EURO 2024 Copenhagen
Abstract Submission

EURO-Online login

4198. Container Terminal Energy Management and Operations Planning Under Uncertainty with Learning-based Onshore Power Scenarios

Invited abstract in session WA-62: Machine Learning and Optimization in Ports I, stream OR in Port Operations.

Wednesday, 8:30-10:00
Room: S12 (building: 101)

Authors (first author is the speaker)

1. Xinyu Tang
Delft University of Technology
2. Frederik Schulte
Transport Engineering and Logistics, Delft University of Technology

Abstract

Container terminal operators reduce the energy costs in container terminals by implementing a demand response system, which can shift energy consumption typically through energy prices. We investigate operations planning and energy management through demand response to reduce energy-related costs. We propose a two-stage stochastic mixed integer programming model with energy-related costs as part of the objective function. The considered operations include vessel scheduling at berths, temperature control of refrigerated containers, and allocation of handling capacity of quay cranes, yard cranes, and automated guided vehicles to serve each vessel. Various scenarios for vessel arrival times and electricity prices are explored to represent the uncertainty of energy demand and supply, respectively. Moreover, onshore power supply (OPS) will become an increasingly important part of energy consumption in ports. We develop a machine-learning-based approach to determine realistic OPS demand scenarios in stochastic optimization. The suggested model is decomposed and solved using a progressive hedging algorithm. A case study of the Alterwerder container terminal in Hamburg is conducted to test the model. Results show a significant improvement when applying a varying real-time energy pricing scheme compared to a single energy pricing scheme.

Keywords

Status: accepted

Back to the list of papers