Optimizing Resource Management in Serverless Computing: A Dynamic Adaptive Scaling Approach
Tanaya Biswas, Prashant Kumar · 2024
Serverless computing, recognized as Function as a Service (FaaS), represents a revolutionary shift in cloud computing, placing a focal point on code-centric development and seamless automated infrastructure management. This paper presents a novel Dynamic Adaptive Resource Scaling Model designed for serverless computing environments, addressing the need for efficient and cost-effective resource management. The model leverages real-time workload monitoring, machine learning algorithms, and predictive analytics to dynamically adjust resource allocation in response to fluctuating demand.. Our findings reveal that the proposed model not only enhances operational efficiency but also substantially reduces costs. Key metrics demonstrate up to 30% improvement in resource utilization and a 25% reduction in operational expenses. The model’s adaptability to diverse workloads makes it a robust solution for modern cloud architectures. Insights from this study are vital for developers, cloud architects, and IT managers seeking to optimize resource management in serverless environments. Future research directions include integrating advanced machine learning techniques and expanding the model’s applicability across different cloud platforms.