Airline Scheduling Research Articles

Taxi-out time prediction at Mohammed V Casablanca Airport

Airports are vital for global connectivity. However, the increasing volume of air travel has presented significant challenges in airport managing. Accurate predictions of taxi-out times (TXOT) offer potential to enhance airport performance, minimize delays, optimize airline schedules, and enhance customer satisfaction. This paper focuses on developing a machine learning model to forecast taxi-out times at Mohammed V Airport. Historical taxiing data from various airports will be analyzed to predict taxi-out times based on diverse runway-stand combinations and congestion levels. we used neural network (NN), support vector machines (SVM), and regression tree (RT) in order to create a real-time model that forecasts TXOT and congestion levels for different runway-stand combinations. The result showed that the NN model outperformed other forecasting models when their performances are compared using the mean absolute percentage error, root mean square error as accuracy measures.

Schedule-level optimization of flight block times for improved airline schedule planning: A data-driven approach

The development of flight block time schedules for future airline operations is a critical aspect of the schedule development process. It involves determining the appropriate gate-to-gate time for each flight to optimize on-time performance and ensure efficient utilization of flight resources. This article presents a modeling framework that addresses the airlines' scheduled block time (SBT) design problem. The framework employs a novel data-driven optimization model that incorporates reliability measures at both the flight and schedule levels. This approach enables airline schedule planners to assess the relationship between the allocated SBT for each flight and the overall schedule reliability, and make informed decisions regarding the trade-off between schedule reliability and operational costs. Experiments show that the proposed methodology outperforms real-world SBT plans implemented by two major U.S. airlines, demonstrating its superiority. The results of this comparison indicate that the developed framework could assist airlines in improving reliability while deploying the same block time budget or in eliminating unnecessary slack in their schedules while achieving their targeted reliability, resulting in significant cost savings.

Spatiotemporal Propagation Learning for Network-Wide Flight Delay Prediction

Accurate and interpretable delay predictions are vital for decision-making in the aviation industry. However, effectively incorporating spatiotemporal dependencies and external factors related to delay propagation remains a challenge. To address this challenge, we propose the SpatioTemporal Propagation Network (STPN), a novel space-time separable graph convolutional network that models delay propagation by considering both spatial and temporal factors. STPN uses a multi-graph convolution model that considers both geographic proximity and airline schedules from a spatial perspective, while employing a multi-head self-attention mechanism that can be learned end-to-end and explicitly accounts for various types of temporal dependencies in delay time series from a temporal perspective. Experiments on two real-world delay datasets show that STPN outperforms state-of-the-art methods for multi-step ahead arrival and departure delay prediction in large-scale airport networks. Additionally, the counterfactuals generated by STPN provide evidence of its ability to learn explainable delay propagation patterns. Comprehensive experiments also demonstrate that STPN sets a robust benchmark for general spatiotemporal forecasting. The code for STPN is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/Kaimaoge/STPN</uri> .

From Aviation to Web Standarts: Transformation of SSIM Files into JSON Format

Considering dynamic changes in the aviation sector, successful data exchange and integration planning plays a pivotal role in maintaining operational efficiency of airlines. Although the SSIM (Standard Schedules Information Manual) file is considered a reliable format, it has certain limitations regarding interaction and compatibility with other web technologies and programs due to its text format strictly defined by the specification. In this work, we propose an approach to convert SSIM files into the JSON (JavaScript Object Notation) format. One of the central aspects of this work is a detailed transformation model that considers all the important structures and levels of information of the SSIM file, conducts their syntactic analysis, and converts them into a flexible and easily recoverable JSON format. To transform a set of aviation flights into a combined flying line, a modified branch and bound method is used. With a series of examples and experiments, the article aims to demonstrate the effectiveness of this methodology in terms of preserving data integrity and ensuring their accuracy. In particular, the problems faced during the transformation, for example, how to consider the consistency of data rows with fixed width in the SSIM file, are considered. The transition from aviation-oriented formats, such as the SSIM file, to global web formats, such as JSON, is a process that goes beyond technologies and aims to increase the flexibility and convenience of collaboration, as well as data processing in the aviation industry. This research helps to implement this change, offering a simple, effective, and scalable approach for converting airline schedules into a format that by its nature meets the needs of modern information applications and systems.

