Tools
Tools
Bhosle, Shraddha (2023) Orchestration and CI/CD automation using MLOps for Cloud-native container deployments. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
With the rise of cloud-native deployments and machine learning, there is a growing demand for efficient orchestration and automation in creating and managing machine learning models. Machine learning Operations (MLOps) blends machine learning and DevOps, streamlining the process from model creation to deployment in containerized systems. This results in a more effective development lifecycle, increased efficiency, and less manual intervention. The ultimate objective of any industrial machine learning work is to create ML products and deliver into production quickly. However, it is extremely difficult to automate and operationalize ML solutions for large datasets, therefore many ML endeavors fail to meet their goals. This is addressed by the MLOps concept. MLOps is a relatively new concept that inherits its main features from DevOps and applies them to Machine Learning to shorten the time it takes to implement ML model into production. This thesis aimed to analyze this new method and explore several tools for building an MLOps architecture. To validate the functionality of the pipeline, the developed ML application utilized Logistic Regression and Multinomial Naive Bayes models, implementing Natural Language Processing techniques. It is containerized using Docker and delivered via an Elastic Kubernetes Service (EKS) built using Kubeflow pipelines and used GitHub actions to automate workflows directly within GitHub repository. This paper offers an extensive analysis of entire implementation process, starting with model development to cloud deployment. By incorporating MLOps, the project successfully established an automated and efficient pipeline for creating, managing, and deploying machine learning models within containerized systems.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Haque, Rejwanul UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software T Technology > T Technology (General) > Information Technology > Computer software T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Cloud Computing |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 26 Mar 2025 12:42 |
| Last Modified: | 26 Mar 2025 12:42 |
| URI: | https://norma.ncirl.ie/id/eprint/7334 |
Actions (login required)
 |
View Item |