VM Power Prediction in Distributed Systems for Maximizing Renewable Energy Usage

1 Abstract In the context of GreenPAD project it is important to predict the energy consumption of individual VMs / workload for optimal scheduling (running those VMs which require higher energy when there is more green energy available and vice-versa) in order to maximize green energy utilization. This involves the following tasks: 1. VM energy measurement for different configurations (flavor + workload) 2. VM energy prediction for a new configuration. We propose a model for predicting the power usage of the VMs based on regression. We first collect the resource usage and the associated power usage for different VM configurations and use this to build a regression model. Then we use the information about the resource usage patterns of the new workload to predict the power usage. 2 Setup For modeling a particular workload / VM we run it on an isolated server and measure the resource and power usage (after recording the static power usage