Air–rail timetable synchronisation: Improving passenger connections in Europe within and across transportation modes

This study addresses the integration of the railway and airline scheduling problems, in order to offer passengers smooth transfers between rail and air. This paper focuses on optimising the air and rail timetables at 18 major European airports including three hubs and their associated train stations. A multimodal passenger demand simulation, using constraint programming and based on real data, is proposed. A typical week, from Monday to Saturday, of December 2019 is analysed. Ten passenger demand simulations are run for each day, resulting in 60 test instances that are publicly released. The air–rail timetable synchronisation is applied to these 60 instances. Three scenarios are tested in which each operator agrees to change its schedule or not. Results show that changing the schedule of only 13% of European flights by 11 min, and half of trains scheduled to stop at the three hubs of 17 min, on average, could increase the number of suitable connections for passengers by 60%. In addition, if both airlines and railway operators adapt their schedules, passenger comfort is improved and operator costs are reduced, even more so than with unilateral changes.

Airline scheduling optimization: literature review and a discussion of modelling methodologies

Abstract The rapid development of civil aviation in recent decades has not only led to increasing competition among airlines, but also to the rise of irregularities, with challenges concerning the improvement of regulations and schedules under the maximization of profitability. Consequently, the airline scheduling optimization problem has received significant research interest as the foundation for an efficient deployment of airline resources and meeting market demand under complex operational requirements. In this paper, we dissect fundamental airline scheduling problems by reviewing thirteen representative mathematical models for schedule design, fleet assignment, aircraft routing, crew scheduling subproblems and their potential for integration. In contrast to existing review studies on airline scheduling problems, our main contribution lies in the introduction of state-of-the-art mathematical models with a specific focus on integration and robustness. In addition, we highlight a set of promising, yet challenging, directions for future research in this domain.

Sustainable airline planning and scheduling

With sustainability becoming one of the core topics in politics, public discussion and, consequently, in various industries, the airline industry, as one of the major greenhouse gas emitters in the transport sector, has also come under scrutiny. Despite many advanced models for airline planning and scheduling, most models do not explicitly consider sustainability issues. Our paper extends existing research by including the five most strategic stages of the airline planning and scheduling process along with explicitly emphasizing sustainability considerations. We use the resulting mixed-integer quadratically constrained problem in a computational study to show that airlines in our setting can reduce the number of flights (and thereby the level of emissions) without the need to make a substantial sacrifice in profitability. Due to the complexity of the problem, the results also indicate the need for a solver specialized in efficiently solving mixed-integer convex problems.

Competitive integrated airline schedule design and fleet assignment

Airline profits are significantly influenced by competitive timetables that match passenger demand to fleet resources. In this research, we develop an integrated, mixed-integer optimization model to derive a comprehensive flight schedule, fleet assignment, and average airfares jointly. Passenger choice behavior is incorporated through a prospect theory-adjusted, nested, multinomial logit model which estimates market share. The competitive fleet assignment and schedule design (CFSD) formulation is embedded in a differentiated Bertrand game, such that each transport operator optimizes their best response function connected through the market share model. To solve the integrated optimization problem efficiently, a hybrid algorithm is developed that combines stabilized column generation with a large neighborhood search algorithm.The game-theoretic framework is applied to a case study in China involving legacy airlines, a low-cost carrier, and a high-speed rail (HSR) operator. The equilibrium outcomes suggest that the low-cost carrier is likely to stimulate demand and improve the level of service through secondary airports. The further development of high-speed rail service is expected to intensify competition among airlines and reduce the overall fare level. The low-cost carriers and HSR are able to significantly increase overall consumer surplus, providing insights into the potential for low-cost service in the Chinese aviation markets and the entrance of the public service obligation program at minimum cost.

Impact of the COVID-19 Pandemic on Multi-airport Systems Worldwide

This study examines the impacts of the COVID-19 pandemic on multi-airport systems (MASs) worldwide. First, the recent literature on MASs is reviewed to identify emerging research topics and development patterns. Then, airline schedule data are collected for 53 sample MASs and used to analyse three dimensions of MAS structures before and during the late stage of the pandemic: (i) traffic and degree centrality distribution within MASs, (ii) intra-MAS airport competition; and (iii) airline competition intensity within MASs. The empirical findings reveal that MAS structures in Europe and the US have remained relatively stable despite the recent pandemic, partly because compared with Asia Pacific, air travel bans in these markets were lifted earlier, and domestic and international airline markets have largely returned to pre-pandemic levels. In comparison, significant changes have been observed in Asia-Pacific MASs due to restrictive bans on international travel and airline operations. As major airlines shifted capacity to domestic markets, in Asia Pacific intra-MAS airport traffic distribution became more balanced, intra-MAS airport competition intensified, smaller airlines dropped out, and airline concentration levels increased. In addition, with more under-utilized slots available, Chinese low-cost carriers increasingly consolidated their operations to selected airports within MASs which would allow them to achieve economies of scale. Overall, this study provides insights into the adaptability of MAS structures in the face of a global crisis.

