An intelligent regressive ensemble approach for predicting resource usage in cloud computing

Cloud Computing has become prime infrastructure for scientists to deploy scientific applications as it offers parallel and distributed environment for large-scale computations. During deployment, the significant prediction of resource usage is essential to achieve optimal scheduling for scientific applications. The existing resource prediction models fall short in providing reasonable accuracy because of high variances of cloud metrics. Therefore, to handle the varying cloud resource demands, it is necessary to accurately predict the future resource requirements for automatically provisioning the resources. In this paper, an Intelligent Regressive Ensemble Approach for Prediction (REAP) has been proposed which integrates feature selection and resource usage prediction techniques to achieve high performance. The effectiveness of proposed approach is evaluated in a real cloud environment by conducting a series of experiments. The experimental results show that the proposed approach outperforms the existing models by significantly improving the accuracy rate and reducing the execution time. The results are further validated by comparing the existing Learning Automata (LA) based ensemble approach with the proposed approach on the basis of error rate.