Year: 2025
Type: article
Abstract: The swift integration of microservices architecture in cloud settings has revolutionized how organizations develop and expand applications, providing greater flexibility, scalability, and isolation from faults. Nevertheless, the task of enhancing the performance of microservices, especially within extensive cloud infrastructures, poses a considerable challenge. Conventional performance optimization techniques frequently struggle to address the complexity, dynamic characteristics, and interdependencies inherent in microservices, leading to inefficiencies, increased latency, and suboptimal resource utilization. Artificial Intelligence (AI) emerges as a viable remedy to these issues by offering adaptive, data-driven, and autonomous optimization methods. This paper investigates how AI methodologies, including machine learning, reinforcement learning, and predictive analytics, can be applied to enhance the performance of microservices in cloud environments. It particularly focuses on harnessing AI to anticipate resource usage, automate scaling processes, optimize communication between services, and bolster fault tolerance. Through a comprehensive literature review and experimental assessments, this research highlights the potential of AI-driven strategies in improving microservices efficiency, lowering costs, and enhancing system robustness. The results provide a detailed framework for incorporating AI optimization techniques into cloud-native microservices architectures, yielding significant implications for both academic and industrial sectors.
Author: Anju Bhole -
Language: English
Subfield: Computer Networks and Communications
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4410927315