Application of an Enhanced Self-adapting Differential Evolution Algorithm to Workload Prediction in Cloud Computing
M. A. Attia, Mohamed M. Arafa, Elsayed Abdelhameed Sallam, M. M. Fahmy · International Journal of Information Technology and Computer Science · 2019
The demand for workload prediction approaches has recently increased to manage the cloud resources, improve the performance of the cloud services and reduce the power consumption.The prediction accuracy of these approaches affects the cloud performance.In this application paper, we apply an enhanced variant of the differential evolution (DE) algorithm named MSaDE as a learning algorithm to the artificial neural network (ANN) model of the cloud workload prediction.The ANN prediction model based on MSaDE algorithm is evaluated over two benchmark datasets for the workload traces of NASA server and Saskatchewan server at different look-ahead times.To show the improvement in accuracy of training the ANN prediction model using MSaDE algorithm, training is performed with other two algorithms: the back propagation (BP) algorithm and the self-adaptive differential evolution (SaDE) algorithm.Comparisons are made in terms of the root mean squared error (RMSE) and the average root mean squared error (ARMSE) through all prediction intervals.The results show that the ANN prediction model based on the MSaDE algorithm predicts the cloud workloads with higher prediction accuracy than the other algorithms compared with.