Probabilistic air route sector traffic demand prediction method

Abstract

The invention relates to a probabilistic air route sector traffic demand prediction method which comprises the following steps: a step of classifying and running statistics on errors of prediction ontime at which an aircraft passes a sector boundary point in a corresponding time period, and a step of probabilistically predicting traffic demand of a air route sector according to a classification statistics; according to the method, based on the existing historical data and prediction data of the time at which the aircraft passes the point, distribution characteristics of the errors of prediction on the time at which the aircraft passes the point and influencing factors thereof are analyzed, and a statistical method for the distribution characteristics of the errors of prediction on the time at which the aircraft passes the point is established; on this basis, the probabilistic air route sector traffic demand prediction method is proposed. Finally, based on actual operation data, probability distribution and a change law of sector traffic demand for a certain period of time are obtained, that accuracy of obtained probabilistic traffic demand prediction results is found to be greatlylarger than accuracy of traditional deterministic traffic demand prediction results, and the method disclosed in the invention can provide a scientific basis for traffic demand forecasting for air traffic flow management.

Description

technical field [0001] The invention relates to the field of aviation, in particular to a probabilistic route sector traffic demand forecasting method. Background technique [0002] In recent years, with the rapid development of China's air transport industry, air traffic congestion has become increasingly prominent and continues to spread from the terminal area to the air route network. In order to alleviate the increasingly frequent airway congestion, it is necessary to implement scientific congestion management methods, and one of the prerequisites is to accurately and objectively predict traffic demand. According to the actual operation of current airspace congestion management, it is mainly realized through the demand forecasting method based on flight path reckoning, that is, the trajectory of each aircraft is determined based on the aircraft motion equation, and the position of each aircraft is predicted for a period of time in the future. The number of aircraft pass...

AI Technical Summary

Problems solved by technology

Although this deterministic prediction result can meet the needs of airspace congestion management to a certain extent, it has several shortcomings: First, although the influence of many uncertain factors in the process of aircraft operation on the prediction result may be considered in the prediction process (such as , unplanned flight cancellations, changes in arrival and departure times, and other random events that cause deviations in aircraft operating time, and unplanned changes in flight paths or altitudes caused by weather, etc.), the expression of this deterministic prediction result is To a certain extent, it cannot fully reflect the actual influence and extent of uncertain factors; in addition, due to objective reasons such as prediction models, input data, and inherent defects in the system, the accuracy of deterministic results will decrease accordingly, so this kind of The degree of loss of accuracy cannot be reflected in the forecast results

Images