An Evolutionary Optimization Approach to Maximize Runway Throughput Capacity for Hub and Spoke Airports

Ahmed, Shohel; Alam, Sameer

doi:10.1007/978-3-319-28270-1_26

Cited by 7 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Air traffic control is a complex domain requiring timely and accurate decision-making to ensure safety and efficiency [30], [31]. However, there are growing concerns regarding air traffic controllers' trust in increasingly autonomous systems.…”

Section: Related Work On Building Trust In Ai For Air Traffic Controlmentioning

confidence: 99%

X-Fuzz: An Evolving and Interpretable Neuro-Fuzzy Learner for Data Streams

Ferdaus,

Dam,

Alam

et al. 2024

IEEE Trans. Artif. Intell.

View full text Add to dashboard Cite

While evolving neuro-fuzzy systems have shown promise for learning from non-stationary streaming data with concept drift, most existing models lack transparency due to the limited interpretability of Takagi-Sugeno fuzzy architecture's linear rule consequents. The lack of transparency limits the reliability of crucial applications. To address this limitation, this paper proposes a new evolving neuro-fuzzy system called X-Fuzz that enhances interpretability by integrating the LIME technique to provide local explanations and evaluates them using faithfulness and monotonicity metrics. X-Fuzz is rigorously tested on streaming datasets with diverse concept drifts via prequential analysis. Experiments demonstrate X-Fuzz's capabilities in mining insights from large and dynamic data streams exhibiting diverse concept drifts including abrupt, gradual, recurring contextual, and cyclical drifts. In addition, for online runway exit prediction using real aviation data, X-Fuzz achieved 98.04% accuracy, significantly exceeding recent methods. With its balance of efficiency and transparency, X-Fuzz represents a promising approach for trustworthy evolving artificial intelligence that can handle complex, non-stationary data streams in critical realworld settings. We have made the X-Fuzz source code available in https://github.com/m-ferdaus/X Fuzz for reproducibility and facilitating future research.Impact Statement-The transparency of current evolving neuro-fuzzy systems restricts trustworthiness, limiting adoption in critical real-world applications. X-Fuzz tackles this barrier by transparently learning from non-stationary data via integrated local explanations and rigorous explanation evaluation. In online runway exit prediction, X-Fuzz achieves 98.04% accuracy, exceeding recent models by 6.7%. With its balanced efficiency and transparency, X-Fuzz significantly advances reliable and interpretable evolving AI. By making model behaviors traceable, X-Fuzz expands the safe deployment of adaptive intelligent systems in mission-critical settings across domains. Overall, X-Fuzz enables trustworthy neuro-fuzzy learners that incrementally adapt to dynamic data, overcoming reliability barriers and driving real-world impact.

show abstract

Section: Related Work On Building Trust In Ai For Air Traffic Controlmentioning

confidence: 99%

X-Fuzz: An Evolving and Interpretable Neuro-Fuzzy Learner for Data Streams

Ferdaus,

Dam,

Alam

et al. 2024

IEEE Trans. Artif. Intell.

View full text Add to dashboard Cite

show abstract

“…The results showed that their proposed model achieved 79% accuracy rate of the decision variable which determined whether a flight rolled out runway exit following the procedure or not. Ahmed et al (2016) [16] proposed an evolutionary optimization approach to maximize runway capacity for arrival and departure on a single runway. The results showed that their proposed model increased the throughput by 3 per hour and decreased processing time by 200 s compared to First-Come First-Serve (FCFS) conventional approach.…”

