A Study on the Feasibility of Using a Genetic Algorithm to Generate Realistic Air Traffic Scenarios Based on Recorded Field Data

Oaks, Robert D.; Hughes, W. J.

doi:10.2514/6.2002-4767

Cited by 5 publications

(2 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Two hours of traffic data was extracted and time-shifted to generate a scenario with a total of 211 aircraft-to-aircraft conflicts. The method used to generate this timeshifted traffic sample of conflicts is documented in [7] and [8]. The experiment used the same traffic scenario throughout and only altered the weather forecast files.…”

Section: Design Of Experimentsmentioning

confidence: 99%

Aircraft conflict probe sensitivity to weather forecasts errors

Paglione

Ryan

2007

2007 IEEE/AIAA 26th Digital Avionics Systems Conference

View full text Add to dashboard Cite

This study investigated the User Request Evaluation Tool's (URET) prediction sensitivity to weather forecast error. A quantitative experiment was designed and performed by the Federal Aviation Administration's Conflict Probe Assessment Team (CPAT) to evaluate the impact of weather forecast errors on URET trajectory and conflict predictions. The experiment used approximately two hours of traffic data recorded at the Indianapolis en route center in May 1999. The flights were time shifted to generate a sufficient number of test conflicts using a genetic algorithm technique developed by CPAT. The resulting scenario was input into the URET Prototype System. To induce weather forecast error, the weather input file (Rapid Update Cycle, RUC) was altered by adding 20 or 60 knots to the wind magnitude, 45 or 90 degrees to the wind direction, and 5 or 15 degrees Kelvin to the air temperature. This produced seven URET runs for the experiment -the unaltered control run and six treatment runs. The analysis compared the control run against the treatment runs. A methodology was developed to compare the trajectory and conflict prediction accuracy of these runs. A statistical analysis provided evidence that the forecast errors in wind magnitude and direction had significant effect on the longitudinal trajectory error and a modest impact on retracted false alerts, which caused at most an increase in the false alert probability by six percent. It also showed that the air temperature runs did not have a significant effect. Based on this experiment, a controller suspecting errors in the input wind forecast should expect only a modest impact on URET predictions. The impact would mainly be a moderate increase in the number of retractions of its conflict predictions (defined in this study as a retracted false alert).

show abstract

Section: Design Of Experimentsmentioning

confidence: 99%

Aircraft conflict probe sensitivity to weather forecasts errors

Paglione

Ryan

2007

2007 IEEE/AIAA 26th Digital Avionics Systems Conference

View full text Add to dashboard Cite

show abstract

“…A genetic algorithm is a stochastic process that is a special case of a class of algorithms called Random Heuristic Search algorithms [7]. The feasibility of its use for time shifting scenarios is documented in [8] and its implementation by CPAT is documented in [9]. In this implementation the genetic algorithm finds a set of time shift values -one for each flight in the scenario -so that the distribution of the aircraft-to-aircraft encounters meet user specified constraints.…”

Section: Time Shifting Using a Genetic Algorithmmentioning

confidence: 99%

Time Shifting Air Traffic Data for Quantitative Evaluation of a Conflict Probe

Paglione¹,

Hughes²,

Oaks³

et al. 2003

AIAA Guidance, Navigation, and Control Conference and Exhibit

Self Cite

View full text Add to dashboard Cite

A conflict probe is an air traffic management decision support tool that predicts aircraft-to-aircraft and aircraft-to-airspace conflicts. In order to achieve the confidence of the air traffic controllers who are provided this tool, a conflict probe must accurately predict these conflicts. This paper discusses how a conflict probe's quantitative accuracy requirements can be tested using hypothesis testing techniques. The paper also asserts that air traffic scenarios based on recorded field data are essential to the evaluation of a conflict probe and states that time shifting these scenarios can create data samples necessary to perform the hypothesis testing. This paper then compares three time shifting techniques: time compression, random time adjustment, and an implementation of a genetic algorithm.

show abstract

Generation of realistic air traffic scenarios using a genetic algorithm

Oaks¹,

Paglione²

Proceedings. The 21st Digital Avionics Systems Conference

View full text Add to dashboard Cite

A Study on the Feasibility of Using a Genetic Algorithm to Generate Realistic Air Traffic Scenarios Based on Recorded Field Data

Cited by 5 publications

References 2 publications

Aircraft conflict probe sensitivity to weather forecasts errors

Aircraft conflict probe sensitivity to weather forecasts errors

Time Shifting Air Traffic Data for Quantitative Evaluation of a Conflict Probe

Generation of realistic air traffic scenarios using a genetic algorithm

Contact Info

Product

Resources

About