A machine learning approach on past ADS-B data to predict planning controller’s actions

En-route airspace is one of the most congested airspaces, as it is mainly used in the cruise phase of the flight. The en-route sector is usually managed by a team of two air traffic controllers: planning controller (D-side) and executive controller (R-side). The D-side controller is responsible for...

Full description

Saved in:
Bibliographic Details
Main Authors: Pham, Duc-Thinh, Alam, Sameer, Su, Yi-Lin, Duong, Vu N.
Other Authors: School of Mechanical and Aerospace Engineering
Format: Conference or Workshop Item
Language:English
Published: 2021
Subjects:
Online Access:https://hdl.handle.net/10356/146669
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:En-route airspace is one of the most congested airspaces, as it is mainly used in the cruise phase of the flight. The en-route sector is usually managed by a team of two air traffic controllers: planning controller (D-side) and executive controller (R-side). The 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 the safety of flights in their sector. A better understanding and predictability of Dside 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 one month of ADS-B data over an en-route sector, and its generalization performance was assessed, using cross-fold validation, in the same sectors. Results indicate that the model for vertical maneuver actions provides the highest prediction accuracy (99.7%). Besides, the model for speed change and heading change action provides predictability accuracy of 88.7% and 72.4% respectively. The model to predict the set of all the actions (altitude, speed, and heading change) for each flight achieves an accuracy of 0.68 implying for 68% of flights, D-Side Controller’s can be predicted for all the actions from trajectory information at sector entry position.