Analysis of Urban Rail Transit Short-term Passenger Flow Forecast and Its Optimization

Abstract

With the growth of urban population and the increase of car ownership, the number of cars continues to increase, leading to traffic congestion becoming a major problem in many cities around the world. Traffic congestion not only wastes time, but also increases air pollution and energy consumption. To address these challenges, governments and transportation authorities around the world have begun to adopt advanced technical models and big data based approaches. By using the power of intelligent data analysis, this paper enables people to understand rail transit more deeply, establish an ARIMA model for short-term prediction, optimize traffic flow, and improve the overall performance of the system. Through the final experimental results, it is found that the trend of rail transit passenger volume in the next few days is increasing, but its growth trend is not as high as that of the previous few days. The ARIMA model infers that the peak period in the next few days may not be as high as that of the previous few days.