Optimizing continuous integration and continuous deployment pipelines with machine learning: Enhancing performance and predicting failures

• Autorzy: Dileepkumar S.R. , Mathew Juby

Identyfikatory

DOI

10.12913/22998624/197406

• Języki publikacji: EN

Abstrakty

EN

Continuous Integration and Continuous Deployment (CI/CD) pipelines form the backbone of modern software development but typically suffer from long build times, repeated failures, and inefficient use of resources. This work presents a machine learning-based framework that systematically improves pipeline performance through predictive modelling. More specifically, the work will focus on developing a Support Vector Machine model to predict pipeline failures; it minimizes build times through optimized resource allocation while building dynamic frameworks for continuous improvement of CI/CD pipelines. The study assumes an exhaustive literature review and propounds a new approach by using an SVM model. Critical performance metrics such as the build duration, test pass/fail rates, and resource consumption are analysed and the framework is found to have significant improvements by the measurements: a 33% decrease in the build time, a 60% decrease in the failure rates, and optimization of CPU and memory utilization. The experiments validated the outcome of being scalable in an intelligent manner such that persistent problems with CI/CD are solved in modern DevOps practices. This work provided initial groundwork by bringing in the concept of ML in CI/CD process, aiming to enhance reliability and efficiency in the pipelines that would lead towards major strides in adaptive systems in the context of software engineering workflows.

Słowa kluczowe

EN

machine learning; CI/CD; performance prediction; reinforcement learning; predictive analytics; DevOps; continuous integration and continuous deployment

• Wydawca: Lublin University of Technology ; Polish Society of Ecological Engineering (PTIE), Branch of PTIE in Lublin
• Czasopismo: Advances in Science and Technology. Research Journal
• Rocznik: 2025
• Tom: Vol. 19, no. 3
• Strony: 108--120
• Opis fizyczny: Bibliogr. 36 poz., fig., tab.

Twórcy

autor

Dileepkumar S.R.

• Computer Science and Multimedia, Lincoln University College Malaysia, No. 2, Jalan Stadium, SS 7/15, Kelana Jaya, 47301, Petaling Jaya, Selangor Darul Ehsan, Malaysia
• Marian College Kuttikanam (Autonomous), Peermade, Kuttikkanam, Kerala 685531, India

• https://orcid.org/0009-0004-9774-1936

autor

Mathew Juby

• Computer Science and Engineering, Amal Jyothi College of Engineering (Autonomous), Kanjirapally, Kerala, India

