Aviation network sweep effect inference method based on two-stage regression

Abstract

The invention relates to an aviation network sweep effect inference method based on two-stage regression, belongs to the technical field of flight delay prediction, and solves the problem that an existing delay propagation analysis model is solidified and established based on idealized hypothesis. Comprising the following steps: constructing an adjacent matrix among all airports in each time slice, and generating a delay state vector of each airport; constructing a flight delay model according to the dynamic function library and the adjacent matrix; according to the delay state vector, fitting a flight delay model through an LASSO regression method to obtain a preliminary fitting equation; sampling from all airports to obtain a plurality of airport combinations, optimizing the preliminary fitting equation corresponding to each airport combination by adopting a weighted akaike information criterion to obtain an optimization equation corresponding to each airport combination, and obtaining a delay propagation equation based on each optimization equation; and obtaining delay time of all airports in corresponding time slices according to the delay propagation equation, and taking the delay time as an inference result of the aviation network sweep effect. And accurate prediction of the aviation network sweep effect is realized.

Description

technical field [0001] The invention relates to the technical field of flight delay prediction, in particular to a double-stage regression-based method for estimating the ripple effect of an aviation network. Background technique [0002] With the rapid development of the civil aviation industry, flight delays have gradually become a world-class challenge. There are many reasons for flight delays, but the inherent contagion effect of the air traffic network is the key factor that makes flight delays continue to worsen. Flight delays accumulate due to contagion effects, such as the sharing of aircraft by different flights, the maintenance of aircraft arrival delays on departure flights, and the sharing of ground resources causing arrival delays to propagate to other aircraft downstream, making any initial delay likely to Continuously amplifying and affecting the entire air traffic network. Therefore, research on flight delay propagation mechanism is important and challengin...

AI Technical Summary

Problems solved by technology

[0005] In view of the above analysis, the embodiment of the present invention aims to provide a two-stage regression-based method for inferring the spread of aviation network effects to solve the problem that the existing delay propagation analysis model is fixed and established based on idealized assumptions

Images