Workload prediction model based on supervised learning for energy efficiency in cloud

Abstract

With the rapid emergence of cloud and its magnificent features such as high availability, reliability and security, a large number of clients are moving to the cloud platform. This migration of clients has led to increased burden on the resources such as CPU, network and memory. Hence, the problem of high power consumption, increased carbon footprints and need for higher cooling effects arose. However, resource scheduling and provisioning has become a milestone to handle such diverse issues related to cloud and get them under centralized control system. Workload prediction is an utmost requirement to dynamically predict the incoming workload and schedule the resources according to client needs. Dynamic workload prediction based on historical data can prove useful for pattern matching of current scenario with the past ones and allocate the resources in the most efficient way. This paper aims to propose a prototype model for workload prediction using machine learning models to handle the dynamic nature of the cloud infrastructure. This prediction is then used for resource provisioning. Diverse scheduling scenarios over the cloud are also covered in this paper and alternate remedies have been suggested for low power consumption and temperature control.