Short-term prediction of outbound truck traffic from the exchange of information in logistics hubs: A case study for the port of Rotterdam

Ali Nadi,Salil Sharma,Maaike Snelder,Taoufik Bakri,Hans Van Lint,Lóránt Tavasszy

doi:10.1016/j.trc.2021.103111

Abstract

Short-term traffic prediction is an important component of traffic management systems. Around logistics hubs such as seaports, truck flows can have a major impact on the surrounding motorways. Hence, their prediction is important to help manage traffic operations. However, The link between short-term dynamics of logistics activities and the generation of truck traffic has not yet been properly explored. This paper aims to develop a model that predicts short-term changes in truck volumes, generated from major container terminals in maritime ports. We develop, test, and demonstrate the model for the port of Rotterdam. Our input data are derived from exchanges of operational logistics messages between terminal operators, carriers and shippers, via the local Port Community System. We propose a feed-forward neural network to predict the next one hour of outbound truck traffic. To extract hidden features from the input data and select a model with appropriate features, we employ an evolutionary algorithm in accordance with the neural network model. Our model predicts outbound truck volumes with high accuracy. We formulate 2 scenarios to evaluate the forecasting abilities of the model. The model predicts lag and non-proportional responses of truck flows to changes in container turnover at terminals. The findings are relevant for traffic management agencies to help improve the efficiency and reliability of transport networks, in particular around major freight hubs.

Highlights

Predicting Short-term traffic flow is indispensable for advanced traffic management systems
As the MSE is in disagreement with the model parameters, the result of the NSGA-II will be a set of non-dominated models that cannot dominate each other as well
We explore the link between logistics activities at a seaport terminal and the truck traffic volume being generated by those activities

Summary

Introduction

Predicting Short-term traffic flow is indispensable for advanced traffic management systems. The truck flow around logistic hubs, which varies by time-of-day, has implications for the traffic on the surrounding motorways. Predicting the hour of truck volumes is a precondition for traffic management systems for controlling the corresponding traffic. Short-term prediction of truck volumes has gained too little attention in contrast to short-term traffic flow prediction. The literature mostly addresses the daily truck generated at logistic hubs or traffic analysis zones rather than addressing the shortterm truck demand on the road network. This implies that no literature describes methods to predict short-term truck (http://creativecommons.org/licenses/by/4.0/)

Objectives

Methods

Results

Conclusion