ICSME 2024
Sun 6 - Fri 11 October 2024
Thu 10 Oct 2024 10:55 - 11:10 at Abineau - Session 7: Software Architecture and Design Chair(s): Bonita Sharif

Although Kubernetes has become a widespread open-source system that automates the management of containerized applications, its complexity can be a significant barrier, particularly for application developers unfamiliar with it. One approach employs large language models (LLMs) to assist developers in generating Kubernetes manifests; however it is currently impossible to determine whether the output satisfies given specifications and is comprehensible. In this study, we proposed a benchmarking method for evaluating the effectiveness of LLMs in synthesizing manifests, using the Compose specification – a standard widely adopted by application developers – as input. The proposed benchmarking method revealed that LLMs generally produce accurate results that compensate for simple specification gaps. However, we also observed that inline comments for readability were often omitted, and completion accuracy was low for atypical inputs with unclear intentions.

Thu 10 Oct

Displayed time zone: Arizona change

10:30 - 12:00
Session 7: Software Architecture and DesignIndustry Track / Tool Demo Track at Abineau
Chair(s): Bonita Sharif University of Nebraska-Lincoln, USA
10:30
25m
How to train your dinosaur: our strategy to migrate mainframe applications to the cloudIndustry Track Talk
Industry Track
Johan Fabry Raincode Labs, Belgium
10:55
15m
Migrating Existing Container Workload to Kubernetes - LLM Based Approach and EvaluationIndustry Track Paper
Industry Track
Masaru Ueno Fujitsu Limited, Tetsuya Uchiumi Fujitsu Limited
Pre-print
11:10
15m
Insights on Microservice Architecture Through the Eyes of Industry PractitionersIndustry Track Paper
Industry Track
Vinicius L. Nogueira Universidade Estadual de Maringa - UEM, Fernando S. Felizardo Universidade Estadual de Maringa - UEM, Aline M. M. M. Amaral State University of Maringá, Wesley Assunção North Carolina State University, Thelma Elita Colanzi State University of Maringa, Brazil
Pre-print
11:25
10m
Stereocode: A Tool for Automatic Identification of Method and Class Stereotypes for Software SystemsTool Demo Paper
Tool Demo Track
Ali F. Al-Ramadan Department of Computer Science, Kent State University, Joshua Behler Kent State University, Michael J. Decker Bowling Green State University, Natalia Dragan Kent State University, Michael L. Collard The University of Akron, Jonathan I. Maletic Kent State University
11:35
15m
Enhancing Legacy Code Quality through Iterative Refactoring: A Case Study at ASMLIndustry Track Paper
Industry Track
Andrei Valentin Girjoaba University of Groningen, Andrea Capiluppi University of Groningen