Leveraging AI for Autonomous Resource Management in Cloud Environments: A Deep Reinforcement Learning Approach
  • Author(s): Kodamasimham Krishna
  • Paper ID: 1702825
  • Page: 394-403
  • Published Date: 17-08-2024
  • Published In: Iconic Research And Engineering Journals
  • Publisher: IRE Journals
  • e-ISSN: 2456-8880
  • Volume/Issue: Volume 5 Issue 1 July-2021
Abstract

As cloud computing continues to evolve, the need for effective and adaptive resource management becomes increasingly critical. Traditional resource management techniques often fall short in handling the dynamic and unpredictable nature of cloud environments, leading to inefficiencies and increased operational costs. This paper explores the application of Deep Reinforcement Learning (DRL) for autonomous cloud resource management, offering a novel approach that leverages AI to optimize resource allocation in real-time. By training a DRL agent to interact with a simulated cloud environment, this study demonstrates how DRL can enhance resource utilization, reduce costs, and improve application performance compared to conventional methods. The proposed approach is evaluated through a comprehensive case study, which highlights its effectiveness in managing varying workloads and achieving superior performance metrics. The findings suggest that DRL has the potential to significantly advance cloud resource management, paving the way for more efficient and cost-effective cloud services.

Keywords

Deep Reinforcement Learning, Cloud Resource Management, Autonomous Systems, AI, Dynamic Resource Allocation, Cloud Computing, Resource Optimization

Citations

IRE Journals:
Kodamasimham Krishna "Leveraging AI for Autonomous Resource Management in Cloud Environments: A Deep Reinforcement Learning Approach" Iconic Research And Engineering Journals Volume 5 Issue 1 2021 Page 394-403

IEEE:
Kodamasimham Krishna "Leveraging AI for Autonomous Resource Management in Cloud Environments: A Deep Reinforcement Learning Approach" Iconic Research And Engineering Journals, 5(1)