A prediction method of airspace sector congestion degree based on random forest

Abstract

The invention discloses a random forest-based airspace sector congestion degree prediction method, which belongs to the field of air traffic congestion degree prediction and can scientifically and reasonably predict the airspace sector congestion degree. The present invention includes five steps of reading in historical data, data preprocessing, constructing a feature set, constructing a decision tree, and using random forests to predict sector congestion levels. The sector capacity saturation, potential conflict times, sector aircraft density, sector The average speed saturation of aircraft in the area and the average distance between aircraft in the sector are processed, and the congestion level corresponding to each time period of the sector is obtained by using the fuzzy evaluation method, and then the ID3 algorithm is used as the core algorithm to build a decision tree, and finally Samples are taken and substituted into the decision tree, classified layer by layer, and the prediction results are obtained. According to the results, three evaluation index data are calculated: prediction accuracy, prediction average absolute error, and prediction average percentage error. The average value of each index is taken to evaluate whether the prediction is accurate.

Description

technical field [0001] The invention belongs to the field of air traffic congestion degree prediction, in particular to a method for predicting airspace sector congestion degree based on random forest. Background technique [0002] With the rapid development of air transport business, under the condition of relatively limited airspace resources, traffic congestion is becoming more and more serious, seriously affecting the safety and efficiency of air traffic operations, although domestic breakthroughs have been made in identifying the degree of air traffic congestion , but just identification is not enough to satisfy the research on air traffic congestion at this stage and in the future. In the face of increasingly saturated airspace and mixed and diverse operating modes, how to accurately predict the degree of traffic congestion in airspace sectors and deploy corresponding traffic management measures in advance according to the prediction has become an urgent problem for ai...

AI Technical Summary

Problems solved by technology

At present, the prediction of air traffic congestion in my country is still in its infancy, and there is a lack of relevant research, and there is a lack of specific application methods.

Images