Scholarlink

Cloud federation allows various cloud service providers (CSPs) to collaborate, aiming to enhance the quality of service (QoS) and generate revenue by utilizing underutilized resources. However, pernicious CSPs within the federation can degrade the QoS. To address this, we propose a feedback-driven machine learning model, the Pernicious CSP Detection Algorithm (PCSPDA), to identify pernicious CSPs. The PCSPDA leverages Linear Support Vector Machines (Linear SVC) and a Random Forest approach to detect pernicious CSPs within a federated cloud environment and prove that our proposed PCSPDA model is competently efficient. Extensive simulation results are presented to validate the effectiveness of the proposed PCSPDA model.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Detecting Pernicious Service Providers in Federated Cloud Environments Using Machine Learning Technique

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Sandeep Singh Sikarwar,
  • Rakesh Kumar,
  • Benay Kumar Ray

摘要

Cloud federation allows various cloud service providers (CSPs) to collaborate, aiming to enhance the quality of service (QoS) and generate revenue by utilizing underutilized resources. However, pernicious CSPs within the federation can degrade the QoS. To address this, we propose a feedback-driven machine learning model, the Pernicious CSP Detection Algorithm (PCSPDA), to identify pernicious CSPs. The PCSPDA leverages Linear Support Vector Machines (Linear SVC) and a Random Forest approach to detect pernicious CSPs within a federated cloud environment and prove that our proposed PCSPDA model is competently efficient. Extensive simulation results are presented to validate the effectiveness of the proposed PCSPDA model.