KUBERNETES-BASED AUTO-SCALING CLOUD WORKLOAD MANAGEMENT

Abstract

Cloud computing has become the backbone of modern application deployment, enabling on-demand resource provisioning, scalability, and cost efficiency. However, managing fluctuating workloads in dynamic cloud environments remains a significant challenge. Kubernetes, a leading container orchestration platform, provides built-in capabilities for automated deployment, scaling, and management of containerized applications. This project focuses on Kubernetes-based auto-scaling techniques to efficiently manage cloud workloads by leveraging the Horizontal Pod Autoscaler (HPA), Vertical Pod Autoscaler (VPA), and Cluster Autoscaler. The proposed system monitors real-time application performance metrics—such as CPU, memory, and network utilization—using Prometheus and Metrics Server, and dynamically adjusts compute resources based on demand. By automatically scaling services during peak loads and reducing resource utilization during idle periods, the system ensures high availability, improved performance, and optimized cloud costs. Experimental results demonstrate that Kubernetesdriven workload auto-scaling significantly enhances application responsiveness, minimizes manual intervention, and provides an intelligent, self-healing cloud infrastructure suitable for micro services and large-scale distributed applications.