Mathematical modeling of traffic volume in the suburban area based on the time series decomposition

Abstract

Abstract This study aims to the development of mathematical modeling methods based on time series decomposition. This method is used to describe various consistency or recurrence processes. Such a process is the distribution of traffic volume throughout the year. Its modeling is one of the leading research tasks in the transport sector. One of the urgent tasks is the assessment and forecasting of the traffic volume in the suburban areas. The study is carried out on the road section P-256 Chuysky Trakt (Novosibirsk - Barnaul - Biysk - Gorno-Altaisk -state border with Mongolia) near Biysk. Traffic data is obtained for 2019. Python is used in modelling. The statmodels module is used to decompose the time series. The multiplicative model is chosen. The adequacy of the model is checked on two groups of data. The first is the traffic volume data on the same road section for 2020. The average relative error was 5%. The second is the road section A-322 Barnaul - Rubtsovsk - the state border with the Republic of Kazakhstan in the suburban area of Aleysk. The average relative error was 6%. The results confirm the adequacy and versatility of the model.