AI-Driven Optimisation Strategies for Data-Centric Cloud Architectures in Machine Learning Applications

• Author(s): Atughara John Chukwuebuka
• Paper ID: 1705187
• Page: 345-359
• Published Date: 30-11-2023
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 7 Issue 5 November-2023

Abstract

In this article, the author focuses on using AI to optimise data-oriented cloud architectures in machine learning applications. Due to dynamic changes in the digital business environment, the concept of artificial intelligence, with the help of machine learning within the cloud, has become inevitable in upgrading data handling, processing, analysis, and storage solutions. Specifically, this work explores modern AI-based optimisation approaches, their effects on cloud environments, and the opportunities and risks introduced to the cloud domains. Real-life examples and a literature review offer readers of the article information about the applicability of these strategies and the prospects for further development. Some findings suggest that AI optimisation improves performance and workload in data-intensive clouds due to taught resource management and proactive scaling. These strategies also result in major cost reduction through better resource management and efficient use of resources. Moreover, AI optimises dynamic scaling, which means cloud architectures can vary depending on the current load and support business growth. Better data protection is another remarkable advantage, and an AI system can identify threats and other anomalies in real time. However, certain factors must be considered to make it more widespread: data privacy issues, integration issues, and the requirement for specialised skills. The observed results can be popular among administrative employees of universities and other organisations, and overall, it has important theoretical and practical implications. For academics, this analysis presents a starting point for investigating the utilisation of AI optimisation procedures. The findings for practitioners may serve as a basis for improving cloud structures and enhancing efficacy and protection to encourage innovation and offer new value. In conclusion, various forms of optimisation by AI take a huge amount of promise in the technological revolution of data-oriented cloud structures in machine learning applications to set the stage for a more enhanced and equipped future.

Keywords

AI Optimisation, Cloud Architecture, Machine Learning, Data-Centric, Cloud Computing, Optimisation Strategies

Citations

IRE Journals:
Atughara John Chukwuebuka "AI-Driven Optimisation Strategies for Data-Centric Cloud Architectures in Machine Learning Applications" Iconic Research And Engineering Journals Volume 7 Issue 5 2023 Page 345-359

IEEE:
Atughara John Chukwuebuka "AI-Driven Optimisation Strategies for Data-Centric Cloud Architectures in Machine Learning Applications" Iconic Research And Engineering Journals, 7(5)