Comparative Performance and Optimization Strategies for Cloud-Native Architectures: A Focus on Scalability, Cost, and Resource Utilization

Cloud-native architectures have become essential for modern application development, offering scalability, flexibility, and cost efficiency through paradigms like microservices, serverless computing, and event-driven systems. However, performance trade-offs, resource underutilization, and operational inefficiencies persist across different architectural models. This study delivers a comparative performance evaluation of four leading cloud-native architectures—Service Mesh, Event-Driven Systems, Serverless Computing, and Polyglot Persistence across AWS and GCP platforms. Using a controlled experimental setup, key performance metrics including response time, throughput, resource utilization, and operational cost (OC) were assessed under varying workloads. Serverless computing demonstrated superior cost-efficiency and dynamic scaling, though hampered by cold-start delays, while event-driven systems struck a balance between responsiveness and cost. Optimization strategies such as cold-start mitigation, adaptive auto-scaling, and hybrid storage improvements yielded significant performance gains across all architectures. The research provides critical insights for developers and system architects, offering data-driven recommendations to guide architectural choices and optimize cloud-native deployments. The study’s significance lies in its empirical approach, bridging theoretical design with real-world implementation to advance best practices in building scalable and sustainable cloud-native applications.