An efficient hybrid prediction approach for predicting cloud consumer resource needs

Abstract

The prediction of cloud consumer resource needs is a vital step for several cloud deployment applications such as capacity planning, workload management, and dynamic allocation of cloud resources. In this paper, we develop a new prediction model for predicting cloud consumer resource needs. The new model uses a new hybrid prediction approach that combines the Multiple Support Vector Regression (MSVR) model and the Autoregressive Integrated Moving Average (ARIMA) model to predict with higher accuracy the resource needs of a cloud consumer in terms of CPU, memory, and disk storage utilization. The new model is also able to predict the response time and throughput which in turn enable the cloud consumers to make a better scaling decision. The new model elucidated a better prediction accuracy than the current prediction models. In terms of CPU utilization prediction, it outperforms the accuracy of the existing cloud consumer prediction models that uses Linear Regression, Neural Network, and Support Vector Machines approaches by 72.66%, 44.24%, and 56.78% respectively according to MAPE and 56.95%, 80.42%, and 63.86% according to RMSE. The analysis, architecture, and experiment results of the new model are discussed in details in this paper. 2016 IEEE.