An Ensemble Learning Model for Short-Term Passenger Flow Prediction

Xiangping Wang,Ziyang Xia,Baoyu Li,Lei Huang,Haifeng Huang,Jing Li,Abd E.I.-Baset Hassanien

doi:10.1155/2020/6694186

Abstract

In recent years, with the continuous improvement of urban public transportation capacity, citizens’ travel has become more and more convenient, but there are still some potential problems, such as morning and evening peak congestion, imbalance between the supply and demand of vehicles and passenger flow, emergencies, and social local passenger flow surged due to special circumstances such as activities and inclement weather. If you want to properly guide the local passenger flow and make a reasonable deployment of operating buses, it is necessary to grasp the changing law of public transportation short-term passenger flow. This paper builds a short-term passenger flow prediction model for urban public transportation based on the idea of integrated learning. The goal is to use the integrated model to accurately predict the short-term passenger flow of urban public transportation, using Multivariable Linear Regression (MLR), K-Nearest Neighbor (KNN), eXtreme Gradient Boosting (XGBoost), and Gated Recurrent Unit (GRU) as the four seed models, and then use regression algorithm to integrate the model and predict the passenger flow, station boarding and landing, and cross-sectional passenger flow data of the typical representative line 428 in the “Huitian Area” of Beijing from January 1, 2020, to May 31, 2020. Finally, the prediction results of the submodels are compared with those of the integrated model to verify the superiority of the integrated model. The research results of this paper can enrich the short-term passenger flow forecasting system of urban public transportation and provide effective data support and scientific basis for the passenger flow, vehicle management, and dispatch of urban public transportation.

Highlights

IntroductionAccording to the annual report on Beijing’s Transport Development in 2020, by the end of 2019, the Beijing Public Transport Group has 28,271 buses and 1,620 routes in operation. e annual passenger volume of electric buses reached 3.564 billion, with an average daily passenger volume of 9.7377 million, providing great convenience for Beijing residents to travel, and it is the main undertaker of Beijing’s surface public transportation.In recent years, the characteristics of public transport network operation have become increasingly obvious; some potential problems gradually emerged, such as traffic jams during rush hours, traffic supply and demand not matching, a large number of passengers commuting security hidden danger in passenger flow gathering in a certain space, and some large activities, bad weather, and bus fault under the special operating environment urgent need for rapid evacuation etc
The prediction results of the submodels are compared with those of the integrated model to verify the superiority of the integrated model. e research results of this paper can enrich the short-term passenger flow forecasting system of urban public transportation and provide effective data support and scientific basis for the passenger flow, vehicle management, and dispatch of urban public transportation
It will inevitably lead to public transport vehicles not being able to get reasonable scheduling, affect the passengers, and impact on the effective running of the bus system. erefore, it is of great importance to use big data situation analysis technology to accurately predict short-time bus passenger flow based on traffic IC card data and external weather data to analyze and master the transport demand and passenger flow rule of public transportation

Summary

Introduction

According to the annual report on Beijing’s Transport Development in 2020, by the end of 2019, the Beijing Public Transport Group has 28,271 buses and 1,620 routes in operation. e annual passenger volume of electric buses reached 3.564 billion, with an average daily passenger volume of 9.7377 million, providing great convenience for Beijing residents to travel, and it is the main undertaker of Beijing’s surface public transportation.In recent years, the characteristics of public transport network operation have become increasingly obvious; some potential problems gradually emerged, such as traffic jams during rush hours, traffic supply and demand not matching, a large number of passengers commuting security hidden danger in passenger flow gathering in a certain space, and some large activities, bad weather, and bus fault under the special operating environment urgent need for rapid evacuation etc. Applications based on big data prediction technology, comprehensive and accurate projections for short bus traffic, are to promote. Erefore, it is of great importance to use big data situation analysis technology to accurately predict short-time bus passenger flow based on traffic IC card data and external weather data to analyze and master the transport demand and passenger flow rule of public transportation. Bus passenger flow related indicators reflect the passenger travel demand and regularity; can, for the operators in time according to the current system resource, adjust operation plans such as temporary or reduce extra trains and other transportation emergency cases combined effective disposal; and provide a scientific basis for narrowing the scope of the influence of the incident. It is necessary for public transportation to study the shortterm passenger flow forecast, build higher prediction accuracy of the model, and obtain more reliable shortterm passenger flow distribution, so as to solve the above problems effectively

Methods

Results

Conclusion