Energy Prediction for Cloud Workload Patterns

The excessive use of energy consumption in Cloud infrastructures has become one of the major cost factors for Cloud providers to maintain. In order to enhance the energy efficiency of Cloud resources, proactive and reactive management tools are used. However, these tools need to be supported with energy-awareness not only at the physical machine (PM) level but also at virtual machine (VM) level in order to enhance decision-making. This paper introduces an energy-aware profiling model to identify energy consumption for heterogeneous and homogeneous VMs running on the same PM and presents an energy-aware prediction framework to forecast future VMs energy consumption. This framework first predicts the VMs’ workload based on historical workload patterns using Autoregressive Integrated Moving Average (ARIMA) model. The predicted VM workload is then correlated to the physical resources within this framework in order to get the predicted VM energy consumption. Compared with actual results obtained in a real Cloud testbed, the predicted results show that this energy-aware prediction framework can get up to 2.58 Mean Percentage Error (MPE) for the VM workload prediction, and up to −4.47 MPE for the VM energy prediction based on periodic workload pattern.