that the model for vertical maneuver actions provides highest prediction accuracy (99%). Besides, the model for speed change and course change action provides predictability accuracy of 80% and 87%, respectively. The model to predict the set of all the actions (altitude, speed, and course change) for each flight achieves an accuracy of 70% implying for 70% of flights; D-side controller’s action can be predicted from trajectory information at sector entry position. In terms of operational validation, the proposed approach is envisioned as ATCO assisting tool, not an autonomous tool. Thus, there is always ATCO discretion element, and as more ATCO actions are collected, the models can be further trained for better accuracy. For future work, we will consider expanding the feature set by including parameters such as weather and wind. Moreover, human in the loop simulation will be performed to measure the effectiveness of the proposed approach.

Departure and Arrival Routes Optimization Near Large Airports

The bottleneck of today’s airspace is the Terminal Maneuvering Areas (TMA), where aircraft leave their routes to descend to an airport or take off and reach the en-route sector. To avoid congestion in these areas, an efficient design of departure and arrival routes is necessary. In this paper, a solution for designing departure and arrival routes is proposed, which takes into account the runway configuration, the surroundings of the airport and operational constraints such as limited slopes or turn angles. The routes consist of two parts: a horizontal path in a graph constructed by sampling the TMA around the runway, to which is associated a cone of altitudes. The set of all routes is optimized by the Simulated Annealing metaheuristic. In the process and at each iteration, each route is computed by defining adequately the cost of the arcs in the graph and then searching a path on it. The costs are chosen so as to avoid zigzag behaviors as much as possible. Two tests were performed, one on an instance taken from the literature and the other on an artificial problem designed specifically to test this approach. The obtained results are satisfying with regard to the current state of air operations management and constraints.

EN-ROUTE AIRSPACE CAPACITY AND TRAFFIC FLOW ENHANCEMENT USING GENETIC ALGORITHMS

Air transportation industry has gone under a rapid and continuous growth for the last four decades. International Civil Aviation Organization (ICAO) and airlines anticipate that annual growth rate of air traffic will be 4.5-5.1% until 2030. Airspace capacity management becomes more critical for the safety, efficiency and sustainable growth of the industry. En-route areas cover the largest portion of the controlled airspace and are subdivided into small segments referred to as ‘en-route sectors’ usually monitored and controlled by a single air traffic controller in the relevant Area Control Center (ACC). When air traffic demand reaches or exceeds the available en-route sector capacity, serious aircraft delays occur at airports or in airspace and lead to system-wide congestions and interruptions in air traffic services, airline flight schedules and airport operations, and therefore result in increased operational costs, passenger dissatisfaction and air traffic controller workload. This study presents a multiple entry point assignment model based on a genetic algorithm to minimize delays and increase throughput of a generic high-altitude en-route sector. The proposed approach intends to use more flexible direct route configuration without changing the sector geometry and provide a framework for a decision support system for air traffic flow and capacity planning and management. The available single entry point sector configuration and its multiple entry point assignment alternatives were compared for various traffic scenarios. Multiple entry point configurations provided up to 10% increase in throughput and significant reductions in average delay per aircraft compared to the single point entry configuration.

An analysis of air traffic controller-pilot miscommunication in the NextGen environment

This paper extends research on miscommunication between air traffic controllers and pilots by developing statistical models that predict the outcome of communications within the scope of controller-pilot data communications in the Next Generation Air Transportation environment. A database of controller-pilot voice messages from high and super-high altitude en-route sectors of US airspace is investigated. Emphasis is given to parameters that can be utilized in the voice-only communication, as well as in the mixed media, environment. This allows formulation of reasonable assumptions about the impact of data communications on controller and pilot behavior. The models indicate that the most important factors affecting communications are length and context of the message, entering of an aircraft into a sector, transfer of communication, and radio frequency congestion. The results also suggest that the transmission of non-time critical routine messages via data communications could reduce the number of communication errors and alleviate radio frequency congestion.

Secondary trading of airport slots as a combinatorial exchange

In our research we propose a market formalization of secondary trading of airport slots. This proposed market is managed through an individual rational and budget balanced combinatorial slot exchange. The suggested market mechanism allows consideration of en-route sector capacities during the slot allocation process. We quantify the potential advantage of the market by comparing it with current practice. The results show that solutions that appear optimal when neglecting en-route sector capacities can be infeasible when taking capacities into account. Finally, in the proposed market the existence of grandfather rights does not seem to affect airline costs in a significant way.