Network science approach for identifying disruptive elements of an airline

Currently, flight delays are common and they propagate from an originating flight to connecting flights, leading to large disruptions in the overall schedule. These disruptions cause massive economic losses, affect airlines’ reputations, waste passengers’ time and money, and directly impact the environment. This study adopts a network science approach for solving the delay propagation problem by modeling and analyzing the flight schedules and historical operational data of an airline. We aim to determine the most disruptive airports, flights, flight-connections, and connection types in an airline network. Disruptive elements are influential or critical entities in an airline network. They are the elements that can either cause (airline schedules) or have caused (historical data) the largest disturbances in the network. An airline can improve its operations by avoiding delays caused by the most disruptive elements. The proposed network science approach for disruptive element analysis was validated using a case study of an operating airline. The analysis indicates that potential disruptive elements in a schedule of an airline are also actual disruptive elements in the historical data and they should be considered to improve operations. The airline network exhibits small-world effects and delays can propagate to any part of the network with a minimum of four delayed flights. Finally, we observed that passenger connections between flights are the most disruptive connection type. Therefore, the proposed methodology provides a tool for airlines to build robust flight schedules that reduce delays and propagation.

Meta-Heuristic Solver with Parallel Genetic Algorithm Framework in Airline Crew Scheduling

Airline crew scheduling is a very important part of the operational planning of commercial airlines, but it is a linear integer programming problem with multi-constraints. Traditionally, the airline crew scheduling problem is determined by solving the crew pairing problem (CPP) and the crew rostering problem (CRP), sequentially. In this paper, we propose a new heuristic solver based on the parallel genetic algorithm and an innovative crew scheduling algorithm, which improves traditional crew scheduling by integrating CPP and CRP into a single problem. The innovative scheduling method includes a global heuristic search and an adjustment for flights and crew so as to realize crew scheduling. The parallel genetic algorithm is used to divide the population into multiple threads for parallel calculation and to optimize the randomly generated flight sequence to maximize the number of flights that meet the crew configuration. Compared with the genetic algorithm, CPLEX and Gurobi, it shows high optimization efficiency, with a time reduction of 16.57–85.82%. The experiment shows that our crew utilization ratio is higher than that for traditional solvers, achieving almost 44 flights per month, with good scalability and stability in both 206 and 13,954 flight datasets, and can better manage airline crew scheduling in times of crew scarcity.

An Optimization of Airline Scheduling Systems Based on a New Airline Pilots’ Fatigue Assessment Algorithm

Flight safety reports from different sources indicate that the proportion of accidents caused by flight fatigue accounts for 6-11% of all types of flight accidents. Current regulations in the civil aviation industry across the world generally emphasize the length of working hours rather than the influences of circadian rhythm disorders. Based on an analysis of the flight mission data of 567 pilots in 2019, which highlighted the associations between circadian rhythm disorders and flight fatigue, we have proposed a new algorithm to reflect pilots’ fatigue status to include five main indicators: actual working hours, circadian rhythm disorders, work rhythm disorder, altitude flight hours and flight crew composition. The results assessed by the new algorithm reported that about 70% of the airline pilots studied were under the threat of a high risk of fatigue in 2019. Subsequently, this research suggests the use of two algorithms to optimize pilot scheduling systems, and findings show that the percentage of pilots with a high level of fatigue can be largely reduced.

