Prediction Of Cloud Computing Resource Utilization

Abstract

Efficient resource utilization leads cloud provider to low cost and high performance. Cloud Computing is a dynamic environment that provides on-demand services over the internet on pay as you go model. Cloud platform has a dynamic resource usage as it is shared among large number of users. Resource allocator provisions resources to dynamic demands of user from finite set of resources. There should be no over and under provisioning of resources. Underutilized resources causes resource wastage and more cost whereas over utilized resource can lead to service degradation. If Resource allocators can presume future resource usage they can take resource provisioning decision efficiently. A resource utilization prediction mechanism is required to assist resource allocator for optimum resource provisioning.Accurate prediction is a challenge in such a dynamic resource usage. Machine learning techniques can help in creating a model that yields accurate prediction results. In machine learning, Ensemble mechanisms are renowned for improving the prediction accuracy which uses a combination of learners rather than a single learner. In this study, an “Ensemble based workload prediction mechanism” is proposed that is based on stack generalization. Experiments are conducted in order to compare the proposed model with the individual and baseline prediction models. For comparison with baseline model, we have used Root Mean Square Error(RMSE) as results of baseline model were given in RMSE. Proposed mechanism has shown 6% and 17% reduction in RMSE in CPU usage and in Memory usage prediction respectively. For comparing our proposed ensemble with independent learner(K Nearest Neighbor, Neural Network, Decision Tree, Support Vector Machine and Naïve Bayes), we have used accuracy as evaluation parameter. The proposed ensemble has improved the prediction accuracy by $\approx 2$%.