Comparative Analysis of Departure Metering at United States and European Airports

Badrinath, Sandeep; Balakrishnan, Hamsa; Ma, Ji; Delahaye, Daniel

doi:10.2514/1.d0179

Cited by 11 publications

(14 citation statements)

References 18 publications

(27 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…resulting in periods of higher demand-capacity imbalance, leading to the formation of larger queues [10]. To evaluate performance of the proposed DRL approach in different environment complexities (other than the one it is trained on) we run experiments with varying fleet-sizes (refer Fig.…”

Section: Methodsmentioning

confidence: 99%

“…This lowers chances of formation of congestion hotspots in the airside network, which in turn reduces Air Traffic Controller's (ATCO) workload [7]. Recent approaches have employed handcrafted multiinteger linear programming models [8], cell transmission models [9], queuing models [10], statistical models [7] etc. to model airside traffic flow.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Reinforcement Learning Based Airport Departure Metering

Ali

Thinh

Alam

2021

2021 IEEE International Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

Airport taxi delays adversely affect airports and airlines around the world in terms of congestion, operational workload, and environmental emissions. Departure Metering (DM) is a promising approach to contain taxi delays by controlling departure pushback times. The key idea behind DM is to transfer aircraft waiting time from taxiways to gates. State-of-the-art DM methods use model-based control policies that rely on airside departure modeling to obtain simplified analytical equations. Consequently, these models fail to capture non-stationarity existing in the complex airside operations and the policies perform poorly under uncertainties. In this work, we propose model-free and learning-based DM using Deep Reinforcement Learning (DRL) approach to reduce taxi delays while meeting flight schedule constraints. We cast the DM problem in an MDP framework and develop a representative airport simulator to simulate airside operations and evaluate the learnt DM policy. For effective state representation, we introduce features to capture both local and airport-wide congestion levels. Finally, the performance of multiple agentssharing the same trained policy, is evaluated on different traffic densities. The proposed approach shows a reduction of up to 25% in taxi delays in medium traffic scenarios. Moreover, upon experiencing increased traffic density, taxi time savings achieved by proposed algorithm significantly increase while the average gate holding times do not increase as much. Results demonstrate that DRL can learn an effective DM policy to better manage airside traffic and contain congestion on the taxiways.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Reinforcement Learning Based Airport Departure Metering

Ali

Thinh

Alam

2021

2021 IEEE International Intelligent Transportation Systems Conference (ITSC)

View full text Add to dashboard Cite

show abstract

“…They indicated that further study was required to consider flight delays and the effects of metering outbound flights on arriving aircraft. Badrinath et al modeled outbound taxiing operations at CLT and Paris-Charles de Gaulle International Airport (CDG) as single queues and estimated potential fuel savings from metering that might be accomplished in the respective environments ( 15 ). As expected, potential savings were estimated to be greater at CLT than at CDG, where congestion was less severe.…”

Section: Related Literaturementioning

confidence: 99%

“…Badrinath et al estimated that the average fuel burn per second of taxing time for scheduled aircraft at CLT is 0.17 kg ( 15 ). In our simulation, there were 95 planes scheduled to be taxiing out in the peak periods and 713 departures scheduled for the full day.…”

Section: Experiments With Alternative Departure-release Strategiesmentioning

confidence: 99%

Study of the Potential Effects of Gate-Hold Strategies on Arrival and Departure Operations at Charlotte Douglas International Airport

Smith

Bilir

2022

Transportation Research Record

View full text Add to dashboard Cite

We employed discrete-event simulation with embedded multivariate statistical models for time and situation-dependent parameters to study the potential impact of regulating the release of planes from their terminal gates in peak periods to reduce congestion on ramps and taxiways at Charlotte Douglas International Airport, a major U.S. hub for of the world’s largest airline, American Airlines. Gate-holding strategies are one of several operational strategies to reduce aviation’s carbon footprint. They have been shown to reduce fuel consumption, air pollution, and greenhouse gas emissions, but past studies have concentrated on taxi times and fuel consumption of outbound aircraft without considering the potential disruptions on inbound traffic, which may be blocked from reaching their intended gates. We verified that reductions in outbound taxi times could be achieved without delaying the times when planes lifted off for departure but, depending on the gate-hold rules employed and the intensity of flight operations, more delays and gate changes occurred for arriving aircraft. Our models allow intensive examination of the tradeoffs involved in improving system performance with various strategies.

show abstract

“…Recent studies have employed handcrafted multi-integer linear programming models [8], cell transmission models [9], queuing models [10], statistical models [7] etc. to model airside trafc ow.…”

Section: Introductionmentioning

confidence: 99%