Integrated Linear Integer Model of a Fleet Allocation and Aircraft Routing Problem with Operational Constraints

One of the topics that have been studied a lot in the field of airline industry optimization is related to flight planning, and air fleets, and how they relate to each other, which is called airline scheduling. Despite the high importance of this issue in the profitability of airline companies and the proper use of their resources, the high computational complexity of these models has led to considering each of them in a mathematical model separately, and as a result, the accuracy of the final decision will be decreased. So far, many articles have studied various relevant issues, in some cases, efforts to create integration in the process can be observed. However, there is a few operational views of the issue, and some key requirements were neglected due to the simplification of provided models. In this study, an integrated model of the two main stages of airline planning, including fleet allocation and aircraft maintenance routing, is considered simultaneously, and the performance of the developed model is investigated using real data from one of the airlines. Also, a sensitivity analysis of the model to some relevant parameters confirms the validity of the developed mathematical model and the solution algorithm. Then, a comparative study was investigated to compare the performance of the developed model with the operational method, including solving sub-problems stepwise. Also, the results are compared with the developed and similar method from the previous studies. The results confirm the superiority of the developed mathematical model.

Deep Learning Architecture for Flight Flow Spatiotemporal Prediction in Airport Network

Traffic flow prediction is a significant component for the new generation intelligent transportation. In the field of air transportation, accurate prediction of airport flight flow can help airlines schedule flights and provide a decision-making basis for airport resource allocation. With the help of Deep Learning technology, this paper focuses on the characteristics of flight flow easily disturbed by environmental factors, studies the spatiotemporal dependence between flight flows, and predicts the spatiotemporal distribution of flight flows from the airport network level. We proposed a deep learning architecture named ATFSTNP, which combining the residual neural network (ResNet), graph convolutional network (GCN), and long short-term memory (LSTM). Based big data analytics of air traffic management, this method takes the spatiotemporal causal relationship between weather impact and flight flow as the core, and deeply mines the complex spatiotemporal relationship of flight flow. The model’s methodologies are improved from the practical application level, and extensive experiments conducted on the China’s flight operation dataset. The results illustrate that the improved model has significant advantages in predicting the flight flow under weather affect. Even in the complex and variable external environment, the model can still accurately predict the spatiotemporal distribution of the airport network flight flow, with strong robustness.

Turbulent skies ahead? Pandemic related workforce issues in air transportation

This short topical issues paper focuses on the workforce issues facing the air transport industry in the post-pandemic landscape. We consider the extent of vaccine mandates and whether these mandates will introduce workforce issues for the global air transportation industry. Then we explore the extent of virus exposure and associated workforce disruptions due to sick calls and associated quarantine guidelines. We argue that vaccine mandates will have a limited impact on air transport in the near term but do not likely have an impact on the long-term workforce shortages expected in the industry. Conversely, employee illness will have a more significant impact in the near and long-term as variants spread and airline scheduling adjusts both tactically and operationally. As aviation rebounds after the pandemic, there have been additional challenges due to workforce shortages. These shortages affect aircrew as well as ground handlers, security agents and other airport workers. Ultimately, policymakers and airlines around the globe should carefully consider the impact of policies and the mechanisms to encourage employees to protect themselves against the COVID-19 virus and future variants, with consideration of the impacts during recovery as well as during the pandemic.

Flight reliability during periods of high uncertainty

In times of great uncertainty for the airline industry, travelers are in search of reliable itineraries now more than ever. With condensed airline schedules and less options, air travelers must rely on making flight connections and manage layover times to arrive at their final destination on time. In an era with readily available information, passengers expect accurate and transparent reliability information to help improve decision making for multi-leg itineraries. However, often for reliability in air travel, this information is incomplete or not useful. In this paper we utilize historical probability distributions of flight arrival and departure times using publicly available data to give an intuitive and predictive flight itinerary reliability metric. The COVID-19 pandemic significantly affected air-travel in the US and this uncertainty is still being felt with cancellations and delays due to staff shortages and reduced demand. Therefore, we extend the stochastic network model from our previous research to air travel during COVID-19 to see the effects on flight reliability. Using this model, we conduct computational experiments to evaluate air travel through multiple reliability metrics. We show that during periods of high uncertainty, predictive historical distributions of flight data considering recency and seasonal effects are less accurate given many cancellations and a reduced flight schedule.