• https://orcid.org/0000-0002-4660-5940

Bibliografia

• 1. Camacho NG. Unlocking the potential of AI/ML in DevSecOps: Effective strategies and optimal practices. Deleted Journal. 2024 Mar 2; 2(1): 79–89. https://doi.org/10.60087/jaigs.v2i1.p89.
• 2. Ska YPJ. A Study and analysis of continuous delivery, continuous integration software development environment, Journal of Emerging Technologies and Innovative Research. 2019 Sep 1; 6(9): 96–107. https://www.jetir.org/papers/JETIRDD06019.pdf.
• 3. Malhotra A, Elsayed A, Torres R, Venkatraman S. Evaluate canary deployment techniques using Kubernetes, Istio, and Liquibase for cloud native enterprise applications to achieve zero downtime for continuous deployments. IEEE Access. 2024 Jan 1; 12: 87883–99. https://doi.org/10.1109/access.2024.3416087.
• 4. Chazhoor A, Mounika Y, Sarobin MVR, Sanjana MV, Yasashvini R. Predictive maintenance using machine learning based classification models. IOP Conference Series Materials Science and Engineering. 2020 Oct 1; 954(1): 012001. https://doi.org/10.1088/1757-899x/954/1/012001.
• 5. Mishra A, Otaiwi Z. DevOps and software quality: A systematic mapping. Computer Science Review. 2020 Oct 3; 38: 100308. https://doi.org/10.1016/j.cosrev.2020.100308.
• 6. Laukkanen E, Itkonen J, Lassenius C. Problems, causes and solutions when adopting continuous delivery—A systematic literature review. Information and Software Technology. 2016 Oct 16; 82: 55–79. https://doi.org/10.1016/j.infsof.2016.10.001.
• 7. Van Belzen M, Trienekens JJM, Kusters RJ. Critical success factors of continuous practices in a DevOps context. Information and Software Technology. 2019 Aug 28.
• 8. Benjamin J, Mathew J. Enhancing continuous integration predictions: a hybrid LSTM-GRU deep learning framework with evolved DBSO algorithm. Computing. 2024 Nov 26; 107(1). https://doi.org/10.1007/s00607-024-01370-2.
• 9. Alnafessah A, Gias AU, Wang R, Zhu L, Casale G, Filieri A. Quality-Aware DevOps Research: Where Do We Stand? IEEE Access. 2021 Jan 1; 9: 44476–89. https://doi.org/10.1109/access.2021.3064867.
• 10. Mishra A, Otaiwi Z. DevOps and software quality: A systematic mapping. Computer Science Review. 2020 Oct 3; 38: 100308. https://doi.org/10.1016/j.cosrev.2020.100308.
• 11. Lwakatare LE, Kilamo T, Karvonen T, Sauvola T, Heikkilä V, Itkonen J, et al. DevOps in practice: A multiple case study of five companies. Information and Software Technology. 2019 Jun 25; 114: 217–30. https://doi.org/10.1016/j.infsof.2019.06.010.
• 12. Vassallo C, Proksch S, Zemp T, Gall HC. Every build you break: developer-oriented assistance for build failure resolution. Empirical Software Engineering. 2019 Oct 9; 25(3): 2218–57. https://doi.org/10.1007/s10664-019-09765-y.
• 13. Ghaleb TA, Da Costa DA, Zou Y. An empirical study of the long duration of continuous integration builds. Empirical Software Engineering. 2019 Mar 1; 24(4): 2102–39. https://doi.org/10.1007/s10664-019-09695-9.
• 14. Saidani I, Ouni A, Mkaouer MW. Improving the prediction of continuous integration build failures using deep learning. Automated Software Engineering. 2022 Jan 20; 29(1). https://doi.org/10.1007/s10515-021-00319-5.
• 15. Zampetti F, Vassallo C, Panichella S, Canfora G, Gall H, Di Penta M. An empirical characterization of bad practices in continuous integration. Empirical Software Engineering. 2020 Jan 8; 25(2): 1095–135. https://doi.org/10.1007/s10664-019-09785-8.
• 16. Saidani I, Ouni A, Chouchen M, Mkaouer MW. On the prediction of continuous integration build failures using search-based software engineering. Proceedings of the Genetic and Evolutionary Computation Conference Companion. 2020 Jul 8; 313–4. https://doi.org/10.1145/3377929.3390050.
• 17. Zampetti F, Vassallo C, Panichella S, Canfora G, Gall H, Di Penta M. An empirical characterization of bad practices in continuous integration. Empirical Software Engineering. 2020 Jan 8; 25(2): 1095–135. https://doi.org/10.1007/s10664-019-09785-8.
• 18. Vassallo C, Proksch S, Gall HC, Di Penta M. Automated Reporting of Anti-Patterns and Decay in Continuous Integration. Proceedings of the 41st International Conference on Software Engineering. 2019 May 1; https://doi.org/10.1109/icse.2019.00028.
• 19. Vassallo C, Proksch S, Jancso A, Gall HC, Di Penta M. Configuration smells in continuous delivery pipelines: a linter and a six-month study on GitLab. Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering. 2020 Nov 7; https://doi.org/10.1145/3368089.3409709.
