Sector flow short-term prediction method based on decomposition integration methodology

Abstract

The invention discloses a sector flow short-term prediction method based on a decomposition integration methodology. According to the method, an original time series data decomposition module and a component prediction module are installed; an original time sequence is decomposed into a plurality of IMFs through a CEEMDAN method, all the IMFs are predicted through an EELM method, and then integrated prediction is conducted in an accumulation mode. By applying the method, a scientific and accurate criterion can be provided for accurately predicting the air traffic flow and accurately taking airtraffic flow management measures.

Description

technical field [0001] The present invention relates to the flow management field of air traffic management, and particularly mentions a short-term prediction method of sector flow based on decomposition and integration methodology, which is suitable for short-term prediction of sector flow and provides accurate flow for implementing flow management measures Predictive value. Background technique [0002] Air traffic flow (referred to as flow) is one of the core indicators to describe air traffic flow, and accurate prediction of flow is one of the key technologies to realize "smart civil aviation". Flow forecast is an estimate of the number of aircraft in a certain airspace range in the future. According to different forecasting time ranges, traffic forecasting can be divided into medium and long-term forecasting and short-term forecasting. Medium- and long-term traffic forecasting usually serves the strategic and pre-tactical stages of traffic management, and is generally...

AI Technical Summary

Problems solved by technology

[0004] Although the method based on chaotic time series can well capture the nonlinear chaotic characteristics of air traffic flow, the calculation process requires phase space reconstruction. However, the selection of parameters such as embedding dimension and delay time in the reconstruction process is relatively subjective. , resulting in unstable results; in addition, although the hybrid model that integrates chaos theory and artificial intelligence can optimize the chaotic model through artificial intelligence and improve the prediction accuracy to a certain extent, the parameter sensitivity, overfitting, and time-consuming of the artificial intelligence model The long-term problem has not been effectively solved, and it is not suitable for short-term forecasting with high real-time requirements

[0005] In recent years, "decomposition and integration methodology" has become a cutting-edge idea in the field of complex nonlinear time series prediction. It decomposes the complex original time series into several low-complexity components, then predicts each component, and finally integrates the prediction, effectively It has improved the accuracy of forecasting and has been well applied in the fields of short-term forecasting of electric power load and short-term ground traffic, but has not been applied to short-term forecasting of air traffic flow

[0006] Considering the research status of the existing air traffic flow short-term forecasting methods, there is still a lack of a fast and effective short-term forecasting method for air traffic flow

Images