Optimal Scheduling and Speed Adjustment in En Route Sector for Arriving Airplanes

Flow control is one of themajor problems for busy airports during rush hours. Air traffic controllersmust quickly arrange the approaching sequence of the aircraft andmake necessary separation arrangements. This paper presents a scheduling algorithm to generate the optimal speed-change advisories that minimize both the time to land a group of aircraft and the changes of scheduled time of arrival from estimated time of arrival of each aircraft in this group. A sequence matrix and a separation-time matrix are used to construct the constraints. Comparing with traditional formulations in which the number of constraints grows with the square of the number of aircraft, the number of constraints in theproposed formulation grows linearlywith the number of aircraft. The speed-change capabilities for different aircraft are also considered in the constraints. Using the proposed optimization process, thefinal results will meet both optimal sequence and minimal changes of scheduled time of arrival from estimated time of arrival requirements. Finally, historical data for Taiwan Taoyuan International Airport are used to demonstrate the effectiveness of our approach.

Concept of Measurement for En-Route Sector Capacity

ATFM (Air Traffic Flow Management) keeps air traffic flows safe and orderly. When the estimated workload exceeds capacity limit, traffic demand is controlled. In Japan, The ATFM system estimates controller's workload by a lot of parameter that depend on sector characteristics represented by traffic flow. The calculation of the value needs a lot of analysis. Author proposes a simple method for estimating the workload created by the traffic situation.

Comparison of Deconfliction Responsibility Procedures for Adjacent En-Route Sectors in NextGen Separation Assurance

The subject of the current research is a Next Generation Air Transportation System (NextGen) concept that involves automation-assisted separation assurance within the high altitude (at or above 29,000 feet) en route environment. The concept is designed to enable controllers to provide both safe and efficient air traffic services at much higher traffic densities than today. The presented research addressed the question of how responsibility should be handled for the resolution of a conflict that is predicted to occur in a sector other than where it was detected. Two possibilities, namely a De-Conflicting AirPlanes procedure (DCAP) versus a De-Conflicting AirSpace procedure (DCAS) were examined with recently retired controllers under human-in-the-loop simulations with scripted aircraft conflicts. Results showed that controllers preferred DCAS, in which they took less time to resolve conflicts and experienced less coordination with one another. However, the results did not yield significant differences among other plane performance metrics between DCAP and DCAS. The present analyses indicated that controllers are capable of meeting demands of NextGen with ownership/coordination procedures (e.g. DCAP.) similar to today. However, allowing separation assurance responsibilities to extend more seamlessly across sector boundaries (e.g. DCAS) could evidently be more agreeable for them.

The design of a market mechanism to allocate Air Traffic Flow Management slots

In Europe, when an imbalance between demand and capacity is detected for air traffic network resources, Air Traffic Flow Management slots are allocated to flights on the basis of a First Planned First Served principle. In the case of a single constrained en-route sector or airport, we propose a mechanism for slot allocation which is based on market principles as it enables airlines to pay for delay reduction or receive compensation for delay increase. The mechanism fulfills the properties of individual rationality, budget balance, coalitional rationality and Pareto efficiency, and it can be implemented through two alternative distributed approaches that do not require airlines to disclose confidential information. Both approaches have the additional advantage that they directly involve airlines in the decision making process. Two computational examples relying on real data indicate that the market-based solution allows the participating airlines to significantly decrease their overall delay-related costs with respect to the First Planned First Served allocation.

En-route sector capacity estimation methodologies: An international survey

Reliable estimation of en-route sector capacity is important, especially in high-density traffic areas where controller workload is the driver. En-route sector capacity is commonly estimated using fast-time computer simulation techniques employing models of controller workload. This paper analyses the methodologies employed by a number of countries in Europe and North America, to estimate the capacity of en-route airspace. The data used was obtained from airspace planners and managers. The survey involved interviews using pre-designed questionnaires. The results show that there are two main models used in the simulation of controller workload, and that there is considerable variation both in their application and controller involvement in the capacity estimation process.

