Abstract
In order to solve the limitation of traditional offline forecasting application scenarios, the author uses a variety of big data open source frameworks and tools to combine with railway real-time data, and proposes a real-time prediction model of railway passenger flow. The model architecture is divided into four levels from bottom to top: data source layer, data transmission layer, prediction calculation layer and application layer. The main components of the model are data flow and prediction flow. Through message queue and ETL, the data process part realizes the synchronization of offline data and real-time data; through the big data technology frameworks such as Spark, Redis and Hive and the GBDT (Gradient Boosting Tree) algorithm, the prediction process partially realizes the real-time passenger flow of the train OD section prediction. The experimental results show that the model proposed by the author has certain practicability and accuracy both in performance and prediction accuracy.
Highlights
The prediction of railway passenger flow is an effective means to reasonably allocate passenger transport resources and alleviate the contradiction between passenger travel demand and limited transport capacity
In the field of railway passenger flow prediction, whether it is based on statistical analysis, machine learning, deep learning and other model research, the research direction of scientists is mainly focused on offline passenger flow forecasting[1,2,3], that is, the model uses offline traffic data to build training set and test set with days as the maximum data granularity, the influence of the real-time dynamic change of the delivery volume on the final delivery volume in the pre-sale period is not considered
For dynamic ticket pre-assignment or capacity control[4], this depends on the real-time business scenario of passenger flow
Summary
The prediction of railway passenger flow is an effective means to reasonably allocate passenger transport resources and alleviate the contradiction between passenger travel demand and limited transport capacity. In the field of railway passenger flow prediction, whether it is based on statistical analysis, machine learning, deep learning and other model research, the research direction of scientists is mainly focused on offline passenger flow forecasting[1,2,3], that is, the model uses offline traffic data to build training set and test set with days as the maximum data granularity, the influence of the real-time dynamic change of the delivery volume on the final delivery volume in the pre-sale period is not considered. For dynamic ticket pre-assignment or capacity control[4], this depends on the real-time business scenario of passenger flow. In view of the above problems, the author puts forward a real-time prediction model of railway passenger flow. The model is based on big data open source architectures such as Spark, message queue and distributed memory database, based on the business data such as ticket records data and remaining tickets to make real-time predictions of the number of trains in the pre-sale period
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
