Secure Cloud Optimization for Tenants, CSP and User Via Deep Learning

Abstract

Abstract: In cloud choosing a right option suitable for CSP, Tenant and user are a challenging task. The proposed system defines a selection mechanism for the cloud service provider (CSP), Tenant, and user. The algorithm designs a service provider that leverages the client for efficient resource allocation for Cloud. Further the system leverages a deep learning metrics to analyze the cloud service provider, tenant and users requirements. The system deliberates a Profit/loss calculator to describe the percentage of profit/loss while choosing. The profit/loss that occurs during allocation or transaction is predicted and suggestions are provided. These strategies are secure, efficient and cost-effective. The monitoring metrics are done with help of deep neural learning (DNL) and Profit/loss Calculation that provides a complete analysis in the cloud. In this process considering the rating, report, or feedback a trustworthy selection is made and a recommendation process is handled for choosing a right option. The experimental results show that the proposed model can benefit both the cloud service provider and users by configuring proper allocation strategies. Keywords: Recommendation, deep learning, profit/loss, tenant, CSP, and user