Skip to main content
Springer Nature Link
Log in

Enhancing Software Defect Prediction in Ansible Scripts Using Code-Smell-Guided Prompting with Large Language Models in Edge-Cloud Infrastructures

  • Conference paper
  • First Online:
Current Trends in Web Engineering (ICWE 2024)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 2188))

Included in the following conference series:

  • 83 Accesses

Abstract

In edge-cloud systems, the quality of infrastructure deployment is crucial for delivering high-quality services, especially when using popular Infrastructure as Code (IaC) tools like Ansible. Ensuring the reliability of such large-scale code systems poses a significant challenge due to the limited testing resources. Software defect prediction (SDP) addresses this limitation by identifying defect-prone software modules, allowing developers to prioritize testing resources effectively. This paper introduces a Large Language Model (LLM)-based approach for SDP in Ansible scripts with Code-Smell-guided Prompting (CSP). CSP leverages code smell indicators extracted from Ansible scripts to refine prompts given to LLMs, enhancing their understanding of code structure concerning defects. Our experimental results demonstrate that CSP variants, particularly the Chain of Thought CSP (CoT-CSP), outperform traditional prompting strategies, as evidenced by improved F1-scores and Recall. To the best of our knowledge, this is the first attempt to employ LLMs for SDP in Ansible scripts. By employing a code smell-guided prompting strategy tailored for Ansible, we anticipate that the proposed method will enhance software quality assurance and reliability, thereby increasing the overall reliability of edge-cloud systems.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    https://github.com/HyunsunHong/CSP_for_LLM-based-SDP-in-Ansible.

References

  1. Agapito, G., et al.: Current Trends in Web Engineering: ICWE 2022 International Workshops, BECS, SWEET and WALS, Bari, Italy, July 5–8, 2022, Revised Selected Papers. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-25380-5

  2. Buyya, R., Srirama, S.N.: Fog and Edge Computing: Principles and Paradigms. Wiley, Hoboken (2019)

    Google Scholar 

  3. Meijer, B., Hochstein, L., Moser, R.: Ansible: Up and Running. O’Reilly Media, Inc., Sebastopol (2022)

    Google Scholar 

  4. Morris, K.: Infrastructure as Code: Managing Servers in the Cloud. O’Reilly Media, Inc., Sebastopol (2016)

    Google Scholar 

  5. Dalla Palma, S., Di Nucci, D., Palomba, F., Tamburri, D.A.: Within project defect prediction of infrastructure-as-code using product and process metrics. IEEE Trans. Softw. Eng. 14(8), 1 (2020)

    Google Scholar 

  6. Hassan, M.M., Rahman, A.: As code testing: characterizing test quality in open source Ansible development. In: 2022 IEEE Conference on Software Testing, Verification and Validation (ICST), pp. 208–219. IEEE (2022)

    Google Scholar 

  7. Kokuryo, S., Kondo, M., Mizuno, O.: An empirical study of utilization of imperative modules in Ansible. In: 2020 IEEE 20Th International Conference on Software Quality, Reliability and Security (QRS), pp. 442–449. IEEE (2020)

    Google Scholar 

  8. Opdebeeck, R., Zerouali, A., De Roover, C.: Andromeda: A dataset of Ansible galaxy roles and their evolution. In: 2021 IEEE/ACM 18th International Conference on Mining Software Repositories (MSR), pp. 580–584. IEEE (2021)

    Google Scholar 

  9. Pearce, H., Tan, B., Ahmad, B., Karri, R., Dolan-Gavitt, B.: Examining zero-shot vulnerability repair with large language models. In: 2023 IEEE Symposium on Security and Privacy (SP), pp. 2339–2356. IEEE (2023)

    Google Scholar 

  10. Xu, J., Yan, L., Wang, F., Ai, J.: A GitHub-based data collection method for software defect prediction. In: 2019 6th International Conference on Dependable Systems and Their Applications (DSA), pp. 100–108. IEEE (2020)

    Google Scholar 

  11. Wahono, R.S.: A systematic literature review of software defect prediction. J. Softw. Eng. 1(1), 1–16 (2015)

    Google Scholar 

  12. Brown, T., et al.: Language models are few-shot learners. In: Advances in Neural Information Processing Systems (NeurIPS 2020), vol. 33, pp. 1877–1901 (2020)

