Short term passenger flow forecast of rail transit based on cloud data fusion

Abstract

Passenger flow forecast is the basis of rail transit operation Department, and it is an important reference for rail transit cloud data fusion and optimal passenger capacity deployment. Due to the randomness and uncertainty of urban rail transit passenger flow, the traditional forecasting technology has been unable to meet the operational needs. Therefore, we should use more accurate methods to predict the short-term passenger flow. Therefore, this paper proposes a short-term passenger flow forecasting method for rail transit based on cloud data fusion, using cloud distributed and virtual technology Combined with big data technology for passenger flow data collection and analysis, line data classification from two dimensions of real-time judgment and real-time prediction, combined with cloud data fusion technology for the synthesis of various algorithms, to achieve the accurate prediction of rail transit short-term passenger flow. Finally, through experiments, it is confirmed that the rail transit short-term passenger flow prediction based on cloud data fusion has high practical application value and fully meets the research requirements requirement.