TY - GEN
T1 - Deep Reinforcement Learning for Real-Time Ground Delay Program Revision and Corresponding Flight Delay Assignments
AU - Liu, Ke
AU - Hu, Fan
AU - Lin, Hui
AU - Cheng, Xi
AU - Chen, Jianan
AU - Song, Jilin
AU - Feng, Siyuan
AU - Su, Gaofeng
AU - Zhu, Chen
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - This paper explores the optimization of Ground Delay Programs (GDP), a prevalent Traffic Management Initiative used in Air Traffic Management (ATM) to reconcile capacity and demand discrepancies at airports. Employing Reinforcement Learning (RL) to manage the inherent uncertainties in the national airspace system-such as weather variability, fluctuating flight demands, and airport arrival rates-we developed two RL models: Behavioral Cloning (BC) and Conservative Q-Learning (CQL). These models are designed to enhance GDP efficiency by utilizing a sophisticated reward function that integrates ground and airborne delays and terminal area congestion. We constructed a simulated single-airport environment, SAGDP_ENV, which incorporates real operational data along with predicted uncertainties to facilitate realistic decision-making scenarios. Utilizing the whole year 2019 data from Newark Liberty International Airport (EWR), our models aimed to preemptively set airport program rates. Despite thorough modeling and simulation, initial outcomes indicated that the models struggled to learn effectively, attributed potentially to oversimplified environmental assumptions. This paper discusses the challenges encountered, evaluates the models' performance against actual operational data, and outlines future directions to refine RL applications in ATM.
AB - This paper explores the optimization of Ground Delay Programs (GDP), a prevalent Traffic Management Initiative used in Air Traffic Management (ATM) to reconcile capacity and demand discrepancies at airports. Employing Reinforcement Learning (RL) to manage the inherent uncertainties in the national airspace system-such as weather variability, fluctuating flight demands, and airport arrival rates-we developed two RL models: Behavioral Cloning (BC) and Conservative Q-Learning (CQL). These models are designed to enhance GDP efficiency by utilizing a sophisticated reward function that integrates ground and airborne delays and terminal area congestion. We constructed a simulated single-airport environment, SAGDP_ENV, which incorporates real operational data along with predicted uncertainties to facilitate realistic decision-making scenarios. Utilizing the whole year 2019 data from Newark Liberty International Airport (EWR), our models aimed to preemptively set airport program rates. Despite thorough modeling and simulation, initial outcomes indicated that the models struggled to learn effectively, attributed potentially to oversimplified environmental assumptions. This paper discusses the challenges encountered, evaluates the models' performance against actual operational data, and outlines future directions to refine RL applications in ATM.
KW - airport capacity
KW - Ground Delay Program
KW - operational uncertainties
KW - reinforcement learning
KW - time sequential decision
UR - https://www.scopus.com/pages/publications/105001670530
U2 - 10.1109/ITSC58415.2024.10920242
DO - 10.1109/ITSC58415.2024.10920242
M3 - Conference article published in proceeding or book
AN - SCOPUS:105001670530
T3 - IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC
SP - 1302
EP - 1307
BT - 2024 IEEE 27th International Conference on Intelligent Transportation Systems, ITSC 2024
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 27th IEEE International Conference on Intelligent Transportation Systems, ITSC 2024
Y2 - 24 September 2024 through 27 September 2024
ER -