关键词 > WSC

WSC 2024: Simulation Challenge Tech. Document

发布时间:2025-06-24

Hello, dear friend, you can consult us at any time if you have any questions, add WeChat: daixieit

WSC 2024

Simulation Challenge

Tech Document

SUMMARY

The Simulation Challenge at the Winter Simulation Conference (WSC), evolving from its initial launch in 2022 as the "Case Study Competition", continues to underscore the critical role of simulation in bridging the gap between academia and industry. This initiative thrives on promoting interdisciplinary collaboration, sparking innovation, and addressing real-world challenges with advanced simulation solutions.

This year, aligning with the WSC 2024 theme “Simulation for the Imagination Age”, the Challenge invites creators to unleash the potential of simulation technology in transforming maritime systems. As we navigate a world increasingly reliant on complex maritime logistics for global trade, we are shifting our focus towards empowering participants to reimagine the future of port operations, yard management, and cargo logistics. The challenge encourages participants to harness their creativity to design, optimize, and evaluate dynamic systems using simulation, crafting solutions that meet the ever-evolving demands ofthe maritime industry with ingenuity and foresight.

This year's Challenge pivots towards maritime logistics, focusing on a cargo port operation issue involving complex interactions and activities within a cargo port, from ship berthing to container handling and automated guided vehicle (AGV) management. Participants are invited to optimize cargo port operations to improve efficiency and foster creative solutions. We have built a basic simulation system model with discrete-event  modeling  methods.  The  model  is  implemented   in  C#  programming  language  using O2DES.NET which is a set of frameworks for object-oriented discrete event simulation. In this competition, participants are required to build, design, and implement their own strategy algorithm. Participants are expected to embed their own algorithms in certain parts of the model, using their skills in model training and large-scale search, with the objective of improving port operation performance. The team that generate the best overall performance stand the best chance to win.

The purpose of this document is to provide the participants with detailed descriptions ofthe model structure and to guide them through the process of downloading the files and the required procedures for submitting their solutions.

Chapter 1.

Overview

1.1 Problem Description

Welcome to the WCS Simulation Challenge 2024 where this year's challenge is dedicated to simulating port operations. As global trade escalates, the efficiency of port operations becomes critical for economic continuity and  competitiveness. Participants  are  invited to delve  into the  complex management  of a container port terminal, emphasizing the optimization of interactions between vessels, containers, and port machinery including quay cranes (QCs), yard cranes (YCs), and automated guided vehicles (AGVs).

Traditional port operations often struggle with inefficiencies stemming from manual processes and static scheduling.  These  conventional  methods  can  lead  to  significant  delays  in  vessel  berthing,  container misallocation, and suboptimal usage of AGVs and cranes. In this competition, for each vessel arriving at the port, a waiting time exceeding two hours before berthing is considered a failure. Our goal is to reduce such failures and the final assessment of solutions submitted for this competition will be based on this performance metric.

In response to these challenges, our competition introduces a simplified but comprehensive port model. This  model  is  centered  around  three  critical  decision  variables:  scheduling  vessel  berths,  allocating containers to  specific  yard  blocks,  and  assigning  AGVs.  These  variables  traditionally  rely  on  fixed schedules and limited real-time data, leading to inefficiencies in throughput and resource allocation. This year, we encourage participants to reimagine these operations using advanced, innovative methods. By employing cutting-edge technologies and methodologies such as simulation, deep learning, and other data- driven  approaches,  contestants  have  the  opportunity  to  significantly  enhance  the  port’s  operational efficiency.

This competition is not only about devising winning strategies but also about fostering learning and discovery  in  port  logistics.  We  aim  for  the  participants  to  gain  deep  insights  about  the  operational complexities of ports and to explore creative, efficient solutions to these real-world challenges. It is an opportunity to apply the theoretical knowledge practically, which may lead to not just personal growth but potentially transformative changes within the industry. We look forward to seeing the unique perspectives and  innovative  solutions  that  each  participant  will  bring  to  the  WCS  Simulation  Challenge  2024. So, engage in this exploration of modern port operations, apply your skills, and enjoy the process of pioneering the future of port logistics!

Good luck and have fun in the WCS Simulation Challenge 2024!

1.2      Competition Rules

As shown in Figure 1, the given model contains data and source code according to the following three building blocks of information flow:

(A) Input: Example simulation scenarios with specific parameters settings.

