10.15480/882.3279
Sanaei, Rasoul
Rasoul
Sanaei
0000-0001-7063-5114
1226686400
Pinto, Brian Alphonse
Brian Alphonse
Pinto
0000-0002-3222-109X
Gollnick, Volker
Volker
Gollnick
0000-0001-7214-0828
129040525
Toward ATM resiliency : a deep CNN to predict number of delayed flights and ATFM delay
Multidisciplinary Digital Publishing Institute
2021
ATFM delay
CNN
resilience
capacity regulations
Handel, Kommunikation, Verkehr
TUHH Universitätsbibliothek
TUHH Universitätsbibliothek
2021-02-08
2021-02-08
2021-01-25
2021-02-05
en
Journal Article
Aerospace 8 (2): 28 (2021)
http://hdl.handle.net/11420/8714
10.15480/882.3279
10.3390/aerospace8020028
https://creativecommons.org/licenses/by/4.0/
The European Air Traffic Management Network (EATMN) is comprised of various stakeholders and actors. Accordingly, the operations within EATMN are planned up to six months ahead of target date (tactical phase). However, stochastic events and the built-in operational flexibility (robustness), along with other factors, result in demand and capacity imbalances that lead to delayed flights. The size of the EATMN and its complexity challenge the prediction of the total network delay using analytical methods or optimization approaches. We face this challenge by proposing a deep convolutional neural network (DCNN), which takes capacity regulations as the input. DCNN architecture successfully improves the prediction results by 50 percent (compared to random forest as the baseline model). In fact, the trained model on 2016 and 2017 data is able to predict 2018 with a mean absolute percentage error of 22% and 14% for the delay and delayed traffic, respectively. This study presents a method to provide more accurate situational awareness, which is a must for the topic of network resiliency.
The European Air Traffic Management Network (EATMN) is comprised of various stakeholders and actors. Accordingly, the operations within EATMN are planned up to six months ahead of target date (tactical phase). However, stochastic events and the built-in operational flexibility (robustness), along with other factors, result in demand and capacity imbalances that lead to delayed flights. The size of the EATMN and its complexity challenge the prediction of the total network delay using analytical methods or optimization approaches. We face this challenge by proposing a deep convolutional neural network (DCNN), which takes capacity regulations as the input. DCNN architecture successfully improves the prediction results by 50 percent (compared to random forest as the baseline model). In fact, the trained model on 2016 and 2017 data is able to predict 2018 with a mean absolute percentage error of 22% and 14% for the delay and delayed traffic, respectively. This study presents a method to provide more accurate situational awareness, which is a must for the topic of network resiliency.
2226-4310
Aerospace
2021
Multidisciplinary Digital Publishing Institute