Bayesian Network Modelling of ATC Complexity Metrics for Future SESAR Demand and Capacity Balance Solutions
| Autor: | Danlin Zheng, Eva María Puntero Parla, Rosa María Arnaldo Valdés, Manuel Villegas Díaz, Victor Fernando Gómez Comendador |
|---|---|
| Jazyk: | angličtina |
| Předmět: |
0209 industrial biotechnology
Operations research Computer science media_common.quotation_subject SESAR Capacity Management General Physics and Astronomy lcsh:Astrophysics 02 engineering and technology Article Set (abstract data type) 020901 industrial engineering & automation lcsh:QB460-466 0202 electrical engineering electronic engineering information engineering Quality (business) DAC lcsh:Science Single European Sky uncertainty TBO DCB media_common FCA Bayesian network Air traffic control Capacity management lcsh:QC1-999 Bayesian networks Trajectory Key (cryptography) lcsh:Q 020201 artificial intelligence & image processing complexity lcsh:Physics |
| Zdroj: | Entropy Volume 21 Issue 4 Entropy, Vol 21, Iss 4, p 379 (2019) |
| ISSN: | 1099-4300 |
| DOI: | 10.3390/e21040379 |
| Popis: | Demand & Capacity Management solutions are key SESAR (Single European Sky ATM Research) research projects to adapt future airspace to the expected high air traffic growth in a Trajectory Based Operations (TBO) environment. These solutions rely on processes, methods and metrics regarding the complexity assessment of traffic flows. However, current complexity methodologies and metrics do not properly take into account the impact of trajectories&rsquo uncertainty to the quality of complexity predictions of air traffic demand. This paper proposes the development of several Bayesian network (BN) models to identify the impacts of TBO uncertainties to the quality of the predictions of complexity of air traffic demand for two particular Demand Capacity Balance (DCB) solutions developed by SESAR 2020, i.e., Dynamic Airspace Configuration (DAC) and Flight Centric Air Traffic Control (FCA). In total, seven BN models are elicited covering each concept at different time horizons. The models allow evaluating the influence of the &ldquo complexity generators&rdquo in the &ldquo complexity metrics&rdquo Moreover, when the required level for the uncertainty of complexity is set, the networks allow identifying by how much uncertainty of the input variables should improve. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
| Nepřihlášeným uživatelům se plný text nezobrazuje | K zobrazení výsledku je třeba se přihlásit. |