    Google Scholar 

  13. Wei, J., et al.: Chain-of-thought prompting elicits reasoning in large language models. In: Advances in Neural Information Processing Systems, (NeurIPS 2022), pp. 24824–24837 (2022)

    Google Scholar 

  14. Nong, Y., Aldeen, M., Cheng, L., Hu, H., Chen, F., Cai, H.: Chain-of-thought prompting of large language models for discovering and fixing software vulnerabilities. arXiv preprint arXiv:2402.17230 (2024)

  15. Ingemann Tuffveson Jensen, R., Tawosi, V., Alamir, S.: Software vulnerability and functionality assessment using LLMs. arXiv e-prints, arXiv-2403

    Google Scholar 

  16. Opdebeeck, R., Zerouali, A., De Roover, C.: Smelly variables in Ansible infrastructure code: detection, prevalence, and lifetime. In: 2022 IEEE/ACM 19th International Conference on Mining Software Repositories (MSR), pp. 61–72. IEEE (2022)

    Google Scholar 

  17. Ali, M.M., Huda, S., Abawajy, J., Alyahya, S., Al-Dossari, H., Yearwood, J.: A parallel framework for software defect detection and metric selection on cloud computing. Clust. Comput. 20, 2267–2281 (2017)

    Article  Google Scholar 

  18. Madeyski, L., Lewowski, T.: Detecting code smells using industry-relevant data. Inf. Softw. Technol. 155, 107112 (2023)

    Article  MATH  Google Scholar 

  19. Kwon, S., Lee, S., Kim, T., Ryu, D., Baik, J.: Exploring the feasibility of ChatGPT for improving the quality of Ansible scripts in edge-cloud infrastructures through code recommendation. In: Casteleyn, S., Mikkonen, T., García Simón, A., Ko, IY., Loseto, G. (eds.) ICWE 2023. CCIS, vol. 1898, pp. 75–83. Springer, Cham (2024). https://doi.org/10.1007/978-3-031-50385-6_7

  20. Piotrowski, P., Madeyski, L.: Software defect prediction using bad code smells: a systematic literature review. In: Poniszewska-Marańda, A., Kryvinska, N., Jarząbek, S., Madeyski, L. (eds.) Data-Centric Business and Applications. LNDECT, vol. 40, pp. 77–99. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-34706-2_5

  21. Danphitsanuphan, P., Suwantada, T.: Code smell detecting tool and code smell-structure bug relationship. In: 2012 Spring Congress on Engineering and Technology, pp. 1–5. IEEE (2012)

    Google Scholar 

  22. Kwon, S., Lee, S., Kim, T., Ryu, D., Baik, J.: Exploring LLM-based automated repairing of Ansible script in edge-cloud infrastructures. J. Web Eng. 22(6), 889–912 (2023)

    Google Scholar 

Download references

Acknowledgments

This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2024-2020-0-01795) supervised by the IITP (Institute for Information & Communications Technology Planning & Evaluation, and Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2022R1I1A3069233).

Author information

Authors and Affiliations

  1. Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea

    Hyunsun Hong, Sungu Lee & Jongmoon Baik

  2. Jeonbuk National University, Jeonju, Republic of Korea

    Duksan Ryu

Authors
  1. Hyunsun Hong
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sungu Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Duksan Ryu
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jongmoon Baik
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jongmoon Baik .

Editor information

Editors and Affiliations

  1. University of Lugano, Lugano, Ticino, Switzerland

    Cesare Pautasso

  2. University of Orléans, Orléans, France

    Patrick Marcel

Rights and permissions

Reprints and permissions

Copyright information

© 2025 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Hong, H., Lee, S., Ryu, D., Baik, J. (2025). Enhancing Software Defect Prediction in Ansible Scripts Using Code-Smell-Guided Prompting with Large Language Models in Edge-Cloud Infrastructures. In: Pautasso, C., Marcel, P. (eds) Current Trends in Web Engineering. ICWE 2024. Communications in Computer and Information Science, vol 2188. Springer, Cham. https://doi.org/10.1007/978-3-031-75110-3_3

Download citation

  • DOI: https://doi.org/10.1007/978-3-031-75110-3_3

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-031-75109-7

  • Online ISBN: 978-3-031-75110-3

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics