Intelligent Code Coverage Optimization Using Machine Learning for Large Scale Systems

Author(s)	Hariprasad Sivaraman
Country	USA
Abstract	Due to the high amount of code paths that large-scale systems need to traverse, and their complex dependency chains, getting the right level of coverage in an efficient and effective way is typically a huge obstacle. As systems grow, traditional testing becomes repetitive, expensive and labor-intensive. In this article, a framework of intelligent code coverage optimization based on machine learning (ML) is introduced. The solution proposed here uses a predictive model to rank code paths based on potential impact, and reinforcement learning is also used to adapt the coverage dynamically so that we have enough tests, but not all of them that it would require an exhaustive effort to cover. Such approaches lead to lower computational burden, more efficient use of the resources, and improved software robustness. Results of several experiments illustrate the potential of this approach to improve test coverage in large complicated systems.
Keywords	Code Coverage, Machine Learning, Large-Scale Systems, Test Optimization, Software Reliability Engineering, Reinforcement Learning
Published In	Volume 5, Issue 5, September-October 2023
Published On	2023-10-25
DOI	https://doi.org/10.36948/ijfmr.2023.v05i05.20826
Short DOI	https://doi.org/g8w24h

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research