Toward ATM Resiliency: A Deep CNN to Predict Number of Delayed Flights and ATFM Delay
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 wi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-01-01
|
| Series: | Aerospace |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2226-4310/8/2/28 |
| _version_ | 1797407738365476864 |
|---|---|
| author | Rasoul Sanaei Brian Alphonse Pinto Volker Gollnick |
| author_facet | Rasoul Sanaei Brian Alphonse Pinto Volker Gollnick |
| author_sort | Rasoul Sanaei |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-09T03:45:58Z |
| format | Article |
| id | doaj.art-e5d7dcef313542b38823002952eee764 |
| institution | Directory Open Access Journal |
| issn | 2226-4310 |
| language | English |
| last_indexed | 2024-03-09T03:45:58Z |
| publishDate | 2021-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Aerospace |
| spelling | doaj.art-e5d7dcef313542b38823002952eee7642023-12-03T14:35:00ZengMDPI AGAerospace2226-43102021-01-01822810.3390/aerospace8020028Toward ATM Resiliency: A Deep CNN to Predict Number of Delayed Flights and ATFM DelayRasoul Sanaei0Brian Alphonse Pinto1Volker Gollnick2Deutsches Zentrum für Luft- und Raumfahrt (DLR), Lufttransportsysteme, 21079 Hamburg, GermanyFaculty of Mechanical Engineering, Hamburg University of Technology (TUHH), 21073 Hamburg, GermanyDeutsches Zentrum für Luft- und Raumfahrt (DLR), Lufttransportsysteme, 21079 Hamburg, GermanyThe 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.https://www.mdpi.com/2226-4310/8/2/28ATFM delayCNNresiliencecapacity regulations |
| spellingShingle | Rasoul Sanaei Brian Alphonse Pinto Volker Gollnick Toward ATM Resiliency: A Deep CNN to Predict Number of Delayed Flights and ATFM Delay Aerospace ATFM delay CNN resilience capacity regulations |
| title | Toward ATM Resiliency: A Deep CNN to Predict Number of Delayed Flights and ATFM Delay |
| title_full | Toward ATM Resiliency: A Deep CNN to Predict Number of Delayed Flights and ATFM Delay |
| title_fullStr | Toward ATM Resiliency: A Deep CNN to Predict Number of Delayed Flights and ATFM Delay |
| title_full_unstemmed | Toward ATM Resiliency: A Deep CNN to Predict Number of Delayed Flights and ATFM Delay |
| title_short | Toward ATM Resiliency: A Deep CNN to Predict Number of Delayed Flights and ATFM Delay |
| title_sort | toward atm resiliency a deep cnn to predict number of delayed flights and atfm delay |
| topic | ATFM delay CNN resilience capacity regulations |
| url | https://www.mdpi.com/2226-4310/8/2/28 |
| work_keys_str_mv | AT rasoulsanaei towardatmresiliencyadeepcnntopredictnumberofdelayedflightsandatfmdelay AT brianalphonsepinto towardatmresiliencyadeepcnntopredictnumberofdelayedflightsandatfmdelay AT volkergollnick towardatmresiliencyadeepcnntopredictnumberofdelayedflightsandatfmdelay |