Airport passenger volume forecasting method based on typical day identification

Abstract

The invention provides an airport passenger volume prediction method based on typical day identification, which comprises the following steps: collecting airport flight history day operation data setP, extracting historical day time feature vector and historical day flight feature vector for each historical day operation data; The similarity of feature dataset is quantified and the optimal weighting factor is obtained. A typical day identification model is established to predict the passenger volume in different time periods. The method for predicting airport passenger volume based on typicalday identification provided by the invention has the following advantages: the invention realizes accurate and effective prediction of airport passenger volume in different time periods, thereby effectively improving airport operating pressure early warning capability.

Description

technical field [0001] The invention belongs to the technical field of passenger flow prediction, and in particular relates to a method for predicting passenger volume at an airport based on typical day identification. Background technique [0002] In recent years, with the rapid growth of my country's civil aviation passenger traffic, airports, as the central nodes of the aviation network, are facing severe challenges. The contradiction between the ever-increasing passenger volume and the limited resources of the airport has become increasingly prominent. Especially during the peak period of passenger departure, counter resource saturation and passenger stranded often occur in the airport terminal, which greatly affects the travel experience of passengers, causes economic losses for airlines, and brings great losses to the airport and the civil aviation industry. negative social impact. How to realize refined airport management and maximize the use of existing terminal se...

AI Technical Summary

Problems solved by technology

In response to this specific requirement, the first type of method requires a large number of repeated simulations of individual passenger behavior, resulting in the superposition and accumulation of small errors, making the prediction results deviate from reality, and in order to establish passenger behavior models under various conditions (reflecting special weather, holidays, etc.) and other events), which require a large amount of historical data and prior knowledge; although the second type of method can provide long-term trend statistics, it cannot reflect the influence of dynamic factors such as flight distribution.

[0005] Therefore, neither of the above two methods can meet the needs of accurate and rapid forecasting of passenger volume.

Images