(B) Interface: The three decision-modules. Here is where users can modify the code for their own

decision algorithms for scheduling vessel berths, allocating containers to specific yard blocks, and the assignment of AGVs. The respective names for the methods are CustomeizedAllocatedBerth”,

“CustomeizedDetermineYardBlock”, and CustomeizedAllocatedAGVs” . The default algorithms are be provided too.

(C) Output: Performance indicators to measure the efficiency and quality of the port operations.

Figure 1 - Information flow diagram.

In this contest, you are expected to rewrite and replace the existing decision modules (in Block B), to maximize the archived performance of the system (in Block C) under different scenarios (from Block A).

You can generate the logic rules in Part (B) in various ways, including but not limited to:

a. Writing rule-based scripts or heuristic algorithms embedded in decision events,

b. Embedding this simulation model into some external optimization search algorithms,

c. Developing a machine learning model to identify and conclude the best rule parameters and embedding them in the decision events.

You only need to provide Part (B) of the program code (with any required data), and there is no need to submit your optimization and training programs.

Please Note: Other source codes (except those for Part B) will not be evaluated or run by the assessors.

1.3      General Conditions of the Challenge

Your data and program code will be embedded in the discrete-event simulation model (that we have provided in advance). It will overwrite the corresponding original code, then it will be compiled and generates an executable simulation program. Your program will run under a variety of scenarios and random seeds. The winner will be the one whose model generates the top average performance index for each case.

For further instructions regarding file downloads and programming please check Chapter 2. Simulation model structures and the available data is explained in Chapter 3. Last but not least, the submission guidelines and detailed assessment criteria for this competition can be found in Chapter 4.

Chapter 2.

Technichal Instractions

2.1 Installing Visual Studio

1) Go to Microsoft website https://visualstudio.microsoft.com/ Then, choose the version that suits your computer and click the Download button to download This IDE.

Figure 2 - Microsoft Visual Studio download page.

2) For detailed instructions on the installation steps, you may refer to the following links:

Windows OS: https://learn.microsoft.com/en-us/visualstudio/install/install-visual-studio?view=vs-2022 Mac OS: https://learn.microsoft.com/en-us/visualstudio/mac/installation?view=vsmac-2022

3) You should select the workload to run the provided simulation model using C# language.

2.2 Source Code (in C#)

1) After registration, you will receive the zip package of our source code by email. The file will look like “WSC Simulation Challenge 2024.zip” .

2) Unzip the package.

3) Figure 3 shows the structure of the provided Source code for the challenge:

Figure 3- A glance on the content of the provided source code.

Here, the conf folder includes the scenario files, and StrategyMaking folder includes the Default and DecisionMaker files.

4) You may open the project by double click on “ WSC_SimChallenge_2024_Net.sln . For

compiling and running the code, you may simply click on the green play button on the top part of the window (shown with a red arrow in Figure 4).

Figure 4- the provided C# code in Visual Studio.

Chapter 3.

Discrete-Event Simulation Model

3.1 Entities

There are seven entities involved in this model, Quay Crane (QC), Berth, Container, Automated Guided Vehicles (AGV), Vessel, Yard Block and Yard Crane. Each is represented by a class and has its own set of attributes. The Entity Relationship Diagram (ERD) is shown in Figure 5 to give an overview of the relationships among the entities and the attributes associated with them.

Figure 5- Entity Relationship Diagram (ERD).

Notes about Figure 5:

1) PK: primary key, which uniquely identifies the entity object.

2) Static attribute: entity attributes that do not change over time. These attributes are owned by the class itself (shown in black color in the ERD).

3) Dynamic attribute (italic): entity attributes that change over time (in red color).

3.1.1          Entity Relationships

The following relationships are in place between the mentioned entities of the system:

Each  Berth has one or many Quay Cranes.

Each  QC corresponds to exactly one Berth.

Each  Berth has either zero or one Vessel.

Each  Vessel corresponds to either zero or one Berth.

Each  Vessel has zero or many Containers.

Each  Container corresponds to exactly one Vessel.

Each  Container corresponds to either zero or one AGV.

Each  AGV can have either zero or one Container.

Each  Container corresponds to either zero or one Yard Block.

Each  Yard Block can have zero or many Containers.

Each Yard Block has one and only one Yard Crane (i.e., each YC corresponds to one and only one Yard Block).