A Prediction based Cloud Resource Provisioning using SVM

Abstract

: Prediction of workload in a Cloud Environment is one of the primary task in provisioning resources. Forecasting the requirements of future workload lies in the competency of predicting technique. Employing an appropriate technique could maximize the usage of resources in a cloud computing environment. A prediction approach grounded on Machine Learning that uses a Support Vector Machine model with reduced training time has been proposed in this paper. Google Cloud Trace dataset has been used to develop and train the model which had depicted an increase in the accuracy of load prediction when compared to other machine learning algorithms as explored in this paper. The developed model is tested on a simulated environment using Cloudsim.