Estimating Taxi-out times with a reinforcement learning algorithm

Abstract

Flight delays have a significant impact on the nation's economy. Taxi-out delays in particular constitute a significant portion of the block time of a flight. In the future, it can be expected that accurate predictions of 'wheels-off' time may be used in determining whether an aircraft can meet its allocated slot time, thereby fitting into an en-route traffic flow. Without an accurate taxi-out time prediction for departures, there is no way to effectively manage fuel consumption, emissions, or cost. Dynamically changing operations at the airport makes it difficult to accurately predict taxiout time. This paper describes a method for estimating average taxi-out times at the airport in 15 minute intervals of the day and at least 15 minutes in advance of aircraft scheduled gate push-back time. A probabilistic framework of stochastic dynamic programming with a learning-based solution strategy called Reinforcement Learning (RL) has been applied. Historic data from the Federal Aviation Administration's (FAA) Aviation System Performance Metrics (ASPM) database were used to train and test the algorithm. The algorithm was tested on John F. Kennedy International airport (JFK), one of the busiest, challenging, and difficult to predict airports in the United States that significantly influences operations across the entire National Airspace System (NAS). Due to the nature of departure operations at JFK the prediction accuracy of the algorithm for a given day was analyzed in two separate time periods (1) before 4:00 P.M and (2) after 4:00 P.M. On an average across 15 days, the predicted average taxi-out times matched the actual average taxi-out times within ±5 minutes for about 65 % of the time (for the period before 4:00 P.M) and 53 % of the time (for the period after 4:00 P.M). The prediction accuracy over the entire day within ±5 minutes range of accuracy was about 60 %. Further, application of the RL algorithm to estimate taxi-out times at airports with multidependent static surface surveillance data will likely improve the accuracy of prediction. The implications of these results for airline operations and network flow planning are discussed.

Taxi-Out Time Prediction for Departures at Charlotte Airport Using Machine Learning Techniques

“…11 In addition, reinforcement learning algorithms were developed and investigated to check the accuracy of taxi-out time prediction at several major airports in the United States. [12][13][14] Various regression methods, including multiple linear regression, least median squared linear regression, support vector regression, model trees, and fuzzy rule-based systems, were also applied to several airports in Europe for taxi time prediction problems. 15,16 Each machine learning method was independently applied to the limited test data at different airports under different conditions, and therefore the prediction performance varied with the prediction model.…”

Aircraft taxi time prediction: Comparisons and insights

“…With the introduction of Collaborative Decision Making (CDM) systems at airports within the last few years, practitioners at airports realised the need for having more accurate taxi times and, driven by that, more researchers have analysed the problem of taxi time prediction. Several authors have published their results about taxi-out time prediction at US airports [7,8,9,10,11,12]. Balakrishna et al [7,8,9, 11] used a reinforcement learning algorithm which showed good results for data from Detroit International Airport (DTW) and Tampa International Airport (TPA), but the results were not very consistent for data from John F. Kennedy International Airport (JFK).…”

“…Several authors have published their results about taxi-out time prediction at US airports [7,8,9,10,11,12]. Balakrishna et al [7,8,9, 11] used a reinforcement learning algorithm which showed good results for data from Detroit International Airport (DTW) and Tampa International Airport (TPA), but the results were not very consistent for data from John F. Kennedy International Airport (JFK). However, this approach cannot provide the same insights into the problem as some other approaches.…”

Algorithms for Reinforcement Learning

“…Value prediction problems arise in a number of ways: Estimating the probability of some future event, the expected time until some event occurs, or the (action-)value function underlying some policy in an MDP are all value prediction problems. Specific applications are estimating the failure probability of a large power grid (Frank et al, 2008) or estimating taxi-out times of flights on busy airports (Balakrishna et al, 2008), just to mention two of the many possibilities.…”