Infrastructure as a Service (IaaS) cloud provides resources as a service from a pool of compute, network, and storage resources.\nCloud providers can manage their resource usage by knowing future usage demand from the current and past usage patterns of\nresources. Resource usage prediction is of great importance for dynamic scaling of cloud resources to achieve efficiency in terms\nof cost and energy consumption while keeping quality of service.The purpose of this paper is to present a real-time resource usage\nprediction system. The system takes real-time utilization of resources and feeds utilization values into several buffers based on\nthe type of resources and time span size. Buffers are read by R language based statistical system. These buffers� data are checked\nto determine whether their data follows Gaussian distribution or not. In case of following Gaussian distribution, Autoregressive\nIntegratedMovingAverage (ARIMA) is applied; otherwiseAutoregressiveNeuralNetwork (AR-NN) is applied. In ARIMA process,\na model is selected based on minimum Akaike Information Criterion (AIC) values. Similarly, in AR-NN process, a network with\nthe lowest Network Information Criterion (NIC) value is selected.We have evaluated our system with real traces of CPU utilization\nof an IaaS cloud of one hundred and twenty servers.
Loading....