Scaling AI Applications on the Cloud toward Optimized Cloud-Native Architectures, Model Efficiency, and Workload Distribution

International Journal of Latest Technology in Engineering Management & Applied Science, Год журнала: 2025, Номер 14(2), С. 200 - 206

Опубликована: Март 15, 2025

Abstract: The rapid growth of Artificial Intelligence (AI) has increasefd the demand for scalable, efficient, and cost-effective computational infrastructure. Traditional on-premise systems face limitations in scalability, resource allocation, cost efficiency, making cloud computing a preferred solution. This paper examines cloud-native architectures, including containerization, Kubernetes orchestration, serverless computing, microservices, as key enablers AI scalability. Modern approaches optimizing models involve using quantization pruning knowledge distillation to make them more efficient without sacrificing their accuracy levels. investigates workload distribution methods like federated learning together with distributed training plus adaptive scaling improving efficiency lowering response times. implementation continues difficulties concerning expense control latency reduction scheduling resources efficiently while ensuring security standards. research presents three possible solutions namely automated scaling, edge-cloud integration provisioning intelligent management overcome current limitations. examination features study present-day trends which consist AI-native orchestration along AutoML-based optimization quantum applications enhancement capabilities. provides comprehensive insights about cloud-based scalability helps researchers well practitioners improve deployment capabilities high-performance systems.

Язык: Английский

AI-driven Dynamic Workload Balancing for Real-time Applications on Cloud Infrastructure

Опубликована: Сен. 18, 2024

Язык: Английский