A Predictive-Proactive Approach for Slot Management of a Loading Facility With Truck ETA Information

Due to the uncertain and dynamic environment around scheduling systems, timely revisions or reschedules of the master plans are essential for achieving optimal utilization. With the recent development of Industry 4.0 technologies, many researchers perceive the creation of cyber-physical systems as a solution for managing systems under uncertainty. This article focuses on a loading facility under uncertain truck arrivals due to road congestion and proposes utilizing real-time truck location information to improve performance. We do this by developing an integrated system consisting of a predictive model using machine learning (MC) classifiers and a mathematical model for real-time slot rescheduling. The ML classifier is used to predict the presence probabilities of all the incoming trucks at a particular slot based on the historical traffic data and the real-time truck location. Subsequently, a Mixed-Integer Quadratic Programming (MIQP) model is developed to solve a Probabilistic Slot Rescheduling Problem (P-SRP), which uses the estimated truck presence probabilities and minimizes the total expected cost of rescheduling. We implemented this by first testing multiple ML classifiers and selected the ANN classifier for prediction as it outperformed others. Our limited experiments showed that the proposed method reduced the total rescheduling cost by 42%. Furthermore, our sensitivity analysis with different congestion levels, complexity, and rescheduling strategy also showed the practicality of the proposed approach.

Automated summary

This article focuses on improving performance of a loading facility with uncertain truck arrivals due to road congestion. By using machine learning classifiers to predict truck presence probabilities and utilizing a mixed-integer quadratic programming model for real-time slot rescheduling, the proposed method minimizes cost and improves performance.