Flight scheduling incorporating bad weather conditions through big data analytics: A comparison of metaheuristics

Abstract

The most important mode of long-distance transportation for people to use time efficiently is air transportation. One of the most significant factors determining air traffic performance is the scheduling created by companies. When creating schedules, various parameters are used, mainly the demand for the determined route, and the availability of airplanes and flight crews. Known climatic conditions on the route are generally neglected. Within the scope of this study, the creation of flight schedules, which are normally the preparation of flight schedules by considering the monthly, daily, and hourly constraints that could cause flight delays, were determined by also considering weather conditions. In this determination process, 32-year flight data between 1987 and 2018 were used as a basis. Apache Spark, one of the big data technologies, was used to determine these constraints. The scheduling was optimized by using the constraints used to prevent flight delays. It was observed in the results obtained that simulated annealing (SA) achieved the most optimal results compared to the genetic algorithm (GA) and the artificial bee colony (ABC) algorithm. As the dimensions of the searched space increased, solving the problem with metaheuristic approaches was more advantageous in terms of time compared to the classical method.

An Overview of Hadoop Job Scheduling Algorithms for Big Data

“…To facilitate rapid recovery from task failure and node failure, this incorporates a novel fault tolerance method that mixes decentralized checkpointing and proactive push mechanisms. This research [62] proposed an optimal Simulated Annealing (SA) metaheuristic approach for flight scheduling issues and delays. By employing the constraints utilized to avoid flight delays, this strategy yielded the most ideal results.…”

A Clustering-based Simulated Annealing Algorithm with Taguchi Method for the Discrete Ordered Median Problem

“…SA algorithm, independent of each other, was described by Kirkpatrick et al [7] and Cerny [8]. SA has been used to solve many combinatorial optimization problems such as traveling salesman problem, scheduling, assignment problem, network design [33] - [34].…”

Integrated recovery system with bidding‐based satisfaction: An adaptive multi‐objective approach

“…The recovery system plays a crucial role in the airline industry, which is primarily divided into three stages: aircraft, crew, and passenger recoveries (Su et al, 2021). It aims to reschedule resources for flights deviating from their original plans (Erdem et al, 2021). The division of the recovery system is driven by the complexity of the integrated case and the existence of multiple diverse objectives and constraints.…”