Section: Introductionmentioning

confidence: 99%

Data-Driven Simulation for Evaluating the Impact of Lower Arrival Aircraft Separation on Available Airspace and Runway Capacity at Tokyo International Airport

et al. 2021

View full text Add to dashboard Cite

Although the application of new wake turbulence categories, the so-called “RECAT (wake turbulence category re-categorization)”, will realize lower aircraft separation minima and directly increase runway throughput, the impacts of increasing arrival traffic on the surrounding airspace and arrival traffic flow as a whole have not yet been discussed. This paper proposes a data-driven simulation approach and evaluates the effectiveness of the lower aircraft separation in the arrival traffic at the target airport. The maximum runway capacity was clarified using statistics on aircraft types, stochastic distributions of inter-aircraft time and runway occupancy time, and the levels of the automation systems that supported air traffic controllers’ separation work. Based on the estimated available runway capacity, simulation models were proposed by analyzing actual radar track and flight plan data during the 6 months between September 2019 and February 2020, under actual operational constraints and weather conditions. The simulation results showed that the application of RECAT would reduce vectoring time in the terminal area by 7% to 10% under the current airspace and runway capacity when following a first-come first-served arrival sequence. In addition, increasing airspace capacity by 10% in the terminal area could dramatically reduce en-route and takeoff delay times while keeping vectoring time the same as under the current operation in the terminal area. These findings clarified that applying RECAT would contribute to mitigating air traffic congestion close to the airport, and to reducing delay times in arrival traffic as a whole while increasing runway throughput. The simulation results demonstrated the relevance of the theoretical results given by queue-based approaches in the authors’ past studies.

show abstract

“…For the aircraft sequencing problem, some meta-heuristic techniques have been proposed in the literature [14][15][16][17]. These approaches consider maximizing runway capacity by finding optimal sequences for arrival and/or departure.…”

Section: Introductionmentioning

confidence: 99%

A Cooperative Co-Evolutionary Optimisation Model for Best-Fit Aircraft Sequence and Feasible Runway Configuration in a Multi-Runway Airport

2018

Self Cite

View full text Add to dashboard Cite

A careful arrival and departure sequencing of aircraft can reduce the inter-arrival/departure time, thereby opening up opportunities for new landing and/or take-off slots, which may increase the runway throughput. This sequence when serviced with a suitable runway configuration may result in an optimal aircraft sequence with a runway configuration that can process the maximum number of aircraft within a given time interval. In this paper, we propose a Cooperative Co-evolutionary Genetic Algorithm (CCoGA) to find the combined solution of a best-fit sequence with a feasible runway configuration for a given traffic demand at an airport. The aircraft sequence and the runway configuration are modelled as individual species, which can cooperatively interact with each other. Therefore, we computationally evolve the best possible combination of aircraft sequence (arrival and departure) and the feasible runway configuration. The proposed CCoGA algorithm is evaluated for Chicago O’Hare International Airport runway layout and resulting configurations. Arrival and departure traffic demand is modelled through a Poisson distribution. Two different arrival/departure sequencing methods, i.e., constraint position shifting with one, two and N-position shifting and first come first serve, are modelled. Runway configuration and traffic sequence (arrivals and departure) are modelled as two species, which are evolved co-operatively, through the CCoGA algorithm, to achieve the optimal traffic sequencing with a feasible runway configuration. Time-space diagrams are presented for the best-evolved population of arrival-departure sequence and runway configuration to illustrate the possibility of using available departure slots between arrivals to maximize capacity. Arrival-departure capacity envelopes are then presented to illustrate the trade-off between the arrivals and departures, given a runway configuration for each sequencing method. Results demonstrate the high mutual dependence between arrival-departure sequence and the runway configuration, as well as its effect on overall runway capacity. The results also demonstrate the viability of using evolutionary computation-based methods for modelling and evaluating complex problems in the air transport domain.

show abstract

An Evolutionary Optimization Approach to Maximize Runway Throughput Capacity for Hub and Spoke Airports

Cited by 7 publications

References 9 publications

X-Fuzz: An Evolving and Interpretable Neuro-Fuzzy Learner for Data Streams

X-Fuzz: An Evolving and Interpretable Neuro-Fuzzy Learner for Data Streams

Data-Driven Simulation for Evaluating the Impact of Lower Arrival Aircraft Separation on Available Airspace and Runway Capacity at Tokyo International Airport

A Cooperative Co-Evolutionary Optimisation Model for Best-Fit Aircraft Sequence and Feasible Runway Configuration in a Multi-Runway Airport

Contact Info

Product

Resources

About