Prospects for Comprehensive Forecasts When Assessing the Load of Railway Transport Infrastructure

Definite construction of time series forecasts is a key element in the system for supporting and making management decisions. This article presents a method for multi-stage system forecasting of time series. The effectiveness of the proposed method is experimentally substantiated using the example of the arrival of car flows at railway junction points. The main goal of scientific research is the formation of an integrated approach for making forecasts of changes in car flows on railway transport. The research methodology is based on various approaches to building forecast models, among which informal and formal methods can be distinguished, combined to carry out complex forecasting. The most important contribution is the introduction of a system forecast, in which the methods for forecasting traffic flows will be mutually consistent and complementary, since the use of only statistical methods will not fully reflect all the changes that occur in the transport complex of the Russian Federation. This comprehensive combination provides more competitive forecasts than other methods. Moreover, such an aggregate model is easier to interpret by decision makers when modeling trend series. A comprehensive method has been developed for predicting car flows in railway transport, which makes it possible to more accurately determine their changes for the subsequent supply of locomotives to the formed trains.