EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Intelligent Quality Assurance in Cloud-Native Systems: A Deep Learning and Reinforcement Learning Approach to Adaptive Test Coverage Optimization

Srikanth Chakravarthy Vankayala

International Journal of Scientific Research in Science, Engineering and Technology · 30.11.2024 · 11 (6) · 546-553

DOI: 10.32628/ijsrset2512555 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Scientific Research in Science, Engineering and Technology, online erschienen am 30.11.2024. Verfasst von Srikanth Chakravarthy Vankayala. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cloud-native systems, characterized by microservices, continuous deployment, and distributed architectures, present significant challenges for ensuring software quality due to their inherent dynamism, scalability requirements, and loosely coupled service interactions. Traditional testing strategies largely designed for monolithic or static systems struggle to scale effectively in such environments, often resulting in redundant test execution, delayed feedback cycles, and insufficient coverage of critical system paths. This paper introduces a deep learning-driven quality intelligence framework for adaptive test coverage optimization in cloud-native environments, aiming to transform testing from a reactive process into a proactive, self-improving system. By integrating deep neural networks for predictive defect analysis, reinforcement learning for adaptive test prioritization, and coverage-guided testing techniques for efficient exploration of execution paths, the proposed approach enables continuous learning from system feedback and runtime telemetry. It dynamically adjusts testing strategies based on historical outcomes, system behavior, and risk profiles, thereby improving both efficiency and effectiveness. Furthermore, the framework leverages observability data and CI/CD pipeline integration to support real-time decision-making and automated test orchestration across distributed services. The study synthesizes foundational work in software testing (2000–2010), advances in AI-driven testing (2015–2023), and modern cloud-native engineering practices to propose a unified, adaptive testing paradigm. Experimental insights drawn from prior research and empirical studies indicate that such intelligent, feedback-driven approaches can significantly enhance defect detection rates, optimize resource utilization, improve test coverage, and increase overall system resilience in complex, large-scale software ecosystems.

Zitieren

APA

Vankayala, S. C. (2024). Intelligent Quality Assurance in Cloud-Native Systems: A Deep Learning and Reinforcement Learning Approach to Adaptive Test Coverage Optimization. International Journal of Scientific Research in Science, Engineering and Technology, 11(6), 546-553. https://doi.org/10.32628/ijsrset2512555

Vancouver

Vankayala SC. Intelligent Quality Assurance in Cloud-Native Systems: A Deep Learning and Reinforcement Learning Approach to Adaptive Test Coverage Optimization. International Journal of Scientific Research in Science, Engineering and Technology. 2024;11(6):546-553. doi:10.32628/ijsrset2512555

BibTeX
@article{Vankayala2024,
  author = {Vankayala, Srikanth Chakravarthy},
  title = {Intelligent Quality Assurance in Cloud-Native Systems: A Deep Learning and Reinforcement Learning Approach to Adaptive Test Coverage Optimization},
  journal = {International Journal of Scientific Research in Science, Engineering and Technology},
  year = {2024},
  volume = {11},
  number = {6},
  pages = {546--553},
  doi = {10.32628/ijsrset2512555}
}
Kostenlos starten →