01090147

Component

https://doi.org/10.3141/2052-07

http://scholar.google.com...erry&publication_year=2008

Flight delay is one of the pressing problems that have far-reaching effects on society and the nation’s economy. A primary cause of flight delay in the National Airspace System is high taxi-out times (time between gate push-back and wheels-off) at major airports. Accurate prediction of taxi-out time is needed to make downstream schedule adjustments and for better departure planning, which could mitigate delays, emissions, and congestion on the ground. However, accurate prediction of taxi-out time is difficult because of uncertainties associated with the dynamically changing airport operation. A novel stochastic approximation scheme based on reinforcement learning (RL) is presented for predicting taxi-out times in the presence of weather and other departure-related uncertainties. The prediction problem is cast in a probabilistic framework of stochastic dynamic programming and solved by using approximate dynamic programming approaches (particularly RL). The strengths of the method are that it is nonparametric, unlike regression models with fixed parameters, it is highly adaptable to the dynamic airport environment since it is learning based, it is scalable, it is inexpensive since it does not need highly sophisticated surface management systems, and it can effectively handle uncertainties because of the probabilistic framework. Taxi-out prediction performance was tested on data obtained from the FAA Aviation System Performance Metrics database on Detroit International and Washington Reagan National Airports. Results show that the root-mean-square prediction error calculated 15 min before gate departure time is on average 2.9 min for about 80% of the predicted flights.

01111962

English

pp 54-61

2008

Transportation Research Record: Journal of the Transportation Research Board

9780309113168

Print

Figures (4) ; References (41) ; Tables (1)

Airport operations; Aviation; Departure time; Dynamic programming; Flight delays; Mathematical prediction; Stochastic programming; Taxiing; Uncertainty

Detroit Metropolitan Wayne County Airport; Ronald Reagan Washington National Airport

Reinforcement learning; Taxi-out time

Aviation; Data and Information Technology; Highways; Planning and Forecasting; Terminals and Facilities

TRIS, TRB, ATRI

Jan 29 2008 3:36PM

• Applications of Geographic Information System in Airfield Infrastructure System Management and Maintenance
• Are Low-Cost Carriers a Bargain? Comparison of Low-Cost and Full-Service Carriers in Southeast Asia
• Comparative Analysis of Regional Airline Industry in Europe and North America and Some Insights into Current Developments
• Cost of Aviation Infrastructure in the United States
• Evaluating Airline Service Quality by Data Envelopment Analysis
• Forecasting Model for Air Taxi, Commercial Airline, and Automobile Demand in the United States
• Multifactor Model for Predicting Delays at U.S. Airports
• Real-Time Intermodal Substitution: Strategy for Airline Recovery from Schedule Perturbation and for Mitigation of Airport Congestion
• Segmentation and Positioning Analysis for International Air Travel Market: Taipei-to-Tokyo Route
• Sensitivity Analysis of Engineered Material Arrestor Systems to Aircraft and Arrestor Material Characteristics
• Short-Haul Airline Crew Rostering by Using Inequality-Based Multiobjective Genetic Algorithm
• Statistical Comparison of Passenger Trip Delay and Flight Delay Metrics
• Toward Time-Based Separation Rules for Landing Aircraft