• 20. Dileep Kumar SR, Mathew J. Ebola optimization search algorithm for the enhancement of devops and cycle time reduction. International Journal of Information Technology. 2023 Mar 1; 15(3): 1309–17. https://doi.org/10.1007/s41870-023-01217-7.
• 21. Hilton M, Tunnell T, Huang K, Marinov D, Dig D. Usage, costs, and benefits of continuous integration in open-source projects. 31st IEEE/ACM International Conference on Automated Software Engineering. 2016 Aug 25; 426–37. https://doi.org/10.1145/2970276.2970358.
• 22. Rausch T, Hummer W, Leitner P, Schulte S. An Empirical Analysis of Build Failures in the Continuous Integration Workflows of Java-Based Open-Source Software. Proceeding of the 14th International Conference on Mining Software Repositories. 2017 May 1; 345–55. https://doi.org/10.1109/msr.2017.54.
• 23. Pan R, Bagherzadeh M, Ghaleb TA, Briand L. Test case selection and prioritization using machine learning: a systematic literature review. Empirical Software Engineering. 2021 Dec 14; 27(2). https://doi.org/10.1007/s10664-021-10066-6.
• 24. Benjamin J, Mathew J. Enhancing the efficiency of continuous integration environment in DevOps. IOP Conference Series Materials Science and Engineering. 2021 Feb 1; 1085(1): 012025. https://doi.org/10.1088/1757-899x/1085/1/012025.
• 25. Zydroń PW, Protasiewicz J. Enhancing code review efficiency: automated pull request evaluation using natural language processing and machine learning. Advances in Science and Technology – Research Journal. 2023 Aug 7; 17(4): 162–7. https://doi.org/10.12913/22998624/169576.
• 26. Tecimer KA, Tüzün E, Moran C, Erdogmus H. Cleaning ground truth data in software task assignment. Information and Software Technology [Internet]. 2022 May 25; 149: 106956. https://doi.org/10.1016/j.infsof.2022.106956.
• 27. Zanjani MB, Kagdi H, Bird C. Automatically recommending peer reviewers in modern code review. IEEE Transactions on Software Engineering. 2015 Nov 12; 42(6): 530–43. https://doi.org/10.1109/tse.2015.2500238.
• 28. Testi M, Ballabio M, Frontoni E, Iannello G, Moccia S, Soda P, et al. MLOPs: A taxonomy and a methodology. IEEE Access. 2022 Jan 1; 10: 63606–18. https://doi.org/10.1109/access.2022.3181730.
• 29. Arachchi SAIBS, Perera I. Continuous Integration and Continuous Delivery Pipeline Automation for Agile Software Project Management. 2022 Moratuwa Engineering Research Conference (MERCon). 2018 May 1; 156–61. https://doi.org/10.1109/mercon.2018.8421965.
• 30. Giorgio L, Nicola M, Fabio S, Andrea S. Continuous defect prediction in CI/CD pipelines: A machine learning-based framework. In: Lecture notes in computer science. 2022; 591–606. https://doi.org/10.1007/978-3-031-08421-8_41.
• 31. Mazumder RK, Salman AM, Li Y. Failure risk analysis of pipelines using data-driven machine learning algorithms. Structural Safety. 2020 Nov 12; 89: 102047. https://doi.org/10.1016/j.strusafe.2020.102047.
• 32. Casale G, Chesta C, Deussen P, Di Nitto E, Gouvras P, Koussouris S, et al. Current and future challenges of software engineering for services and applications. Procedia Computer Science. 2016 Jan 1; 97: 34–42. https://doi.org/10.1016/j.procs.2016.08.278.
• 33. Satapathy BS, Satapathy SS, Singh SI, Chakraborty J. Continuous integration and continuous deployment (CI/CD) pipeline for the SaaS documentation delivery. In: Lecture notes in electrical engineering [Internet]. 2023; 41–50. https://doi.org/10.1007/978-981-99-5994-5_5.
• 34. Lwakatare LE, Raj A, Bosch J, Olsson HH, Crnkovic I. A taxonomy of software engineering challenges for machine learning systems: An empirical investigation. In: Lecture notes in business information processing [Internet]. 2019. p. 227–43. https://doi.org/10.1007/978-3-030-19034-7_14.
• 35. Kreuzberger D, Kühl N, Hirschl S. Machine learning operations (MLOps): Overview, definition, and architecture. IEEE Access. 2023 Jan 1; 11: 31866–79. https://doi.org/10.1109/access.2023.3262138.
• 36. Beller M, Gousios G, Zaidman A. Travis torrent: Synthesizing travis CI and GitHub for full-stack research on continuous integration. In Proceedings of the 14th International Conference on Mining Software Repositories (MSR). 2017 May 1; https://doi.org/10.1109/msr.2017.24.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).