A multi-variable hybrid system for port container throughput deterministic and uncertain forecasting

Abstract

Container transport is the most environmentally friendly and sustainable way to transport bulk cargo currently. The accurate prediction of container throughput is of great significance to the operation of the port. It is directly related to the healthy development of the entire logistics system, and also serves as a reference for decision makers in the construction of port infrastructure. However, the container throughput sequence contains the influence and restriction of a variety of superimposed factors, and has the characteristics of nonlinear and non-stationary. Traditional technology cannot effectively capture the changes of external related factors. To make up for the deficiencies, a multi-variable hybrid deterministic and uncertain forecasting framework based on improved preprocessing technique and swarm intelligence optimizer is constructed. It not only considers the impact of port hinterland economic indicators, port transport system and transport capacity factors, but also calculates the upper and lower limits of container throughput under different probabilities. The results and tests show that mean absolute percentage errors obtained by the presented forecast system are 1.1551%, 2.0936% and 2.5546% respectively, and the prediction interval coverage probability values of 1 can be achieved. The hybrid system is effective, stable and has reasonable running time, which can be widely popularized. And it is conducive to the orderly operation of transportation industry and the development of container port cities.