A Two-Stage Regression-Based Method for Inferring Airborne Network Contagion Effects

Abstract

The invention relates to an aviation network ripple effect inference method based on two-stage regression, belongs to the technical field of flight delay prediction, and solves the problem that the existing delay propagation analysis model is solidified and established based on idealized assumptions. Including constructing the adjacency matrix between all airports in each time slice, and generating the delay state vector of each airport; constructing the flight delay model according to the dynamic function library and the adjacency matrix; according to the delay state vector, fitting the flight delay model by the LASSO regression method, and obtaining a preliminary Fitting equation; multiple airport combinations are sampled from all airports, and the weighted Akaike information criterion is used to optimize the preliminary fitting equation corresponding to each airport combination, and the optimization equation corresponding to each airport combination is obtained. Delay propagation equation: According to the delay propagation equation, the delay time of all airports in the corresponding time slice is obtained as the inference result of the aviation network ripple effect. Accurate prediction of the spillover effect of the aviation network is achieved.

Description

technical field [0001] The invention relates to the technical field of flight delay prediction, in particular to an aviation network ripple effect inference method based on two-stage regression. 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 propagation effects of the air traffic network are the key factors that make flight delays continue to worsen. Due to propagation effects, factors 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 spread to other aircraft downstream, all allow the accumulation of flight delays, making any initial delay possible Amplifying and affecting the entire air traffic network. Therefore, it is important and challenging to study the propagation mechanism of f...

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