항만 컨테이너 터미널 반출입 혼잡 영향 요소 분석을 통한 반출입 혼잡도 예측 모델 아키텍처 개념 설계

Design of a Predictive Model Architecture for In-Out Congestion at Port Container Terminals Through Analysis of Influencing Factors

Purpose The purpose of this study is to identify and analyze the key factors influencing congestion in the in-out transportation at port container terminals, and to design of a predictive model for in-out congestion based on these analysis. This study focused on architecting a deep learning-based predictive model. Design/methodology/approach This study was conducted through the following methodology. First, hypotheses were established and data were analyzed to examine the impact of vessel schedules and external truck schedules on in-out transportation. Next, explored time series forecasting models to a design the architecture for deep learning-based predictive model. Findings According to the empirical analysis results, this study confirmed that vessel schedules significantly affect in-out transportation. Specifically, the volume of transportation increases as the vessel arrival/departure time and the cargo cutoff time approach. Additionally, significant congestion patterns in transportation volume depending on the day of the week and the time of day were observed.