A multi-agent approach for reactionary delay prediction of flights
Flight schedules are highly sensitive to delays and witness these events on a very frequent basis. In an interconnected and interdependent air transportation system, these delays can magnify and cascade as the flight itineraries progress, causing reactionary delays. The airlines, passengers and airp...
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/144370 |
| _version_ | 1811680761958367232 |
|---|---|
| author | Guleria, Yash Cai, Qing Alam, Sameer Li, Lishuai |
| author2 | School of Mechanical and Aerospace Engineering |
| author_facet | School of Mechanical and Aerospace Engineering Guleria, Yash Cai, Qing Alam, Sameer Li, Lishuai |
| author_sort | Guleria, Yash |
| collection | NTU |
| description | Flight schedules are highly sensitive to delays and witness these events on a very frequent basis. In an interconnected and interdependent air transportation system, these delays can magnify and cascade as the flight itineraries progress, causing reactionary delays. The airlines, passengers and airports bear the negative economic implications of such phenomenon. The current research draws motivation from this behavior and develops a multi-agent based method to predict the reactionary delays of flights, given the magnitude of primary delay that the flights witness at the beginning of the itinerary. Every flight is modeled as an agent which functions in a dynamic airport environment, receives information about other agents and updates its own arrival and departure schedule. To evaluate the performance of the method, this paper carries out a case study on the flights in Southeast Asia, which covers eleven countries. The model is tested on a six-month ADS-B dataset that is collected for the calendar year 2016. Through the reactionary delay values predicted by the multi-agent based method, the flights are first classified as delayed or un-delayed in terms of departure. The classification results show an average accuracy of 80.7%, with a delay classification threshold of 15 minutes. Further, a delay multiplier index is evaluated, which is a ratio of the total delays (primary+reactionary delays) and the primary delays for each aircraft. The majority of delay multiplier values range between 1-1.5, which signifies that for except a few outliers, the primary delays do not significantly cascade into reactionary delays for the flights in Southeast Asia. The outliers represent scenarios where primary delays magnify and propagate as reactionary delays over subsequent flight legs. Therefore, the proposed method can assist in better flight scheduling by identifying itineraries which experience higher reactionary delays. |
| first_indexed | 2024-10-01T03:30:12Z |
| format | Journal Article |
| id | ntu-10356/144370 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:30:12Z |
| publishDate | 2020 |
| record_format | dspace |
| spelling | ntu-10356/1443702020-11-07T20:10:45Z A multi-agent approach for reactionary delay prediction of flights Guleria, Yash Cai, Qing Alam, Sameer Li, Lishuai School of Mechanical and Aerospace Engineering Air Traffic Management Research Institute Engineering::Aeronautical engineering Air Traffic Management Agent Based Method Flight schedules are highly sensitive to delays and witness these events on a very frequent basis. In an interconnected and interdependent air transportation system, these delays can magnify and cascade as the flight itineraries progress, causing reactionary delays. The airlines, passengers and airports bear the negative economic implications of such phenomenon. The current research draws motivation from this behavior and develops a multi-agent based method to predict the reactionary delays of flights, given the magnitude of primary delay that the flights witness at the beginning of the itinerary. Every flight is modeled as an agent which functions in a dynamic airport environment, receives information about other agents and updates its own arrival and departure schedule. To evaluate the performance of the method, this paper carries out a case study on the flights in Southeast Asia, which covers eleven countries. The model is tested on a six-month ADS-B dataset that is collected for the calendar year 2016. Through the reactionary delay values predicted by the multi-agent based method, the flights are first classified as delayed or un-delayed in terms of departure. The classification results show an average accuracy of 80.7%, with a delay classification threshold of 15 minutes. Further, a delay multiplier index is evaluated, which is a ratio of the total delays (primary+reactionary delays) and the primary delays for each aircraft. The majority of delay multiplier values range between 1-1.5, which signifies that for except a few outliers, the primary delays do not significantly cascade into reactionary delays for the flights in Southeast Asia. The outliers represent scenarios where primary delays magnify and propagate as reactionary delays over subsequent flight legs. Therefore, the proposed method can assist in better flight scheduling by identifying itineraries which experience higher reactionary delays. Published version 2020-11-02T05:25:28Z 2020-11-02T05:25:28Z 2019 Journal Article Guleria, Y., Cai, Q., Alam, S., & Li, L. (2019). A multi-agent approach for reactionary delay prediction of flights. IEEE Access, 7, 181565-181579. doi:10.1109/ACCESS.2019.2957874 2169-3536 https://hdl.handle.net/10356/144370 10.1109/ACCESS.2019.2957874 7 181565 181579 en IEEE Access © 2019 IEEE. This work is licensed under a Creative Commons Attribution 4.0 License. For more information, see http://creativecommons.org/licenses/by/4.0/ application/pdf |
| spellingShingle | Engineering::Aeronautical engineering Air Traffic Management Agent Based Method Guleria, Yash Cai, Qing Alam, Sameer Li, Lishuai A multi-agent approach for reactionary delay prediction of flights |
| title | A multi-agent approach for reactionary delay prediction of flights |
| title_full | A multi-agent approach for reactionary delay prediction of flights |
| title_fullStr | A multi-agent approach for reactionary delay prediction of flights |
| title_full_unstemmed | A multi-agent approach for reactionary delay prediction of flights |
| title_short | A multi-agent approach for reactionary delay prediction of flights |
| title_sort | multi agent approach for reactionary delay prediction of flights |
| topic | Engineering::Aeronautical engineering Air Traffic Management Agent Based Method |
| url | https://hdl.handle.net/10356/144370 |
| work_keys_str_mv | AT guleriayash amultiagentapproachforreactionarydelaypredictionofflights AT caiqing amultiagentapproachforreactionarydelaypredictionofflights AT alamsameer amultiagentapproachforreactionarydelaypredictionofflights AT lilishuai amultiagentapproachforreactionarydelaypredictionofflights AT guleriayash multiagentapproachforreactionarydelaypredictionofflights AT caiqing multiagentapproachforreactionarydelaypredictionofflights AT alamsameer multiagentapproachforreactionarydelaypredictionofflights AT lilishuai multiagentapproachforreactionarydelaypredictionofflights |