Economic Benefits of Increased En Route Sector Capacity from Controller-Pilot Data Link Communications

The En Route Controller-Pilot Data Link Communications (CPDLC) program is designed to enable digital data communications between controllers and pilots. CPDLC Build 1A has been proposed as the first step in the nationwide rollout of this program to en route airspace by implementation in eight air route traffic control centers. Because CPDLC will automate several routine air-ground communications tasks, one potential benefit is reduced controller workload, which could lead to increased sector capacity and thus reduced flight times for flights traversing busy sectors. To quantify the workload reduction, a comparison has been made of the time currently required to perform communications tasks, as determined from recordings of actual air-ground communications, and the time required to perform the same tasks with CPDLC, as determined by a controller-in-the-loop simulation. This comparison indicated the potential for a significant reduction in the time spent on controller-pilot communications. A model was constructed to relate the reduced controller communications workload to increased sector capacity. The National Airspace System Performance Analysis Capability (NASPAC) model was used to estimate the reduction in flight times associated with the modeled sector capacity increase. NASPAC was run for both an idealized good weather day and a sample actual bad weather day. By 2017, the last year of the projected economic lifetime of CPDLC, average flight time savings from CPDLC-related capacity increases were estimated to exceed 9, 400 min/day.

Wake vortex control - a challenge for large transport aircraft

One of the most promising routes to increase capacity at over-crowded European airports is to reduce the separation distances between aircraft on landing and take-off, or vertical separations in densely flown en-route sectors. Separations are necessary to avoid the risk of encountering a wake from a preceding aircraft - and hence are vital for flight safety. This is becoming even more critical with the advent of very-large transport aircraft. This article explains the characterisation of wave vortices, and explores the European Projects looking at the problem.

Concept of Future Air Traffic Management and its Real-Time Decision Support utilizing Concept Learning

Finding possible solutions for costly aircraft delays and congestion problem is the most important theme for the future air traffic control(ATC). Therefore, intelligent air traffic management (ATM) systems are highly required, which can manage air traffic flows and flight schedules strategically in real time fashion. For this objective, in this paper, an automated decision support system for the efficient ATM in one enroute sector or terminal area (TMA) is designed. This system uses concept learning scheme, a kind of machine learning techniques. The system has capabilities to find a suboptimal solution without interrupting real-time operations, in order to deal with various emergencies and to discover new better scheduling heuristics. Simulation studies show that the proposed scheduling architecture works rather efficiently than the current ATC procedure based on simple heuristic rules such as first-in first-out (FIFO) rule. An intelligent decision support system for ATM in a global airspace consisting of many airports and airroutes is also suggested toward future simulation studies.

An airspace design and evaluation of enroute sector by air traffic control simulation experiments

AbstractIn the enroute air traffic control which controls the aircraft flying between airports, the broad area of airspace is divided into units called sectors. This paper describes the air traffic control simulation experiments considering the function expansion project of the Tokyo International Airport and discusses the evaluation of the airspace design for the enroute air traffic control sectors.First, the traffic volume after the function expansion is estimated. The result is compared to the already obtained result of experiments for the sector traffic capacity estimation in the present airspace. The sector for which the airspace redesign is needed is pointed out.Next, based on the evaluation criteria considering the control process, three trial plans (A, B, and C) for the airspace design are presented and examined by experiments. Based on the results of evaluation, the fourth trial plan (D) is presented, including a new control technique. It is shown that, by using that technique, the average traffic volume in the busiest hours anticipated after the function expansion can be controlled smoothly.

ATC Simulations for the Implementation of Bilingual IFR Control in Canada

Enroute and Terminal Control Area simulation exercises involving certified bilingual controllers from Montreal Center have been conducted in order to develop procedures for the implementation of bilingual IFR control in the Province of Quebec. The enroute phase of the program was designed to determine the effect of bilingual control on controller performance and the supplementary procedures required in both a radar and non-radar environment. The effects of traffic load, language, and type of sector on communication characteristics, controller errors, and control effectiveness were also observed. In the terminal control phase, the effect of varying work load as a function of the runway-in-use was also included in the analysis of arrival and departure control. Aircraft simulators integrated within the simulations, initially by voice-link and later by data-link, enabled representative pilots from professional aviation associations to evaluate the simulation exercises and the proposed bilingual system. Independent exercises investigated bilingual control procedures in situations of an exceptional nature in the terminal and enroute sectors.