Passenger-Centric Integrated Airline Schedule and Aircraft Recovery

Airlines are known to compete for passengers, and airline profitability heavily depends on the ability to estimate passenger demand, which in turn depends on flight schedules, fares, and the number of seats available at each fare, across all airlines. Interestingly, such competitive interactions and passenger substitution effects may not be limited to the planning stages. Existing regulations in some countries and regions impose monetary compensations to passengers in case of disruptions, altering the way they perceive the utility of other travel alternatives after the disruption starts. These passenger rights regulations may act as catalysts of passengers’ response to recovered schedules. Ignoring such passenger response behavior under operational disruptions may lead airlines to develop subpar recovery schedules. We develop a passenger response model and embed it into a novel integrated optimization approach that recovers airline schedules, aircraft, and passenger itineraries while endogenizing the impacts of airlines' decisions on passenger compensation and passenger response. We also develop an original solution approach, involving exact linearization of the nonlinear passenger cost terms, combined with delayed constraint generation for ensuring aircraft maintenance feasibility and an acceleration technique that penalizes deviations from planned schedules. Computational results on real-world problem instances from two major European airlines are reported, for scenarios involving disruptions, such as delayed flights, airport closures, and unexpected grounding of aircraft. Our approach is found to be tractable and scalable, producing solutions that are superior to airline’s actual decisions and highly robust in the face of passenger response uncertainty. Of particular relevance to the practitioners, our simulation results highlight that accounting for passengers’ disruption response behaviors, even in a highly approximate manner, yields significant benefits to the airline compared with not accounting for them at all, which is the current state-of-the-art. Funding: This work was supported by the Agencia Estatal de Investigación [Grant PID2020-112967GB-C33], the Ministerio de Economía y Competitividad, Spain [Grant TRA2016-76914-C3-3-P], and the Ministerio de Ciencia, Innovación y Universidades, Spain [Grant CAS19/00036].

The substitution of short-haul flights with rail services in German air travel markets: A quantitative analysis

In recent years, a ban on short-haul flights for which alternative, more environmentally friendly transportation is available has been on European regulatory agendas, particularly in countries like Germany, with its well-developed high-speed rail (HSR) and a dense network of low-cost, point-to-point airline traffic. This study aims to quantify the potential impact on CO2 emissions of substituting short-haul flights with rail frequencies in 87 German air travel corridors. Using OAG data on passenger bookings and airline schedules for 2019, as well as current rail travel times, we determine the target flights by looking at the actual proportion of connecting passengers per frequency. We estimate a potential reduction in CO2 emissions of between 2.7% and 22%, depending on how strict the flight substitution is. However, the social benefits of those carbon emissions might fall short of the travel time losses experienced by the passengers. Increased investment to improve rail speeds and intermodal accessibility appears necessary before the substitution policies can be implemented.

A data-driven method to assess the causes and impact of delay propagation in air transportation systems

Air transportation systems are exposed to disruptions, which have significant impact on operations. Airlines operate tight schedules to maximise resource utilisation, however, the lack of sufficient buffers often result in propagating delays. Thus, understanding how likely it is to experience delays, why they keep happening and what is their impact on airline operations are important steps for the management of the disruptions they cause. In this paper, we propose a data-driven method to empirically analyse how delays propagate and their impact on an airline schedule. Our multi-layer network method captures different variables that are influenced by schedule disruption, namely aircraft (tail), crew, passengers and their interfaces. The method is tested on the schedule disruptions of a hub-and-spoke airline where we empirically demonstrate that incorporating information in this multi-layered manner results in a more robust assessment of delay propagation. The method along with the empirical results of this study can support aviation system planners gain additional insights into flight delay propagation patterns and consequently support their resource allocation decisions while improving overall system performance.

A mathematical model for integrated aircraft and crew recovery after a disruption: a Benders’ decomposition approach

PurposeAirline scheduling is an extremely complex process. Moreover, disruption in a single flight may damage the entire schedule tremendously. Using an efficient recovery scheduling strategy is vital for a commercial airline. The purpose of this paper is to present an integrated aircraft and crew recovery plans to reduce delay and prevent delay propagation on airline schedule with the minimum cost.Design/methodology/approachA mixed-integer linear programming model is proposed to formulate an integrated aircraft and crew recovery problem. The main contribution of the model is that recovery model is formulated based on individual flight legs instead of strings. This leads to a more accurate schedule and better solution. Also, some important issues such as crew swapping, reassignment of aircraft to other flights as well as ground and sit time requirements are considered in the model. Benders’ decomposition approach is used to solve the proposed model.FindingsThe model performance is also tested by a case including 227 flights, 64 crew, 56 aircraft and 40 different airports from American Airlines data for a 24-h horizon. The solution achieved the minimum cost value in 35 min. The results show that the model has a great performance to recover the entire schedule when disruption happens for random flights and propagation delay is successfully limited.Originality/valueThe authors confirm that this is an original paper and has not been published or under consideration in any other journal.