Optimization of cloud computing resource allocation using reinforcement learning

Thesis Abstract

Cloud computing resource allocation is a critical aspect of ensuring efficient and cost-effective utilization of cloud resources. Traditional resource allocation methods often rely on static heuristics or manual tuning, which may not adapt well to dynamic workloads and changing resource demands. In this project, we propose to investigate the application of reinforcement learning techniques to optimize cloud computing resource allocation. By leveraging the capabilities of reinforcement learning, we aim to develop a dynamic resource allocation framework that can adapt to varying workloads and optimize resource utilization in real time. The proposed framework has the potential to improve the efficiency and cost-effectiveness of cloud computing environments, leading to better performance and reduced operational costs for cloud service providers and users.