Improving Etms' Ground Time Predictions

You are here: Homepage > Search

Improving Etms' Ground Time Predictions

Futer, Aron

An algorithm is proposed that improves predictions of the flights' wheels-up times. FAA's Enhanced Traffic Management System (ETMS) has been developed to assist Air Traffic Control in making air traffic planning decisions. One of the main ETMS functions is to predict the future demand for the elements of National Air Space (NAS) - airports, sectors, and fixes. The main source of ETMS errors in demand prediction is directly attributed to departure time errors. Departure times enter the system with flight plans filed by NAS users. ETMS uses a special function - Ground Time Predictor (GTP) that was developed to adjust the filed departure times and thus reduce the errors. This paper is aimed at analysis of the GTP with two goals in mind: to prove the GTP effectiveness and to propose ways to further improve ETMS ground time predictions. For the first goal, the paper proves that the GTP reduces the errors in estimating flights' departure times and makes the error distributions narrower. For this study, a metric was developed to quantitatively measure the effectiveness of the GTP. According to the metric, the GTP provides about 15% reduction in departure time error. The metric also demonstrates that there might be room for further improvement. For the second goal, this paper proposes an algorithm that reduces departure time error in case of large departure delays.